Subjects -> ENGINEERING (Total: 2688 journals)
    - CHEMICAL ENGINEERING (229 journals)
    - CIVIL ENGINEERING (237 journals)
    - ELECTRICAL ENGINEERING (176 journals)
    - ENGINEERING (1325 journals)
    - ENGINEERING MECHANICS AND MATERIALS (452 journals)
    - HYDRAULIC ENGINEERING (56 journals)
    - INDUSTRIAL ENGINEERING (98 journals)
    - MECHANICAL ENGINEERING (115 journals)

ENGINEERING (1325 journals)            First | 1 2 3 4 5 6 7 | Last

Showing 201 - 400 of 1205 Journals sorted alphabetically
Concurrent Engineering     Hybrid Journal   (Followers: 3)
Continuum Mechanics and Thermodynamics     Hybrid Journal   (Followers: 8)
Control Engineering Practice     Hybrid Journal   (Followers: 46)
Control Theory and Informatics     Open Access   (Followers: 9)
Corrosion Science     Hybrid Journal   (Followers: 23)
CT&F - Ciencia, Tecnología y Futuro     Open Access  
CTheory     Open Access  
Current Applied Physics     Full-text available via subscription   (Followers: 4)
Current Applied Science and Technology     Open Access  
Current Journal of Applied Science and Technology     Open Access  
Current Research in Nanotechnology     Open Access   (Followers: 23)
Current Science     Open Access   (Followers: 115)
Dams and Reservoirs     Hybrid Journal   (Followers: 3)
Data-Centric Engineering     Open Access  
Decision Making : Applications in Management and Engineering     Open Access   (Followers: 1)
Design Journal : An International Journal for All Aspects of Design     Hybrid Journal   (Followers: 33)
Designed Monomers and Polymers     Open Access   (Followers: 1)
Designs     Open Access  
Designs, Codes and Cryptography     Hybrid Journal   (Followers: 7)
Development Engineering     Open Access   (Followers: 3)
Diálogos Interdisciplinares     Open Access  
Diffusion Foundations     Full-text available via subscription   (Followers: 4)
Digital Signal Processing     Hybrid Journal   (Followers: 34)
Dinamisia : Jurnal Pengabdian Kepada Masyarakat     Open Access  
Discrete Optimization     Full-text available via subscription   (Followers: 7)
Dokuz Eylül Üniversitesi Denizcilik Fakültesi Dergisi     Open Access  
Düzce Üniversitesi Bilim ve Teknoloji Dergisi / Duzce University Journal of Science & Technology     Open Access  
Dyes and Pigments     Hybrid Journal   (Followers: 1)
Dynamical Systems : An International Journal     Hybrid Journal  
E&S Engineering and Science     Open Access  
e-Phaïstos : Revue d’histoire des techniques / Journal of the history of technology     Open Access  
EAU Heritage Journal Science and Technology     Open Access   (Followers: 1)
El-Cezeri Fen ve Mühendislik Dergisi / El-Cezeri Journal of Science and Engineering     Open Access  
Electromagnetics     Hybrid Journal   (Followers: 13)
Electrophoresis     Hybrid Journal   (Followers: 18)
Elkawnie : Journal of Islamic Science and Technology     Open Access  
Emerging Science Journal     Open Access   (Followers: 1)
Emitter : International Journal of Engineering Technology     Open Access  
ENERGETIKA. Proceedings of CIS higher education institutions and power engineering associations     Open Access  
Energies     Open Access   (Followers: 4)
Energy and Power Engineering     Open Access   (Followers: 23)
Energy Conversion and Management     Hybrid Journal   (Followers: 15)
Energy Conversion and Management : X     Open Access   (Followers: 1)
Energy Engineering     Full-text available via subscription   (Followers: 8)
Energy for Sustainable Development     Hybrid Journal   (Followers: 13)
Energy Science & Engineering     Open Access   (Followers: 6)
Energy Science and Technology     Open Access   (Followers: 10)
Energy Sources, Part A: Recovery, Utilization, and Environmental Effects     Hybrid Journal   (Followers: 1)
Energy Sources, Part B: Economics, Planning, and Policy     Hybrid Journal   (Followers: 7)
Energy Systems     Hybrid Journal   (Followers: 11)
EnergyChem     Hybrid Journal   (Followers: 1)
Engenharia de Interesse Social     Open Access  
ENGEVISTA     Open Access  
Engineer : Journal of the Institution of Engineers, Sri Lanka     Open Access  
Engineering     Open Access   (Followers: 1)
Engineering & Technology     Hybrid Journal   (Followers: 22)
Engineering Analysis with Boundary Elements     Hybrid Journal   (Followers: 2)
Engineering Computations     Hybrid Journal   (Followers: 3)
Engineering Economics     Open Access   (Followers: 4)
Engineering Economist, The     Hybrid Journal   (Followers: 4)
Engineering Failure Analysis     Hybrid Journal   (Followers: 68)
Engineering Geology     Hybrid Journal   (Followers: 16)
Engineering Journal of Research and Development     Open Access  
Engineering Management in Production and Services     Open Access  
Engineering Management Research     Open Access   (Followers: 6)
Engineering Optimization     Hybrid Journal   (Followers: 19)
Engineering Reports     Open Access  
Engineering Science and Technology, an International Journal     Open Access   (Followers: 1)
Engineering Sciences     Open Access  
Engineering Studies     Hybrid Journal   (Followers: 1)
Engineering With Computers     Hybrid Journal   (Followers: 5)
Engineering, Technology & Applied Science Research     Open Access   (Followers: 1)
ENP Engineering Science Journal     Open Access  
Entramado     Open Access  
Entre Ciencia e Ingeniería     Open Access  
Entropy     Open Access   (Followers: 5)
Environmental & Engineering Geoscience     Full-text available via subscription   (Followers: 5)
Environmental and Ecological Statistics     Hybrid Journal   (Followers: 7)
Environmetrics     Hybrid Journal  
Épités - Épitészettudomány     Full-text available via subscription   (Followers: 1)
EPJ Photovoltaics     Open Access   (Followers: 2)
Ergonomics in Design: The Quarterly of Human Factors Applications     Hybrid Journal   (Followers: 21)
ESAIM: Control Optimisation and Calculus of Variations     Open Access   (Followers: 2)
ESAIM: Mathematical Modelling and Numerical Analysis     Open Access   (Followers: 5)
ESAIM: Proceedings     Open Access  
eScience     Open Access   (Followers: 1)
Estuaries and Coasts     Hybrid Journal   (Followers: 22)
EUREKA : Physics and Engineering     Open Access  
Euro-Mediterranean Journal for Environmental Integration     Hybrid Journal  
European Journal of Combinatorics     Full-text available via subscription   (Followers: 3)
European Journal of Engineering Education     Hybrid Journal   (Followers: 9)
European Journal of Lipid Science and Technology     Hybrid Journal   (Followers: 1)
European Journal of Mass Spectrometry     Hybrid Journal   (Followers: 16)
European Physical Journal - Applied Physics     Full-text available via subscription   (Followers: 19)
European Transport Research Review     Open Access   (Followers: 22)
Evolutionary Intelligence     Hybrid Journal   (Followers: 2)
Evolving Systems     Hybrid Journal  
Experimental and Computational Multiphase Flow     Hybrid Journal  
Experimental Techniques     Hybrid Journal   (Followers: 51)
Experiments in Fluids     Hybrid Journal   (Followers: 17)
Farm Engineering and Automation Technology Journal     Open Access  
Fibers and Polymers     Full-text available via subscription   (Followers: 4)
FIGEMPA : Investigación y Desarrollo     Open Access   (Followers: 1)
Filtration & Separation     Full-text available via subscription   (Followers: 4)
Finite Fields and Their Applications     Full-text available via subscription   (Followers: 5)
Fırat University Turkish Journal of Science & Technology     Open Access  
Fire Science Reviews     Open Access   (Followers: 12)
Flexible Services and Manufacturing Journal     Hybrid Journal   (Followers: 2)
Flow, Turbulence and Combustion     Hybrid Journal   (Followers: 30)
Fluid Dynamics     Hybrid Journal   (Followers: 27)
Fluid Phase Equilibria     Hybrid Journal   (Followers: 4)
Focus on Catalysts     Full-text available via subscription  
Focus on Pigments     Full-text available via subscription   (Followers: 3)
Focus on Powder Coatings     Full-text available via subscription   (Followers: 5)
Focus on Surfactants     Full-text available via subscription   (Followers: 2)
Food Engineering Reviews     Hybrid Journal   (Followers: 2)
Food Science and Technology     Open Access   (Followers: 2)
Forces in Mechanics     Open Access   (Followers: 2)
Formación Universitaria     Open Access   (Followers: 4)
FORMakademisk - forskningstidsskrift for design og designdidaktikk     Open Access   (Followers: 2)
Formal Methods in System Design     Hybrid Journal   (Followers: 6)
Forschung     Hybrid Journal   (Followers: 1)
Forschung im Ingenieurwesen     Hybrid Journal  
Foundations and Trends in Systems and Control     Full-text available via subscription   (Followers: 4)
Foundations and Trends® in Communications and Information Theory     Full-text available via subscription   (Followers: 6)
Foundations and Trends® in Electronic Design Automation     Full-text available via subscription   (Followers: 1)
Foundations of Science     Hybrid Journal   (Followers: 1)
Frontiers in Aerospace Engineering     Open Access   (Followers: 20)
Frontiers in Energy     Hybrid Journal   (Followers: 4)
Frontiers in Nanotechnology     Open Access   (Followers: 1)
Frontiers of Environmental Science & Engineering     Hybrid Journal   (Followers: 3)
Fuel and Energy Abstracts     Full-text available via subscription   (Followers: 7)
Fuel Cells     Hybrid Journal   (Followers: 8)
Fuel Cells Bulletin     Full-text available via subscription   (Followers: 9)
Fusion Engineering and Design     Hybrid Journal   (Followers: 6)
Fuzzy Information and Engineering     Open Access   (Followers: 2)
Fuzzy Sets and Systems     Hybrid Journal   (Followers: 3)
Georisk: Assessment and Management of Risk for Engineered Systems and Geohazards     Hybrid Journal   (Followers: 8)
Géotechnique     Hybrid Journal   (Followers: 27)
Geothermics     Hybrid Journal   (Followers: 7)
Glass Technology - European Journal of Glass Science and Technology Part A     Full-text available via subscription   (Followers: 1)
Global Journal of Engineering Research     Full-text available via subscription  
Global Transitions Proceedings     Open Access  
GPS Solutions     Hybrid Journal   (Followers: 28)
Graphs and Combinatorics     Hybrid Journal   (Followers: 4)
Grass and Forage Science     Hybrid Journal   (Followers: 4)
Groundwater for Sustainable Development     Full-text available via subscription   (Followers: 5)
Heat Transfer - Asian Research     Hybrid Journal   (Followers: 10)
Heat Transfer Engineering     Hybrid Journal   (Followers: 36)
Heat Treatment and Surface Engineering     Open Access  
High Voltage     Open Access  
Himalayan Journal of Science and Technology     Open Access  
Historical Records of Australian Science     Hybrid Journal   (Followers: 2)
Human Behavior and Emerging Technologies     Hybrid Journal   (Followers: 1)
Human Factors in Ergonomics & Manufacturing     Hybrid Journal   (Followers: 12)
Human-Intelligent Systems Integration     Hybrid Journal  
I+D Revista de Investigaciones     Open Access  
IBM Journal of Research and Development     Hybrid Journal   (Followers: 16)
IEEE Antennas and Propagation Magazine     Hybrid Journal   (Followers: 112)
IEEE Antennas and Wireless Propagation Letters     Hybrid Journal   (Followers: 88)
IEEE Communications Magazine     Full-text available via subscription   (Followers: 139)
IEEE Embedded Systems Letters     Hybrid Journal   (Followers: 60)
IEEE Engineering Management Review     Full-text available via subscription   (Followers: 117)
IEEE Geoscience and Remote Sensing Letters     Hybrid Journal   (Followers: 150)
IEEE Geoscience and Remote Sensing Magazine     Hybrid Journal   (Followers: 6)
IEEE Industry Applications Magazine     Full-text available via subscription   (Followers: 82)
IEEE Instrumentation & Measurement Magazine     Hybrid Journal   (Followers: 148)
IEEE Journal of Biomedical and Health Informatics     Hybrid Journal   (Followers: 14)
IEEE Journal of Oceanic Engineering     Hybrid Journal   (Followers: 11)
IEEE Journal of Selected Topics in Quantum Electronics     Hybrid Journal   (Followers: 7)
IEEE Journal of Selected Topics in Signal Processing     Hybrid Journal   (Followers: 43)
IEEE Journal of Solid-State Circuits     Full-text available via subscription   (Followers: 24)
IEEE Journal on Selected Areas in Communications     Hybrid Journal   (Followers: 39)
IEEE Latin America Transactions     Full-text available via subscription   (Followers: 2)
IEEE Magnetics Letters     Hybrid Journal   (Followers: 7)
IEEE Microwave and Wireless Components Letters     Hybrid Journal   (Followers: 35)
IEEE Microwave Magazine     Full-text available via subscription   (Followers: 63)
IEEE Nanotechnology Magazine     Hybrid Journal   (Followers: 45)
IEEE Open Journal of Engineering in Medicine and Biology     Open Access   (Followers: 1)
IEEE Open Journal of Nanotechnology     Open Access   (Followers: 1)
IEEE Potentials     Full-text available via subscription   (Followers: 42)
IEEE Reviews in Biomedical Engineering     Hybrid Journal   (Followers: 19)
IEEE Signal Processing Letters     Hybrid Journal   (Followers: 60)
IEEE Solid-State Circuits Magazine     Hybrid Journal   (Followers: 11)
IEEE Spectrum     Full-text available via subscription   (Followers: 219)
IEEE Technology and Society Magazine     Full-text available via subscription   (Followers: 8)
IEEE Transactions on Advanced Packaging     Full-text available via subscription   (Followers: 8)
IEEE Transactions on Antennas and Propagation     Full-text available via subscription   (Followers: 79)
IEEE Transactions on Applied Superconductivity     Hybrid Journal   (Followers: 5)
IEEE Transactions on Automation Science and Engineering     Full-text available via subscription   (Followers: 13)
IEEE Transactions on Autonomous Mental Development     Hybrid Journal   (Followers: 8)
IEEE Transactions on Biomedical Engineering     Hybrid Journal   (Followers: 35)
IEEE Transactions on Broadcasting     Hybrid Journal   (Followers: 11)
IEEE Transactions on Circuits and Systems II: Express Briefs     Hybrid Journal   (Followers: 20)
IEEE Transactions on Components and Packaging Technologies     Full-text available via subscription   (Followers: 17)
IEEE Transactions on Control Systems Technology     Hybrid Journal   (Followers: 111)
IEEE Transactions on Education     Hybrid Journal   (Followers: 11)
IEEE Transactions on Electronics Packaging Manufacturing     Hybrid Journal   (Followers: 21)
IEEE Transactions on Energy Conversion     Hybrid Journal   (Followers: 16)
IEEE Transactions on Engineering Management     Hybrid Journal   (Followers: 74)

  First | 1 2 3 4 5 6 7 | Last

Similar Journals
Journal Cover
IEEE Geoscience and Remote Sensing Letters
Journal Prestige (SJR): 1.486
Citation Impact (citeScore): 4
Number of Followers: 150  
 
  Hybrid Journal Hybrid journal (It can contain Open Access articles)
ISSN (Print) 1545-598X
Published by IEEE Homepage  [228 journals]
  • Multiscale Fusion Signal Extraction for Spaceborne Photon-Counting Laser
           Altimeter in Complex and Low Signal-to-Noise Ratio Scenarios

    • Free pre-print version: Loading...

      Authors: Yaming Nan;Zhihui Feng;Bincheng Li;Enhai Liu;
      Pages: 1 - 5
      Abstract: Extracting signal photons from noisy raw data is one of the critical processes for the new generation of spaceborne photon-counting laser altimeter. Affected by vast noise photon-counting events, the extraction of weak signal events still faces challenges in complex scenarios with low signal-to-noise ratio (SNR). Aiming to improve the extraction ability of signal photon events in these scenarios, a multiscale fusion signal extraction method was proposed, characterized by combining global spatial correlation constraint with optimized local spatial correlation constraint. The local constraint is implemented based on a density-based spatial clustering of applications with noise (DBSCAN) clustering method with adaptive parameter estimation, which is used to extract possible signal photons. A subsequent global constraint based on the spatial correlation of the terrain profiles is designed to remove the pseudo-signal photons clustered in the local constraints’ step. The global constraint is implemented based on a cost function, which is used to quantify different candidate paths. Our method was verified based on the actual Ice, Cloud, and land Elevation satellite-(ICESat2) data containing vegetation, mountains, and residential areas. The experimental results show that compared with the ICESat-2 extraction method, our method can significantly improve the precision and recall rate of signal photon events from the low SNR photon-counting data.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Wind Speed Retrieval Method for Shipborne GNSS-R

    • Free pre-print version: Loading...

      Authors: Lingyu Qin;Ying Li;
      Pages: 1 - 5
      Abstract: This study presents a sea surface wind speed retrieval method for the maritime environment, using forward-scattering signals from the global navigation satellite system (GNSS), which benefits from reduced costs compared with active radar detection. Most retrieval algorithms for GNSS-reflectometry (GNSS-R)-based wind measurement technique have predominantly focused on spaceborne and airborne platforms, whereas research related to shipborne platforms is relatively lacking. However, owing to the low altitude of shipborne receiving equipment, the Glistening Zone is concentrated in a small chip range. Therefore, based on the different slopes’ change in the front and rear stages of the time-delay waveforms, a threshold wind speed retrieval algorithm was established to improve the retrieval accuracy of shipborne GNSS-R. The experimental results using an actual ship show that the algorithm produces smaller root-mean-square error and mean error, and a maximum deviation of less than 2 m/s.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Azimuthal Variation of L-Band Tilting Roughness Inside Tropical Cyclones

    • Free pre-print version: Loading...

      Authors: Paul A. Hwang;
      Pages: 1 - 5
      Abstract: With a wind wave spectrum model and input of surface wind speed and dominant wave period, the L-band lowpass mean square slope (LPMSS) can be calculated. Wind and wave data simultaneously measured in four different hurricane hunter missions are analyzed to study the spatial pattern of LPMSS inside tropical cyclones (TCs). There is a clear azimuthal variation in the LPMSS dependence on wind speed. Dividing the TC coverage area into quarters or halves with reference to the TC heading for the same wind speed, the LPMSS in the back quarter (half) is about 12% higher than that in the front quarter (half) for wind speeds up to about 50 m/s. The LPMSSs of the left and right quarters are between those of the front and back quarters and with much smaller differences. There is indication that the LPMSS wind speed dependence steepens in winds greater than 50 m/s, which occurs more frequently in the right half of the TC coverage area. Including all data available with a maximum wind speed up to 67 m/s, the front/back LPMSS difference is about 20%.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Improving CO₂ Concentration Profile Measurements From a Ground-Based
           CO₂-DIAL Through Conditional Adjustment

    • Free pre-print version: Loading...

      Authors: Tianqi Shi;Xin Ma;Ge Han;Zhipeng Pei;Hao Xu;Haowei Zhang;Wei Gong;
      Pages: 1 - 5
      Abstract: Ground-based differential absorption lidar (DIAL) can measure vertical CO2 concentration profiles in the troposphere. Here, we propose a method of improving the accuracy and precision of CO2 concentration profiles measurements. This method combines a conditional adjustment with Chebyshev fitting to reduce the error of the retrieved results in view of the received signal around the atmospheric boundary layer (ABL) with a high signal-to-noise ratio (SNR). Simulation experiments verified the effectiveness of this method. The accuracy of CO2 concentration profiles can be improved larger than 83.4% when compared with that via traditional methods, and the standard deviation of the measured CO2 concentration profiles calculated by our method was reduced by approximately 0.43–22.51 ppm when compared with the results calculated by traditional methods. Two real cases in different locations were also examined with the proposed technique. The results indicated the applicability of our method in measuring other trace gases by using DIAL.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Scene Aggregation Network for Cloud Detection on Remote Sensing Imagery

    • Free pre-print version: Loading...

      Authors: Xi Wu;Zhenwei Shi;
      Pages: 1 - 5
      Abstract: There has been a breakthrough in cloud detection by using convolutional neural networks (CNNs) during these years. However, there are still weaknesses among current cloud detection algorithms because only cloud mask information is used. As clouds represent differently in different scenes, the scene information may give hints to improve cloud detection performance. Therefore, different from the previous cloud detection literature, in this letter, we propose an end-to-end new deep learning network named scene aggregation network (SAN), which aggregates the scene information in the framework. Specifically, basic features are first extracted by utilizing all levels of network features. Then, the aggregated features used to produce the final cloud masks are created by fusing the basic features and the specially introduced scene information. Experimental results have demonstrated that with scene information aggregated, our proposed method can be robust on images with different scenes. Additionally, as SAN outperforms other state-of-the-art methods, our proposed method suits for cloud detection and can achieve improvement on this task.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Research of the Area of Generation of High-Frequency Infrasound
           Oscillations in the Sea of Japan, Caused by Typhoons

    • Free pre-print version: Loading...

      Authors: Grigory I. Dolgikh;Vladimir A. Chupin;Egor S. Gusev;
      Pages: 1 - 5
      Abstract: This letter discusses the results of microseismic oscillations’ recording in the “voice of the sea” range (5–10 Hz), generated jointly by wind waves and the wind during the passage of typhoons in the Sea of Japan. Amplitude-time dependence of these infrasonic oscillations’ variations is investigated, with account for their energy characteristics, determined on the laser-interference measuring complex data. As a result of accounting for the directional diagrams of the measuring devices, comparing the data obtained with satellite imagery and model data on the atmosphere surface layer, we determined the areas of signal generation in accordance with the change in the typhoons’ vortex components. The length of these areas is up to 300 km.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Multitask Learning for Human Settlement Extent Regression and Local
           Climate Zone Classification

    • Free pre-print version: Loading...

      Authors: Chunping Qiu;Lukas Liebel;Lloyd Haydn Hughes;Michael Schmitt;Marco Körner;Xiao Xiang Zhu;
      Pages: 1 - 5
      Abstract: Human settlement extent (HSE) and local climate zone (LCZ) maps are both essential sources, e.g., for sustainable urban development and Urban Heat Island (UHI) studies. Remote sensing (RS)- and deep learning (DL)-based classification approaches play a significant role by providing the potential for global mapping. However, most of the efforts only focus on one of the two schemes, usually on a specific scale. This leads to unnecessary redundancies since the learned features could be leveraged for both of these related tasks. In this letter, the concept of multitask learning (MTL) is introduced to HSE regression and LCZ classification for the first time. We propose an MTL framework and develop an end-to-end convolutional neural network (CNN), which consists of a backbone network for shared feature learning, attention modules for task-specific feature learning, and a weighting strategy for balancing the two tasks. We additionally propose to exploit HSE predictions as a prior for LCZ classification to enhance the accuracy. The MTL approach was extensively tested with Sentinel-2 data of 13 cities across the world. The results demonstrate that the framework is able to provide a competitive solution for both tasks.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Rain False-Alarm-Rate Reduction for CSCAT

    • Free pre-print version: Loading...

      Authors: Xingou Xu;Ad Stoffelen;Wenming Lin;Xiaolong Dong;
      Pages: 1 - 5
      Abstract: In tropical regions, Ku-band scatterometer observations are affected by heavy rain, and affected data are labeled in the quality control (QC) step during wind product generation. This is achieved by setting thresholds for QC indicators. Among the applied indicators, it has been shown that $J_{mathrm {oss}}$ can be beneficially applied for reducing the false alarm rate (FAR) for Ku-band observations for data sets collocated to C-band observations. In this letter, the FAR reduction method based on $J_{mathrm {oss}}$ is further generalized to be tested without collocated C-band observations, which extension is subsequently applied to the CSCAT wind products. Results prove the effectiveness of the FAR reduction method without C-band collocations for Ku-band scatterometers. Verification with rain rates from the Global Precipitation Mission (GPM) proves the capability of the recruited data set to benefit nowcasting applications. Moreover, the results of this research indicate the consistency of products in rainy conditions for the new rotating-fan-beam CSCAT and the existing rotating-pencil-beam Ku-band scatterometers. Further research would be to analyze detailed rain effects in different rain development stages in a wind vector cell (WVC) for tropical regions.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Deep Space Observations of Cloud Glints: Spectral and Seasonal Dependence

    • Free pre-print version: Loading...

      Authors: Tamás Várnai;Alexander Marshak;Alexander B. Kostinski;
      Pages: 1 - 5
      Abstract: From a distance of about one-and-a-half million kilometers, the Earth Polychromatic Camera (EPIC) onboard the Deep Space Climate Observatory (DSCOVR) spacecraft takes roughly hourly images of the sunlit side of the Earth. Earlier studies showed that these images often feature sun glint from water surfaces and from ice crystals that are suspended inside clouds in a horizontal orientation. This letter draws a wider view of the earlier analyses of observed glints caused by clouds, focusing on how the appearance of these glints varies with wavelength and season. The statistical analysis of all EPIC images taken in 2017 reveals that the wavelength dependence of glints is mainly shaped by the Rayleigh scattering and gaseous absorption caused by the air above the cloud top. The analysis also reveals that the radiative impact of cloud glints displays seasonal variations that are consistent with seasonal changes in the prevalence of ice clouds that were observed independently by the Moderate Resolution Imaging Spectroradiometer (MODIS).
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • The Environmental Story During the COVID-19 Lockdown: How Human Activities
           Affect PM2.5 Concentration in China'

    • Free pre-print version: Loading...

      Authors: Zhenyu Tan;Xinghua Li;Meiling Gao;Liangcun Jiang;
      Pages: 1 - 5
      Abstract: At the end of 2019, the very first COVID-19 coronavirus infection was reported and then it spread across the world just like wildfires. From late January to March 2020, most cities and villages in China were locked down, and consequently, human activities decreased dramatically. This letter presents an “offline learning and online inference” approach to explore the variation of PM2.5 pollution during this period. In the experiments, a deep regression model was trained to establish the complex relationship between remote sensing data and in situ PM2.5 observations, and then the spatially continuous monthly PM2.5 distribution map was simulated using the Google Earth Engine platform. The results reveal that the COVID-19 lockdown truly decreased the PM2.5 pollution with certain hysteresis and the fine particle pollution begins to increase when advancing resumption of work and production gradually.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • DeepDT: Generative Adversarial Network for High-Resolution Climate
           Prediction

    • Free pre-print version: Loading...

      Authors: Jianxin Cheng;Jin Liu;Qiuming Kuang;Zhou Xu;Chenkai Shen;Wang Liu;Kang Zhou;
      Pages: 1 - 5
      Abstract: Climate prediction is susceptible to a variety of meteorological factors, and downscaling technology is used for high-resolution climate prediction. This technology can generate small-scale regional climate prediction from large-scale climate output information. Inspired by the concept of image super resolution, we propose to apply the convolutional neural network (CNN) to downscaling technology. However, some unpleasant artifacts always appear in the final climate images generated by existing CNN-based models. To further eliminate these unpleasant artifacts, we present a new training strategy for the generative adversarial network, termed DeepDT. The key idea of our DeepDT is to train a generator and a discriminator separately. More specifically, we apply the residual-in-residual dense block as the basic frame structure to fully extract the features of the input. Additionally, we innovatively use a CNN model to fuse multiple climate elements to generate trainable climate images, and build a high-quality climate data set. Finally, we evaluate the DeepDT using the proposed climate data sets, and the experiments indicate that DeepDT performs best compared to most CNN-based models in climate prediction.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • On the Generation of Daily Gridded Ocean Surface Vector Wind Products From
           Scatsat-1

    • Free pre-print version: Loading...

      Authors: Abhisek Chakraborty;Atul Kumar Varma;Raj Kumar;
      Pages: 1 - 3
      Abstract: An optimal interpolation (OI)-based technique is utilized to generate global daily gridded wind products from Scatsat-1 data. The first guess (i.e., background) for the OI is used from the analyses of National Centre for Medium Range Weather Forecasting (NCMRWF) global operational model. The generated gridded products are subsequently validated using observations from global moored buoys and surface winds analyses from European Centre for Medium-Range Weather Forecasts (ECMWF), and that shows a root mean square error of ~1.3 m/s in wind speed and ~19° in wind direction. Along with the gridded winds, several wind-dependent products (e.g., wind stress, wind divergence, wind stress curl, sensible and latent heat flux, etc.) are also generated. The gridded products from Scatsat-1 are available freely from Meteorological and Oceanographic Satellite Data Archival Center (http://www.mosdac.gov.in) since October 03, 2016.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Bayesian Frequency-Dependent AVO Inversion Using an Improved Markov Chain
           Monte Carlo Method for Quantitative Gas Saturation Prediction in a Thin
           Layer

    • Free pre-print version: Loading...

      Authors: Yan-Xiao He;Gang He;Sanyi Yuan;Jianguo Zhao;Shangxu Wang;
      Pages: 1 - 5
      Abstract: One of the main objectives in the hydrocarbon reservoir characterization is determining rock and fluid properties that rely extensively on inference from seismic observations. In this letter, we present a novel Bayesian prestack inversion method using frequency-dependent amplitude versus offset (AVO) analysis with the goal to directly estimate gas saturation and porosity of a target thin reservoir zone. The proposed methodology is based on an improved Markov chain Monte Carlo (MCMC) sampling algorithm, which is computationally very coefficient due to its satisfactory acceptance probability and the convergence speed of Markov chains. Using a nonlinear rock physics model (RPM), properly calibrated for the investigating area, and a seismic forward operator based on the frequency-domain propagator matrix approach in the Bayesian inversion framework, we then evaluate the full posterior probability distribution of petrophysical parameters conditioned to seismic data and available prior information, using the MCMC algorithm in which we iteratively sample within the petrophysical property space. The proposed inversion approach is validated through applications to a synthetic reservoir model and the real seismic data from gas-bearing reservoirs with strong velocity dispersion.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Deep Precipitation Downscaling

    • Free pre-print version: Loading...

      Authors: Tingzhao Yu;Qiuming Kuang;Jiangping Zheng;Junnan Hu;
      Pages: 1 - 5
      Abstract: Precipitation downscaling, which is similar to the mechanism of single-image super-resolution (SR), aims to improve the spatial resolution of rain maps. It is of great practical value and theoretical significance. This letter presents a new deep precipitation downscaling (DPD) method, named auxiliary guided spatial distortion (AGSD) network, motivated by SR techniques. Specifically, an auxiliary guided module (AGM), which takes multiple meteorological elements (e.g., temperature, relative humidity, and wind) as input, is proposed for getting more accurate rain map features. Meanwhile, a simple but effective spatial distortion module (SDM) is proposed. Benefitting from SDM, the DPD model can rectify the rain map via terrain correlation. Furthermore, to improve the model performance among various rain intensity (including small rain, moderate rain, heavy rain, and storm), a threat score-driven pseudo threat-score (PTS) loss is presented. Experimental results compared with state-of-the-art methods demonstrate the superiority of the proposed method.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Retrieving the Optical Properties of Aerosols Over Land With Directional
           Polarimetric Camera Observations and an Adaptive Algorithm

    • Free pre-print version: Loading...

      Authors: Han Wang;Xiaobing Sun;Meiru Zhao;Leiku Yang;
      Pages: 1 - 5
      Abstract: The Directional Polarimetric Camera (DPC) is a polarization sensor mounted on Chinese Gaofen-5 satellite. It has the capability of observing multispectral, multiangular, and polarized light, and can be used to monitor global aerosols and clouds. This work developed an adaptive algorithm to retrieve aerosol properties based on DPC measurements. It performs initial surface property estimations, aerosol parameter retrievals, surface parameter adjustments, and result assessments. In the algorithm, it allows global aerosol optical depths (AODs) and Angstrom exponents (AEs) to be retrieved. The AOD values show good consistency with that from AErosol RObotic NETwork (AERONET) and Moderate Resolution Imaging Spectroradiometer (MODIS). The regression line between AODs from DPC and AERONET is $y = 0.895x + 0.056$ , with a correlation coefficient of 0.894, and 49% of the DPC-retrieved AODs are within the expected error range of ±(15%AOD +0.05). For the AEs, the regression line is $y = 0.728x + 0.395$ , the correlation coefficient is 0.763, and 41.4% of the AEs are within the error range of (AE ± 0.4). We also investigated the possible influence of AOD errors retrieved from the DPC measurements over three typical areas. It was found that though the DPC-retrieved dust aerosols did not show so good consistency with the MODIS measurements as the smoke aerosols, the retrievals still matched well on the whole. It demonstrates the potential of DPC and the adaptive algorithm for aerosol remote sensing.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Multitechnique Observations on the Impacts of Declining Air Pollution on
           the Atmospheric Convective Processes During COVID-19 Pandemic at a
           Tropical Metropolis

    • Free pre-print version: Loading...

      Authors: Gargi Rakshit;Soumyajyoti Jana;Animesh Maitra;
      Pages: 1 - 5
      Abstract: The present study addresses the impacts of reduced anthropogenic activities during the lockdown period of COVID-19 pandemic on the aerosol concentration, treated as heat absorbing agent, and on the related atmospheric processes, using ground-based and spaceborne measurements over a highly polluted Indian metropolis, Kolkata. The investigation reveals that reduced aerosol concentrations during the pre-monsoon of 2020, when the lockdown was implemented, decreased atmospheric instability as indicated by low values of the convective available potential energy (CAPE). This hindered the abundance of aerosols above the atmospheric boundary layer. Also, micro rain radar (MRR) observations showed a significant reduction of convective precipitation occurrences over Kolkata during this period. The back trajectory analysis has revealed the absence of continental component toward the wind clusters associated with rain occurrences during pre-monsoon 2020. This resulted in increased occurrences of stratiform rain events during the pre-monsoon of 2020 compared to the same period of previous years.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Estimation of Air Temperature under Cloudy Conditions Using
           Satellite-Based Cloud Products

    • Free pre-print version: Loading...

      Authors: Huapin Li;Hailei Liu;Minzheng Duan;Xiaobo Deng;Shenglan Zhang;
      Pages: 1 - 5
      Abstract: This letter presents a novel method for instantaneous air temperature under cloudy conditions ( $T_{a,text {cloudy}}$ ) estimation using satellite-derived cloud top temperature (CTT), cloud top height (CTH), and Global Forecast System (GFS) forecasts. The radiosonde profiles were used to analyze the relationship between $T_{a,text {cloudy}}$ and CTT, CTH. The results showed that it is feasible to estimate $T_{a,text {cloudy}}$ using CTT and CTH, especially for low and middle cloud conditions. Linear and neural network (NN)-based $T_{a,text {cloudy}}$ estimation models were constructed and validated using the Visible Infrared Imaging Radiometer Suite (VIIRS) CTT, CTH, and GFS $T_{text {air}}$ for summer 2017 and 2018. The NN model performs better than the linear model, and GFS $T_{text {air}}$ can obviously improve the accuracy of $T_{a,text {cloudy}}$ estimation. The correlation coefficient (R), root-mean-square error (RMSE), and bias of the NN model with GFS $T_{text {air}}$ were 0.953, 1.950 °C, and −0.030 °C, respectively. The estimation model performed better under low and warm clouds than high and cold cloud conditions.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Performance of Speckle Filters for COSMO-SkyMed Images From the Brazilian
           Amazon

    • Free pre-print version: Loading...

      Authors: Tahisa N. Kuck;Luis D. Gomez;Edson E. Sano;Polyanna da C. Bispo;Douglas D. C. Honório;
      Pages: 1 - 5
      Abstract: Speckle filtering is an important step for target detection in SAR images since this effect makes it difficult or even impossible to extract information from these images. There are several filters available in the literature although evaluating their performances is not a trivial task since it requires comparing the filtered images with a speckle-free image, which is generally unknown. This evaluation is even more complex when the features in the images are heterogeneous, for example, from tropical forests. The objective of this study is to evaluate the performance of the Lee, deGrandi, GammaMAP, single Anisotropic Nonlinear Diffusion (ANLD), multitemporal ANLD, Fast Adaptive Nonlocal SAR (FANS), and Fast GPU-Based Enhanced Wiener filters to reduce the speckle present in the COSMO-SkyMed Stripmap X-band images from the Brazilian Amazon forest region. The evaluation was conducted qualitatively through the visual inspection of the ratio image and the edge detection in the ratio images and quantitatively through the $alpha beta $ estimator and other statistical parameters of the filtered images. The GammaMAP filter showed the best performances, both qualitatively and quantitatively, and the FANS filter only qualitative.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • A Novel Thin Cloud Removal Method Based on Multiscale Dark Channel Prior
           (MDCP)

    • Free pre-print version: Loading...

      Authors: Shaoqi Shi;Ye Zhang;Xinyu Zhou;Jin Cheng;
      Pages: 1 - 5
      Abstract: Cloud contamination is a common phenomenon in the optical remote sensing field, which limits their application in land surface studies and causes the waste of satellite images. This letter presents a new framework for removing thin clouds from visible images based on multiscale dark channel prior (MDCP). The cloud removal of cloudy images (target images) is carried out with the assistance of a different temporal cloudless image (reference image) from the perspective view of multiscale transform (MST). In order to make it more suitable for the application of thin cloud removal, two improvements are made to this traditional fusion method. For one thing, a dark channel prior module is integrated into the low-frequency component of the target image in the framework of MST. For another, we choose the weighted average for high-frequency components and sparse representation (SR) for low-frequency components as fusion rules. After the fusion process, the modified Laplacian sharpening whose model is optimized is carried out. The performance of MDCP was evaluated with both simulated and real cloudy images. Experimental results show that the proposed MDCP has a good performance.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Precipitable Water Vapor Variation in the Clear-Cloud Transition Zone From
           the ARM Shortwave Spectrometer

    • Free pre-print version: Loading...

      Authors: Guoyong Wen;Alexander Marshak;
      Pages: 1 - 5
      Abstract: A new technique to retrieve precipitable water vapor (PWV) amount in the clear-cloud transition zone using ground-based zenith spectral radiance is developed. The method uses zenith radiances at the water vapor band at 720 nm and at the adjacent nonadsorbing band at 750 nm. Radiative transfer calculations show that the relative difference in zenith radiance between the two bands depends on PWV and the variations in cloud optical depth introduce a small change in the relative difference which is independent of PWV amount. This allows us to retrieve PWV variations in the clear-cloud transition zone for clouds over dark ocean surface. We applied this method to a Cu cloud case with zenith radiance observations by Shortwave Array Spectroradiometer-Zenith (SASZe) during the Marine ARM GPCI Investigation of Clouds (MAGIC) field campaign. We found that there is about 10% change in PWV amount from the known-cloudy region to known-clear sky in the cloud edges.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Validation of Synthetic Storm Technique for Rain Attenuation Prediction
           Over High-Rainfall Tropical Region

    • Free pre-print version: Loading...

      Authors: Swastika Chakraborty;Pooja Verma;Bishal Paudel;Ashish Shukla;Saurabh Das;
      Pages: 1 - 4
      Abstract: Validation of synthetic storm technique (SST) has been done for prediction of attenuation due to rain over a hilly, high-rainfall, tropical location, Shillong (25°N, 91°E), India. In this letter, considering one year of rain attenuation and rain rate data shows that SST predicted attenuation overestimates while comparing the available experimental result. Storm speed has been found to have no significant effect on the attenuation prediction by SST. Second-order rain attenuation prediction, i.e., prediction of fade slope, has also been studied. Fade slope is found to have been overestimated by SST for all categories of rain events at 20.2- and 30.3-GHz frequency. Exceedance plot of fade duration by SST shows an overestimation for higher frequency and underestimation for lower frequency.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Bio-Physical Changes in the Gulf of Mexico During the 2018 Hurricane
           Michael

    • Free pre-print version: Loading...

      Authors: Ebenezer S. Nyadjro;Zhankun Wang;James Reagan;Just Cebrian;Jay F. Shriver;
      Pages: 1 - 5
      Abstract: We investigate the impacts of one of the strongest recorded hurricanes to have hit the Florida Panhandle, Hurricane Michael (2018), on the upper ocean using a suite of satellite data, in situ profiles, and outputs from the HYbrid Coordinate Ocean Model (HYCOM). Strong, low-level cyclonic winds associated with the hurricane generated strong Ekman suction that propagated ahead of the hurricane and caused changes in the surface and subsurface ocean. Following the passage of Hurricane Michael, a 3 °C drop in sea surface temperature (SST) was accompanied with a 4–5 mg $text{m}^{-3}$ increase in chlorophyll-a concentration. In the subsurface, a $sim 15$ m mixed layer deepening preceded upward displacements of the isotherms and cooling of the mixed layer. The impact of hurricane conditions on sea surface salinity (SSS) was localized and influenced by competing processes, with upwelling of salty subsurface water increasing SSS and enhanced precipitation decreasing SSS. During the peak of the hurricane, the impact of upwelling was greater than that of enhanced precipitation and, thus, SSS increased. Further away from the upwelling centers, hurricane-influenced precipitation, and river runoff freshened SSS.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • A Novel Machine Learning Algorithm for Planetary Boundary Layer Height
           Estimation Using AERI Measurement Data

    • Free pre-print version: Loading...

      Authors: Jin Ye;Lei Liu;Qi Wang;Shuai Hu;Shulei Li;
      Pages: 1 - 5
      Abstract: Accurately determining the height of the planetary boundary layer (PBL) is important since it can affect the climate, weather, and air quality. Ground-based infrared hyperspectral remote sensing is an effective way to obtain this parameter. Compared with radiosonde measurements, its temporal resolution is much higher. In this study, a method to retrieve the PBL height (PBLH) from the ground-based infrared hyperspectral radiance data is proposed based on machine learning. In this method, the channels that are sensitive to temperature and humidity profiles are selected as the feature vectors, and the PBLHs derived from radiosonde are taken as the true values. The support vector machine (SVM) is applied to train and test the data set, and the parameters are optimized in the process. The data set collected at the Atmospheric Radiation Measurement (ARM) program Southern Great Plains (SGP) from 2012 to 2015 is analyzed. The instruments used in this letter include Atmospheric Emitted Radiance Interferometer (AERI), Vaisala CL31 ceilometer, and radiosonde. It shows that the root mean square error (RMSE) between the PBLHs calculated by the proposed method using AERI data and those from radiosonde data can be within 370 m, and the square correlation coefficient (SCC) is greater than 0.7. Compared with the PBLHs derived from the ceilometer, it can be found that the new method is more stable and less affected by clouds.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Diurnal Variations in Ocean Wind Speeds Measured by CYGNSS and Other
           Satellites

    • Free pre-print version: Loading...

      Authors: Yuchan Yi;Joel T. Johnson;Xiaochun Wang;
      Pages: 1 - 5
      Abstract: Ocean wind speed and/or wind vector measurements from the cyclone global navigation satellite system (CYGNSS), advanced scatterometer (ASCAT), and WindSat satellites are used to investigate diurnal wind variations over the tropical ocean using a method previously reported for diurnal amplitude estimation. The resulting diurnal variability in wind speed is examined in terms of its spatial and temporal properties. The results also show that the remotely sensed diurnal amplitudes obtained are largely consistent with those predicted by the existing reanalysis products such as the European Centre for Medium-range Weather Forecasts (ECMWF) ERA5.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Uncertainty in Aqua-MODIS Aerosol Retrieval Algorithms During COVID-19
           Lockdown

    • Free pre-print version: Loading...

      Authors: Muhammad Bilal;Zhongfeng Qiu;Janet E. Nichol;Alaa Mhawish;Md. Arfan Ali;Khaled Mohamed Khedher;Gerrit de Leeuw;Wang Yu;Pravash Tiwari;Majid Nazeer;Max P. Bleiweiss;
      Pages: 1 - 5
      Abstract: This letter reports uncertainties in the Aqua-Moderate Resolution Imaging Spectroradiometer (MODIS) Level 2 dark target (DT), deep blue (DB), and multiangle implementation of atmospheric correction (MAIAC) aerosol optical depth (AOD) during the COVID-19 lockdown period (February–May 2020) compared to the pre-COVID-19 period (February–May 2019). Validation of AOD retrievals was conducted against AErosol RObotic NETwork (AERONET) Version 3 Level 1.5 AOD data obtained from three sites located in urban (Beijing_CAMS and Beijing_RADI) and suburban (XiangHe) areas of China. The results show the poor performance of the DT and DB algorithms compared to the MAIAC algorithm, which performed better during the lockdown period. Overall, all MODIS algorithms overestimated the AOD and showed higher positive bias under high aerosol loading conditions during lockdown than during prelockdown. This is mainly attributed to the overestimation of the aerosol single-scattering albedo (SSA), which was found higher during lockdown than during the same period in 2019.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • A Spatiotemporal Attention Model for Severe Precipitation Estimation

    • Free pre-print version: Loading...

      Authors: Cong Wang;Ping Wang;Pingping Wang;Bing Xue;Di Wang;
      Pages: 1 - 5
      Abstract: Quantitative precipitation estimation (QPE) is an essential task in meteorology and hydrology and is of great significance for disaster prevention and control. The starting point of QPE is to establish a point-by-point mapping relationship between atmospheric observations and rain gauges. Traditional methods called Z-R relationships fit the parameters in a given paradigm to perform QPE under meteorology prior guidance. Methods based on machine learning (ML) construct the QPE models from statistical views, which could benefit from large historical data. However, in operational applications, these methods are challenging to estimate severe precipitation accurately. The reason is that severe precipitation is usually caused by convective systems. The point-by-point QPEs only focus on fixed isolated points and are difficult to characterize convective systems that cause precipitation effectively. In this letter, a spatiotemporal attention model is proposed for one-hour QPE. For each pixel, the spatiotemporal attention guides the model to find and focus on the most worthy attention region at each moment instead of a definite isolated point, making the model view more flexible and insightful. In experiments, the radar data from 2015 to 2016 in North China are used to train and evaluate the model. Compared with other methods, the results show that the spatiotemporal attention model could effectively improve the accuracy of QPE, especially for intense precipitation. The case study also shows that the operation of our model is more consistent with meteorological perspectives.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Possible Thermal Anomalies Associated With Global Terrestrial Earthquakes
           During 2000–2019 Based on MODIS-LST

    • Free pre-print version: Loading...

      Authors: Munawar Shah;Muhsan Ehsan;Ayesha Abbas;Arslan Ahmed;Punyawi Jamjareegulgarn;
      Pages: 1 - 5
      Abstract: The recent advances in satellite-based earthquakes (EQs) precursors provide an opportunity to correlate the seismic variation on lithosphere with atmosphere during the EQ preparation period through a rigorous atmospheric monitoring system. In the present study, seismic-induced thermal anomalies from cloud-free satellite thermal images of Moderate Resolution Imaging Spectroradiometer-Land Surface Temperature (MODIS-LST) are analyzed within a time interval of three months (precedent two months and succeeding one month to each EQ day) of 13 $text{M}_{w} ge6.0$ terrestrial EQs during 2000–2019. All these EQs occur in low vegetation and no snow cover regions except $text{M}_{w}~6.7$ , Siberia Russia event. Remote sensing data show evidence of significant perturbation with reference to confidence bounds in LST within 5–20 time window upon the antecedent and the descendant of EQ day. The studied thermal anomalies are obtained from LST values over the epicenter region. This work endorses the performance of MODIS-LST for detecting EQ-induced thermal anomalies in terrestrial regions with no vegetation and snow cover and also assisting to the development of lithosphere-atmosphere hypothesis over the epicenter region.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Wind-Generated Gravity Waves Retrieval From High-Resolution 2-D Maps of
           Sea Surface Elevation by Airborne Interferometric Altimeter

    • Free pre-print version: Loading...

      Authors: Qiufu Jiang;Yongsheng Xu;Hanwei Sun;Lideng Wei;Lei Yang;Quanan Zheng;Haoyu Jiang;Xiangguang Zhang;Chengcheng Qian;
      Pages: 1 - 5
      Abstract: This letter describes the new ability to measure wind-generated gravity waves using the airborne $Ka$ -band interferometric altimeter (AirKaIA). Although the original definition of wave parameters is derived from wave-induced sea surface elevation (WSSE), it is difficult to directly measure the WSSE, so most remote sensing of waves use other types of signals to obtain wave parameters. Here, we present the measurement of 2-D WSSE from AirKaIA. A new wave retrieval method based on the 2-D WSSE has been developed, tested with simulation data, and applied to AirKaIA data. The results indicate that the retrieved dominant wave directions, dominant wavelengths, and significant wave heights from AirKaIA are in agreement with in situ measurements while highlighting the need for further method tests using more observations. The study of ocean signals from interferometric altimeter is an emerging research topic. AirKaIA’s measurements of wind-generated gravity waves with 2-D WSSE have implications for the assessment of future interferometric altimeter missions.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Observation of Deep Occultation Signals in Tropical Cyclones With COSMIC-2
           Measurements

    • Free pre-print version: Loading...

      Authors: Paweł Hordyniec;Yuriy Kuleshov;Suelynn Choy;Robert Norman;
      Pages: 1 - 5
      Abstract: Global navigation satellite system (GNSS) signals in the radio occultation (RO) technique using new measurements from constellation observing system for meteorology, ionosphere & climate (COSMIC-2) mission were observed very deep below the Earth’s limb. Selected occultations collocated with severe tropical cyclones showed the existence of signal-to-noise ratio (SNR) variations at or below −200 km in terms of height of straight line (HSL) connecting a pair of occulting satellites. The presence of such signals is considered as indicative of sharp inversion layers associated with planetary boundary layer. We investigate the potential application of deep occultation signals for detection of tropical cyclones often resulting in strong vertical gradients of refractivity. The most prominent deep signatures computed using 1 s running mean filter can reach 400 V/V, whereas the majority of deep signals exceed the noise level by a factor of two. The cross-satellite interference is important mechanism affecting the structure of deep signals, especially for global positioning system (GPS) occultations.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Influence of Reduced Anthropogenic Activities on Rain Microphysical
           Properties and Related Atmospheric Parameters Over an Urban Tropical
           Location

    • Free pre-print version: Loading...

      Authors: Gargi Rakshit;Soumyajyoti Jana;Animesh Maitra;
      Pages: 1 - 5
      Abstract: This letter reveals the prevailing scenario of raindrop size distribution (DSD) in terms of mass-weighted mean drop diameter ( $D_{m}$ ) over a tropical metropolis, Kolkata (22.57°N, 88.37°E), India, in a contrasting aerosol environment that occurred during the COVID-19 pandemic in the absence of usual human activities. In the premonsoon months (March–May), the probability of $D_{m}$ values exceeding 2 mm has increased in 2020, indicating the dominance of large raindrops, compared to the years 2017–2019. Increased number densities of larger drops have influenced the drop fall velocity spectrum as measured by a laser precipitation monitor in terms of the percentage occurrence of high-velocity small drops (superterminal) and low-velocity large drops (subterminal) for both convective and stratiform precipitations. As measured from a Ka-band microrain Doppler radar, the mean melting layer altitude during stratiform rain has decreased by ~800 m during the premonsoon of 2020 compared to 2017–2019. According to the ERA-5 reanalysis data, changing rain microphysical characteristics are related to decreasing zero-degree isotherm height and reduced wind shear.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • A Correlation Context-Driven Method for Sea Fog Detection in
           Meteorological Satellite Imagery

    • Free pre-print version: Loading...

      Authors: Yixiang Huang;Ming Wu;Jun Guo;Chuang Zhang;Mengqiu Xu;
      Pages: 1 - 5
      Abstract: Sea fog detection is a challenging and essential issue in satellite remote sensing. Although conventional threshold methods and deep learning methods can achieve pixel-level classification, it is difficult to distinguish ambiguous boundaries and thin structures from the background. Considering the correlations between neighbor pixels and the affinities between superpixels, a correlation context-driven method for sea fog detection is proposed in this letter, which mainly consists of a two-stage superpixel-based fully convolutional network (SFCNet), named SFCNet. A fully connected Conditional Random Field (CRF) is utilized to model the dependencies between pixels. To alleviate the problem of high cloud occlusion, an attentive Generative Adversarial Network (GAN) is implemented for image enhancement by exploiting contextual information. Experimental results demonstrate that our proposed method achieves 91.65% mIoU and obtains more refined segmentation results, performing well in detecting fogs in small, broken bits and weak contrast thin structures, as well as detects more obscured parts.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • A Proof of Concept for Estimating the Annual Atmospheric Carbon Dioxide
           Variation From Orbiting Carbon Observatory-3 vEarly Data

    • Free pre-print version: Loading...

      Authors: Barun Raychaudhuri;Santanu Roy;
      Pages: 1 - 5
      Abstract: This work investigates the possibility of estimating the seasonal variation of global carbon dioxide (CO2) from the data procured by Orbiting Carbon Observatory-3 (OCO-3) during the global lockdown related to the novel coronavirus (COVID-19) pandemic. A comparative analysis with the National Aeronautics and Space Administration’s (NASA’s) Orbiting Carbon Observatory-2 (OCO-2) is carried out using the time series data on column-averaged dry air CO2 mole fraction ( $x$ CO2) and solar-induced fluorescence (SIF), a parameter pertinent to CO2, for nine crowded urban places and nine unpopulated places with negligible human activity, each of $2^{circ } times 2^{circ }$ area selected randomly from different global locations. The resulting similarities and dissimilarities in the trends of the seasonal variations of $x$ CO2 and SIF give clear indication of a reduction in the CO2 column average, especially in the crowded urban regions, which experienced restricted fossil fuel burning situation during the global COVID-19 pandemic in year 2020. A wavelet coherence technique is suggested for quantifying the temporary reduction using the OCO-2 data recorded in years 2018–2020 as reference. This methodology is hoped to be useful in future comparison of OCO-3 with its own annual data.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Transformer for EI Niño-Southern Oscillation Prediction

    • Free pre-print version: Loading...

      Authors: Feng Ye;Jie Hu;Tian-Qiang Huang;Li-Jun You;Bin Weng;Jian-Yun Gao;
      Pages: 1 - 5
      Abstract: Accurate prediction of EI Niño-southern oscillation (ENSO) is of great significance to seasonal climate forecast. Recently, a convolutional neural network (CNN) has shown an optimal skill for ENSO prediction. However, it is difficult for the convolutional kernel to capture long-range precursors of ENSO due to its build-in local property. The transformer model has long been used in natural language processing (NLP) for its ability to focus on global features. Here, we introduce it to the ENSO research community and propose the ENSO transformer (ENSOTR). We show that using the ENSOTR model, the monthly average Niño3.4 index can be skillfully predicted up to one and a half years ahead. The model can also predict strong EI Niño cases more than a year ahead, such as 1997–1998. Experimental results show that our model achieves better skill than CNN for ENSO prediction.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Ocean Temperature Prediction Based on Stereo Spatial and Temporal 4-D
           Convolution Model

    • Free pre-print version: Loading...

      Authors: Xinyi Zuo;Xiaofeng Zhou;Daquan Guo;Shuai Li;Shurui Liu;Chunhui Xu;
      Pages: 1 - 5
      Abstract: Ocean temperature prediction has always occupied an important position in the research of ocean-related fields. The current studies are mostly based on the temperature of the sea surface, but the prediction of ocean internal temperature is more important in practical applications. At present, most of the research studies on the prediction of ocean internal temperature are based on time series, few of which consider the dual characteristics of time and space. Therefore, the accuracy is insufficient, especially for the prediction of thermocline and deep-sea locations. This letter proposes the stereo spatial and temporal 4-D convolution model (SST-4D-CNN) to predict the temperature in the ocean, which fully considers the dual characteristics of time series and oceanic spatial relationship to improve the prediction accuracy. The model includes 4-D convolution module, residual module and recalibration module to predict the horizontal and profile temperature changes from the sea surface to 2000-m underwater. In this letter, the prediction experiment is carried out using the real-time analysis data-temperature dataset from National Marine Data Center. The results show that the accuracy of this method in horizontal and profile prediction is above 98.02%, and most of them are more than 99%.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Prediction of Synoptic-Scale Sea Level Pressure Over the Indian Monsoon
           Region Using Deep Learning

    • Free pre-print version: Loading...

      Authors: Aryaman Sinha;Mayuna Gupta;K. S. S. Sai Srujan;Hariprasad Kodamana;S. Sandeep;
      Pages: 1 - 5
      Abstract: The synoptic-scale (3–7 days) variability is a dominant contributor to the Indian summer monsoon (ISM) seasonal precipitation. An accurate prediction of ISM precipitation by dynamical or statistical model remains a challenge. Here, we show that the sea level pressure (SLP) can be used as a proxy to predict the active-break cycle as well as the genesis of low-pressure systems (LPSs), using a deep learning model, namely convolutional long short-term memory (ConvLSTM) networks. The deep learning model is able to reliably predict the daily SLP anomalies over central India and the Bay of Bengal at a lead time of 7 days. As the fluctuations in SLP drive the changes in the strength of the atmospheric circulation, the prediction of SLP anomalies is useful in predicting the intensity of ISM. A comparison of the ConvLSTM predicted SLP with the forecast of a conventional numerical weather prediction model indicates that the deep learning model possesses better skill in capturing the synoptic-scale SLP fluctuations over central India and Bay of Bengal.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • An Effective Convolutional Neural Network for Visualized Understanding
           Transboundary Air Pollution Based on Himawari-8 Satellite Images

    • Free pre-print version: Loading...

      Authors: Fangzhou Lin;Chenyang Gao;Kazunori D. Yamada;
      Pages: 1 - 5
      Abstract: Air pollution is a societal and cross-boundary environmental problem that can be visualized using a satellite. Satellite imaging is not only useful to the home country but also to the neighboring countries. Moreover, monitoring the movement of air pollution can help susceptible people avoid acid rain and photochemical smog. Using advanced remote sensing (RS) images, substantial information can be obtained, which can produce numerous effective methods for visualizing air pollution. In this article, a novel method for extracting air pollution has been proposed; it applies various pipeline networks along with a focus area method to exploit the spectral aspect information. Afterward, three indices with numerous modified fully convolutional networks (FCNs) were extracted. Then, by employing a multivote module, visualized air pollution can be presented. In the conducted experiments, five-year Himawari-8 satellite images have been utilized in the North–East Asia area to validate the frameworks. Furthermore, the experimental result indicating that the given methods could effectively visualize air pollution. Source code and data sets are available at https://github.com/ark1234/Himawari-8-based-visualized-understanding.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • A Long Short-Term Memory-Based Solar Irradiance Prediction Scheme Using
           Meteorological Data

    • Free pre-print version: Loading...

      Authors: Mohtasin Golam;Rubina Akter;Jae-Min Lee;Dong-Seong Kim;
      Pages: 1 - 5
      Abstract: Solar irradiance prediction is an indispensable area of the photovoltaic (PV) power management system. However, PV management may be subject to severe penalties due to the unsteadiness pattern of PV output power that depends on solar radiation. A high-precision long short-term memory (LSTM)-based neural network model named SIPNet to predict solar irradiance in a short time interval is proposed to overcome this problem. Solar radiation depends on the environmental sensing of meteorological information such as temperature, pressure, humidity, wind speed, and direction, which are different dimensions in measurement. LSTM neural network can concurrently learn the spatiotemporal of multivariate input features via various logistic gates. Moreover, SIPNet can estimate the future solar irradiance given the historical observation of the meteorological information and the radiation data. The SIPNet model is simulated and compared with the actual and predicted data series and evaluated by the mean absolute error (MAE), mean square error (MSE), and root MSE. The empirical results show that the value of MAE, MSE, and root mean square error of SIPNet is 0.0413, 0.0033, and 0.057, respectively, which demonstrate the effectiveness of SIPNet and outperforms other existing models.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • ATMConvGRU for Weather Forecasting

    • Free pre-print version: Loading...

      Authors: Tingzhao Yu;Qiuming Kuang;Ruyi Yang;
      Pages: 1 - 5
      Abstract: Weather forecasting, which is challenging due to the complex atmospheric correlation, focuses on providing explicit meteorological estimations as accurate as possible. Recently, techniques based upon convolutional-recurrent networks have shown dramatic performance in domains including radar echo prediction and precipitation forecasting, indicating that deep learning models have great potential in this area. However, existing methods concentrate on adding extra paralleled memory cells to the inner recurrent unit, where the information is mutually independent. To extract spatial–temporal features with stronger correlation, this letter introduced an axial attention memory module with quasi state-in-state cascaded manner. Benefitting from this unit, the spatial–temporal features can be aggregated and embedded into standard ConvGRU formulating Axial aTtention Memory Cascaded ConvGRU (ATMConvGRU) for sequential weather prediction. Experimental results compared with many state-of-the-art methods on four types of weather forecasting related datasets, including temperature, relative humidity, wind, and radar echo, demonstrate the effectiveness and superiority of the proposed ATMConvGRU.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Does AGRI of FY4A Have the Ability to Capture the Motions of
           Precipitation'

    • Free pre-print version: Loading...

      Authors: Siyu Zhu;Ziqiang Ma;
      Pages: 1 - 5
      Abstract: Calculating the motion vectors based on the infrared observations can complement the gaps of the passive microwave and radar observations. So, it is an essential step in numerical weather models and other meteorological applications. FengYun-4A (FY4A) geosynchronous satellite was launched in 2016 by the Chinese government. Carrying on board the Advanced Geosynchronous Radiation Imager (AGRI), FY4A can provide instantaneous observations from visible to infrared wavelength. However, the ability of FY4A to capture precipitation motions still needs to be explored, and the optimal scale for generating the motion vectors remains unclear. In this study, a reasonable sliding window strategy is applied to calculate the correlation coefficients (CCs) between two image sequences to determine the motion vectors. Based on this, the China Merged Precipitation Analysis (CMPA) data are recognized as the true precipitation data and are compared with the 10.7- $mu text{m}$ observations of AGRI aboard FY4A. The results in August 2018 show that based on the quantified directions of the motion vectors between the CMPA and FY4A-TBB (the Temperature of Black Body from FY4A), the CC and root mean square error (RMSE) are about 0.64 and 2.1, respectively, which are acceptable at the resolution of 0.5°. The result indicates that FY4A can capture precipitation motions. Meanwhile, as the resolution becomes lower, the probability distributions of the motion vectors in FY4A-TBB are more similar to those in CMPA, and they become stable at 0.5°. Therefore, 0.5° is considered the optimal resolution to generate the motion vectors for FY4A-TBB. The study results have great potentials for precipitation estimate retrieval and fusion for FY4A and also FY4B.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Satellite Remote Sensing of Daily Surface Ozone in a Mountainous Area

    • Free pre-print version: Loading...

      Authors: Songyan Zhu;Hao Zhu;Jian Xu;Qiaolin Zeng;Dejun Zhang;Xiaoran Liu;
      Pages: 1 - 5
      Abstract: High levels of surface ozone (O3) pollution threaten human and environmental health. Chongqing, a mountainous municipality located in southwest China, is exposed to serious O3 pollution and requires more studies. Due to its complex terrain and always foggy weather, it is difficult to maintain many in situ sites in Chongqing, and chemical transportation model (CTM) simulations are also challenged. The recently launched (in 2017) Sentinel-5p satellite provides O3 columns with advanced spatiotemporal resolution. Without the dependence on CTMs, we linked O3 columns and surface monitoring data from 2019 to 2021 in virtue of a deep forest machine learning model. Compared with another widely used machine learning model and previous studies, our results showed great advantages in estimating surface O3 on a daily scale. Validated against in situ sites in Chongqing, averaged $R^{2}$ of cross validations reached 0.9, while the root-mean-squared error (RMSE) and mean bias error (MBE) were 13.57 and $0.37~mu text {g}/text {m}^{3}$ , respectively. We found out that the model performance is associated with the relative height difference between training sites and the test site. The model performed stably when the height difference was lower than 200 m, but obvious performance degradation was seen when the height difference is exceeding 400 m.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Spatiotemporal Variation of Aerosol Optical Depth Based on 3-D
           Spatiotemporal Interpolation

    • Free pre-print version: Loading...

      Authors: Lei Zhang;Ming Zhang;
      Pages: 1 - 5
      Abstract: To solve the problem of low coverage of MODIS aerosol optical depth (AOD) products, this letter proposes a 3-D spatiotemporal interpolation method to predict missing values for time series AOD products. In this study, ordinary Kriging interpolation and 3-D spatiotemporal interpolation are applied to analyze the dynamics of AOD in Beijing–Tianjin–Hebei urban agglomeration (BTHUA), China, and the performances of the two methods are compared. The results show that the 3-D spatiotemporal interpolation has a better performance in predicting missing data of AOD products. The proposed interpolation method provides a feasible solution for the establishment of long-term MODIS aerosol products with temporal and spatial consistency, and also provides effective data support for the study of urban environmental changes.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Multi-Spectrum Hierarchical Segmentation Algorithm: A New Aerosol Optical
           Thickness Retrieval Algorithm for Urban Areas

    • Free pre-print version: Loading...

      Authors: Yunping Chen;Yue Yang;Yaju Xiong;Yuan Sun;
      Pages: 1 - 5
      Abstract: Retrieving aerosol optical thickness (AOT) from remote-sensing images of urban areas remains challenging, especially for bright-reflecting land surfaces. In this study, a novel algorithm, called multi-spectrum hierarchical segmentation (MSHS), was developed to retrieve the AOTs for urban surfaces. In this algorithm, the apparent reflectance of multiple shortwave infrared (SWIR) bands was employed and divided into tiny segments successively and hierarchically. Each segment was further segmented into object and nonobject parts using the Otsu algorithm in the coastal band. Hereafter, the congeneric apparent reflectance pixels of the object part were extracted, and the surface reflectance of this congener was obtained based on the minimum reflectivity and 6S model. AOT was then retrieved based on a precalculated lookup table (LUT) using the coastal band. Aerosol Robotic Network (AERONET) sun/sky radiometer measurements from 2013 to 2019 from Beijing, China, were used for validation. Results showed that the 30-m AOT retrievals obtained using Landsat-8 images exhibited good consistency with the ground-based measurements, with an overall correlation coefficient of ~0.871, expected error of ~59.04%, root mean square error of ~0.148, and mean absolute error of ~0.096. Compared to dense dark vegetation (DDV) algorithm, MSHS algorithm exhibited higher correlation and lower error. This implied that this new algorithm can help in characterizing aerosol distribution patterns within a city in a more refined way and provide support for tracing air pollution sources.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • MetPGNet: Meteorological Prior Guided Network for Temperature Forecasting

    • Free pre-print version: Loading...

      Authors: Qiuming Kuang;Tingzhao Yu;
      Pages: 1 - 5
      Abstract: High temperature is one of the most severe disasters in the world, which causes the death of millions of people each year. Accurate temperature forecasting, as a key member of weather prediction, is of great application value. Many recent contributions treat weather forecasting as a spatio-temporal learning task, in which these methods mainly capture the motion of a rigid body while neglecting the generation and dispersion of fluid elements. However, typical spatio-temporal prediction is quite different from meteorological forecasting. To resolve this key issue, this letter proposes MetPGNet, a meteorological prior guided network for hourly temperature forecasting. Specifically, under the framework of atmospheric theory, three simple but effective multidimensional attention branches, i.e., the advection branch, the vertical branch, and the temporal branch, are elaborately designed to depict the temperature variation of spatial atmospheric advection, vertical atmospheric movement, and temporal heat exchange, respectively. Experiments compared with state-of-the-art spatio-temporal learning and weather prediction methods demonstrate the superiority of the proposed MetPGNet. Specifically, MetPGNet gets an improvement of 0.52 on mean absolute error (MAE) compared with vanilla ConvGRU.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • A Deep Learning Framework for the Detection of Tropical Cyclones From
           Satellite Images

    • Free pre-print version: Loading...

      Authors: Aravind Nair;K. S. S. Sai Srujan;Sayali R. Kulkarni;Kshitij Alwadhi;Navya Jain;Hariprasad Kodamana;S. Sandeep;Viju O. John;
      Pages: 1 - 5
      Abstract: Tropical cyclones (TCs) are the most destructive weather systems that form over the tropical oceans, with about 90 storms forming globally every year. The timely detection and tracking of TCs are important for advanced warning to the affected regions. As these storms form over the open oceans far from the continents, remote sensing plays a crucial role in detecting them. Here we present an automated TC detection from satellite images based on a novel deep learning technique. In this study, we propose a multistaged deep learning framework for the detection of TCs, including, 1) a detector—Mask region-convolutional neural network (R-CNN); 2) a wind speed filter; and 3) a classifier—convolutional neural network (CNN). The hyperparameters of the entire pipeline are optimized to showcase the best performance using Bayesian optimization. Results indicate that the proposed approach yields high precision (97.10%), specificity (97.59%), and accuracy (86.55%) for test images.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Evaluating the Reliability of Air Temperature From ERA5 Reanalysis Data

    • Free pre-print version: Loading...

      Authors: Barry McNicholl;Yee Hui Lee;Abraham G. Campbell;Soumyabrata Dev;
      Pages: 1 - 5
      Abstract: The reliability of European Remote Sensing 5 (ERA5) satellite-based air temperature data is under investigation in this letter. To evaluate this, the ERA5 data will be compared with land-based data obtained from weather stations on the global historical climatology network (GHCN). Two climate regions are taken into consideration, temperate and tropical. Five years worth of data is collected and compared through box plots, regression models, and statistical metrics. The results show that the satellite temperature performs better in the temperate region than the tropical region. This suggests that the time of year and climate region have an impact on the accuracy of the satellite data as milder temperatures produce better approximations.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Thin Cloud Removal for Remote Sensing Images Using a Physical-Model-Based
           CycleGAN With Unpaired Data

    • Free pre-print version: Loading...

      Authors: Yue Zi;Fengying Xie;Xuedong Song;Zhiguo Jiang;Haopeng Zhang;
      Pages: 1 - 5
      Abstract: Thin cloud removal from remote sensing (RS) images is challenging. Recently, deep-learning-based methods have achieved excellent results using supervised training on paired image data. However, in practice, real paired image data are unavailable. Therefore, in this letter, we propose a novel thin cloud removal method, a physical-model-based CycleGAN (PM-CycleGAN), which can be trained using only unpaired data. The PM-CycleGAN training process comprises forward and backward loops. The forward loop first decomposes a cloudy image into a cloud-free image, thin cloud thickness map, and thickness coefficient using three generators. Then, it combines these three components using a physical model to reconstruct the original cloudy image to obtain the cycle consistency constraint. The backward loop first uses the physical model to synthesize a cloud-free image, thin cloud thickness map, and thickness coefficient into a cloudy image, which are then decomposed into the original three components using the three generators. Visual and quantitative comparisons against several state-of-the-art (SOTA) methods on a cloudy image dataset demonstrated the superiority of PM-CycleGAN.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • ED-DRAP: Encoder–Decoder Deep Residual Attention Prediction Network
           for Radar Echoes

    • Free pre-print version: Loading...

      Authors: Hongshu Che;Dan Niu;Zengliang Zang;Yichao Cao;Xisong Chen;
      Pages: 1 - 5
      Abstract: Precipitation nowcasting is quite important and fundamental. It underlies various public services ranging from rainstorm warnings to flight safety. In order to further improve the prediction accuracy for the spatiotemporal sequence forecasting problem, we propose an encoder–decoder deep residual attention prediction network, which adaptively rescales the multiscale sequence- and spatial-wise features and achieves very deep trainable residual prediction by integrating global residual learning and local deep residual sequence and spatial attention blocks (RSSABs). Experiments in a real-world radar echo map dataset of South China show that compared with the ingenious PredRNN++, TrajGRU methods, and newly proposed Unet-based methods, our ED-DRAP network performs better on the precipitation nowcasting metrics, as well as occupies small GPU memory.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • An Adaptive Rainfall Estimation Algorithm for Dual-Polarization Radar

    • Free pre-print version: Loading...

      Authors: Leilei Kou;Jiaqi Tang;Zhixuan Wang;Yinfeng Jiang;Zhigang Chu;
      Pages: 1 - 5
      Abstract: Dual-polarization radar provides information about precipitation microphysics through drop size distribution and hydrometeor classification, and, therefore, can produce improvement in quantitative precipitation estimation. Rainfall relations combination is an optimization algorithm; however, optimally selecting the rainfall relation is challenging in dual-polarization rainfall estimation. In this study, an adaptive rainfall algorithm is developed using a logistic regression model to guide the choice of the optimal radar rainfall relation. The logistic model is established according to the matched dual-polarization radar data and rain gauge data. Only liquid particles are considered for the rainfall estimation determined by the hydrometeor classification of dual-polarization radar, and the polarimetric rainfall relations are obtained with a neural network algorithm based on the disdrometer data. The proposed algorithm is validated with C-band dual-polarization radar data, and the results show that the adaptive algorithm outperforms the single rainfall relation and conventional combination algorithm.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Daytime and Nighttime Medium-Scale Traveling Ionospheric Disturbances to
           the June 2015 Geomagnetic Storm Detected by GEONET

    • Free pre-print version: Loading...

      Authors: Jun Tang;Xin Gao;Yinjian Li;Zhengyu Zhong;
      Pages: 1 - 5
      Abstract: Medium-scale traveling ionospheric disturbances (MSTIDs) to the June 22 and 23, 2015 geomagnetic storm over Japan are investigated by using the Global Navigation Satellite System Earth Observation Network of Japan (GEONET) in this letter. We have detected two groups of MSTIDs on June 22 and 23 and a negative ionospheric disturbance response on June 22 observed by the high-resolution detrended total electron content (TEC) maps from GPS observations. The negative ionospheric response (IR) performs a large-scale ionosphere depletion covering a wide range of areas (~125°E to ~140°E and ~25°N to ~40°N) simultaneously, which starts at 1900 universal time (UT) [04:00 local time (LT)] with a period of ~30 min on June 22. Compared with typical MSTIDs, the nighttime and the daytime MSTIDs in this letter both have a southwestward propagated direction and a propagated velocity of ~87.8 and ~157.8 m/s, respectively. The physical sources of the IRs over Japan during this geomagnetic storm are possibly attributed to the prompt penetration electric field (PPEF) and lower atmospheric gravity waves (AGW) referring to the previous studies. We believe that these findings can contribute to the complement of ionospheric research on MSTIDs over Japan.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Retrieval of Multiple Atmospheric Environmental Parameters From Images
           With Deep Learning

    • Free pre-print version: Loading...

      Authors: Peifeng Su;Yongchun Liu;Sasu Tarkoma;Andrew Rebeiro-Hargrave;Tuukka Petäjä;Markku Kulmala;Petri Pellikka;
      Pages: 1 - 5
      Abstract: Retrieving atmospheric environmental parameters such as atmospheric horizontal visibility and mass concentration of aerosol particles with a diameter of 2.5 or 10 ${mu }text{m}$ or less (PM2.5, PM10, respectively) from digital images provides new tools for horizontal environmental monitoring. In this study, we propose a new end-to-end convolutional neural network (CNN) for the retrieval of multiple atmospheric environmental parameters (RMEPs) from images. In contrast to other retrieval models, RMEP can retrieve a suite of atmospheric environmental parameters including atmospheric horizontal visibility, relative humidity (RH), ambient temperature, PM2.5, and PM10 simultaneously from a single image. Experimental results demonstrate that: 1) it is possible to simultaneously retrieve multiple atmospheric environmental parameters; 2) spatial and spectral resolutions of images are not the key factors for the retrieval on the horizontal scale; and 3) RMEP achieves the best overall retrieval performance compared with several classic CNNs such as AlexNet, ResNet-50, and DenseNet-121, and the results are based on experiments on images extracted from webcams located in different continents (test $R^{2}$ values are 0.63, 0.72, and 0.82 for atmospheric horizontal visibility, RH, and ambient temperature, respectively). Experimental results show the potential of utilizing webcams to help monitor the environment. Code and more results are available at https://github.com/cvvsu/RMEP.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Simulating Tropical Cyclone Passive Microwave Rainfall Imagery Using
           Infrared Imagery via Generative Adversarial Networks

    • Free pre-print version: Loading...

      Authors: Fan Meng;Tao Song;Danya Xu;
      Pages: 1 - 5
      Abstract: Tropical cyclones (TCs) generally carry large amounts of water vapor and can cause large-scale extreme rainfall. Passive microwave (PMW) rainfall (PMR) estimation of TC with high spatial and temporal resolution is crucial for disaster warning of TC, but remains a challenging problem due to low temporal resolution of microwave sensors. This study attempts to solve this problem by directly predicting PMW rainfall images (PMRIs) from satellite infrared (IR) images of TC. We develop a generative adversarial network (GAN) to simulate PMRI using IR images and establish the mapping relationship between TC cloud-top brightness temperature and PMR, and the algorithm is named tropical cyclone rainfall (TCR)-GAN. Meanwhile, a new dataset that is available as a benchmark, Dataset of TC IR-to-Rainfall Prediction (TCIRRP), was established, which is expected to advance the development of artificial intelligence in this direction. The experimental results show that the algorithm can effectively extract key features from IR. The end-to-end deep learning approach shows potential as a technique that can be applied globally and provides a new perspective TC precipitation prediction via satellite, which is expected to provide important insights for real-time visualization of TC rainfall globally in operations.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Long-Term Impact of Continental and Maritime Airflow on Aerosol
           Environment and Rain Microstructure Near Land–Sea Boundary

    • Free pre-print version: Loading...

      Authors: Gargi Rakshit;Soumyajyoti Jana;Animesh Maitra;
      Pages: 1 - 5
      Abstract: The present study deals with the interplay of multiple atmospheric processes in changing the microphysical properties of precipitation during the pre-monsoon season (March–May) using the long-term experimental data of raindrop size distributions (DSDs) spanning over 15 years (2005–2019) obtained at an urban tropical location, Kolkata (22.57°N, 88.37°E), near the land–sea boundary. The changing pattern of air mass flows from the maritime and continental region, which contribute to the formation of precipitation processes, has been responsible for the varying characteristics of rain. Changes in raindrop sizes are related to aerosol properties, cloud features, temperature, and relative humidity that change mass-weighted mean drop diameter ( $D_{m}$ ) differently in low and high rain rate regimes. $D_{m}$ has shown an increasing trend over time for low rain rates (< 15 mm/h), but a decreasing trend for high rain rate regimes (≥15 mm/h). An increase (decrease) in mean temperature (relative humidity) below the atmospheric boundary layer (< 1.6 km) has enhanced the evaporation of small raindrops and altered rain microphysical features. Based on satellite observations, it has been found that the increasing aerosol optical depth (AOD) has been accompanied by an increase in cloud effective radius (CER), resulting in the anti-Twomey effect, which is due to the dominance of maritime influence over continental activities. Because of the predominant maritime activities, sea salt aerosols have a greater presence, causing an increase in CER, which consequently prevents raindrops from becoming large enough before they fall, thereby reducing $D_{m}$- at high rainfall rates.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • An Informer Architecture-Based Ionospheric foF2 Model in the Middle
           Latitude Region

    • Free pre-print version: Loading...

      Authors: Cheng Bi;Peng Ren;Ting Yin;Yang Zhang;Bai Li;Zheng Xiang;
      Pages: 1 - 5
      Abstract: Monitoring of critical frequency variation in the ionospheric F2 layer (foF2) has lately received considerable attention for the frequency selection in skywave communication. Currently, both the deep learning and machine learning model have made a striking accomplishment in comprehending the ionosphere. In this letter, we utilize an Informer architecture to predict the foF2 parameter under the two scenarios in terms of the quiet space weather and storm events. The Informer method applied the past and present foF2 samples to capture time sequence processing characteristics, trained and tested for 2017–2018 years’ measurement samples at Beijing, China (40.3°N, 116.2°E). It is evident from the results that the Informer performed better than International Reference Ionosphere 2016, Elman network, long short-term memory (LSTM), and bidirectional LSTM models. The Informer models extensively captured the correlation within the foF2 sequence features and better predicted it in storm events.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • A Binned Triple Collocation for Estimating Regime-Dependent Uncertainties
           of Precipitation

    • Free pre-print version: Loading...

      Authors: Victor Pellet;
      Pages: 1 - 5
      Abstract: Triple collocation (TC)-based methods have become popular to estimate the uncertainty of many geophysical variables retrieved from satellite observations. The true advantage of these methods is that no ground-based truth is required and they can thus be applied on a global scale. So far, the TC-based methods have been limited to estimate the STandard Deviation (STD) at grid scale. These estimates represent an overall STD error for the precipitation products over each grid. Such information is useful to investigate sources of errors such as topography or surface properties, but as “static” information, it is limited and cannot represent precipitation error for a particular time step. Regime-dependent uncertainties of the satellite products are mandatory to better assess their quality and combine them a posteriori. In this letter, a simple and easy-to-implement method is introduced to estimate regime-dependent STD error of precipitation with the TC framework. Instead of considering collocation at grid scale, the method relies on clustering to distinguish various precipitation regimes. The method then estimates the corresponding STD errors of the three precipitation datasets for each one of the bins (i.e., clusters). These regime-dependent STDs offer a temporal as well as a spatial description of the error statistics. Tests are conducted for multisource precipitation estimates over Europe.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Ground-Based Remote Sensing of Total Columnar CO2, CH4, and CO Using
           EM27/SUN FTIR Spectrometer at a Suburban Location (Shadnagar) in India and
           Validation of Sentinel-5P/TROPOMI

    • Free pre-print version: Loading...

      Authors: Vijay Kumar Sagar;Mahesh Pathakoti;Mahalakshmi D.V.;Rajan K.S.;Sesha Sai M.V.R.;Frank Hase;Darko Dubravica;Mahesh Kumar Sha;
      Pages: 1 - 5
      Abstract: Greenhouse gases (GHGs) play an important role in controlling local air pollution as well as climate change. In this study, we retrieved column-averaged dry-air ( $X$ ) mole fractions of carbon dioxide (CO2), methane (CH4), and carbon monoxide (CO) using a ground-based EM27/SUN Fourier transform infrared spectrometer (FTIR). The EM27/SUN spectrometers are widely in use in the COllaborative Carbon Column Observing Network (COCCON). The PROFFAST software provided by COCCON has been used to analyze the measured atmospheric solar absorption spectra. In this letter, the diurnal variation and the time series of daily averaged $X$ CO2, $X$ CH4, and $X$ CO covering the period from December 2020 to May 2021 are analyzed. The maximum values of $X$ CO2, $X$ CH4, and $X$ CO are observed to be 420.57 ppm, 1.93 ppm, and 170.40 ppb, respectively. Less diurnal but clear seasonal changes are observed during the study period. $X$ CH4 and $X$ CO from the Sentinel-5Precursor (S5P)/TROPOspheric Monitoring Instrument (TROPOMI) are compared against the EM27/SUN retrievals. The correlation coefficient for the EM27/SUN retrieved $X$ CH4 and $X$
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Underwater Image Enhancement Using Laplace Decomposition

    • Free pre-print version: Loading...

      Authors: Mehwish Iqbal;Muhammad Mohsin Riaz;Syed Sohaib Ali;Abdul Ghafoor;Attiq Ahmad;
      Pages: 1 - 5
      Abstract: This letter presents underwater image enhancement using Laplace decomposition. Underwater image undergoes Laplace decomposition resulting in low- and high-frequency bands. Haze is removed from the low-frequency band, and then it is normalized for white balancing. The high-frequency band is amplified for edge preservation. Adding the two frequency images results in an enhanced image. It has improved, in contrast, color, object prominence, edge preservation, reduced artifacts, and naturalness as compared to other methods related to underwater image enhancement.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Discharge Estimation via Assimilation of Multisatellite-Based Discharge
           Products: Case Study Over the Amazon Basin

    • Free pre-print version: Loading...

      Authors: Charlotte M. Emery;Adrien Paris;Sylvain Biancamaria;Aaron Boone;Stephane Calmant;Pierre-Andre Garambois;Joecilia Santos Da Silva;Cedric H. David;
      Pages: 1 - 5
      Abstract: River flows are an essential component of the water cycle and are directly accessible for human consumption and activities. River water flux (i.e., river discharge) not only can be measured locally at in situ gauges but also can be estimated at larger scales with the river routing models. However, the number of in situ gauges is declining worldwide while emerging river-related products from satellites are becoming more available. Especially, discharge products based on satellite altimetry water elevations are emerging. These altimetry missions provide different spatial and temporal coverages and may not provide the same amount of information. In this study, discharge products from two satellite altimetry missions (ENVISAT and JASON-2) were assimilated into the large-scale hydrologic model Intéractions Sol-Biosphére-Atmosphére-CNRM’s Total Runoff and Integrating Pathways (ISBA-CTRIP) using an ensemble Kalman filter, to correct the simulated discharge. This work investigates whether it is better to assimilate products with a dense spatial coverage but a lower temporal sampling (ENVISAT) or the opposite (JASON-2). Three experiments have been performed: the first two assimilated each product separately, and the last one assimilated the combined product. The open-loop normalized root-mean-square error evaluated against in situ discharge (RMSEn) is 69%. RMSEn is decreased for all experiments. Specifically, it is slightly lower when assimilating ENVISAT-based discharge product (51%) than JASON-2 product (53%) as the ENVISAT-based product spatial coverage is denser. The best results are obtained when both products are assimilated (RMSEn=49%). These results are very encouraging and could be improved when the future Surface Water and Ocean Topography (SWOT)-wide swath altimetry mission discharge product will be available.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • A Method to Derive Bathymetry for Dynamic Water Bodies Using ICESat-2 and
           GSWD Data Sets

    • Free pre-print version: Loading...

      Authors: Nan Xu;Yue Ma;Hui Zhou;Wenhao Zhang;Zhiyu Zhang;Xiao Hua Wang;
      Pages: 1 - 5
      Abstract: Detailed information on lake bathymetry is essential for both hydrology-related studies and water resource management. Conventionally, lake bathymetry was mapped using high-cost approaches (e.g., ship/boat-based multibeam echosounders or airborne bathymetric lidars). With only satellite remotely sensed data sets, a method for deriving high-resolution bathymetry for dynamic areas was proposed by combining the new Ice, Cloud, and land Elevation Satellite-2 (ICESat-2) lidar data and the Landsat-based Global Surface Water Data Set (GSWD). First, ICESat-2 can provide accurate along-track topographic points after the point cloud processing and bathymetric error correction, and the GSWD can supply water occurrence information within the lake dynamic area between 1984 and 2018. Second, using the derived relationship between the elevation and water occurrence, the bathymetric map of Lake Mead, USA, was produced with the dynamic area exceeding 235 km2, elevation ranging nearly 37 m, and a resolution of 30 m. The local reference data (i.e., the airborne topographic lidar data and ship/boat-based bathymetric data) in six areas around Lake Mead were used for the validations. In general, the produced lake bathymetry achieved an accuracy of approximately 2 m in elevation with $R^{2}$ of 0.97. The proposed method is promising to obtain global bathymetry for inland water bodies (e.g., the lake and reservoir) and coastal areas (e.g., the tidal zone) where water level fluctuations are strong and the water clarity is sufficient.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Hierarchical Spatial–Spectral Features for the Chlorophyll-a
           Estimation of Lake Balik, Turkey

    • Free pre-print version: Loading...

      Authors: Erchan Aptoula;Sema Ariman;
      Pages: 1 - 5
      Abstract: Estimating reliably chlorophyll-a (Chl-a) concentration from remote sensing images constitutes a vastly superior alternative to field measurements. To this end, spectral pixel signatures are used commonly for developing regression models. Spatial information has been traditionally ignored in this context, as Chl-a concentration is a spatially localized measurement, and sensors’ spatial resolutions have been relatively low in the past. However, the increased spatial resolution of newer satellites and a recent study have given strong indications that spatial–spectral description can boost estimation performance. Consequently, in this letter, we address the problem of Chl-a estimation from remote sensing images using attribute profiles, one of the paramount spatial–spectral description tools. We further propose an original technique to remove their cumbersome threshold requirement via operating on each pixel’s “attribute lineage.” We validate our approach with multispectral Sentinel-2 images, and a data set formed by field measurements spanning almost two years over Lake Balik (Turkey). We show that the proposed method outperforms various alternatives in terms of regression performance, across multiple experimental setups, and finally, we highlight a validation malpractice encountered often in the field of water quality estimation.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • GrabRiver: Graph-Theory-Based River Width Extraction From Remote Sensing
           Imagery

    • Free pre-print version: Loading...

      Authors: Zifeng Wang;Jinbao Li;Yi Lin;Ying Meng;Junguo Liu;
      Pages: 1 - 5
      Abstract: River width can reveal the water extent and water flow on the earth’s surface. Remote sensing facilitates river width extraction at large scales in an automatic way. This letter proposes a new method named GrabRiver that implements whole-process automation from image preparation to river width calculation. It also, for the first time, develops river graph as the simultaneous river topology for width extraction, combining river planform morphology and network. Three major steps are proposed: 1) mapping and connecting rivers. The Multispectral Water Index (MuWI) is used to produce high-accuracy water maps from imagery, whereby specialized algorithms are used to reduce the impacts from nonriver water (lakes, reservoirs, wetlands) and on-channel objects (bridges, dams, ships) and to enforce river connectivity; 2) Constructing the river graph. A connected river map is skeletonized into the graph while maintaining georeferences as properties of edges and nodes in the river graph, and it is followed by river graph pruning to remove false and redundant river tributaries in the topologic structure; and 3) Measuring river widths. The cross-sectional measure is conducted on the river-reach (graph edge) basis, where orthogonals to centerlines are determined by the bounding geometry. In our experiments, the output results of GrabRiver are consistent with the reference river widths ( $R^{2} = 0.98$ in the mean width validation and $R^{2} = 0.91$ in the transient width validation). Despite that GrabRiver is a promising method, random uncertainty in water mapping is identified as the major source of width measurement errors. The outputs of GrabRiver will be applicable in fluvial analysis and satellite-derived discharge estimates.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Assessing the Ocean Surface Current Impact on Scatterometer (C- and
           Ku-Bands) and Altimeter (Ka-Band) Derived Winds in the Bay of Bengal

    • Free pre-print version: Loading...

      Authors: Rashmi Sharma;Neeraj Agarwal;Abhisek Chakraborty;Subrat Mallick;Raj Kumar;
      Pages: 1 - 5
      Abstract: A 2-year data set from Indian Space Research Organizations (ISRO’s) scatterometer mission (SCATSAT-1) has been used to investigate the impact of ocean surface current on the derived winds in the Bay of Bengal. For this purpose, wind speed residuals obtained between Ku-band SCATSAT-1 and buoy were regressed with buoy measured ocean surface currents. Results show a good agreement between wind residuals and surface current under stable air–sea interaction conditions for the region signifying a considerable impact of currents on the radar backscatter. A further analysis was carried out to ascertain the quantitative impact of currents on the C-band ASCAT derived winds and Ka-band SARAL/AltiKa derived wind speed. This study showed that impact of surface current is much higher on Ka-band altimeter-derived wind speed when compared to C-band and Ku-band scatterometer-derived wind speed. The correlation coefficient so obtained is found to be −0.34 in the case of Ka-band and nearly −0.26 for C-band and Ku-band scatterometer-derived winds. Higher correlation magnitude in the case of Ka-band suggests that surface current impact is slightly more for Ka-band when compared to C- and Ku-bands. These statistics suggest that wind speed retrieved from radar systems are indeed current relative and not fixed earth relative. Basin scale analysis for the Bay of Bengal indicates that surface current feedback in the Tropical Ocean Global Atmosphere Coupled Ocean-Atmosphere Response Experiment (TOGA-COARE) flux formulation results in 5%–15% reduction in the mechanical energy input to the ocean.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • A GLRT-Based Polarimetric Detector for Sea-Surface Weak Target Detection

    • Free pre-print version: Loading...

      Authors: Yixin Zhang;Qianqian Shu;Tao Jiang;
      Pages: 1 - 5
      Abstract: In this letter, different polarization characteristics of the sea clutter and target are considered to address the sea-surface weak target detection problem. We first construct a logarithmic generalized likelihood ratio test (log-GLRT) problem under the compound Gaussian model by considering multiple texture factors of sea clutter and four polarized channels. Based on the log-GLRT framework, a multivariable optimization problem is formulated to obtain the characteristic parameters of sea clutter and target. Then, under the block majorization-minimization (block-MM) framework, three parameters’ estimation strategies are designed to solve the optimization problem of the proposed parameters. Finally, a log-GLRT-based polarimetric detector is proposed by applying the estimated characteristic parameters. The experimental results on the Intelligent PIxel processing Xband (IPIX) data sets demonstrate that our proposed detector can achieve better detection performance than the several existed detectors.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Hybrid Attention Networks for Flow and Pressure Forecasting in Water
           Distribution Systems

    • Free pre-print version: Loading...

      Authors: Ziqing Ma;Shuming Liu;Guancheng Guo;Xipeng Yu;
      Pages: 1 - 5
      Abstract: Multivariate geo-sensory time series prediction is challenging because of the complex spatial and temporal correlations. In urban water distribution systems (WDSs), numerous spatial-correlated sensors have been deployed to continuously collect hydraulic data. Forecasts of the monitored flow and pressure time series are of vital importance for operational decision making, alerts, and anomaly detection. To address this issue, we proposed a hybrid dual-stage spatial–temporal attention-based recurrent neural networks (hDS-RNN). Our model consists of two stages: a spatial attention-based encoder and a temporal attention-based decoder. Specifically, a hybrid spatial attention mechanism that employs inputs along the temporal and spatial axes is proposed. Experiments on a real-world data set are conducted, which demonstrate that our model outperformed seven baseline models in flow and pressure predictions in WDS.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Underwater Acoustic Target Classification Based on Dense Convolutional
           Neural Network

    • Free pre-print version: Loading...

      Authors: Van-Sang Doan;Thien Huynh-The;Dong-Seong Kim;
      Pages: 1 - 5
      Abstract: In oceanic remote sensing operations, underwater acoustic target recognition is always a difficult and extremely important task of sonar systems, especially in the condition of complex sound wave propagation characteristics. The expensively learning recognition model for big data analysis is typically an obstacle for most traditional machine learning (ML) algorithms, whereas the convolutional neural network (CNN), a type of deep neural network, can automatically extract features for accurate classification. In this study, we propose an approach using a dense CNN model for underwater target recognition. The network architecture is designed to cleverly reuse all former feature maps to optimize classification rates under various impaired conditions while satisfying low computational cost. In addition, instead of using time–frequency spectrogram images, the proposed scheme allows directly utilizing the original audio signal in the time domain as the network input data. Based on the experimental results evaluated on the real-world data set of passive sonar, our classification model achieves the overall accuracy of 98.85% at 0-dB signal-to-noise ratio (SNR) and outperforms traditional ML techniques, as well as other state-of-the-art CNN models.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Google Earth Engine Implementation of the Floodwater Depth Estimation Tool
           (FwDET-GEE) for Rapid and Large Scale Flood Analysis

    • Free pre-print version: Loading...

      Authors: Brad G. Peter;Sagy Cohen;Ronan Lucey;Dinuke Munasinghe;Austin Raney;G. Robert Brakenridge;
      Pages: 1 - 5
      Abstract: The Floodwater Depth Estimation Tool (FwDET) provides rapid-response floodwater depth estimations during time-sensitive flood events. Recently, modern cloud-computing advancements and platforms, such as Google Earth Engine (GEE), have further enabled the streamlining and scalability of large-scale geoprocessing. This letter presents a FwDET implementation in GEE (FwDET-GEE) that is open access, utilizes cloud-stored elevation data, and performs geospatial analytics on the fly. This tool offers an innovative solution for producing timely floodwater data during flood activations that require emergency response and post-flood assessment. Accuracy metrics were generated to validate the comparability of FwDET-GEE to FwDETv2.0, which used Python in ArcGIS. To demonstrate the geographic scalability of the model, both local- and region-scale flood events/systems were evaluated. This letter also highlights a use case wherein flooded areas are overlain with building footprint data to identify infrastructure at risk of damage.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Satellite Data Analysis of the Upper Ocean Response to Hurricane Dorian
           (2019) in the North Atlantic Ocean

    • Free pre-print version: Loading...

      Authors: Corinne B. Trott;Bulusu Subrahmanyam;
      Pages: 1 - 5
      Abstract: A suite of satellite-derived data and high-resolution ocean model outputs were used to study the response of the upper ocean to Hurricane Dorian (2019), which impacted the Bahamas and the eastern coast of the United States in August and September of 2019. We observe enhanced upwelling that in conjunction with surface cooling from precipitation led to an approximate 4 °C drop in sea surface temperature (SST) along and slightly ahead of Dorian’s path. The upwelling also increased the local coastal chlorophyll-a levels. Soil Moisture Active Passive (SMAP) sea surface salinity (SSS) shows a clear eye and eye wall structure on September 4 (the day of peak intensity), which has never been seen due to the recency of the SMAP satellite’s launch and the strength of Hurricane Dorian (2019). The initial forecast path of Hurricane Dorian was set to travel northward through central Florida; however, we can see from satellite observations that a high-pressure system in the north Atlantic redirects the path of the hurricane offshore. We show a clear upper ocean response to Hurricane Dorian using satellite observations and hope that this multiparameter approach can improve the current quantification of air–sea interactions during Category 5 conditions.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Prediction of ENSO Beyond Spring Predictability Barrier Using Deep
           Convolutional LSTM Networks

    • Free pre-print version: Loading...

      Authors: Mayuna Gupta;Hariprasad Kodamana;S. Sandeep;
      Pages: 1 - 5
      Abstract: An accurate prediction of El Niño Southern Oscillation (ENSO) holds the key to produce skillful seasonal weather predictions across the globe. All the statistical and dynamical ENSO models developed in the past four decades face a common problem, spring predictability barrier, which is the sudden drop in the skill of the ENSO prediction when the forecast is initiated before the onset of boreal summer. Recent studies suggest that data-driven machine learning models can overcome the spring predictability barrier. We show that using a convolutional long short-term memory (ConvLSTM) network, the monthly mean Nino3.4 index can be skillfully predicted up to one year ahead. The model was also able to predict strong El Niño cases, such as 1997–1998 and 2015–2016 a year ahead. Our results suggest that the proposed ConvLSTM model has significant skill in multiseasonal weather predictions.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Using Sea Wave Simulations to Interpret the Sunglint Reflection Variation
           With Different Spatial Resolutions

    • Free pre-print version: Loading...

      Authors: Xinyi Wu;Yingcheng Lu;Junnan Jiao;Jing Ding;Wenxue Fu;Weixian Qian;
      Pages: 1 - 4
      Abstract: Ocean surface sunglint reflection is very important for detecting ocean surface roughness, oil spills, oceanic internal waves, and so on. Although statistical sunglint models (i.e., Cox–Munk model) have been used successfully on coarse-resolution spaceborne optical images for several decades, it is still a challenge to apply it to high spatial resolution images due to scale effects of the optical remote sensing. In this study, a sea wave model and the Pinhole camera model were employed to simulate the sunglint reflection images with different spatial resolutions and viewing angles. Coefficient of variation (CV) of sunglint reflection collected from various images indicates that there is uncertainty in sunglint reflection in images with different spatial resolutions. This study presents the applicability of sunglint statistical models in images with different spatial resolutions and viewing angles.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Potential of Melt Pond Fraction Retrieval From High Spatial Resolution
           AMSR-E/2 Channels

    • Free pre-print version: Loading...

      Authors: Yasuhiro Tanaka;Randall Kenneth Scharien;
      Pages: 1 - 5
      Abstract: Estimation of melt pond fraction (MPF) using the Advanced Microwave Scanning Radiometer for the Earth Observing System (EOS)/2 (AMSR-E/2) brightness temperature ( $T_{mathrm {B}}$ ) data is required for enhancing understanding of the role of melt ponds in the Arctic and in the earth’s climate system. An original MPF retrieval is based on gradient ratio (GR), defined as the normalized difference between the 6.9 GHz horizontal (H) channel and the 89.0 GHz vertical channel GR(6/89) of AMSR-E. However, using the coarsest spatial resolution 6.9 GHz channel includes potential land contamination in $T_{mathrm {B}}$ in regions of narrow waterways such as the Canadian Arctic Archipelago (CAA). This letter aims to provide a higher resolution MPF product, derived by using 10.7, 18.7, 23.8, 36.5, and 89.0 GHz $T_{mathrm {B}}text{s}$ at H-polarization instead of the 6.9 GHz $T_{mathrm {B}}$ H-polarization in the GR calculation. For GR(10/89)- and GR(18/89)-based MPF retrievals, the difference standard deviations were ~3.8%. This is lower than the ~14.3% standard deviation of the GR(23/89)-, GR(36/89)-, and PR(89)-based MPF retrievals. Our results suggest that the GR(10/89) and (18/89) MPF retrievals are available at a product quality similar to the original GR(6/89)-based MPF retrieval. We recommend that the GR(18/89) MPF retrieval adopted is used in nearshore environments such as in the CAA.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Application of Neural Networks for Dynamic Modeling of an
           Environmental-Aware Underwater Acoustic Positioning System Using Seawater
           Physical Properties

    • Free pre-print version: Loading...

      Authors: Ahmad A. Aziz El-Banna;Kaishun Wu;Basem M. ElHalawany;
      Pages: 1 - 5
      Abstract: Node localization is one of the major challenges that exist in underwater communication. Various techniques exist for terrestrial networks, while few of them are applicable in underwater networks due to the dynamic characteristic of the underwater channels, e.g., the lack of global positioning system (GPS) coverage under the water surface. Moreover, assorted environmental properties affect almost all employed communication techniques. In this letter, we propose an environmental-aware positioning system by considering the variations of the underwater speed of sound according to the dynamic changes in the physical properties of the seawater, such as temperature, salinity, and pressure, besides the internal waves’ effects. The proposed system employs the received signal strength (RSS) technique in estimating the distances between the network nodes. Moreover, we examine the application of various dynamic responses neural networks (NNs) in predicting the underwater node position, such as the feedforward, recurrent, time delay, and distributed delay NNs. The results show that the NN-based prediction models enhance the performance of the positioning system and could achieve small prediction errors in the range of 0.002 for both training and testing patterns.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Sea Surface Height Prediction With Deep Learning Based on Attention
           Mechanism

    • Free pre-print version: Loading...

      Authors: Jingjing Liu;Baogang Jin;Lei Wang;Lingyu Xu;
      Pages: 1 - 5
      Abstract: Sea surface height (SSH) prediction is theoretically and practically significant for global and regional ocean-related research. Numerous studies have been conducted to acquire accurate prediction results. However, most investigations on SSH ignore the importance of data at each time step on the prediction, which limits the accuracy of the final prediction. Therefore, a deep learning model combined Long Short-Term Memory (LSTM) network and Attention mechanism is proposed in this letter. This model integrates attention mechanism in both of time and space dimensions into LSTM. For time dimension, it assigns reasonable weight for data at each time step. For space dimension, it groups the data points close to each other, let model concentrate on points in the same group and eliminates the impact from other points. Daily absolute dynamic topography (ADT) in the South China Sea from January 2010 to December 2017 is adopted to conduct experiments. The proposed model demonstrates reliable results, the root mean square error is 0.38 cm, the mean absolute error is 0.0031, and the correlation coefficient reaches up to 0.999. The results show that the deep learning method based on attention mechanism is reliable for SSH prediction with high performance.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Mid-Term Simultaneous Spatiotemporal Prediction of Sea Surface Height
           Anomaly and Sea Surface Temperature Using Satellite Data in the South
           China Sea

    • Free pre-print version: Loading...

      Authors: Qi Shao;Wei Li;Guangchao Hou;Guijun Han;Xiaobo Wu;
      Pages: 1 - 5
      Abstract: Marine forecasting techniques based on data-driven method generally treat each variable as independent and analyze the time series of a single and specific variable, while the real marine environment is the result of the interaction of multiple variables. In this letter, a data-driven method combining the empirical orthogonal function of multivariate (MEOF), complete ensemble empirical mode decomposition (CEEMD), and multilayer perceptron (MEOF-CEEMD-MLP in brief) is proposed to perform mid-term prediction of daily sea surface height anomaly (SSHA) and sea surface temperature (SST) simultaneously, considering that there is a correlation between them in the real marine environment. In this model, application of MEOF not only considers the correlation between SSHA and SST but also establishes the temporal and spatial relationship between discrete points, making predictions more accurate. A case study in the South China Sea (SCS) that predicts the daily SSHA and SST 30 days ahead shows that MEOF-CEEMD-MLP model is highly promising for mid-term daily prediction of SSHA and SST simultaneously. Also, the correlation between these two kinds of ocean variables can be simulated very well by this prediction model.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Analysis of the High-Latitude Sea Surface Wind Acquisition Ability of
           Seven Satellite Scatterometers

    • Free pre-print version: Loading...

      Authors: Juhong Zou;Zhixiong Wang;Mingsen Lin;
      Pages: 1 - 5
      Abstract: Seven satellite scatterometers, namely, the C-band MetOp-A/Advanced Scatterometer (ASCAT), MetOp-B/ASCAT, MetOp-C/ASCAT, Ku-band HY-2A/SCAT, HY-2B/SCAT, Chinese-French Oceanography Satellite (CFOSAT)/SCAT, and SCATSAT-1/OceanSat Satellite Scatterometer (OSCAT2), are operating in orbits. These satellites make a high-frequency observation of sea surface winds possible, particularly at high latitudes. This work analyzes the passing time, passing frequency, coverage of these seven scatterometers, and the quality of high-latitude surface wind products. All the scatterometer wind products were reproduced with the same processing procedures, in terms of backscatter calibration, wind retrieval, numerical weather prediction (NWP) wind, and quality control. The target region (74–78 N, 167°–171 W) was chosen to analyze the passing frequency. A spatial grid of $0.25^{circ } times 0$ .25° in the range of 60° N–88° N was chosen to analyze the spatial coverage of the scatterometers. The results show that more than 40 observation times can be provided daily by all the seven scatterometers; however, there is a 9-h gap between UTC 9:00 and UTC 18:00, suggesting that international cooperation is needed for optimizing the equatorial crossing time in future scatterometer missions, such that an optimal virtual scatterometer constellation can be achieved. The scatterometer winds are compared with the European Centre for Medium-Range Weather Forecasts (ECMWF) Reanalysis 5th Generation (ERA5) winds, and with each other. The comparison results confirmed noticeable wind speed biases due to sea surface temperature (SST) in all Ku-band scatterometer winds with respect to the C-band scatterometer and ERA5 winds.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Weak Edge Identification Network for Ocean Front Detection

    • Free pre-print version: Loading...

      Authors: Qingyang Li;Guoqiang Zhong;Cui Xie;Rachid Hedjam;
      Pages: 1 - 5
      Abstract: Ocean fronts have an important influence on global ocean–atmosphere interactions and marine fishery. Hence, it is of great significance to obtain the positions of the ocean fronts. However, current ocean front detection research confronts two challenges: scarcity of labeled data and limitations of ocean front detection algorithms. To address these two problems, we have collected and labeled an ocean front data set and proposed a new deep learning model for ocean front detection. For concreteness, due to the weak edge property of the ocean fronts, we formulate ocean front detection as a weak edge identification problem and propose the weak edge identification network (WEIN) for ocean front detection. WEIN consists of four convolutional blocks. Each block has a side output layer used to detect front edges at a specific image representation level. The side outputs are then fused to predict (detect) the locations of the ocean fronts. In this work, we adopt two metrics to measure the experimental results, i.e., the $F_{1}$ -score and intersection over union (IoU). The experimental results with comparison to traditional and deep learning approaches demonstrate the superiority of WEIN for ocean front detection.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • An Evolving Sea Surface Temperature Predicting Method Based on
           Multidimensional Spatiotemporal Influences

    • Free pre-print version: Loading...

      Authors: Jiang Xie;Jiaming Ouyang;Jiyuan Zhang;Baogang Jin;Suixiang Shi;Lingyu Xu;
      Pages: 1 - 5
      Abstract: In global climate researches, marine ecosystem researches, and ocean-related applications, it is of considerable significance to accurately observe and predict sea surface temperature (SST). However, various physical and environmental factors affect the changes in SST, making it highly random and uncertain. Therefore, it is still a challenge to propose a highly accurate SST prediction method. SST prediction methods based on the temporal information usually focus on capturing the temporal influence of the historical SST but ignore the spatial influence in the sea area, so these methods meet the performance bottlenecks. To fuse the multidimensional spatiotemporal influence and further improve the accuracy of the SST prediction, this letter proposed the convolutional gated recurrent unit (GRU) with multilayer perceptron (CGMP) to predict SST in the Bohai Sea and the South China Sea. The convolutional layer of CGMP can capture the neighbor influence effectively in the spatial dimension, making up for the shortcomings of methods that are based on the temporal information and do not consider the spatial information. The GRU layer and the MLP layer of CGMP can process historical information effectively in the temporal dimension. Experiments showed that the prediction performance of CGMP was better than those of other comparison methods in different sea areas, different schemas, and different prediction scales. Besides, the error distribution law in the Bohai Sea daily mean SST prediction was explored.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Learning Relevant Features of Optical Water Types

    • Free pre-print version: Loading...

      Authors: Katalin Blix;Ana Belen Ruescas;Juan Emmanuel Johnson;Gustau Camps-Valls;
      Pages: 1 - 5
      Abstract: This work introduces a novel method that makes use of machine learning (ML) techniques to classify hyper- and multi spectral observations into optical water types (OWTs). Classification was done using $k$ -means clustering, which was followed by a feature relevance step based on the sensitivity analysis (SA) of the predictive mean and variance function of a Gaussian process (GP) regression model. The method was used both in training and predictive mode. The latter allows applying the approach for new unlabeled observations, so that the OWTs and the associated relevant features can automatically be assessed. The methods were studied on hyperspectral synthesized and in situ Arctic data, and were further evaluated on a test image acquired over Arctic seas. Good empirical results encourage wide adoption of the methodology to be applied in operational processing and assessment of water types.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • GRNN-Based Predictors of UHF-Band Sea Clutter Reflectivity at Low Grazing
           Angle

    • Free pre-print version: Loading...

      Authors: Peng-Lang Shui;Xiao-Fan Shi;Xin Li;Tian Feng;Xiao-Yun Xia;Yue Han;
      Pages: 1 - 5
      Abstract: As a basic characteristic of sea clutter, the reflectivity of sea surface depends on many factors. Various universal empirical models of low precision have been developed to predict the reflectivity of sea surface. In this letter, a method is proposed to train specific predictors by big data learning, where the universal empirical models are embedded to the architecture of the generalized regression neural network (GRNN) to enhance the learning ability and efficiency. On the sea clutter database measured by an island-based UHF-band radar in the offshore waters of the Yellow sea of China at low grazing angle, the GRNN-based predictors of different structures are compared with other predictors. The results on the database show that the GRNN-based predictors behave better at learning efficiency, prediction precision, and robustness.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • A Deep Learning Method for Ocean Front Extraction in Remote Sensing
           Imagery

    • Free pre-print version: Loading...

      Authors: Yangdong Li;Junhao Liang;Hengrong Da;Liang Chang;Hongli Li;
      Pages: 1 - 5
      Abstract: Oceanfront is a typical and important sea surface feature that is reported to be associated with marine ecosystems and can be used as a reference for locating fishing grounds. Frontal zone extraction is often performed using a gradient threshold to classify image pixels and the result can sometimes contain too many spikes and become chaotic, leading to a negative effect for visual interpretation. And most conventional methods that focus on extracting the ridges of fronts struggle with false fronts due to imperfect data. Also, choosing appropriate thresholds for them is another dilemma, which sometimes leads to too many frontal ridges in unwanted areas or too little than needed in the region of interest. To meet the needs for visual interpretation and automatic front detection in significant frontal areas, a novel method based on deep learning is proposed in this letter. In this method, a deep learning model with U-Net architecture was designed to detect and locate significant frontal zones in grayscale sea surface temperature (SST) images. Then, an area threshold was adopted to filter the output of the model to improve the result. To demonstrate the effect of the proposed method, it was applied to an example SST image. The results show that the proposed method can not only merge messy fronts but also capture the overall patterns of frontal zones and work with conventional methods to get a better frontal ridge extraction result.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Endorheic Waterbodies Delineation From Remote Sensing as a Tool for
           Immersed Surface Topography

    • Free pre-print version: Loading...

      Authors: Carole Delenne;Jean-Stephane Bailly;Antoine Rousseau;Renaud Hostache;Olivier Boutron;
      Pages: 1 - 5
      Abstract: For several decades, it becomes possible to delineate waterbodies and their dynamics from optical or radar images, that are now available at high spatial and temporal resolutions. We present here an interpolation approach that takes benefits from this waterbodies delineation in endorheic areas. It consists in computing isovalue contour lines to improve topography estimates classically obtained from measurement points only. The approach, based on a minimization problem, uses thin plate spline (TPS) interpolation functions, the coefficients of which are determined along with the unknown water level of each curve. Results obtained on a generated topography show that this approach, applied with three contour-line curves, yields a lower root mean square error (RMSE) using only one measurement point compared to the one obtained with nine points and the classical approach.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Spectral Anomaly Detection Based on Dictionary Learning for Sea Surfaces

    • Free pre-print version: Loading...

      Authors: Xiaolin Han;Huan Zhang;Weidong Sun;
      Pages: 1 - 5
      Abstract: Anomalies in remote sensing images are generally reflected in two aspects of spatial and spectral ones, as for the anomaly detection of sea surface using multispectral or hyperspectral images, spectral information is more important. To this end, a novel spectral anomaly detection method based on dictionary optimization is proposed in this letter. More specifically, the normal scene is first defined to distinguish the anomaly. Then, without any assumption about the distribution of anomaly, a spectral dictionary is formulated and derived theoretically with optimization to express the normal scenes. Using the sparse and low-rank constraints, the alternating direction method of multiplier (ADMM) is employed to solve the above optimization in the spectral domain. Finally, for a given sea-surface image to be detected, the error matrix that cannot be fully expressed by the optimized spectral dictionary is regarded as anomalies. It shows certain generality for various kinds of spectral anomalies on the sea surface. Taking multispectral images obtained by the HY-1C satellite as an example, comparisons with related state-of-the-art methods demonstrate that our proposed method achieves the best anomaly detection performance not only for oil-spill pollution but also for algae pollution.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Sea Surface Temperature Forecasting With Ensemble of Stacked Deep Neural
           Networks

    • Free pre-print version: Loading...

      Authors: Mohammad Jahanbakht;Wei Xiang;Mostafa Rahimi Azghadi;
      Pages: 1 - 5
      Abstract: Oceanic temperature has a great impact on global climate and worldwide ecosystems, as its anomalies have been shown to have a direct impact on atmospheric anomalies. The major parameter for measuring the thermal energy of oceans is the sea surface temperature (SST). SST prediction plays an essential role in climatology and ocean-related studies. However, SST prediction is challenging due to the involvement of complex and nonlinear sea thermodynamic factors. To address this challenge, we design a novel ensemble of two stacked deep neural networks (DNNs) that uses air temperature, in addition to water temperature, to improve the SST prediction accuracy. To train our model and compare its accuracy with the state-of-the-art, we employ two well-known datasets from the national oceanic and atmospheric administration as well as the international Argo project. Using DNNs, our proposed method is capable of automatically extracting required features from the input time series and utilizing them internally to provide a highly accurate SST prediction that outperforms state-of-the-art models.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Quantifying GNSS-R Delay Sea State Bias and Predicting Its Variation Based
           on Ship-Borne Observations in China’s Seas

    • Free pre-print version: Loading...

      Authors: Fan Wu;Wei Zheng;Zongqiang Liu;
      Pages: 1 - 5
      Abstract: Global navigation satellite system reflectometry (GNSS-R) is able to achieve intensive and high-frequency measurements of global sea levels. The sea state bias (SSB) makes the measurement uncertain. Based on ship-borne GNSS-R observations in China’s Seas, we obtained reflected signal delay. We constructed a new mean sea surface (MSS) reflection surface model to calculate the modeled reflection delay. By combining the observation and modeled reflection delay, we separated and quantified the SSB. The SSB was approximately 1.3 m for spring and summer alternate seasons in China’s Seas, with obvious differences in the spatial distribution of sea area, latitude, and distance from shore. Based on the quantified SSB and sea state parameters, we introduced reflection incident angle parameter and constructed a new parameter model of SSB suitable for GNSS-R. We applied the parameter model to predict variations in delay SSB. The parameter model had a variance explanation rate of approximately 70%, it can reliably predict large-scale SSB variations, and it performed better in higher elevation scenarios. This letter proposes a regional approach to quantify GNSS-R delay SSB and to predict its variations, and it is expected to be applied to GNSS-R satellite altimetry to support SSB correction.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Characterizing Ancient Channel of the Yellow River From Spaceborne SAR:
           Case Study of Chinese Gaofen-3 Satellite

    • Free pre-print version: Loading...

      Authors: Ning Li;Zhishun Guo;Jianhui Zhao;Lin Wu;Zhengwei Guo;
      Pages: 1 - 5
      Abstract: The lower reaches of the ancient Yellow River (AYR) migrated very frequently, like a loong swinging its tail on the land of China. As the origin of Chinese civilization, AYR provided natural conditions for the people to thrive. However, the sediment carried by AYR still has a negative impact on local agricultural production. This letter, based on Gaofen-3, extracted scattering characteristics of archeological anomalies, detecting part of AYR during Song and Jin Dynasties, which was confirmed with field investigations. Then, an adaptive irregular convolution kernel U-Net (AICK-U-Net) was proposed to reconstruct the channel of AYR, based on the images obtained by the different polarization decomposition methods in October, and the precision and recall reached 96.21% and 94.45%, respectively. Finally, two decision-level methods were proposed to optimize the reconstruction results, improving the precision and recall to 96.39% and 97.36%, respectively. In summary, Spaceborne synthetic aperture radar (SAR), with the application of polarization decomposition and neural network, provides new insights for detecting archeological anomalies and reconstructing archaeolandscapes.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Uncertainty Estimate of Satellite-Derived Normalized Water-Leaving
           Radiance

    • Free pre-print version: Loading...

      Authors: Giuseppe Zibordi;Marco Talone;Frédéric Mélin;
      Pages: 1 - 5
      Abstract: The quantification of uncertainties affecting satellite ocean color products is a fundamental step to ensure their compliance with mission and science requirements. This work investigated a methodology relying on the use of in situ radiometric data with known uncertainties to determine those affecting matching satellite data. By exploiting in situ radiometric data from the Ocean Color component of the Aerosol Robotic Network (AERONET-OC), an advanced method was applied to radiometric data products from the Ocean and Land Color Instruments onboard the Sentinel-3A satellite (OLCI-A) and the Visible Infrared Imager Radiometer Suite onboard the Suomi National-Polar Orbiting Partnership satellite (VIIRS-S). The results from the analysis support the relevance of the method proposed.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Phenology of Phytoplankton Size Classes in the Arabian Sea

    • Free pre-print version: Loading...

      Authors: Rebekah Shunmugapandi;Shirishkumar Gedam;Arun B Inamdar;
      Pages: 1 - 5
      Abstract: Phytoplankton size classes (PSC) patterns are distinctive, tightly coupled to environmental controls of the upper ocean layer, with sensitiveness toward the seasonal cycle. This letter focuses on the phenology of PSC to investigate the spatiotemporal assemblage of each PSC influenced by the environmental drivers over the Arabian Sea (AS). We applied an abundance-based approach on 16-year time series gap-filled satellite-derived chl- $a$ products to retrieve the PSC. Further, we estimated the PSC phenology indices for the AS as the timing of initiation, termination, duration, peak, and mean. The threshold criterion method is used to extract and map the PSC phenology indexes. The unique environmental adaptation of each PSC on both spatial and seasonal variability is highlighted and discussed based on the connection with the sea surface temperature (SST) and mixed layered depth (MLD). From the results, a new perspective is drawn on the PSC phenology patterns in the AS and how environmental controls influence each PSC.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • River Slope Observation From Spaceborne GNSS-R Carrier Phase Measurements:
           A Case Study

    • Free pre-print version: Loading...

      Authors: Yang Wang;Y. Jade Morton;
      Pages: 1 - 5
      Abstract: This letter demonstrates the potential of estimating river surface slope using space-borne global navigation satellite system-reflectometry (GNSS-R) carrier phase measurements. A case study is presented where the slopes of several segments of the Orinoco river are retrieved based on the processing of raw intermediate-frequency (IF) data recorded by the cyclone global navigation satellite system (CYGNSS) mission. The retrieved river slopes mostly vary between 3.9 and 5.1 cm/km and are in agreement with the surveyed mean slope of 4.5 cm/km for the lower Orinoco River. The correction and calibration of several systematic errors, i.e., CYGNSS satellite orbit errors, tropospheric and ionospheric effects, and river surface reference height error, are discussed in this letter. For the Orinoco River case study, the river slope retrieval is calibrated using the reflection signal over a nearby lake to mitigate the mis-modeled and unmodeled errors. Analysis of the specular point (SP) tracks of GPS reflection signal indicates that CYGNSS has the potential to provide river slope observations for rivers that have sufficient width with high temporal and spatial resolutions.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Enhancing Spatial Resolution of Sea Surface Salinity in Estuarine Regions
           by Combining Microwave and Ocean Color Satellite Data

    • Free pre-print version: Loading...

      Authors: Xuchen Jin;Xianqiang He;Yan Bai;Difeng Wang;Qiankun Zhu;Fang Gong;Delu Pan;
      Pages: 1 - 5
      Abstract: In this letter, we propose a downscaling approach to improve the spatial resolution of sea surface salinity (SSS) in estuarine areas using combined microwave and ocean color data. The model established a relationship between SSS and normalized sea surface emissivity and colored dissolved organic matter (CDOM). The model was validated by in situ measurements conducted in the East China Sea (ECS) and Mississippi River Estuary (MRE). The model showed relatively good agreement with in situ SSS measurements and illustrated enhanced SSS at high (4 km) resolution compared with low (40 km) resolution, with root mean square errors (RMSEs) of 1.55 versus 2.58 psu in the ECS and 0.39 versus 1.49 psu in the MRE. Overall, the proposed downscaling approach enhances the spatial resolution and accuracy of satellite SSS observations over estuarine areas, which should be helpful for ocean dynamic and biogeochemical studies in these regions.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Accurate Water Level Measurement in the Bridge Using X-Band SAR

    • Free pre-print version: Loading...

      Authors: S.-W. Kim;Y.-K. Lee;
      Pages: 1 - 5
      Abstract: Bridges are an important infrastructure during natural hazards; however, the water levels of reservoirs on which exist bridges have often been restricted in practice owing to the lack of gauging stations. This letter presents a method for measuring the relative water level at bridges using synthetic aperture radar (SAR) single-look complex data with an X-band. Unique multiscattering between the bridge and water surface provides a basis for the range shifting of the strong backscattering in the SAR data according to the water level change. The performance was evaluated using multitemporal Constellation of Small Satellites for Mediterranean Basin Observation (COSMO-SkyMed) images with strong backscatter related to the bridge. A time-series of water level is estimated from double-and triple-bounced backscatters and compared with the gauged data. The estimated relative water levels at the subpixel shift aided by oversampling of Hough image have a squared correlation coefficient of 0.985 and 0.999 for the double and triple bounce, respectively. The triple bounce was more consistent with the gauged water level, as the sensitivity of the range distance change is twice that of the double bounce, and the disturbance by the bridge substructure is low. In particular, the standard deviation of the relative water level change using the triple bounce was 0.17 m. The results demonstrated accurate water level measurements with subpixel precision. Therefore, it can be effectively used to monitor hydrological changes in remote areas with bridges.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Evaluation of OLCI Neural Network Radiometric Water Products

    • Free pre-print version: Loading...

      Authors: Ilaria Cazzaniga;Giuseppe Zibordi;Frédéric Mélin;Ewa Kwiatkowska;Marco Talone;David Dessailly;Juan I. Gossn;Dagmar Müller;
      Pages: 1 - 5
      Abstract: Radiometric water products from the neural network (NNv2) in the alternative atmospheric correction (AAC) processing chain of Ocean and Land Colour Instrument (OLCI) data were assessed over different marine regions. These products, not included among the operational ones, were custom-produced from Copernicus Sentinel-3 OLCI Baseline Collection 3. The assessment benefitted of in situ reference data from the Ocean Color component of the Aerosol Robotic Network (AERONET-OC) from sites representative of different water types. These included clear waters in the Western Mediterranean Sea, optically complex waters characterized by varying concentrations of total suspended matter and chromophoric dissolved organic matter (CDOM) in the northern Adriatic Sea, and optically complex waters characterized by very high concentrations of CDOM in the Baltic Sea. The comparison of the water-leaving radiances $L_{text {WN}}(lambda)$ derived from OLCI data on board Sentinel-3A and Sentinel-3B with those from AERONET-OC confirmed consistency between the products from the two satellite sensors. However, the accuracy of satellite data products exhibited dependence on the water type. A general underestimate of ${L}_{text {WN}}(lambda)$ was observed for clear waters. Conversely, overestimates were observed for data products from optically complex waters with the worst results obtained for CDOM-dominated waters. These findings suggest caution in exploiting NNv2 radiometric products, especially for highly absorbing and clear waters.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Adaptive Wavelet Threshold Denoising for Bathymetric Laser Full-Waveforms
           With Weak Bottom Returns

    • Free pre-print version: Loading...

      Authors: Xinglei Zhao;Hui Xia;Jianhu Zhao;Fengnian Zhou;
      Pages: 1 - 5
      Abstract: Wavelet threshold denoising with different threshold selection rules (TSRs) were used to reduce random noise (RN) in bathymetric laser full-waveforms. A nonreasonable threshold used for denoising can result in over-smoothing or under-smoothing of the signal and easily remove details of weak bottom return (BR). A unique and optimal TSR for all bathymetric full-waveforms of waters with different depths or turbidities is unavailable. Hence, an adaptive threshold selection (ATS) is proposed to improve the performance of RN reduction by adaptively selecting a threshold for each full-waveform based on the prominence of BR-to-noise ratio. The proposed method is applied to reduce the RN in raw green laser full-waveforms collected via Optech coastal zone mapping and imaging LIght Detection And Ranging (LiDAR). Compared with other traditional methods, the ATS improves the ratio of detectable BR by 5.64% and achieves a root mean squared error (RMSE) closer to the real RN level. Therefore, ATS can effectively remove the RN, enhance the prominence, and ensure the fidelity of weak BR.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Monitoring Sargassum Inundation on Beaches and Nearshore Waters Using
           PlanetScope/Dove Observations

    • Free pre-print version: Loading...

      Authors: Shuai Zhang;Chuanmin Hu;Brian B. Barnes;Tanya N. Harrison;
      Pages: 1 - 5
      Abstract: Sargassum beaching events have been reported in recent years around the Caribbean Sea and FL, USA, causing numerous environmental and economic problems. Satellite remote sensing has been widely used to monitor Sargassum blooms in open waters, yet due to either coarse spatial resolution or low-revisit frequency, it is difficult to provide timely information on Sargassum inundation from traditional satellite instruments. In this study, we demonstrate the capacity of 3-m resolution daily Dove imagery in monitoring Sargassum beaching events on Miami beach (FL, USA) and Cancun beach (Mexico). A U-net deep learning (DL) computer model is developed to extract Sargassum features from Dove imagery over beaches and nearshore waters. Application of the model to Dove image sequences between May and August 2019 shows two major inundation events on both Miami beach and Cancun beach, consistent with local reports. With the availability of 3-m resolution PlanetScope/Dove and PlanetScope/SuperDove data around the globe, the findings suggest that it is possible to monitor dynamic inundation events of not only Sargassum but also other macroalgae in many other regions.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Significant Wave Height Retrieval Method Based on Spaceborne GNSS
           Reflectometry

    • Free pre-print version: Loading...

      Authors: Jinwei Bu;Kegen Yu;
      Pages: 1 - 5
      Abstract: A geophysical model function (GMF) for significant wave height (SWH) retrieval is developed based on the spaceborne Global Navigation Satellite System Reflectometry (GNSS-R) data measured by the Cyclone GNSS (CYGNSS) satellites. The spreading characteristics of delay-Doppler maps (DDMs) generated by receivers onboard satellites are affected by the surface roughness, which is closely related to the SWH. Four GNSS-R observables [i.e., leading edge slope (LES) of normalized integrated delay waveform (NIDW), LES of normalized central delay waveform (NCDW), trailing edge slope (TES) of NCDW, leading edge waveform summation (LEWS) of NCDW] derived from DDM are first used in this letter to retrieve SWH. Collocated ERA5 SWH data are used as the ground truth to develop and evaluate the SWH models based on the four GNSS-R observables. The results show that there is high consistency between the SWH estimates and the ground truth, with a correlation coefficient of 0.88 and a root mean square error (RMSE) of 0.503 m. This letter demonstrates the feasibility of the spaceborne GNSS-R in SWH retrieval.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Evolution of a Sub-Mesoscale Eddy Leeward of Andaman Islands From HF
           Radars

    • Free pre-print version: Loading...

      Authors: Samiran Mandal;Avijit Gangopadhyay;Balaji Ramakrishnan;Sourav Sil;
      Pages: 1 - 4
      Abstract: Remotely sensed high-resolution ocean surface currents from high-frequency radars (HFRs) on the western Andaman Sea (AnS) reveals signature of a sub-mesoscale coastal anticyclonic eddy leeward of Little Andaman (LA) Island during August 4–9, 2017. This “Lee eddy” had a mean radius of ~11 km, negative values of normalized vorticity, divergence, and Okubo–Weiss (OW) parameter, and smaller values of strain. A term-by-term vorticity budget analysis suggests that the vortex stretching term and wind stress curl dominate during the evolution and demise of the Lee eddy than does advection.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • A Color Cast Image Enhancement Method Based on Affine Transform in Poor
           Visible Conditions

    • Free pre-print version: Loading...

      Authors: Zheng Liang;Xueyan Ding;Jie Jin;Yafei Wang;Yulin Wang;Xianping Fu;
      Pages: 1 - 5
      Abstract: In this letter, a simple yet effective dehazing framework is proposed, which consists of a novel color correction and a contrast enhancement. Most of the existing dehazing works focus on enhancing the contrast of the degraded images, but rarely of them concern about the color cast, which is ubiquitous in the scattering medium. To address the color distortion, an affine transform model-based color correction method is first proposed to improve the appearance of the image while preserving the details, which is inspired by the traditional color transfer. The color transfer alters the color values of a source image by sharing the global color statistics of a reference image, which makes it unsuitable to address the locally variable color deviations encountered in highly color distorted images as in poor visibility conditions (sandstorms and underwater). To alter color correction locally, we add local color fidelity and gradient constraint to the proposed technique, which overcomes the limitation that the traditional method depends too much on the global color statistics of the reference image and encourages it to handle the degraded image with various color casts and light conditions. In addition, a multiscale gradient-domain processing is applied to enhance the contrast. In this procedure, by extracting the information of different layers, we can easily restore the contrast while limiting the significant amplification of noise. The extensive qualitative and quantitative experiments reveal that the color and the contrast can be significantly improved by the proposed technique.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Skewness-Based Classification and Environmental Indication of Spectral
           Probability Distribution of Global Closed Connected Waters

    • Free pre-print version: Loading...

      Authors: Weining Zhu;Zaiqiao Yang;Shuangyan He;Qian Cheng;
      Pages: 1 - 5
      Abstract: Optical types of waters are important indicators of water quality and watershed environment. In this study, we proposed a novel classification approach that is based on water’s spectral probability distribution (SPD) in satellite images. Using the Landsat-8 images, we processed 690 global water bodies and their SPDs were then classified into seven types in terms of their skewness (SK). We analyzed the statistical features of these water types and their relationships with some environmental factors. The results show that if water bodies are clearer, simpler, more in their raw status, and having less interaction with humans, then their SPD SK is more positive, while if they are more complex, turbid, and highly interacted with human activities, then their SPD SK is more negative. Our study demonstrates that SPD is a good optical parameter and hence with more potential to indicate the quality and environmental properties of water bodies.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Extracting Lakes and Reservoirs From GF-1 Satellite Imagery Over China
           Using Improved U-Net

    • Free pre-print version: Loading...

      Authors: Chuangjie Ge;Wenjun Xie;Lingkui Meng;
      Pages: 1 - 5
      Abstract: Lakes and reservoirs (LaR) are important parts of water resources and their rapid and accurate monitoring is an essential guarantee for maintaining ecological health and social development. The existing waterbody extraction methods are mostly targeted at local water bodies, with little attention on the national scale. In this letter, an improved U-Net method is proposed for LaR extraction from GF-1 satellite imagery. First, 21 scenes of GF-1 images are evenly selected across China, and the training set and validation set are produced by image processing, cropping, and augmentation. Second, a deep learning network is constructed by modifying the U-Net, deepening the network and introducing multiple skip connections, which is suitable for extracting LaR China-wide. Experiments on the GF-1 imagery demonstrate that the superiority of the improved U-Net when compared with other deep learning methods (U-Net, UNet++, FastFCN, DeepLabv3+) and traditional methods [the normalized difference water index (NDWI), maximum likelihood method (MLM)]. In addition, 20 LaR are selected for further evaluation of the model, and all of them achieve good extraction results, showing excellent generalization of the model.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Lake Water Storage Changes in Northeast Hoh Xil Observed by Cryosat-2 and
           Landsat-5/7/8: Impact of the Outburst of Zhuonai Lake in 2011

    • Free pre-print version: Loading...

      Authors: Haihong Wang;Zhengkai Huang;Zhiqiang Wen;Zhicai Luo;
      Pages: 1 - 5
      Abstract: The outburst of Zhuonai Lake (ZL) in 2011 changed the local hydro-ecological system in northeast Hoh Xil (HX). This study focuses on the impact of the outburst on lake water storage changes (LWSCs) of four lakes in this region. Monthly LWSC from 2009 to 2016 were constructed using Landsat and Cryosat-2 data. We determined and validated lake levels and areas derived from Cryosat-2 and Landsat data, respectively. The two satellite-derived sequences were merged by interpolation to compute LWSC, based on the level-area curve derived from the digital elevation model (DEM). Results reveal the apparent impact of the outburst on the hydrological system. Before the outburst, water volumes in all four lakes continuously grew from January 2009 to September 2011, with a total increase of 1.49 ± 0.08 Gt. Most increased water was distributed in ZL and Kusai Lake (KL). The LWSC of each lake was strongly correlated (>0.9) with those of the whole basin. However, from October 2011 to December 2016, there was no ascending trend in LWSC of the three upper stream lakes, although the water volume in the basin was still increasing. More than 80% of the increased water flowed into Salt Lake (SL). Only the LWSC of SL kept a high correlation (0.91) with those of the whole basin.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Estimation of Flood Inundation and Depth During Hurricane Florence Using
           Sentinel-1 and UAVSAR Data

    • Free pre-print version: Loading...

      Authors: Sananda Kundu;Venkataraman Lakshmi;Raymond Torres;
      Pages: 1 - 5
      Abstract: We studied the temporal and spatial changes in flood water elevation and variation in the surface extent due to flooding resulting from Hurricane Florence (September 2018) using the L-band observation from an unmanned aerial vehicle synthetic aperture radar (UAVSAR) and C-band synthetic aperture radar (SAR) sensors on Sentinel-1. The novelty of this study lies in the estimation of the changes in the flood depth during the hurricane and investigating the best method. Overall, flood depths from SAR were observed to be well-correlated with the spatially distributed ground-based observations ( $R^{2} = 0.79$ –0.96). The corresponding change in water level ( $partial text{h}/partial text{t}$ ) also compared well between the remote sensing approach and the ground observations ( $R^{2} = 0.90$ ). This study highlights the potential use of SAR remote sensing for inundated landscapes (and locations with scarce ground observations), and it emphasizes the need for more frequent SAR observations during flood inundation to provide spatially distributed and high temporal repeat observations of inundation to characterize flood dynamics.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Analysis and Simulation of the Micro-Doppler Signature of a Ship With a
           Rotating Shipborne Radar at Different Observation Angles

    • Free pre-print version: Loading...

      Authors: Fangyuan Shi;Zhiqiang Li;Min Zhang;Jinxing Li;
      Pages: 1 - 5
      Abstract: Differences in the motion of different parts of a target cause the echo signal to contain specific Doppler modulation information, i.e., the micro-Doppler (m-D) effect. This phenomenon provides an effective way to detect targets in marine environments. In this study, based on the establishment of the micromotion model of a rotating surveillance radar and analysis of the m-D frequency, the geometrical optics and physical optics (GO-PO) method and the time-frequency analysis technique are used to obtain the radar cross section (RCS) and m-D signature of a ship with a shipborne radar at different observation angles. The ship, as the main component of the echo, is associated with the main energy. Finding the optimum angle to observe the shipborne radar is of great importance. The results show that the m-D signatures of the shipborne radar are not clear when the elevation angle is greater than 60° but are clear when the elevation angle is less than 55°. Moreover, some motion parameters can be extracted from the m-D signature, such as the period of the ship micromotion. The rotation speed of the shipborne radar can be obtained and is consistent with the set speed. This can help identify and track the key parts of a ship with local motion.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Multiple Granularity Spatiotemporal Network for Sea Surface Temperature
           Prediction

    • Free pre-print version: Loading...

      Authors: Cheng Zha;Weidong Min;Qing Han;Xin Xiong;Qi Wang;Qian Liu;
      Pages: 1 - 5
      Abstract: Sea surface temperature (SST) prediction has an important practical value in marine disaster prevention and mitigation. Most current methods only use the temporal correlation of SST during prediction, but the spatial correlation is not considered, resulting in low prediction accuracies. In addition, the changing trend of SST as reflected by the single granularity feature is unreliable, and the degrees of dependence between historical SST and future SST tend to vary. In order to overcome these issues, the multiple granularity spatiotemporal network (MGSN) is proposed for SST prediction. The proposed method consists of three parts. First, a multibranch network structure is constructed to extract different temporal features of different granularities. Second, a temporal dependence representation module is developed to represent the different degrees of dependence between historical SST and predicted SST in the temporal dimension. Third, the spatiotemporal fusion prediction module is used to achieve a spatiotemporal prediction of the SST and fuse the prediction results of different granular features. Comparative experiments have been conducted. The experimental results show that the root-mean-square error (RMSE) of the proposed method is reduced by 0.1360, 0.1608, and 0.1448 compared with the RMSE of convolutional LSTM (ConvLSTM), when predicting SST for the next one day, three days, and seven days, respectively. Our method has strong spatiotemporal feature modeling capabilities and is suitable for regional SST prediction.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Video-Based Convolutional Neural Networks Forecasting for Rainfall
           Forecasting

    • Free pre-print version: Loading...

      Authors: Andrew P. Barnes;Thomas R. Kjeldsen;Nick McCullen;
      Pages: 1 - 5
      Abstract: This study presents a new methodology for improving forecasts of current monthly, regional precipitation using video-based convolutional neural networks (CNNs). Using 13 administrative regions of Great Britain as a case study, three CNN architectures are trained for each region to forecast monthly rainfall totals given forecast mean sea-level pressure and 2-m air temperature videos from the MetOffice GloSEA5 model and a benchmark rainfall data. The forecasts generated by the CNN and the GloSEA5 precipitation forecasts are both compared directly against a benchmark rainfall dataset for each of the regions. Following this, the CNN models are combined with the GloSEA5 forecasts to generate a new ensemble for each region which is then compared with the benchmark rainfall. The results show that the trained CNNs produce errors similar to the GloSEA5 model with RMSEs of 63 mm (single frame), 44 mm (slow fusion), and 37 mm (early fusion) compared with the GloSEA5 error of 33 mm. Regional variability remained consistent throughout the compared models. However, the CNN models all outperform GloSEA5 in the prediction of extreme events. Furthermore, treating the forecasts as an ensemble results in errors of 32 mm (CNN ensemble) and 31 mm (post-processing ensemble), both of which improve on the independent GloSEA5 forecasts.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Predicting Sea Surface Temperature Based on a Parallel Autoreservoir
           Computing Approach With Short-Term Measured Data

    • Free pre-print version: Loading...

      Authors: Yin Wang;Shutang Liu;
      Pages: 1 - 5
      Abstract: Sea surface temperature (SST) is an essential parameter for observing the marine environment. It directly reflects the state of heat storage and release in the ocean. The change in SST will cause many phenomena that profoundly affect human production and life. Therefore, predicting SST accurately and efficiently can help us avoid many risks. In this article, we present a method based on neural networks. First, we propose a finite-dimensional description of SST, which investigates SST in the finite-dimensional phase space. Based on phase space reconstruction technology and the autoreservoir neural network (ARNN), the Spatial Parallel ARNN (SPARNN) is proposed for predicting SST. Unlike the previous machine learning methods that require big data, our approach only needs a small amount of locally short-term data to catch the dynamic features of the SST field. It also has excellent parallelism and is easy to run on a large-scale computer platform.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Auto Color Correction of Underwater Images Utilizing Depth Information

    • Free pre-print version: Loading...

      Authors: Jingchun Zhou;Dehuan Zhang;Wenqi Ren;Weishi Zhang;
      Pages: 1 - 5
      Abstract: The red spectrum is saliently attenuated due to the absorption and scattering properties of water. The acquired underwater images show severe color cast in underwater scenes. In this letter, we propose a novel color correction method for underwater images, which removes color cast on single pixels based on scene depth. The experimental results demonstrate that our approach can significantly improve the color effect and provide a correct input for the subsequent underwater image defogging methods.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Measuring Ice Flow Velocity on the Greenland Ice Sheet Using Stable
           Supraglacial River

    • Free pre-print version: Loading...

      Authors: Shuai Gao;Kang Yang;Yao Lu;Xin Lu;Manchun Li;
      Pages: 1 - 5
      Abstract: The ice flow velocities of many outlet glaciers on the Greenland Ice Sheet (GrIS) have increased dramatically over the past two decades, leading to significant GrIS mass loss. It is challenging to match multitemporal synthetic aperture radar or optical images because the GrIS ice surface changes dramatically, particularly during melt seasons. Therefore, ice surface features used for image matching are required to remain persistent even if the other image characteristics change significantly. This letter proposes that supraglacial rivers can be used to match multitemporal images’ tie points (TPs) and to measure the ice flow velocities. First, multitemporal 10-m Sentinel-2 images are used to detect supraglacial rivers by integrating cross-sectional and longitudinal channel information. Second, potential river TPs are created using GIS buffer and overlaying operations. Third, a nonrigid coherent point drift algorithm is used to match river TPs, and the spatial displacements among the corresponding matching river TPs are used to calculate the ice flow velocities. A typical outlet glacier of the northeast GrIS is selected as the study area and six multispectral Sentinel-2 images are used to calculate the summer and annual ice flow velocities during 2016–2018. The results show that the summer ice flow velocity is ~ 640–665 m/a, 9%–14% higher than the annual ice flow velocity (~ 581–588 m/a). The summer and annual ice flow velocities both decrease along the ice and river flow direction. The derived ice flow velocities are closely correlated with two state-of-the-art ice flow velocity products (R2 ≥ 0.981), indicating the high accuracy of the proposed method.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Evaluating Snow Bidirectional Reflectance of Models Using Multiangle
           Remote Sensing Data and Field Measurements

    • Free pre-print version: Loading...

      Authors: Lizao Ye;Pengfeng Xiao;Xueliang Zhang;Xuezhi Feng;Rui Hu;Wei Ma;Haixing Li;Yina Song;Tengyao Ma;
      Pages: 1 - 5
      Abstract: Because of the anisotropy of snow surface reflectance, it is essential to select a proper snow bidirectional reflectance model for extracting snow cover and inverting snow properties from remote sensing image, especially during the period of snow rapidly changed. In this letter, the ability of reproducing snow bidirectional reflectance by three semiempirical bidirectional reflectance distribution function (BRDF) models (Ross–Li, Roujean, and Raman–Pinty–Verstraete) and the asymptotic radiative transfer theory (ART) model was evaluated using the polarization and directionality of the earth reflectance (POLDER) data. In addition, the ART model was compared with the bicontinuous geometric optics (bic-GORT) model based on field measurements. The results indicated that the root mean square errors (RMSEs) are small and similar for all models during the stable-snow period. The physical models perform better than the semiempirical models in capturing the bidirectional signatures of snow during the periods of snow rapidly changed. The bic-GORT model achieves higher accuracy, while the ART model holds the advantages of simple and efficient to be used.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Monthly Surface Elevation Changes of the Greenland Ice Sheet From
           ICESat-1, CryoSat-2, and ICESat-2 Altimetry Missions

    • Free pre-print version: Loading...

      Authors: Yen-Ru Lai;Lei Wang;
      Pages: 1 - 5
      Abstract: The Greenland Ice Sheet (GrIS) mass balance shows significant variabilities over a range of time scales. As geodetic records lengthen over time, it becomes insufficient to characterize the temporal evolution of the ice sheet by using a best-fit linear trend over a given observation period. This study investigates the joint analysis of laser and radar satellite altimeter measurements for estimating GrIS surface elevation changes (SECs) with a 30-day resolution. We first apply a crossover analysis to assess the precisions of the surface elevations measured by ICESat-1/2 laser altimeters and CryoSat-2 radar altimeter over the GrIS, which are needed for assigning weights for each data set in the joint analysis. Then, based on a modified repeat-track approach, we analyze the surface elevation measurements of ICESat-1/2 and CryoSat-2 to produce monthly SEC estimates for the past two decades, together with their associated uncertainties. The multimission SEC estimates are further assessed by using IceBridge airborne laser measurements, showing differences with a median value of −12 cm ± 60 cm. The monthly SEC time series reveal important variations over a range of time scales across different parts of the GrIS and would facilitate the investigation of complex spatiotemporal patterns of GrIS changes.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Can the Depth of Seasonal Snow be Estimated From ICESat-2 Products: A Case
           Investigation in Altay, Northwest China

    • Free pre-print version: Loading...

      Authors: Xiaojing Hu;Xiaohua Hao;Jian Wang;Guanghui Huang;Hongyi Li;Qian Yang;
      Pages: 1 - 5
      Abstract: Snow depth (SD) is an indispensable parameter for many studies. Launched in 2018, the Ice, Cloud and land Elevation Satellite-2 (ICESat-2) is designed to obtain global glacial elevations, but it can also acquire canopy and terrain elevations. Whether the depth of seasonal snow can be estimated by directly comparing the difference in elevations in snow-cover and snow-free cases, many people may reasonably ask. In this letter, we conduct such an investigation in Altay, Northwest China, using ICESat-2 ATL08 elevation products. Our investigation suggests: 1) in mountainous areas, the answer maybe is no because the estimation is obviously affected by rugged topography; 2) but in flat regions, SDs have been effectively estimated. (The $R^{2}$ is up to 0.88 between estimates and ground measurements.); and 3) as expected, land-cover types also affect the accuracy of the results, and the best estimation happens over the type of bare land. Therefore, estimating the depth of seasonal snow from the ICESat-2 product may be feasible, but we must check the results carefully.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Joint Total Variation With Nonnegative Constrained Least Square for Sea
           Ice Concentration Estimation in Low Concentration Areas of Antarctica

    • Free pre-print version: Loading...

      Authors: Tingting Liu;Miaojiang Wang;Zemin Wang;Ruyi Feng;Chunxia Zhou;Liangpei Zhang;
      Pages: 1 - 5
      Abstract: Sea ice concentration (SIC) is an indispensable parameter for the study of polar sea ice. The existing methods can obtain accurate SICs for most situations, but they usually perform poorly in low SIC regions because of the spatial differences in the neighboring pixels induced by the discontinuity of the sea ice cover. In this letter, to cope with the difficulty of this problem, an improved SIC estimation method is proposed to retrieve SIC, focusing on low SIC regions. The proposed method introduces the spatial relationships into SIC estimation by employing a total variation (TV) regularizer. Moreover, nonnegative constrained least squares (NCLS) is used to derive the optimal solutions from the SIC estimation equation. Verification was conducted in low SIC regions (0%–50%) of the Antarctic utilizing ship-based in situ data and the Moderate Resolution Imaging Spectroradiometer (MODIS), and the results were compared with those of some of the mature methods. The results indicated that the proposed method can obtain a superior accuracy with a smaller root-mean-square error (RMSE) (6.0%–14.61%) than the other algorithms in low SIC regions. Furthermore, the proposed method can accurately estimate the SIC of both first-year ice and multiyear ice. The findings of this study confirm the need to consider the spatial relationships in the processing of SIC estimation.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Automatically Structuralize the Curvilinear Glacier Using Phase-Coded
           Convolution

    • Free pre-print version: Loading...

      Authors: Yang Liu;
      Pages: 1 - 5
      Abstract: The morphological structure of glaciers is essential to understand and model their dynamics. In this letter, a novel method based on phase-coded disk (PCD) and phase-coded convolution is presented to automatically delineate the morphological structure of curvilinear glaciers from ice surface velocities. First, a region-growing algorithm is used to identify the glacier image object from an ice surface velocity remote sensing product. Second, the phase-coded convolution is applied to derive the image object’s magnitude surface. A Markov chain Monte Carlo (MCMC) approach is then developed to extract the centerlines of glacier tributaries. Finally, the morphological structure and attributes of the glacier image object are numerically derived based on the centerlines. A glacier in Alaska was employed to test the proposed method and conventional hydrologic method. The results proved the effectiveness of the proposed PCD-based method. This study is a trailblazing pilot study that novelly employs computer vision technology to automatically structuralize curvilinear glaciers. The outcomes enable the inspection and monitoring of complex glacier dynamics on a tributary level.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • An Improved Surface Slope Estimation Model Using Space-Borne Laser
           Altimetric Waveform Data Over the Antarctic Ice Sheet

    • Free pre-print version: Loading...

      Authors: Huan Xie;Hong Tang;Yanmin Jin;Binbin Li;Zhijie Zhang;Shijie Liu;Xiaohua Tong;
      Pages: 1 - 5
      Abstract: A full-waveform laser altimeter measures the round-trip time-of-flight of the laser pulse to estimate the range between the altimeter and the target, while the vertical distribution information of the terrain within the laser footprint is recorded in the full-waveform data. However, the waveform width is broadened by the target surface slope and roughness. In previous studies, the relationship between the laser altimetry waveform width and the target surface slope and roughness has been modeled based on the assumption that the laser footprint on the Earth’s surface is a circle. In this letter, based on the previous model, we propose an improved within-footprint slope estimation model by combining the shape and orientation information of the elliptic laser footprint, which further improves the accuracy of the model. The validation and accuracy assessment were performed using a high-resolution digital elevation model (DEM) of the Antarctic ice sheet. The results show that the slopes within the footprint calculated using the improved model are close to the slopes extracted from the DEM, with the mean value of the slope bias being 0.18°, standard deviation (STD) being 1.36° and root-mean-square error being 1.46°.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Detection of Soil Freeze/Thaw States at a High Spatial Resolution in
           Qinghai-Tibet Engineering Corridor

    • Free pre-print version: Loading...

      Authors: Xin Zhou;Junxiong Zhou;Qinghua Xie;Zhengjia Zhang;Qihao Chen;Xiuguo Liu;
      Pages: 1 - 5
      Abstract: The freeze/thaw (F/T) state of the soil is an essential indicator for permafrost monitoring. However, current soil F/T products with a coarse spatial resolution (>1 km) have limited their use on a fine scale. In this letter, a new approach integrating two microwave sensors [i.e., Sentinel-1 and advanced microwave scanning radiometer 2 (AMSR-2)] is developed to identify the soil F/T state at a spatial resolution of 10 m in the Qinghai-Tibet engineering corridor (QTEC). Using a linear regression model to integrate the coarse AMSR-2 data with the finer Moderate Resolution Imaging Spectroradiometer (MODIS) land surface temperature (LST), the frozen frequency product at a 1-km resolution can be obtained. Then, the high-spatial-resolution F/T map based on Sentinel-1 synthetic aperture radar (SAR) time-series images can be produced using the threshold extracted from each pixel of frozen-frequency products. We tested soil F/T results via both visual and quantitative evaluations. The overall accuracy of the 10-m soil F/T map achieves 84.63% and 77.09% for ascending and descending orbits based on four meteorological stations, respectively.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • NAU-Net: A New Deep Learning Framework in Glacial Lake Detection

    • Free pre-print version: Loading...

      Authors: Jinxiao Wang;Fang Chen;Meimei Zhang;Bo Yu;
      Pages: 1 - 5
      Abstract: Glacial lake mapping is essential for understanding the response of glacial lakes to climate change and the risk assessment of glacial lake outburst floods (GLOFs). Given that glacial lakes have little area compared with background objects, extracting glacial lakes high precisely is still challenging. Recently, U-Net, a deep learning (DL) method, has shown great potential in glacial lake extraction, due to its elaborate encoder-decoder structure and powerful skip connections. However, the skip connections transmit a lot of information irrelevant to glacial lakes from the low-level appearance features to the high-level semantic features, leading to inefficient utilization of the low-level features. In this letter, we propose a normalized difference water index (NDWI) attention U-Net (NAU-Net) for pixel-wise glacial lake segmentation, which utilizes NDWI as a spatial attention to highlight the signals of water regions in low-level feature maps, thereby making the network pay more attention to glacial lakes. Compared with the classical networks and the state-of-the-art non-DL methods, our NAU-Net shows better performance on glacial lake extraction. The source code can be found at https://github.com/JinxiaoWang/NAU-Net.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Improvement in Modeling Soil Dielectric Properties During Freeze-Thaw
           Transitions

    • Free pre-print version: Loading...

      Authors: Shuyang Wu;Tianjie Zhao;Jinmei Pan;Huazhu Xue;Lin Zhao;Jiancheng Shi;
      Pages: 1 - 5
      Abstract: Soil freeze-thaw cycles have a profound impact on heat and water fluxes at the land-atmosphere interface and transport in soils. Microwave remote sensing is a widely used technique to detect near-surface soil freeze/thaw states due to significant changes in dielectric properties associated with water phase transitions in soils, where uncertainty remains. This letter proposes a new parameterization scheme for the estimation of unfrozen water content to improve the modeling of soil dielectric properties during freeze-thaw transitions. Predictions from the new model referred to as Zhang-Zhao’s model were compared with dielectric measurements during thawing processes of soil samples collected from Baoding (silty clay soil), Zhangjiakou (loamy sandy soil), and Zhengzhou (clay loam soil) in China. The mean biases of the predictions were 3.25 (4.44 and 2.07 for the thawed value and frozen value, respectively) and 1.54 (2.22 and 0.88 for the thawed value and frozen value, respectively) for the real part and imaginary part, respectively. The model-predicted soil complex relative permittivity (CRP) was highly correlated with measurements, with correlation coefficients ranging from 0.7944 to 0.9865. The normalized root mean square errors of the predictions were 13.72% (real part) and 25.41% (imaginary part).
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Learning CNN Filters From User-Drawn Image Markers for Coconut-Tree Image
           Classification

    • Free pre-print version: Loading...

      Authors: Italos Estilon de Souza;Alexandre Xavier Falcão;
      Pages: 1 - 5
      Abstract: Identifying species of trees in aerial images is essential for land-use classification, plantation monitoring, and impact assessment of natural disasters. The manual identification of trees in aerial images is tedious, costly, and error-prone, so automatic classification methods are necessary. Convolutional neural network (CNN) models have well succeeded in image classification applications from different domains. However, CNN models usually require intensive manual annotation to create large training sets. One may conceptually divide a CNN into convolutional layers for feature extraction and fully connected layers for feature space reduction and classification. We present a method that needs a minimal set of user-selected images to train the CNN’s feature extractor, reducing the number of required images to train the fully connected layers. The method learns the filters of each convolutional layer from user-drawn markers in image regions that discriminate classes, allowing better user control and understanding of the training process. It does not rely on optimization based on backpropagation, and we demonstrate its advantages on the binary classification of coconut-tree aerial images against one of the most popular CNN models.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Cropland Change Detection With Harmonic Function and Generative
           Adversarial Network

    • Free pre-print version: Loading...

      Authors: Jiage Chen;Wenzhi Zhao;Xi Chen;
      Pages: 1 - 5
      Abstract: Time-series image change detection is one of the most challenging tasks to remote sensing society. Due to complex phenological patterns of cropland, it is difficult to design an efficient strategy for cropland change detection. In this work, an integrated framework is proposed to perform change detection with a limited number of training samples. There are two improvements in this proposed cropland change detection method: 1) the harmonic function is utilized to fill the missing data within a time-series image stack by considering phenological patterns of cropland and 2) the CropGAN was developed to generate realistic samples for training data set enrichment. Compared to the traditional change detection methods, the proposed strategy able to detect different kinds of cropland changes even with few number of samples. Experiments on a Landsat time-series image stack demonstrated that the proposed CropGAN can significantly improve change detection accuracies, given a limited number of labeled samples.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Learning Geometric Features for Improving the Automatic Detection of
           Citrus Plantation Rows in UAV Images

    • Free pre-print version: Loading...

      Authors: Laura Elena Cué La Rosa;Dário A. B. Oliveira;Maciel Zortea;Bruno Holtz Gemignani;Raul Queiroz Feitosa;
      Pages: 1 - 5
      Abstract: Unmanned aerial vehicles (UAVs) allow on-demand imaging of orchards at an unprecedented level of detail. The automated detection of plantation rows in the images helps in the successive analysis steps, such as the detection of individual fruit trees and planting gaps, aiding producers with inventory and planting operations. Citrus trees can be planted in curved rows that form intricate geometric patterns in aerial images, requiring robust detection approaches. While deep learning methods rank among state-of-the-art methods for segmenting images with particular geometrical patterns, they struggle to hold their performance when testing data differs much from training data (e.g., image intensity differences, image artifacts, vegetation characteristics, and landscape conditions). In this letter, we propose a method to learn geometric features of orchards in UAV images and use them to improve the detection of plantation rows. First, we train a detection encoder–decoder network (DetED) to segment planting rows in RGB images. Then, with labeled data, we train an encoder–decoder correction network (CorrED) that learns to map binary masks with spurious row segmentation geometries into corrected ones. Finally, we use the CorrED network to fix geometric inconsistencies in DetED outcome. Our experiments with commercial plantations of orange trees show that the proposed CorrED postprocessing can restore missing segments of plantation rows and improve detection accuracy in testing data.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • A Two-Step Method to Calibrate CYGNSS-Derived Land Surface Reflectivity
           for Accurate Soil Moisture Estimations

    • Free pre-print version: Loading...

      Authors: Wei Wan;Rui Ji;Baojian Liu;Huan Li;Siyu Zhu;
      Pages: 1 - 5
      Abstract: Based on a statistical analysis of the currently available 3-year on-orbit Cyclone Global Navigation Satellite System (CYGNSS) data (2017–2019), this study proposes a two-step calibration method to improve the accuracy of the CYGNSS-derived land surface reflectivity (SR) and the resulting soil moisture (SM) estimates. The method is designed for two purposes: the one is to correct the system errors of the SR estimates induced by the calibration of the CYGNSS Version 2.1 L1B data, and the other is to eliminate vegetation attenuation in the SR of the soil layer. Mean SR corrections of ~ −0.9 and 2.2 dB are achieved through the first and second steps of calibration, respectively. This resulted in better SM estimates compared with the Soil Moisture Active Passive (SMAP) product and the in situ measurements, i.e., improved correlations between the CYGNSS SR and the SMAP SM (from $R = 0.46$ to $R = 0.74$ ), improved correlations between the CYGNSS SR and the in situ SM (from $R = 0.47$ to $R = 0.62$ ), and between the CYGNSS SM and the in situ SM with the best $R = 0.64$ .
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Building Data Sets for Rainforest Deforestation Detection Through a
           Citizen Science Project

    • Free pre-print version: Loading...

      Authors: Fernanda Beatriz Jordan Rojas Dallaqua;Fabio Augusto Faria;Álvaro Luiz Fazenda;
      Pages: 1 - 5
      Abstract: Originally, the ForestEyes project aims to detect deforestation in tropical forests based on citizen science (CS) and machine learning (ML) approaches, in which the volunteers analyze and label segments of remote sensing images to build new training sets for creating different classification models. In previous work, only three modules related to CS have been proposed. In this letter, two new modules are created: 1) organization and selection and 2) ML. Therefore, these modules turn the ForestEyes project a more robust system in the deforestation detection task, building high-confidence labeled collections, increasing the monitoring coverage, and decreasing volunteer dependence. Performed experiments show that volunteers create better data sets than those based on automatic PRODES-based approaches, selecting the most relevant samples and discarding noisy segments that might disrupt ML techniques. Finally, the results showed the feasibility of allying CS with ML for rainforest deforestation detection task.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Quantitative Assessment of Satellite L-Band Vegetation Optical Depth in
           the U.S. Corn Belt

    • Free pre-print version: Loading...

      Authors: Kaitlin Togliatti;Colin Lewis-Beck;Victoria A. Walker;Theodore Hartman;Andy VanLoocke;Michael H. Cosh;Brian K. Hornbuckle;
      Pages: 1 - 5
      Abstract: Satellite L-band vegetation optical depth (L-VOD) contains new information about terrestrial ecosystems. However, it has not been evaluated against the geophysical variable that it represents, plant water, the mass of liquid water contained within vegetation tissue per ground area. We quantitatively assess the seasonal variation of three L-VOD products at the South Fork Core Validation Site in the Corn Belt state of Iowa where L-VOD is directly proportional to crop plant water. We use three satellite-scale crop plant water estimates: in situ measurements; a normalized difference water index (NDWI) calibrated with in situ measurements; and a crop model. We find that overall the L-VOD satellite products are 0.02–0.09 Np (0.4– ${1.7} ,,text {kg} cdot text {m}^{-2}$ ) lower than the three estimates. We show that overestimation of L-VOD can be attributed to dynamic soil surface roughness, and hypothesize that crop plant water observations will require the incorporation of this effect into retrieval algorithms.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • DenseNet-Based Land Cover Classification Network With Deep Fusion

    • Free pre-print version: Loading...

      Authors: Lianlei Shan;Weiqiang Wang;
      Pages: 1 - 5
      Abstract: Recently, fully convolutional network (FCN)-based (Long et al., 2015) networks have made impressive success in semantic segmentation, and these approaches achieve satisfactory results in natural images. However, in the field of high-resolution remote sensing image segmentation, the accuracy has a considerable huge gap compared with that of natural images. Through the development process of semantic segmentation, we found that the key to accurate segmentation is the context. Effective networks can always obtain large contexts, which means that context is the key to one successful segmentation network. For high-resolution remote sensing images, their elements always extend to large scope and they have no clear or regular boundaries. As a result, it needs more context to correctly classify each pixel. However, the networks designed for natural images obviously do not meet this requirement, and thus, they achieve poor segmentation results for high-resolution images. Therefore, we do some targeted improvements. Based on one powerful backbone, we add two new fusions called unit fusion and cross-level fusion, respectively. Unit fusion makes the connection from the encoder part to the decoder part not only occur in the final output of each dense block but also in the middle feature layers inside one dense block. These added fusions make feature fusion in the same level more complete, which is of great significance for complex and zigzag boundary areas. As a complement for unit fusion, cross-level fusion aims to enhance the fusion of different dense blocks. Specifically, cross-level fusion learns from the internal structure of the dense block and applies the design to the whole network level. It can incorporate nonadjacent features and rapidly increase the receptive field and context, which is very effective for the segmentation of targets with very large sizes. Experiments on Deepglobe (Demir et al., 2018) show significant improvements in -ur work.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Land Use Classification With Engineered Features

    • Free pre-print version: Loading...

      Authors: Christoph Rasche;
      Pages: 1 - 5
      Abstract: We report on a methodological framework that analyzes land-use images with engineered (manually designed) features. As older feature engineering methods suffered from excessive computation of their features, we therefore, introduce techniques that are faster and also more elaborate than any previous approach. Feature extraction and description is based on contour and region information. The contour analysis comprises the detection of ridge, river, and edge contours and is based on a technique of minimal complexity (without requiring costly multiplicative operations). The traced contour segments are then partitioned and abstracted; then they are clustered to form group descriptors. The region analysis consists of the detection of brighter, darker, and flatter regions, as well as regions obtained from clustering; the clustering is carried out with minimal complexity using a hierarchical analysis. Region segments are partitioned and abstracted using a fast implementation of the symmetric-axis transform. A total of ca. 70 parameters is developed and land-use classification experiments are performed. On the UC Merced (UCMD) collection, the classification accuracy of Deep Nets is reached; on the NWPU-RESISC45 collection the accuracy still lags somewhat.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Corn-Plant Counting Using Scare-Aware Feature and Channel Interdependence

    • Free pre-print version: Loading...

      Authors: Yong-Yang Ma;Zhan-Li Sun;Zhigang Zeng;Kin-Man Lam;
      Pages: 1 - 5
      Abstract: Corn-plant counting is an important process for predicting corn yield and analyzing corn-plant phenotypes. In this letter, an effective corn-plant counting method is proposed, which is based on utilizing the scale-aware (SA) contextual feature and channel interdependence (CI). Given the Visual Geometry Group (VGG) Network features, the SA features are extracted by spatial pyramid pooling to derive multiscale context information. In order to utilize the channel interdependent information, the VGG features are integrated via a channel attention module. Moreover, an encoder–decoder structure is constructed to fuse the SA features and the CI-based features. Considering the sparsity of a corn plant, a hybrid loss function is adopted to train the network, by considering a density map loss function and an absolute count loss function. Experimental results demonstrate the effectiveness of the proposed method for corn-plant counting.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Multisource-Domain Generalization-Based Oil Palm Tree Detection Using
           Very-High-Resolution (VHR) Satellite Images

    • Free pre-print version: Loading...

      Authors: Juepeng Zheng;Wenzhao Wu;Shuai Yuan;Haohuan Fu;Weijia Li;Le Yu;
      Pages: 1 - 5
      Abstract: Providing accurate and timely oil palm information on a large scale is essential for both economic development and ecological significance. However, owing to different sensors, photograph acquisition conditions, and environmental heterogeneity, the large volume and the variety of the data make it extremely challenging for large-scale and cross-regional oil palm tree detection. It is computationally expensive to train a model from images covering large heterogeneous regions and all environmental conditions for continuously accumulated multisource remote sensing data. In this letter, we propose a new multisource domain generalization (DG) method, Maximum Mean Discrepancy Deep Reconstruction Classification Network (MMD-DRCN). It learns representations from multiple source domains and obtains inspiring performance in an unknown and “unseen” target domain. Besides classification loss, our MMD-DRCN distills more representative features through reconstruction loss and aligns multisource latent features by MMD loss, both of which effectively enhance the capacity of generalization. MMD-DRCN achieves an average F1-score of 82.70% in all transfer tasks, attaining a 5.83% gain compared to Baseline (a straightforward convolutional neural network (CNN) model). Experimental results demonstrate DG poses a promising potential for large-scale and cross-regional oil palm tree detection without any information of the target domain.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Spatial–Temporal Prediction of Vegetation Index With Deep Recurrent
           Neural Networks

    • Free pre-print version: Loading...

      Authors: Wentao Yu;Jing Li;Qinhuo Liu;Jing Zhao;Yadong Dong;Cong Wang;Shangrong Lin;Xinran Zhu;Hu Zhang;
      Pages: 1 - 5
      Abstract: Vegetation index (VI) derived from remotely sensed images is a proxy of terrestrial vegetation information and widely used in land monitoring and global change studies. Recently, the prediction of vegetation properties has been an interest in related communities. With the accumulation of satellite records over the past few decades, the spatial–temporal prediction of VI becomes feasible. In this letter, we developed deep recurrent neural networks (RNNs) with long short-term memory (LSTM) and gated recurrent units (GRUs) to predict the short-term VI based on historical observations. The pixel-based fully connected networks GRU and LSTM (FCGRU and FCLSTM) and patch-based convolutional networks (ConvGRU and ConvLSTM) are established and compared with the traditional multilayer perceptron (MLP) model. Moderate Resolution Imaging Spectroradiometer (MODIS) and Sentinel-2 normalized difference VI (NDVI) data sets were used in the experiments. The prediction performance is evaluated globally in different regions, different vegetation types, and different growing seasons. Results demonstrate that the RNN models can predict VI with high accuracy (average root mean square error (RMSE) around 0.03), which is superior to the MLP model. In general, the pixel-based RNN models performed better than the patch-based models especially in regions with a larger proportion of outliers. And the prediction accuracy is stable over different vegetation types and growing seasons.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Unsupervised Land-Cover Segmentation Using Accelerated Balanced Deep
           Embedded Clustering

    • Free pre-print version: Loading...

      Authors: Ahmad Obeid;Ibrahim M. Elfadel;Naoufel Werghi;
      Pages: 1 - 5
      Abstract: In this letter, we address the issue of the automatic labeling of remote sensing datasets using a novel deep learning clustering algorithm. The proposed algorithm addresses the inherent susceptibility of the deep embedded clustering (DEC) algorithm to data imbalance using additional search and extraction steps. Furthermore, the proposed algorithm is highly parallelizable. A graphics processing unit (GPU) implementation is shown to achieve 40X to 2600X of performance speedup and improved clustering accuracy with respect to DEC and other clustering approaches.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Locality-Constrained Bilinear Network for Land Cover Classification Using
           Heterogeneous Images

    • Free pre-print version: Loading...

      Authors: Xiao Li;Lin Lei;Gangyao Kuang;
      Pages: 1 - 5
      Abstract: Optical and SAR modalities provide complementary information of land properties, which can lead to outstanding classification performance. Recently, factorized bilinear coding (FBC) as an extension of bilinear pooling in respect of coding-pooling perspective, which extracted compact bilinear fusion features with second-order interaction information in the form of sparse representation, brought the performance improvements on multimodal learning tasks. However, it lost locality attributes among similar samples to be encoded. In this letter, we propose a novel locality-constrained bilinear network (LC-BNet) for land cover classification with heterogeneous remote sensing (RS) images. Specifically, the locality-constrained bilinear coding (LC-BC) introduces locality information to generate compact and discriminative fusion features for land cover classification. Extensive experimental results show superior performances of our work on two broad coregistered optical and SAR datasets.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Accuracy Assessment of ICESat-2 Ground Elevation and Canopy Height
           Estimates in Mangroves

    • Free pre-print version: Loading...

      Authors: Jianan Yu;Sheng Nie;Wenjie Liu;Xiaoxiao Zhu;Dajin Lu;Wenyin Wu;Yue Sun;
      Pages: 1 - 5
      Abstract: Rapid and accurate ecological surveys of mangroves are of great significance for coastal protection and global carbon balance assessments. Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2)/Advanced Topographic Laser Altimeter System (ATLAS) data provide an opportunity to conduct large-scale surveys of mangroves. The purpose of this study was to assess the expressiveness of ICESat-2 data for ground and canopy height retrievals in mangroves. First, the ICESat-2 data were processed to obtain the ground and canopy heights of mangrove areas. Second, the accuracies of the ground and canopy heights retrieved from the ICESat-2 data were verified by airborne light detection and ranging (LiDAR) data. Finally, we analyzed the influence of various factors on the ground and canopy height estimation accuracies. The results showed that the average errors of ICESat-2 for the ground and canopy heights were 0.28 and −0.21 m and that the root mean squared errors (RMSEs) were 0.96 and 2.50 m. The accuracies of the ICESat-2 ground and canopy height estimates differed significantly when day/night and strong/weak beams were used. The strong beams at night provided the most accurate estimations of canopy height (RMSE% = 24.4%) and are thus the most suitable choice for studying mangrove areas. In addition, the results indicated that slope is the variable that has the greatest influence on the accuracy of the ground elevation estimates of the four factors above, while the accuracy of canopy height estimates is significantly affected by the canopy height itself. Overall, our study found that ICESat-2 data are suitable for ecological investigations of mangroves.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Time-Resolved Sentinel-3 Vegetation Indices Via Inter-Sensor 3-D
           Convolutional Regression Networks

    • Free pre-print version: Loading...

      Authors: Ruben Fernandez-Beltran;Damian Ibañez;Jian Kang;Filiberto Pla;
      Pages: 1 - 5
      Abstract: Sentinel missions provide widespread opportunities of exploiting inter-sensor synergies to improve the operational monitoring of terrestrial photosynthetic activity and canopy structural variations using vegetation indices (VI). In this context, continuous and consistent temporal data are logically required to rapidly detect vegetation changes across sensors. Nonetheless, the existing temporal limitations inherent to satellite orbits, cloud occlusions, data degradation, and many other factors may severely constrain the availability of data involving multiple satellites. In response, this letter proposes a novel deep 3-D convolutional regression network (3CRN) for temporally enhancing Sentinel-3 (S3) VI by taking advantage of inter-sensor Sentinel-2 (S2) observations. Unlike existing regression and deep learning-based methods, the proposed approach allows convolutional kernels to slide across the temporal dimension to exploit not only the higher spatial resolution of the S2 instrument but also its own temporal evolution to better estimate time-resolved VI in S3. To validate the proposed approach, we built a database made of multiple day-synchronized S2 and S3 operational products from a study area in Extremadura (Spain). The conducted experimental comparison, including multiple state-of-the-art regression and deep learning models, shows the statistically significant advantages of the presented framework. The codes of this work will be made available at https://github.com/rufernan/3CRN.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Separable Attention Network in Single- and Mixed-Precision Floating Point
           for Land-Cover Classification of Remote Sensing Images

    • Free pre-print version: Loading...

      Authors: Mercedes E. Paoletti;Juan M. Haut;T. Alipour-Fard;Swalpa K. Roy;Eligius M. T. Hendrix;A. Plaza;
      Pages: 1 - 5
      Abstract: Land-cover information is of paramount importance in a wide range of environmental and socioeconomic applications. Deep learning (DL) provides a large variety of potential models for extracting useful information from raw images. However, remote sensing image (RSI) classification remains a challenging goal due to the intrinsic features of the data, such as the high sample variability and lack of labeled data. This provides a challenge to the reliability of deep classifiers. In particular, convolution-based models are greatly affected by overfitting and vanishing gradient problems. To overcome these drawbacks, this letter presents a new attention-based architecture, including attention modular blocks. These blocks divide their input feature maps into several groups and split them along the channel dimension and then combine them to create an attention mask encoding global contextual information. The mask is applied to obtain a refined feature representation, strengthening those features that affect most significantly the classification and attenuating the rest. Our new method reduces significantly the number of trainable parameters. Our results, obtained using several widely used RSIs, demonstrate that the new method exhibits higher classification performance when compared to several state-of-the-art methods.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Quantification of Alpine Grassland Fractional Vegetation Cover Retrieval
           Uncertainty Based on Multiscale Remote Sensing Data

    • Free pre-print version: Loading...

      Authors: Xingchen Lin;Jianjun Chen;Peiqing Lou;Shuhua Yi;Guoqing Zhou;Haotian You;Xiaowen Han;
      Pages: 1 - 5
      Abstract: Fractional vegetation cover (FVC) retrieval results of high spatial resolution satellite remote sensing images are usually upscaled as training and validation data (FVCUIH) for low spatial resolution satellite remote sensing images. However, few studies have focused on the impact of the spatial scale conversion on the evaluation of FVC retrieval accuracy. In this study, we first investigated the influence of spatial scale conversion on FVC retrieval accuracy based on FVC measured by unmanned aerial vehicle (FVCUAV) at three scales (Sentinel-2 MSI, Landsat-8 OLI, and MODIS). Then, the NDVI threshold method is proposed to further analyze the uncertainty caused by the underlying surface heterogeneity. The results showed that the use of FVCUIH as training and validation data in the process of spatial scale conversion led to overestimation of FVC accuracy, and its influence on FVC retrieval cannot be ignored. In addition, the uncertainty of the underlying surface heterogeneity at the measured sites increased the uncertainty of the FVC retrieval, while these results could be optimized by detecting the underlying surface heterogeneity. Our results suggested that both spatial scale conversion and underlying surface heterogeneity would cause the inaccurate FVC retrieval, while the latter could be optimized by detecting the underlying surface heterogeneity. This study provided a reference for the improvement of multiscale FVC retrieval accuracy based on single-scale FVC-measured data.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Estimating Bare Earth in Sparse Boreal Forests With WorldView Stereo
           Imagery

    • Free pre-print version: Loading...

      Authors: Christopher S. R. Neigh;William C. Wagner;Paul M. Montesano;Margaret Wooten;
      Pages: 1 - 5
      Abstract: Circumboreal forests are currently experiencing rapid climate warming which is altering their structure, productivity, and status as a carbon sink. Very high-resolution (VHR; < 2 m) stereo-derived digital surface models are available to monitor these forests, but a similar resolution digital terrain model (DTM) is required to extract information about tree height, which is often used to estimate carbon content. To the best of our knowledge, no openly available VHR DTM currently exists. To address this need, we developed approaches to extract DTMs by filtering VHR stereo point clouds (PCs) in sparse canopies of Alaska. Our evaluation consisted of two stereo processing methods with three PC search radii at six different tree canopy cover (TCC) intervals. We found that VHR DTMs were robust for estimating bare ground at TCC intervals less than 40% with vertical errors < 1.6 m using airborne small footprint light detection and ranging (LiDAR) as reference.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Open Set Semantic Segmentation for Multitemporal Crop Recognition

    • Free pre-print version: Loading...

      Authors: Jorge A. Chamorro Martinez;Hugo Oliveira;Jefersson A. dos Santos;Raul Queiroz Feitosa;
      Pages: 1 - 5
      Abstract: Multitemporal remote-sensing images play a key role as a source of information for automated crop mapping and monitoring. The spatial/spectral pattern evolution along time provides information about the dynamics of the crops and are very useful for productivity estimation. Although the multitemporal mapping of crops has progressed considerably with the advent of deep learning in recent years, the classification models obtained still have limitations when exposed to unknown classes in the prediction phase, reducing their usefulness. In other words, these models are trained to identify a closed set of crops (e.g., soy and sugar cane) and are therefore unable to recognize other types of crops (e.g., maize). In this letter, we deal with the challenges of multitemporal crop recognition by proposing a new approach called OpenPCS++ that is not only able to learn known classes but is also capable of identifying new crops in the predicting phase. The proposed approach was evaluated in two challenging public datasets located in tropical climates in Brazil. Results showed that OpenPCS++ achieved increases of up to 0.19 in terms of area under the receiver-operating characteristic (ROC) curve in comparison with baselines. Code is available at https://github.com/DiMorten/osss-mcr.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Optimizing Two-Band Spectral Indices to Estimate Leaf Chlorophyll Content
           Using the Non-Polarized Reflectance Factors

    • Free pre-print version: Loading...

      Authors: Yuefeng Li;Zhongqiu Sun;Shan Lu;
      Pages: 1 - 5
      Abstract: Leaf chlorophyll content (LCC) is a key indicator of plant photosynthesis and can be estimated by the optical properties of leaves. Due to the random distribution of leaf angles and the change of incident light angle, it is necessary to reduce the effects of specular reflection when estimating LCC under different measurement geometries. Because the polarized reflectance factor can account for specular reflection, which does not relate to LCC, it is possible to improve LCC estimation using spectral indices when the polarized reflectance is removed from the total reflectance. In this study, polarimetric measurements of leaves from three different plant species were performed with different measurement geometries in both laboratory and field conditions. We tested all possible waveband combinations in the 400–1000 nm range with two types of spectral indices: simple ratio (SR) ( $R_{lambda 1}/R_{lambda 2})$ and normalized difference vegetation index (NDVI) ( $R_{lambda mathrm {i}} - R_{lambda mathrm {j}}$ )/( $R_{lambda mathrm {i}} + R_{lambda mathrm {j}}$ ), using both total intensity [defined as $I$ parameter reflectance factor (IpRF)] and non-polarized [defined as non-polarized reflectance factor (NpRF)] information. By comparing the LCC estimation accuracy based on IpRF with that based on NpRF, we found that NpRF increased the number of bands that can estimate LCC with relatively high accuracy. These results indicate that the simple two-band indices based on the NpRF are robust and accurate for estimating LCC at leaf scale, and the broad effective wavelength range of NpRF may have the ability to overcome bandwidth limitations. The results of this study sup-ort future vegetation indices design and model development.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • On the Dependence of Amplitude and Phase Scintillation Indices on Magnetic
           Field Aligned Angle: A Statistical Investigation at High Latitudes

    • Free pre-print version: Loading...

      Authors: Mahith Madhanakumar;Anton Kashcheyev;P. T. Jayachandran;
      Pages: 1 - 5
      Abstract: This letter presents for the first time the results of a statistical study that had looked into the dependence of scintillation on the propagation geometry of GPS signals at high latitudes by combining the geometrical parameters, namely elevation and azimuth, along with the magnetic field vector into a single variable called the magnetic field aligned angle (MFAA). An increase in the value of scintillation indices when MFAA approaches zero is observed. This indicates the presence of field-aligned irregularities and the fact that MFAA is sensitive to irregularities whose size extends to Fresnel scales as well. Contrary to previous experimental and modeling studies which have shown higher variations of $sigma _{phi }$ index as compared to the $S_{4}$ index with the propagation geometry of GPS signals, our results suggest that these higher fluctuations in $sigma _{phi }$ were refractive in origin and were the result of improper detrending of the phase at high latitudes where the use of constant cutoff of 0.1 Hz is not accurate due to higher ionospheric plasma drift velocities at these latitudes.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Species Classification of Automatically Delineated Regenerating Conifer
           Crowns Using RGB and Near-Infrared UAV Imagery

    • Free pre-print version: Loading...

      Authors: Andrew J. Chadwick;Nicholas C. Coops;Christopher W. Bater;Lee A. Martens;Barry White;
      Pages: 1 - 5
      Abstract: Unmanned aerial vehicles (UAVs) and deep learning are important tools at the forefront of automated forest monitoring research, where classification of individual tree species is a critical forest management goal. Near-infrared (NIR) information provided by specialized UAV sensors may improve classification accuracy at the cost of added operational complexity; however, this potential for improvement is context-dependent and, therefore, may not be necessary. We assessed the performance of conventional red-green-blue (RGB) versus NIR imagery when classifying regenerating lodgepole pine and white spruce crowns automatically delineated by a trained deep learning algorithm. Models trained on NIR imagery slightly outperformed those trained on RGB imagery. Models trained on spectral bands outperformed those trained on spectral indices. The minor difference in performance between the two sets of imagery showed that accurate classification of lodgepole pine and white spruce can be carried-out using conventional RGB imagery.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • A Graph-Cut-Based Method for Road Labels Making With OSM Data

    • Free pre-print version: Loading...

      Authors: Le Yang;Jingsheng Zhai;Xing Wang;
      Pages: 1 - 5
      Abstract: Aiming at producing the road labels for deep neural networks (DNNs), this letter proposes a graph-cut-based method to make road annotations on very high-resolution (VHR) remote-sensing images. With the aid of OpenStreetMap (OSM), a superpixel method and the graph cut method are employed for road segmentation. After that, the road areas are refined by the OSM. In this process, the road annotations are made automatically. In experiments, two traditional methods, two deep learning methods, and the proposed method are utilized to segment the roads on two types of satellite images in Tianjin port area. The results show that the proposed method creates more accurate and integrated road labels compared with other methods.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Vegetation Canopy Height Retrieval Using L1 and L5 Airborne GNSS-R

    • Free pre-print version: Loading...

      Authors: J. F. Munoz-Martin;D. Pascual;R. Onrubia;H. Park;A. Camps;C. Rüdiger;J. P. Walker;A. Monerris;
      Pages: 1 - 5
      Abstract: Vegetation canopy height (CH) is one of the important remote-sensing parameters related to forests’ structure, and it can be related to the biomass and the carbon stock. Global navigation satellite system-reflectometry (GNSS-R) has proved capable to retrieve vegetation information at a moderate resolution from space (20–65 km) using L1 C/A signals. In this study, data retrieved by the airborne microwave interferometric reflectometer (MIR) GNSS-R instrument at L1 and L5 are compared to the Global Forest CH product, with a spatial resolution of 30 m. This work analyzes the waveforms (WFs) measured at both bands, and the correlation of the waveform width and the reflectivity values to the CH product. A neural network algorithm is used for the retrieval, showing that the combination of the reflectivity and the waveform width allows to estimate the CH information at a very high resolution, with a root-mean-square error (RMSE) of 4.25 and 4.07 m at L1 and L5, respectively, which is an error about 14% of the actual CH.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Landslide Mapping From PlanetScope Images Using Improved Region-Based
           Level Set Evolution

    • Free pre-print version: Loading...

      Authors: Ping Lu;Wenyang Shi;Zhongbin Li;
      Pages: 1 - 5
      Abstract: A timely and reliable inventory is essential for landslide hazard assessment and risk management. In this study, we use images from PlanetScope, which provides global 3 m daily Earth observations, for rapid mapping of landslide inventory. We propose a semiautomated method that combines change detection and region-based level set evolution (RLSE) to improve landslide mapping efficiency. Our approach uses change detection methods of independent component analysis (ICA), principal component analysis (PCA), and change vector analysis (CVA) for automated generation of landslide zero-level curves (ZLCs), and then incorporates the RLSE method to refine landslide mapping results. To corroborate the applicability of the proposed method, we test the landslide mapping performance on the Kodagu event (India, 2018) using ICA-, PCA- and CVA-based RLSE. The results show that ICA-based RLSE can achieve better landslide mapping accuracy in terms of completeness, correctness, and the Kappa coefficient. This study demonstrates the suitability and potential of low-orbit miniature satellites such as PlanetScope for landslide mapping. To the best of our knowledge, it is the first attempt to incorporate PlanetScope images and the change detection-based RLSE method for landslide mapping.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Automatic Framework of Mapping Impervious Surface Growth With Long-Term
           Landsat Imagery Based on Temporal Deep Learning Model

    • Free pre-print version: Loading...

      Authors: Ranyu Yin;Guojin He;Guizhou Wang;Tengfei Long;Hongfeng Li;Dengji Zhou;Chengjuan Gong;
      Pages: 1 - 5
      Abstract: The impervious surface (IS) cover and its dynamics are key parameters in research about urban and ecology. This letter proposed an automatic framework to map the IS growth end-to-end based on the temporal deep learning (DL) model and long time-series Landsat imagery. First, the training and validating datasets were auto-generated by a joint strategy. Then, a DL network was designed, and the IS growth was predicted in temporal windows. Finally, the results from multi-temporal windows are combined to generate the IS growth map. The data around the core of Beijing, China, is tested, and the result shows that the proposed method could: 1) efficiently model the IS growth; 2) map IS growth with less salt-and-pepper noise and false alarm compared to existing products; and 3) be extended to future data easily.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Fusion of All-Weather Land Surface Temperature From AMSR-E and MODIS Data
           Using Random Forest Regression

    • Free pre-print version: Loading...

      Authors: Quan Zhang;Jie Cheng;Ninglian Wang;
      Pages: 1 - 5
      Abstract: On the basis of preceding study of microwave (MW) land surface temperature (LST) downscaling, this letter proposed an all-weather LST fusion method based on random forest (RF) and evaluated it using the Moderate Resolution Imaging Spectroradiometer (MODIS) and Advanced Microwave Scanning Radiometer for the Earth Observing System (AMSR-E) LSTs in four areas of China that represent different landscapes. The results show that the RF method can effectively avoid the problem of oversmoothing patterns derived by the widely used Bayesian maximum entropy (BME) method and obtained LSTs more consistent with reality. Taking MODIS LST in the Yunnan–Guizhou Plateau (YGP) region and the border of Shanxi Province and Henan Province (BSH) region as a reference, the accuracy of RF method improved up to 13% and 11% compared with those of BME method under different cloud proportions. Taking field observations in the Heihe River Basin (HRB) and the Naqu area as references, the accuracy of RF-derived LST under cloudy conditions is basically consistent with that of MODIS LST in clear sky, differing by only 0.004–0.067 K. Due to the introduction of environmental variables, the performance of RF method is more stable than that of the BME method under different cloud proportions. In summary, RF is promising for fusing MW and thermal infrared (TIR) LSTs.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Classification of Medicinal Plants Astragalus Mongholicus Bunge and
           

    • Free pre-print version: Loading...

      Authors: Congcong Wang;Xiaobo Zhang;Tingting Shi;Chunhong Zhang;Minhui Li;
      Pages: 1 - 5
      Abstract: Accurate information regarding cultivated areas of medicinal plants is useful for taking macro-level decisions for medicinal plant management and contingency plans. In this study, the capabilities and limitations of mapping Astragalus mongholicus Bunge and Sophora flavescens Aiton using GaoFen-6 (GF-6) and multitemporal Sentinel-2 (S-2) data were assessed through a case study in Naiman Banner, Inner Mongolia, China. First, an object-based approach was used to produce a cropland mask based on the GF-6 images. Then, different spectral indices were generated from multitemporal S-2 imagery acquired in 2019, and a temporal phonological pattern analysis was conducted. Subsequently, optimal feature selection was carried out for each of the crops (A. mongholicus Bunge, S. flavescens Aiton, and Zea mays L.). The selection was performed by sorting all features according to their global separability index and removing those whose contribution to the model accuracy was negligible. Finally, the medicinal crops were distinguished using the random forest classification algorithm. An overall accuracy and a kappa coefficient of 94.51% and 0.90 were achieved, respectively, demonstrating that the synergistic use of time-series GF-6 and S-2 data were more suitable for A. mongholicus Bunge and S. flavescens Aiton mapping.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Exploring the Applicability of the Semi-Empirical BRDF Models at Different
           Scales Using Airborne Multi-Angular Observations

    • Free pre-print version: Loading...

      Authors: Juan Cheng;Jianguang Wen;Qing Xiao;Dalei Hao;Xingwen Lin;Qinhuo Liu;
      Pages: 1 - 5
      Abstract: Semi-empirical bidirectional reflectance distribution function (BRDF) models are developed based on various spatial-resolution pixels. Because of its simplicity and physical significance, it is widely used in medium- and low-spatial-resolution quantitative remote sensing. With the emergence of high-spatial-resolution remote sensing data and the lack of high-spatial-resolution BRDF models, semi-empirical BRDF models have also been directly applied to high-spatial-resolution qualitative and quantitative remote sensing research. However, whether semi-empirical BRDF models can be directly applied to pixels with high resolution remains unclear. To answer this question, this letter quantitatively evaluates the applicability of semi-empirical BRDF models for remote sensing data with 0.5–30 m spatial resolution based on the WIDAS multi-angular observation dataset obtained during the HiWATER experiment in 2012. The results demonstrate that the semi-empirical BRDF models are not applicable at the 0.5 m pixel scale but are applicable at the 10 m pixel scale. There is a transitional pixel scale from not applicable to applicable between 0.5 and 10 m. We define this scale as the optimal minimum pixel scale (OMS) of semi-empirical BRDF models. The OMS is related to the spatial structure of the vegetation scene, and it is highly consistent with the canopy characteristic scale calculated based on the semivariogram method ( $R^{2}=0.901$ ). Therefore, the range of the semivariogram can be used to estimate the OMS to answer the question of which scale semi-empirical BRDF models are applicable to high-spatial-resolution images.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • MAENet: Multiple Attention Encoder–Decoder Network for Farmland
           Segmentation of Remote Sensing Images

    • Free pre-print version: Loading...

      Authors: Hai Huan;Yuan Liu;Yaqin Xie;Chao Wang;Dongdong Xu;Yi Zhang;
      Pages: 1 - 5
      Abstract: With the rapid development of computer vision, semantic segmentation as an important part of the technology has made some achievements in different applications. However, in the farmland segmentation scenario of remote sensing images, the capability of common semantic segmentation methods in restoring the farmland edge and identifying narrow farmland ridges needs to be improved. Therefore, in this letter a semantic segmentation method–multiple attention encoder–decoder network (MAENet)–for farmland segmentation is proposed. The design of a dual-pooling efficient channel attention (DPECA) module and its embedment in the backbone to improve the efficiency of feature extraction is described; secondly, a dual-feature attention (DFA) module is proposed to extract contextual information of high-level features; finally, a global-guidance information upsample (GIU) module is added to the decoder to reduce the influence of redundant information on feature fusion. We use three self-made farmland image datasets representing UAV data to train MAENet and compare them with other methods. The results show that the performances of segmentation and generalization of MAENet are improved compared with other methods. The MIoU and Kappa coefficient in the farmland multi-classification test set can reach 93.74% and 96.74%.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Novel Multiscale Decision Fusion Approach to Unsupervised Change Detection
           for High-Resolution Images

    • Free pre-print version: Loading...

      Authors: Pan Shao;Yunqi Yi;Zhewei Liu;Ting Dong;Dong Ren;
      Pages: 1 - 5
      Abstract: High-resolution remote sensing images usually contain multiscale information, which can be used to enhance the change detection (CD) performance. How to make effective use of multiscale information needs intensive study. This letter presents a novel multiscale decision fusion (MDF) method for unsupervised CD based on Dempster–Shafer (DS) theory and modified conditional random field (CRF). The method consists of three main steps: 1) images of three different scales are created automatically by image segmentation, and then three-scale difference images (DIs) are produced by applying change vector analysis to the three-scale images; 2) the membership function of each scale DI is estimated by fuzzy clustering, and the fusion membership, as well as an initial CD map, is obtained by combining the estimated membership using DS theory; and 3) the initial CD map is refined with an improved CRF that incorporates a spatial attraction model. The proposed method can combine the multiscale information in images and the spatial contextual information. The effectiveness of the proposed method was validated by two experiments with high-resolution remote sensing images.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Potential of ANN for Prolonging Remote Sensing-Based Soil Moisture
           Products for Long-term Time Series Analysis

    • Free pre-print version: Loading...

      Authors: Xiaozhuang Geng;Huan Li;Zhaoyuan Yao;Xi Chen;Zekun Yang;Sien Li;Lifeng Wu;Yaokui Cui;
      Pages: 1 - 5
      Abstract: Soil moisture (SM) plays an important role in the water–heat–energy exchange and water cycle of the land ecosystem. Long-term SM products are vital in the time series study of ecology and hydrology. Therefore, it is vital to extend the time span with limited SM monitoring sensors, since there is no single long-term SM product currently. In this study, an SM product prolonging method based on an artificial neural network (ANN) and moderate-resolution imaging spectroradiometer (MODIS) optical products was proposed. The prolonging results of Soil Moisture Active Passive (SMAP) and Fenyun-3B (FY3B) products were validated in Tibetan Plateau to present the feasibility of this method. The result shows this method is feasible in areas under medium vegetation cover (0.2 < NDVI < 0.6), but it still needs to be improved in some areas (especially in areas with very high or very low NDVI). The prolonging data fits well ( $R $ = 0.84, RMSE < 0.06 cm3 ${cm}^{-3}$ ) with in situ measurements for both SMAP and FY-3B products. The generated long-term SM will benefit the global water cycle study.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • MLP-Based Efficient Stitching Method for UAV Images

    • Free pre-print version: Loading...

      Authors: Moxuan Ren;Jianan Li;Liqiang Song;Hui Li;Tingfa Xu;
      Pages: 1 - 5
      Abstract: Unmanned aerial vehicle (UAV) image stitching techniques based on position and attitude information have shown clear speed superiority over feature-based counterparts. However, how to improve stitching accuracy and robustness remains a great challenge since position and attitude parameters are sensitive to noise introduced by sensors and external environment. To mitigate this issue, this work presents a simple yet effective stitching algorithm for UAV images based on a coarse-to-fine strategy. Specifically, we first conduct coarse registration using the position and attitude information obtained from GPS, IMU, and altimeter. Then, we introduce a novel offline calibration phase that is designed to regress the obtained global transformation matrix to the optimal one computed from feature-based algorithms, by using multi-layer perceptron (MLP) neural networks for fast correction. Consequently, the proposed method well integrates the complementary strengths of both parameter and feature-based methods, achieving an ideal speed–accuracy tradeoff. Moreover, to facilitate research on this topic, we establish a new dataset, named UAV-AIRPAI, that comprises over 100 UAV image pairs with position and attitude annotations to the community, opening up a promising direction for UAV image stitching. Extensive experiments on the UAV-AIRPAI dataset show that our method achieves superior accuracy compared to priors while running at a real-time speed of 0.0124 s per image pair. Code and data will be available at https://github.com/dededust/UAV-AIRPAI.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Estimating LAI From Winter Wheat Using UAV Data and CNNs

    • Free pre-print version: Loading...

      Authors: Lucas Wittstruck;Thomas Jarmer;Dieter Trautz;Björn Waske;
      Pages: 1 - 5
      Abstract: With the advent of high-resolution unmanned aerial vehicle (UAV) data and advancing methods of deep learning, new opportunities have emerged in remote sensing to assess biophysical plant parameters. In this study, we investigated the potential of UAV-borne RGB data and convolutional neural networks (CNNs) to estimate the leaf area index (LAI) of winter wheat during two cropping seasons. In this context, spectral RGB and geometric plant information based on a normalized surface model (nDSM) were used as input variables. The results of the study demonstrated the suitability of optical UAV data and CNNs for LAI estimation of winter wheat at different growth stages and under various lightning conditions. The combination of RGB data and plant structures provided the best overall prediction accuracy ( $r^{2} = 0.83$ ) compared to the models with only one input source (RGB: $r^{2} = 0.58$ , nDSM: $r^{2} = 0.75$ ). Especially the estimation of low and high LAI values was improved using the complementary image information. Moreover, the results showed that the CNN models outperformed two classical machine learning (ML) approaches in terms of accuracy.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Estimating Surface BRDF/Albedo Over Rugged Terrain Using an Extended
           Multisensor Combined BRDF Inversion (EMCBI) Model

    • Free pre-print version: Loading...

      Authors: Jianguang Wen;Dongqin You;Yuan Han;Xingwen Lin;Shengbiao Wu;Yong Tang;Qing Xiao;Qinhuo Liu;
      Pages: 1 - 5
      Abstract: Land surface albedo is a crucial variable of earth energy budget and global climate change. Rugged terrain significantly impacts surface bidirectional reflectance distribution function (BRDF) and the subsequent albedo retrieval using satellite remote sensing. Existing studies of estimating surface BRDF/albedo from satellite observations are limited to neglecting topographic impacts, resulting in large uncertainty in satellite albedo product, especially for low spatial resolution satellite sensors that are primarily regulated by subpixel-scale topographic effects. To fill this knowledge gap, we proposed an extended multisensor combined BRDF inversion (EMCBI) model to characterize subpixel-scale topographic effects, and applied this model to estimate BRDF/albedo from the Himawari-8 Advanced Himawari Imager (AHI) and Terra/Aqua moderate resolution imaging spectroradiometer (MODIS) data and finally validated the satellite-derived albedo with ground measurements of two stations located in Tibet plateau. Our results show that: 1) EMCBI can generate a daily BRDF/albedo dataset with more than 90% spatial coverage and 2) EMCBI-derived albedo agrees well with the referenced albedo corrected from ground measurement, with a root-mean-square-error (RMSE) of 0.0537 and 0.0608 for black-sky albedo (BSA) and white-sky albedo (WSA), and a mean absolute percentage error (MAPE) of 21.93% and 25.13% for BSA and WSA, respectively. These results demonstrate EMCBI has great potential for mapping large-scale high temporal resolution BRDF/albedo product over rugged terrain.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Multiscale Feature Learning by Transformer for Building Extraction From
           Satellite Images

    • Free pre-print version: Loading...

      Authors: Xin Chen;Chunping Qiu;Wenyue Guo;Anzhu Yu;Xiaochong Tong;Michael Schmitt;
      Pages: 1 - 5
      Abstract: Extracting buildings from very high-resolution satellite images is a challenging yet important task for applications such as urban monitoring. Multiscale feature learning proves to be a potential solution toward accurate extraction of buildings. This study exploits a powerful multiscale feature learning module, a hierarchical vision transformer by shifted windows (swin), as a backbone within a building extraction network. To this end, we first designed a general structure for building extraction, consisting of a backbone to extract multiscale features and a head network to fuse and refine features. Then, we integrated swin into the structure as a backbone and utilized channel-wise and spatial-wise enhancement in a head network. Experimental results show that our method achieves improvements regarding both F1-score and intersection over union (IoU) compared to the multiple attending path neural network (MAP-Net), which is the current state-of-the-art (SOTA) algorithm for building extraction from remote sensing images. Our study thus confirms the potential of swin transformers as backbones for semantic segmentation tasks based on satellite images.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Adaptive Moving Ground-Target Detection Method Based on Seismic Signal

    • Free pre-print version: Loading...

      Authors: Qiuzhan Zhou;Xinyi Yao;Cong Wang;Jikang Hu;Pingping Liu;Jun Lin;
      Pages: 1 - 5
      Abstract: Moving ground-target detection system is widely used to monitor illegal activities of pedestrians and vehicles. However, existing detection methods are restricted by the power consumption in hardware and are usually based on some single feature of the seismic signal, which leads to low detection accuracy and false alarms. To address these issues, we propose a new moving ground-target detection method for detecting the weak seismic signals generated by distant moving ground targets. This method combines an adaptive strategy and support vector machines (SVMs). Both time- and frequency-domain features of seismic signals are considered in the detection method. Additionally, we carry out field experiments to evaluate the performance of the proposed method. The results show that the proposed moving ground-target detection method can detect distant moving ground targets and avoid false alarms as many as possible, which indicates good performance.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Coherent and Incoherent Change Detection for Soil Moisture Retrieval From
           Sentinel-1 Data

    • Free pre-print version: Loading...

      Authors: Davide Palmisano;Giuseppe Satalino;Anna Balenzano;Francesco Mattia;
      Pages: 1 - 5
      Abstract: This study proposes a hybrid incoherent–coherent change detection (CD) approach to retrieve surface soil moisture (SSM) from Sentinel-1 data. It combines time-series observations of synthetic aperture radar (SAR) backscatter and interferometric closure phase to deliver a method that does not require external calibration. A proof-of-concept assessment based on synthetic and experimental data is presented. Sentinel-1 and in situ data over a study site in Southern Italy during the Winter–Spring season 2017 that covered both bare and vegetated soil conditions have been acquired and analyzed. For bare soils, results indicate good performance, that is, Pearson correlation ≈0.8 and root mean square error (RMSE) ≈0.05 m3/m3. Conversely, over vegetated surfaces, poor results are found.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • IRCNN: An Irregular-Time-Distanced Recurrent Convolutional Neural Network
           for Change Detection in Satellite Time Series

    • Free pre-print version: Loading...

      Authors: Bin Yang;Le Qin;Jianqiang Liu;Xinxin Liu;
      Pages: 1 - 5
      Abstract: Deep learning (DL)-based methods incorporating convolutional neural networks (CNNs) and recurrent neural networks (RNNs) have been successfully applied to change detection in satellite time series. However, traditional RNNs assume identical time interval between image sequences, which hardly meets the real case in satellite time series because of clouds and shadows. In this letter, a novel irregular-time-distanced recurrent CNN (IRCNN) is proposed. IRCNN consists of three sub-networks: a multi-branch Siamese CNN, irregular-time-distanced long short-term memory (ILSTM), and fully connected (FC) layers. Superior to the existing methods, IRCNN can account for temporal dependency among time series with irregular time distances. It is end-to-end trainable with samples generated using an automatic annotation generation method, which is proposed based on the prior knowledge from the continuous change detection and classification (CCDC) approach. IRCNN was tested over five study areas using Landsat time series collected between 2013 and 2020. Experiments demonstrate the effectiveness and stability of the proposed network with better performance, compared to the state-of-the-art approaches in terms of both qualitative and quantitative aspects. Our IRCNN Pytorch code and data are available at https://github.com/thebinyang/IRCNN.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Semi-Supervised Semantic Segmentation of Remote Sensing Images With
           Iterative Contrastive Network

    • Free pre-print version: Loading...

      Authors: Jia-Xin Wang;Si-Bao Chen;Chris H. Q. Ding;Jin Tang;Bin Luo;
      Pages: 1 - 5
      Abstract: With the development of deep learning, semantic segmentation of remote sensing images has made great progress. However, segmentation algorithms based on deep learning usually require a huge number of labeled images for model training. For remote sensing images, pixel-level annotation usually consumes expensive resources. To alleviate this problem, this letter proposes a semi-supervised segmentation method of remote sensing images based on an iterative contrastive network. This method combines few labeled images and more unlabeled images to significantly improve the model performance. First, contrastive networks continuously learn more potential information by using better pseudo labels. Then, the iterative training method keeps the differences between models to better improve the segmentation performance. The semi-supervised experiments on different remote sensing datasets prove that this method has a better performance than the related methods. Code is available at https://github.com/VCISwang/ICNet.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Tiny-Scene Embedding Network for Coastal Wetland Mapping Using Zhuhai-1
           Hyperspectral Images

    • Free pre-print version: Loading...

      Authors: Binge Cui;Xinhui Li;Jing Wu;Guangbo Ren;Yan Lu;
      Pages: 1 - 5
      Abstract: The fine mapping of coastal wetlands is a major challenge due to the spectral aliasing of vegetation. In this letter, we selected Zhuhai-1 hyperspectral images (HSIs) for coastal wetland mapping and proposed a tiny-scene embedding network (TSE-Net) based on scene representation and attention mechanism. In TSE-Net, the tiny-scene representation associated with each hyperspectral pixel was extracted and used to enhance the spectral discrimination of ground objects. DenseNet was chosen as the backbone network, and the attention mechanism was introduced into the dense blocks to extract remarkable features. Experiments on the Yellow River estuary coastal wetland showed that the results of TSE-Net had a significant improvement in accuracy compared to other models, especially for the coastal wetland vegetation with confusing spectra, such as Spartina alterniflora, Suaeda salsa, Phragmites australis, and Tamarix.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Measuring Soil Moisture With Refracted GPS Signals

    • Free pre-print version: Loading...

      Authors: Yunwei Li;Kegen Yu;Jiancheng Li;Taoyong Jin;Xin Chang;Qiang Zhang;Shiqi Yang;
      Pages: 1 - 5
      Abstract: In the last 20 years, the reflected signal of Global Navigation Satellite System (GNSS) has been used for remotely sensing a series of geophysical parameters, resulting in two GNSS based remotely sensing techniques: GNSS reflectometry (GNSS-R) and GNSS interferometric reflectometry (GNSS-IR). In this letter, the refracted GNSS signal is first proposed to estimate near-surface soil moisture (SM). Amplitude of the refracted GNSS signal will attenuate when penetrated into soil due to refraction and propagation of the signal in the soil. Amplitude attenuation degree of the refracted signal is quantified as the amplitude ratio (AR) of the direct GNSS signal to the refracted signal. Two low-cost navigational GNSS chips and right-hand circularly polarized (RHCP) antennas are used to collect the refracted and direct GNSS signal in an experimental campaign, respectively. To simplify the modeling, the AR at elevation angle of 20° is used to develop the model to describe the relationship between SM, AR, and soil temperature (ST) in the letter; and the AR and ST observation can be converted into SM accurately with a 2nd-order polynomial. The modeled SMs are strongly correlated with the sensor-based ones with correlation coefficient of 0.947 and root-mean-square error (RMSE) of 0.013 cm3/cm3 (or, 1.3%) when SM is between 0.272 and 0.489 cm3/cm3. The study also suggests that, based on the proposed method, the low-cost GNSS instrument can be treated as a new type of sensor monitoring SM in a cost-effective way.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Mapping Deforestation Using Fractions Indices and the Non-Seasonal PVts-β
           Detection Approach

    • Free pre-print version: Loading...

      Authors: Yonatan Tarazona Coronel;
      Pages: 1 - 5
      Abstract: This letter focuses on the mapping of deforestation between 2008 and 2018 in a small region in Brazil through time series. Vegetation indices as variables that are strongly influenced by seasonality were used. Whereas to reduce seasonality in the time series, dense series of fraction indices obtained from the physical spectral mixture analysis (SMA) model were used. Both the indices were obtained from Landsat images. Then, changes were detected through a non-seasonal detection approach (called PVts- $beta $ approach). To evaluate the detections obtained, true ground reference data of the study area were used. Results showed that the quantifications obtained with fraction indices had an overall accuracy (OA) of 90.00% higher than vegetation indices. Additionally, the different atmospheric correction algorithms strongly influenced the values of the fraction indices. This study focuses on the basis for future work to implement the PVts- $beta $ approach on platforms such as Google Earth engine (GEE).
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Object-Based Sorted-Histogram Similarity Measurement for Detecting Land
           Cover Change With VHR Remote Sensing Images

    • Free pre-print version: Loading...

      Authors: Zhiyong Lv;Xuan Yang;Xiaokang Zhang;Jón Atli Benediktsson;
      Pages: 1 - 5
      Abstract: Land cover change detection (LCCD) with very high-resolution (VHR) remote sensing images has been widely used in various applications. However, pseudo-changes and noise usually affect the performance of detection map. In this letter, an object-oriented sorted-histogram similarity measurement (OSSM) is proposed for measuring the change magnitude between bi-temporal remote sensing images. First, multi-scale objects are acquired for the post-event image using a multi-scale segmentation algorithm, and then the pixels within each object are considered to construct the pairwise histograms and the bin of each histogram is sorted in descending order. Second, a bin-to-bin (B2B) distance is defined to measure the change magnitude between the pairwise object-based histograms, and the change magnitude image (CMI) is generated after all the bi-temporal images are scanned object by object. Finally, a simple yet effective method called Otsu is used to divide the CMI into binary change detection maps. The experiments on three pairs of VHR images produced promising results compared with five popular LCCD approaches, for example, the improvement is about 2.5% for F-score.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Domain-Adversarial Neural Networks for Deforestation Detection in Tropical
           Forests

    • Free pre-print version: Loading...

      Authors: Pedro J. Soto;Gilson A. Costa;Raul Q. Feitosa;Mabel X. Ortega;José D. Bermudez;Javier N. Turnes;
      Pages: 1 - 5
      Abstract: Many deep-learning (DL)-based, domain adaptation (DA) methods for remote sensing (RS) applications rely on adversarial training strategies to align features extracted from images of different domains in a shared latent space. However, the performance of such representation matching techniques is negatively impacted when class occurrences in the target domain, for which no labeled data are available during training, are highly imbalanced. In this work, we propose a DL-based representation matching approach for DA in the context of change detection tasks. We further evaluate the approach in a deforestation mapping application, characterized by a high-class imbalance between the deforestation and no-deforestation classes. The domains represent different sites in the Amazon and Brazilian Cerrado biomes. To mitigate the class imbalance problem, we devised an unsupervised pseudolabeling scheme based on change vector analysis (CVA) that prevents the feature alignment to be biased toward the overrepresented class. The experimental results indicate that the proposed approach can improve the accuracy of cross-domain deforestation detection.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Investigating Impacts of Ambient Air Pollution on the Terrestrial Gross
           Primary Productivity (GPP) From Remote Sensing

    • Free pre-print version: Loading...

      Authors: Songyan Zhu;Jian Xu;Hao Zhu;Jingya Zeng;Yapeng Wang;Qiaolin Zeng;Dejun Zhang;Xiaoran Liu;Shiqi Yang;
      Pages: 1 - 5
      Abstract: In contrast to the threats to urban human health, impacts of air pollutants on the ecosystem photosynthesis seem to be less concerned. The existence of aerosols could promote photosynthesis by increasing the ratio of diffuse to direct solar radiation; on the contrary, ozone (O3) could inhibit photosynthesis, as it is detrimental to leaf stomata. However, it is unknown whether these two opposite impacts worldwide cancel each other out. In the current mainstream methods, earth system models may show conflicts with in situ experimental results due to their relatively coarse resolution. In virtue of satellite remote sensing and a global eddy covariance (EC) network, we studied ten years of data to explore the impacts of aerosol and O3 on photosynthesis by fitting an explainable machine learning model. The impacts of aerosol on gross primary productivity (GPP) were positive in many cases, yet very weak. By means of the nitrogen dioxide (NO2) to formaldehyde (HCHO) ratio, O3 was seen with positive impacts on photosynthesis under the NOx-sensitive regime, but the apparent positive impacts correlated with the plant phenology. Under the volatile organic compound (VOC)-sensitive regime, the impacts of O3 on GPP were not obvious, which was likely due to the prioritized depletion of O3 by NO2 and VOCs. The impacts of air pollutants depended on many factors and results varied case by case, but the overall net impacts were negative.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Nonlocal Multiscale Single Image Statistics From Sentinel-1 SAR Data for
           High Resolution Bitemporal Forest Wind Damage Detection

    • Free pre-print version: Loading...

      Authors: T. Manninen;E. Jääskeläinen;E. Tomppo;
      Pages: 1 - 5
      Abstract: Change detection of synthetic aperture radar (SAR) data is a challenge for high-resolution applications. This study presents a new nonlocal averaging approach (STATSAR) to reduce the speckle of single Sentinel-1 SAR images and statistical parameters derived from the image. The similarity of SAR pixels is based on the statistics of $3times3$ window as represented by the mean, standard deviation, median, minimum, and maximum. K-means clustering is used to divide the SAR image in 30 similarity clusters. The nonlocal averaging is carried out within each cluster separately in magnitude order of the $3times3$ window averages. The nonlocal filtering is applicable not only to the original pixel backscattering values but also to statistical parameters, such as standard deviation. The statistical parameters to be filtered can represent any window size, according to the need of the application. The nonlocally averaged standard deviation derived in two spatial resolutions, $3times3$ and $7times7$ windows, are demonstrated here for improving the resolution in which the forest damages can be detected using the VH polarized backscattering spatial variation change.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Robust Multisensor Prediction of Drought-Induced Yield Anomalies of
           Soybeans in Argentina

    • Free pre-print version: Loading...

      Authors: Martin D. Maas;Mercedes Salvia;Pablo C. Spennemann;María Elena Fernandez-Long;
      Pages: 1 - 4
      Abstract: A multisensor method for the prediction of drought-induced agricultural impact is put forth in this letter. The input data considered include MODIS NDVI and land surface temperature (LST), ESA-CCI Soil Moisture, and CHIRPS rain data, which are processed at the department level in a large and sparsely monitored cropland in Argentina. As ground truth, we have used department-scale crop losses estimated by an annual agricultural census. In particular, the period under consideration (2001–2019) includes five severe drought events where soybean production in the area was considerably affected. The proposed method is based on Lasso regression of the corresponding rank values of the satellite data to the relative yield anomalies. Importantly, the proposed methodology is robust to extreme drought events. In addition, an associated early warning classification method results in an overall accuracy no worse than 70% up to one month before the harvest, and 62% two months before the harvest. The proposed methodology offers a valuable method for the prediction of agricultural drought impact and should be especially valuable in sparsely monitored regions of the world.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • NL-LinkNet: Toward Lighter But More Accurate Road Extraction With Nonlocal
           Operations

    • Free pre-print version: Loading...

      Authors: Yooseung Wang;Junghoon Seo;Taegyun Jeon;
      Pages: 1 - 5
      Abstract: Road extraction from very high resolution (VHR) satellite images is one of the most important topics in the field of remote sensing. In this letter, we propose an efficient nonlocal LinkNet with nonlocal blocks (NLBs) that can grasp relations between global features. This enables each spatial feature point to refer to all other contextual information and results in more accurate road segmentation. In detail, our single model without any postprocessing like conditional random field (CRF) refinement performed better than any other published state-of-the-art ensemble model in the official DeepGlobe Challenge. Moreover, our nonlocal LinkNet (NL-LinkNet) beat the D-LinkNet, the winner of the DeepGlobe challenge (Demir et al., 2018), with 43% less parameters, less giga floating-point operations per seconds (GFLOPs), and shorter training convergence time. We also present empirical analyses on the proper usages of NLBs for the baseline model.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • The Impact of In Situ Probe Orientation on SMAP
           Validation Statistics

    • Free pre-print version: Loading...

      Authors: Aaron A. Berg;Jaison Thomas Ambadan;Andreas Colliander;Heather McNairn;Jarrett Powers;Erica Tetlock;
      Pages: 1 - 5
      Abstract: Ongoing evaluation of the soil moisture active passive (SMAP) soil moisture products has utilized validation networks distributed in several regions around the world. The in situ reference used for validation of the soil moisture retrieval algorithm is associated with measurements from soil moisture probes typically located at 5 cm beneath the soil surface; however, some networks also consider a vertically oriented probe that measures from 0 to 5 cm. In this study, we compare the correlation and unbiased root mean square error (ubRMSE) from the SMAP L2 radiometer soil moisture product when compared to in situ measurements taken at 5 cm (approximately 3.5–6.5 cm) below the surface and measurements taken as an integrated measure from 0 to 5.7 cm. The data were obtained from two SMAP validation networks in Canada: the Kenaston network in Saskatchewan and Carman network situated in Manitoba. At both sites, correlations between the in situ and the SMAP L2 product were consistently higher with vertically oriented probes following rain events. With respect to the ubRMSE, the vertically oriented probes at the Carman site had lower ubRMSE with the SMAP product than the horizontal probes that are currently used for validation activities. In some cases, vertical probe information should be considered in validation approaches when this data is available and could be considered in the design of in situ calibration/validation networks. These results may be useful in design considerations of networks for upcoming soil moisture product validation.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • A Subsurface Targets’ Classification Method Utilizing Gradient
           Learning Technique

    • Free pre-print version: Loading...

      Authors: Wupeng Xie;Xiaojuan Zhang;Yaxin Mu;Yaoxin Zheng;
      Pages: 1 - 5
      Abstract: Recent advances in the time-domain electromagnetic (TDEM) method have dramatically improved detection and discrimination of subsurface targets. Inversion of observed response using a 3-D orthogonal magnetic dipolar model provides location, orientation, and intrinsic responses of the target based on deterministic optimization methods, which is dependent on the initial values and could be trapped in local minimum solutions. In this letter, we applied a supervised descent method (SDM) to the inversion of electromagnetic induction (EMI) data accurately by individually and simultaneously training every single sample in the training set to avoid the direct use of the SDM that causes inaccurate classification results. This method provides a new way to incorporate prior information using gradient learning and reduce the computational complexity as it does not compute partial derivatives in the nonlinear least-squares problem or groups difference in the heuristic random search algorithm. Then the simulation and field experiments are performed to verify the feasibility of this method. Both the simulation and experimental results demonstrate that the SDM shows good performance and robustness in the classification of subsurface anomalous targets.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Learning to Count Grave Sites for Cemetery Observation Models With
           Satellite Imagery

    • Free pre-print version: Loading...

      Authors: Dalton Lunga;Rohan Dhamdhere;Sarah Walters;Lauryn Bragg;Nikhil Makkar;Marie Urban;
      Pages: 1 - 5
      Abstract: Understanding how people occupy open spaces is important for research in support of population modeling, policy, national security, emergency response, and sustainability. For the past decade, there has been an increase in research toward capturing and reporting population dynamics and patterns of life at the building level and in some open public spaces such as cemeteries and parks. This is done through observation models developed from local sociocultural information acquired at various spatiotemporal scales to inform night, day, and episodic population occupancy estimates (people/1000 sq ft). Sociocultural information for cemeteries and parks is scarcely available and often collected manually. The process is not only marred by inconsistencies but is laborious and time consuming. In this study, we leverage convolutional neural networks (CNNs) and satellite imagery to derive grave site counts as proxy variables to support scalable and accurate sociocultural data required in a population observation model. Through a hybrid workflow (weak localization plus regression model), we characterize a large scale automation process to counting of grave sites. We evaluate and demonstrate the efficacy of proposed workflow using out-of-data set large satellite imagery and establish its broader impact on cemetery observation models.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Synthesis of Satellite-Like Urban Images From Historical Maps Using
           Conditional GAN

    • Free pre-print version: Loading...

      Authors: Henrique J. A. Andrade;Bruno J. T. Fernandes;
      Pages: 1 - 4
      Abstract: One method for encouraging the public interest in the use of historical maps as a source of reliable knowledge is to represent them in a more familiar aspect, such as the style of the current-day popular application Google Maps’ satellite view. We present a method for synthesizing satellite-images from historical maps, translating their visuals using conditional generative adversarial networks (conditional GANs). We discuss a typical representation of these dated documents to allow such translations. We observe how the semantics involved in the process influence the outcomes. Finally, we discuss the effective result of bringing the past to a familiar look for the viewer.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Semi-automatic Extraction of Rural Roads From High-Resolution Remote
           Sensing Images Based on a Multifeature Combination

    • Free pre-print version: Loading...

      Authors: Jiguang Dai;Rongchen Ma;Haibin Ai;
      Pages: 1 - 5
      Abstract: Roads play a vital role in rural economic development. However, rural roads feature irregular curvature changes, are narrow, and are built using diverse construction materials, which renders the analysis of road geometric and spectral characteristics less certain and reduces the automation ability of existing methods. Thus, this letter proposes a semiautomatic extraction of rural roads from high-resolution remote sensing images based on a multifeature combination. First, to address irregular curvature change characteristics of rural roads, we modify multiscale line segment orientation histogram (MLSOH) descriptors to reduce the impact of local curvature change on tracking. Second, we design a multicircle template to analyze the contrast between roads and nonroads and solve the problem of narrow roads. Last, we propose a panchromatic and hue, saturation, value (HSV) space interactive matching model to solve the problem of matching diverse road construction materials. This letter employs Pleiades satellite and GF-2 imagery. Compared with other methods, the proposed method improves automated road extraction by ensuring the extraction accuracy.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Road Extraction From Remote Sensing Images in Wildland–Urban
           Interface Areas

    • Free pre-print version: Loading...

      Authors: Ruonan Chen;Xiang Li;Yuan Hu;Congcong Wen;Ling Peng;
      Pages: 1 - 5
      Abstract: In this letter, we address the problem of road extraction in Wildland–urban interface (WUI) areas. In recent years, with the great success of convolutional neural networks (CNNs) in various vision-related tasks, researchers have developed many CNN-based methods for road extraction on remote sensing images. Nevertheless, these methods mostly treat road extraction as a binary classification problem on semantic labeling. In WUI areas, the road is narrower and tends to be occluded by trees, which may result in the serious discontinuous problem of inferred road maps. To address this issue, we propose transforming the input representation of the binary classification map into a continuous signed distance map. In this way, our model is forced to predict the continuous distance representations and, thus, improve the spatial continuities of inferred roads. In addition, a real-value regression task is designed to train along with the original binary classification task to generate spatially continuous and semantically accurate road maps. Then, we conduct experiments on the public Massachusetts road data set and a homemade data set collected from Yajishan Mountain, Beijing, China. Finally, our proposed method achieves intersection-over-unions (IoUs) of 64.11% and 65.92% for the Massachusetts and WUI-Yajishan data sets, respectively, without any postprocessing. In addition, the ablation analysis shows that introducing the regression task on the proposed signed distance representation can effectively alleviate the problem of discontinuous road prediction. Furthermore, comparing with the state-of-the-art methods demonstrates the superiority of our method for road extraction in WUI areas.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Identifying and Quantifying Urban Polycentric Development in China From
           DMSP-OLS Data and Urban Land Data Sets

    • Free pre-print version: Loading...

      Authors: Kaifang Shi;Jingwei Shen;Yizhen Wu;Xuguang Tang;
      Pages: 1 - 5
      Abstract: This study attempted to identify and quantify the morphology of intercity urban polycentric development (UPD) from the Defense Meteorological Satellite Program’s Operational Linescan System (DMSP-OLS) data and urban land (UL) data sets in China at the provincial level. The spatiotemporal change and impact factors of UPD from 2000 to 2012 were also evaluated. The accuracy verification results indicated that the UPD could effectively and accurately identify and evaluate from the DMSP-OLS data and UL data sets in China. China’s urban structure presented a UPD trend from 2000 to 2012 and showed a pattern of high values in the eastern region and low values in the western region. In addition, the gross domestic product was proven to be a significant factor and had an inverted U-shaped impact on the UPD. The study can provide accurate time-series UPD data sets for decision-makers to evaluate the spatiotemporal change and driving mechanism of the intercity urban structure in China at the provincial level.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Shannon Entropy-Based Seismic Local Correlation Measure and Enhancement

    • Free pre-print version: Loading...

      Authors: Weilin Huang;Xiaoyu Chuai;Ying Rao;Baoyu Li;
      Pages: 1 - 5
      Abstract: Estimation of seismic structural correlation can provide useful information for structural interpretation, events correlation enhancement, signal-to-noise ratio (SNR) improvement, subsurface modeling, and geophysical inversion. In this letter, we propose a Shannon entropy-based method to measure seismic local correlation and further enhance the correlation of seismic events. The proposed method is derived from the local plane-wave model and formulated as a Shannon entropy form. The probabilities are calculated along with the coordinate direction of local slope and estimated by solving two least-squares problems in local areas. Application to both synthetic and field data sets demonstrates the superior performance of the Shannon entropy-based method over traditional alternatives.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Gas-Bearing Prediction Using Transfer Learning and CNNs: An Application to
           a Deep Tight Dolomite Reservoir

    • Free pre-print version: Loading...

      Authors: Jianhu Gao;Zhaohui Song;Jinyong Gui;Sanyi Yuan;
      Pages: 1 - 5
      Abstract: Predicting gas-bearing zone of deep tight dolomite reservoirs from prestack seismic data is challenging and subject to great uncertainty. Machine learning especially for deep learning (DL) provides a new potential. One main limitation of the DL-based supervised methods is that they require large amounts of training data. However, well-log labels from the real deep reservoirs are very insufficient. To address this issue, we investigate a method based on convolutional neural networks (CNNs) considering transfer learning to predict gas distribution of deep tight dolomite reservoirs. The CNNs model we used contains three convolutional layers for automatic feature extraction from prestack data and one fully connected (FC) layer for gas-bearing probability prediction. A numerical model is designed based on petrophysical parameters extracted from the real target work area associated with deep tight dolomite reservoirs. The model is used to generate synthetic samples to pretrain the CNNs model. We then fix the network parameters in the first two convolutional layers and decay the learning rates of the third convolutional layer and the FC layer. Using the real samples to fine-tune the pretrained CNNs model with epoch increasing. The optimal predictor is finally trained well for gas-bearing prediction. The method is applied to a real work area of deep tight dolomite reservoir located in western China covering approximately 800 km2. Examples illustrate the roles of transfer learning on improving gas-bearing distribution of deep tight dolomite reservoirs and increasing the generalization of the method.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Seismic Local Instantaneous Frequency Extraction for Describing Superposed
           Sands

    • Free pre-print version: Loading...

      Authors: Naihao Liu;Teng Huang;Jinghuai Gao;Xiudi Jiang;Fangyu Li;
      Pages: 1 - 5
      Abstract: Seismic instantaneous frequency (IF), as one of the instantaneous attributes, is widely used for seismic interpretation and stratigraphy analysis. The Hilbert transform (HT)-based complex analysis approaches are commonly used to extract seismic IF, which are sensitive to kinds of noise contained in field data. Although the normalized HT (NHT) improves the antinoise property of HT by normalizing the original trace, the HT-based methods are a global operator that is not suitable for the local analysis. For example, IF calculated by using the HT-based method is unstable when meeting strong seismic events. In this letter, we propose a workflow to extract local IF (LIF) and then apply it to describe superposed sands. Note that the proposed workflow extracts a stable IF result even when processing a seismic trace with strong events. To demonstrate the effectiveness of the proposed workflow, we apply it to both synthetic and field data. Compared with results from HT and NHT, the proposed workflow provides a stable IF extraction and offers potentials in precisely highlighting superposed sands.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Multisynchrosqueezing Generalized S-Transform and Its Application in Tight
           Sandstone Gas Reservoir Identification

    • Free pre-print version: Loading...

      Authors: Xuping Chen;Hui Chen;Rui Li;Ying Hu;Yuxia Fang;
      Pages: 1 - 5
      Abstract: Synchrosqueezing transform (SST) is a high-resolution time-frequency (TF) analysis (TFA) approach for seismic spectral anomaly detection. Here, a novel method called multisynchrosqueezing generalized S-transform (GST) is proposed and applied for the identification of tight sandstone gas reservoirs. In this method, a signal model named the Gaussian-Modulated Signal Model (GMSM) is introduced to estimate the instantaneous frequency (IF) of the signal in the GST’s spectrum. Then, an iterative algorithm constantly approximating IF is constructed to provide a highly energy-concentrated TF representation while allowing for signal reconstruction. Compared to some advanced TFA methods, the proposed method has better energy-concentrated performance due to an accurate estimate of the IF. A simulated signal and field data are employed to verify the effectiveness of the proposed method. It is concluded that the proposed method has great potential as a TFA technique for identifying tight sandstone gas reservoirs.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • 3-D Gravity Inversion Based on Deep Convolution Neural Networks

    • Free pre-print version: Loading...

      Authors: Qianguo Yang;Xiangyun Hu;Shuang Liu;Qu Jie;Huaijiang Wang;Qiuhua Chen;
      Pages: 1 - 5
      Abstract: The distribution of physical features in the Earth’s interior could be estimated by geophysical inversion from the acquired data at or above the surface. Inverse problems are generally considered as least-squares optimization issues in high-dimensional parameter space. Existing approaches are largely based on linear inversion methods, which are limited by the initial model. Nonlinear inversion methods, despite their significant ability in uncertainty quantification, still remain a formidable computational task. In this letter, a new gravity inversion approach is developed based on convolutional neural networks (CNNs). Although the training stage of this method is time-consuming, the actual prediction can be performed in only seconds. Thus, the high computational time of geophysical inversion can be considerably decreased once an appropriate network is constructed. The tests on synthetic data demonstrate that good results could be attained by applying this method to gravity data inversion compared with the least-squares regularization inversion and fully convolutional networks (FCNs).
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Deep Recurrent Neural Networks Approach to Sedimentary Facies
           Classification Using Well Logs

    • Free pre-print version: Loading...

      Authors: Daniel Theisges dos Santos;Mauro Roisenberg;Marivaldo dos Santos Nascimento;
      Pages: 1 - 5
      Abstract: Determination of lithofacies is one of the most important steps for reservoir characterization. Well log curves are not always sufficient to determine lithology as some times the signals are similar for different lithologies. We believe that the sequence of sedimentary patterns that follows the general geologic rules can be essential to help this disambiguation. This work aims to present a computational system based on deep recurrent neural networks (RNNs) as an effective method to automatically identify lithofacies patterns from well logs. We show that bidirectional long-short-term memory (BiLSTM) RNNs can learn long-term dependencies between time steps of sequence data improving the context available to facies classification. We validated our method by applying it to a real case study from Rio Bonito Formation (Paraná Basin, Brazil) and the proposed method is compared with XGBoost, Random Forest, Naïve Bayes, and support vector machine (SVM) learning approaches. The results indicate that the performance of the proposed method for lithology identification is higher when compared with these other methods.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Landslide Susceptibility Prediction Using Sparse Feature Extraction and
           Machine Learning Models Based on GIS and Remote Sensing

    • Free pre-print version: Loading...

      Authors: Li Zhu;Gongjian Wang;Faming Huang;Yan Li;Wei Chen;Haoyuan Hong;
      Pages: 1 - 5
      Abstract: Landslide susceptibility prediction (LSP) is a useful technology for landslide prevention. Due to the complex nonlinear correlations among environmental factors, traditional machine learning (ML) models have unsatisfactory LSP accuracies. In this letter, a sparse feature extraction network (SFE+) is proposed for LSP. First, the landslides and environmental factors are collected, and frequency ratios of environmental factors are calculated as the model inputs. Second, the input data are passed through the input layer with the dropout, and then, the features are passed through the hidden layers, that is, the k% lifetime sparsity layers. The hidden layers are employed to further sparse these factors to obtain the independent and redundant prediction features as much as possible. Finally, certain classifiers are used to realize the LSP in the study area. SFE-support vector machine (SVM), SFE-logistic regression (LR), and SFE-stochastic gradient descent (SGD) models are built. For comparison, principal component analysis (PCA)-SVM, PCA-LR, PCA-SGD, SVM, LR, and SGD models are also built for LSP in Shicheng County, China. Results show that the SFE-based ML models, especially the SFE-SVM, can effectively extract the sparse nonlinear features of environmental factors to improve LSP accuracies and have promising prospects for LSP.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • On the Use of Google Earth Engine and Sentinel Data to Detect “Lost”
           Sections of Ancient Roads. The Case of Via Appia

    • Free pre-print version: Loading...

      Authors: Rosa Lasaponara;Nicodemo Abate;Nicola Masini;
      Pages: 1 - 5
      Abstract: The currently available tools and services as open and free cloud resources to process big satellite data opened up a new frontier of possibilities and applications including archeological research. These new research opportunities also pose several challenges to be faced, as, for example, the data processing and interpretation. This letter is about the assessment of different methods and data sources to support a visual interpretation of EO imagery. Multitemporal Sentinel 1 and Sentinel 2 data sets have been processed to assess their capability in the detection of buried archeological remains related to some lost sections of the ancient Via Appia road (herein selected as case study). The very subtle and nonpermanent features linked to buried archeological remains can be captured using multitemporal (intra- and inter-year) satellite acquisitions, but this requires strong hardware infrastructures or cloud facilities, today also available as open and free tools as Google Earth Engine (GEE). In this study, a total of 2948 Sentinel 1 and 743 Sentinel 2 images were selected (from February 2017 to August 2020) and processed using GEE to enhance and unveil archeological features. Outputs obtained from both Sentinel 1 and Sentinel 2 have been successfully compared with in situ analysis and high-resolution Google Earth images.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Fine-Grained Road Scene Understanding From Aerial Images Based on
           Semisupervised Semantic Segmentation Networks

    • Free pre-print version: Loading...

      Authors: Rong Xiao;Yuze Wang;Chao Tao;
      Pages: 1 - 5
      Abstract: High-precision electronic maps are required to provide more detailed and accurate information than traditional maps. With the rapid development of high-resolution remote sensing technology, it has become possible to extract fine-grained road scene information such as vehicles, road lines, zebra crossings, ground signs, and lane widths of roads from unmanned aerial vehicle (UAV) remote sensing images, which opens up opportunities for automatic mapping high-precision maps. The traditional method of deciphering remote sensing images is often obtained through manual visual interpretation. Due to the high cost and long lead time of this method, it leads to inefficiencies in updating large amounts of information. To address this problem, this letter models the fine-grained road scene understanding task as an image semantic segmentation problem and innovatively proposes a semisupervised fully convolutional neural network to extract the information efficiently at a low cost. Compared with the traditional supervised full convolutional neural network, this method can simultaneously optimize the standard supervised classification loss on labeled samples and the unsupervised consistency loss on unlabeled samples by using an integrated prediction technology and then input them to the end-to-end semantic segmentation network for training. This method is designed to effectively improve the classification accuracy of the semantic segmentation network and validly alleviates overfitting problems in the case of small numbers of labeled samples. In order to verify the effectiveness of this method, we constructed a data set for experimental, which is used to verify the effect of a variable number of unlabeled samples on model performance. Experimental results show that our method can efficiently complete the extraction of fine-grained road scene information such as vehicles, road lines, zebra crossings, ground signs, and lane widths of roads with a small number of labeled samples.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Deep Feature-Review Transmit Network of Contour-Enhanced Road Extraction
           From Remote Sensing Images

    • Free pre-print version: Loading...

      Authors: Zhijin Ge;Yanling Zhao;Jin Wang;Duo Wang;Qi Si;
      Pages: 1 - 5
      Abstract: The acquisition of road information from remote sensing images is of significant value with regard to intelligent transportation research. This study focuses on enhancing the contour-learning ability to mitigate the phenomenon of fragmented road segments and missing connections in road extraction. A novel Deep Feature-Review (FR) Transmit Network (TransNet) is proposed to review and facilitate the flow of contour features into an encoder network. Meanwhile, multiscale features are linked via a bridge between the encoder and the decoder. Compared with the state-of-the-art models such as fully convolutional network (FCN), SegNet, DeepLabv3, D-LinkNet, spatial consistency-FCN, and generative adversarial network (GAN), the proposed network achieves better overall performance for the Massachusetts Roads data set, with accuracy, precision, recall, and mean intersection-over-union (IoU) scores of 97.48%, 83.72%, 78.13%, and 0.6286%, respectively. For the DeepGlobe Road Extraction data set, the proposed network outperforms FCN, SegNet, DeepLabv3, D-LinkNet, and Deep TransNet, achieving accuracy, precision, recall, and mean IoU scores of 98.70%, 87.30%, 81.15%, and 0.7244%, respectively. Overall, these experiments indicate that the proposed network can effectively address the phenomenon of fragmented road segments and poor connectivity in remote sensing images, indicating its potential for utilization in practical intelligent transportation scenarios.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Retrieval of Canopy Gap Fraction From Terrestrial Laser Scanning Data
           Based on the Monte Carlo Method

    • Free pre-print version: Loading...

      Authors: Yifan Xu;Shihua Li;Hangkai You;Ze He;Zhonghua Su;
      Pages: 1 - 5
      Abstract: Canopy gaps affect the spatial distribution of radiation in the canopy. The estimation of gap fraction (GF) is important for the study of leaf area index (LAI). Terrestrial laser scanning (TLS) has been widely used for retrieving canopy structure parameters through massive high-resolution spatial samples in the form of 3-D point cloud data sets. Monte Carlo simulations can be used to obtain approximate solutions to quantitative problems through a large number of random sampling while avoiding complicated mathematical calculations. Monte Carlo simulations are suitable for analyzing TLS data and could help overcome resolution reductions inherent to current point cloud processing approaches. However, few studies have applied the Monte Carlo method to capture the canopy structure features implicit in high-resolution point clouds. This letter proposes a method for estimating the GF based on Monte Carlo simulations. A large number of randomly simulated laser beams were emitted to identify the canopy and gaps according to the discrimination distance, and the results were compared with the GFs derived from digital hemispherical photography (DHP). In general, the proposed TLS method estimated smaller GFs than the DHP method since DHP was vulnerable to exposure conditions and complex canopy structure. The GF estimated by the two methods is consistent ( $R^{2} =0.7522$ ), indicating the effectiveness of the Monte Carlo method.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Building Instance Extraction Method Based on Improved Hybrid Task Cascade

    • Free pre-print version: Loading...

      Authors: Xiaoxue Liu;Yiping Chen;Mingqiang Wei;Cheng Wang;Wesley Nunes Gonçalves;José Marcato;Jonathan Li;
      Pages: 1 - 5
      Abstract: Automatic building extraction from remote sensing imagery is crucial to urban construction and management. To address the main challenges of diverse building scale and appearance, this letter proposes an automatic building instance extraction method based on an improved hybrid task cascade (HTC). Our method consists of three components by obtaining high-resolution representation, defining guided anchor, and forming focal loss to boost the adaptability of automatic building instance extraction. Comprehensive experimental results on WHU aerial building data set demonstrated that compared with the mainstream Mask R-CNN method, our method increased AP and AR in bounding box branch and mask branch by 9.8%–6.5% and 10.7%–8.0% respectively, especially AP $_{S}$ and AP $_{L}$ in the two branches by 10.1%–6.9% and 3.4%–2.4%, respectively. We evaluated the effectiveness and complexity of these components separately and discussed the universality and practicability of deep learning method in automatic building extraction.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • A Method for Downscaling Satellite Soil Moisture Based on Land Surface
           Temperature and Net Surface Shortwave Radiation

    • Free pre-print version: Loading...

      Authors: Yawei Wang;Pei Leng;Jianwei Ma;Jian Peng;
      Pages: 1 - 5
      Abstract: Due to the coarse spatial resolution of currently available microwave (mostly passive) soil moisture (SM) products, it is difficult to apply these SM data in watersheds or at local scales. To this end, a number of downscaling approaches have been developed to improve the spatial resolution of microwave SM products. Specifically, the optical-/thermal-based downscaling methods are most widely used in recent decades. However, such methods normally rely on instantaneous optical/thermal land surface parameters, which are commonly inapplicable under cloudy conditions. The purpose of this study is to develop a new downscaling method based on the temporal variation in geostationary satellite-derived land surface temperature and net surface shortwave radiation. The proposed method has a certain potential to improve data availability under cloudy conditions, because geostationary satellites are capable of providing land surface parameters at high temporal resolution. The proposed method was tested over the REMEDHUS network in Spain. The scaling strategy of cumulative distribution function matching was used to remove systematic differences in spatial mismatch between satellite pixels and in situ SM measurements. Results indicate that the downscaled SM agrees well with in situ measurements and has comparable accuracy with the original microwave SM product. The overall root mean square errors with the in situ measurements for the original microwave SM and the downscaled SM are 0.054 and 0.057 $text{m}^{3}/text{m}^{3}$ , respectively. This method not only has a successful attempt to downscale microwave SM data using temporal information but also has the potential to avoid the failure of traditional instantaneous observations-based downscaling procedure due to clouds.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Open-Pit Mine Road Extraction From High-Resolution Remote Sensing Images
           Using RATT-UNet

    • Free pre-print version: Loading...

      Authors: Dong Xiao;Lingyu Yin;Yanhua Fu;
      Pages: 1 - 5
      Abstract: With the further development of the construction of “smart mine,” the technology of mine unmanned truck has developed rapidly. Road data are an important prerequisite for the mature application of mining and transportation dispatching system and unmanned driving, so it is particularly important to extract the road in open-pit mines timely and accurately. Different from urban roads, mine roads have no clear road edge and more background interference. In view of the above problems, a convolutional neural network called RATT-UNet (R: residual connection; ATT: attention), which combines residual connection, attention mechanism, and U-Net, is proposed to extract mine road from high-resolution remote sensing images. The advantages of the proposed method are listed as follows: first, the well-designed RATT unit combining residual connection and attention mechanism is used to construct the proposed neural network, which improves the network’s perception ability of detailed features. Second, the abundant skip connections and residual connections can improve the information flow, allowing a better network to be designed with fewer parameters. Third, a composite loss function based on structural similarity is proposed, which effectively alleviates the noise and edge blurring phenomenon and improves segmentation quality. Finally, we perform postprocessing optimization operations on the road extraction results. Experimental results demonstrate that the proposed RATT-UNet outperforms all the comparing network models in terms of the quality of extraction results and evaluation indicators in the mining road extraction task.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • An Adversarial Domain Adaptation Framework With KL-Constraint for Remote
           Sensing Land Cover Classification

    • Free pre-print version: Loading...

      Authors: Mengxi Liu;Pengyuan Zhang;Qian Shi;Mengwei Liu;
      Pages: 1 - 5
      Abstract: Land cover classification plays a crucial role in land resource monitoring and planning. Recently, deep learning-based methods are becoming the dominating method for precise land cover mapping. However, the large-scale application of them is deeply hindered by the domain shift between different images, which is easily caused by illumination, climate, regional divergence, and so on. With the aim to cope with the problem of domain shift, many domain adaptation (DA) methods have been provided and great achievements have been made, especially the newborn adversarial DA, which usually contains a generator and a discriminator. Among these methods, the pixel-level methods are of high memory consumption, whereas feature-level methods are found hard to decode the structured information for semantic segmentation tasks due to the lack of low-dimensional information. Therefore, we propose an adversarial domain adaptation framework with Kullback–Leibler constraint (KL-ADDA) for remote sensing land cover classification. A state-of-the-art (SOTA) semantic segmentation network is utilized as the generator, which directly outputs the segmentation results to the discriminator to retain more low-level information. Besides, a Kullback–Leibler (KL)-divergence is calculated to improve the discriminative ability of the discriminator and thus enhance the generator’s performance. Experiments on the international society for photogrammetry and remote sensing (ISPRS) data set and two simulated target data sets have shown the effectiveness of KL-ADDA for DA.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • SIFT: Modeling Solar-Induced Chlorophyll Fluorescence Over Sloping Terrain

    • Free pre-print version: Loading...

      Authors: Hanyu Shi;Zhiqiang Xiao;
      Pages: 1 - 5
      Abstract: Solar-induced chlorophyll fluorescence (SIF) is found well correlated with gross primary productivity (GPP) and a good indicator of vegetation status. However, the influence of topography on SIF has not been studied, and SIF models with topographic consideration are needed to analyze this influence. Unfortunately, apart from computationally expensive 3-D models, current SIF models cannot work with sloping terrain. An efficient 1-D SIF model with topographic consideration (SIFT) is proposed in this study based on the well-known Soil Canopy Observation, Photochemistry and Energy fluxes (SCOPE) model. The evaluation of SIFT, by comparing with the 3-D Discrete Anisotropic Radiative Transfer (DART) model, demonstrates that it has high accuracy. This study also demonstrates that ignoring topography induces significant errors (exceeding 125% for a 60° slope) in canopy SIF simulations. The conclusion that the topography is an important factor for SIF and the proposed SIFT model will benefit those who are interested in SIF simulations and applications.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Coastal Altimetry Using Interferometric Phase From GEO Satellite in
           Quasi-Zenith Satellite System

    • Free pre-print version: Loading...

      Authors: Yunqiao He;Fan Gao;Tianhe Xu;Xinyue Meng;Nazi Wang;
      Pages: 1 - 5
      Abstract: Global navigation satellite system reflectometry (GNSS-R) altimetry has great potential to provide high spatial–temporal resolution sea surface heights (SSHs) at low cost. Interferometric phase measurements between direct and reflected signals can be used for altimetry retrieval to achieve high-precision solutions. The motions of the medium Earth orbit (MEO) satellites cause interferometric phase change rapidly, which would increase the probability of occurrence of the phase unwrapping errors than the case of the geosynchronous Earth orbit (GEO) satellite. In order to overcome this problem, we propose a coastal GNSS-R altimetry algorithm using the signals from Quasi-Zenith Satellite System (QZSS) GEO satellite. Precise SSH variations can be achieved using the interferometric phase measurements without ambiguity fixed. We also perform coastal experiments on a trestle using a specialized GNSS-R setup to verify our algorithm. It is composed of an intermediate frequency (IF) data collector and two antennas. The up-looking antenna is used to receive direct signals, while the down-looking antenna receives the signals reflected from the sea surface. Raw IF data sampled at 62 MHz are collected and processed to derive interferometric carrier phase delay measurements using a self-developed software-defined receiver. Approximately 7 h of reflector heights are retrieved at 1-min intervals and the solutions are evaluated via comparison with measurements provided by a 26-GHz altimetry radar located near the GNSS-R setups. The results show that the root mean square error (RMSE) of sea level estimation is about 1.4 cm by using the QZSS GEO data.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Synchrosqueezing Polynomial Chirplet Transform and Its Application in
           Tight Sandstone Gas Reservoir Identification

    • Free pre-print version: Loading...

      Authors: Rui Li;Hui Chen;Yuxia Fang;Ying Hu;Xuping Chen;Jun Li;
      Pages: 1 - 5
      Abstract: Polynomial chirplet transform (PCT) can effectively characterize the instantaneous frequency (IF) of mono-mode frequency-modulated (FM) signal, but it is unsuitable to analyze multimode signals. Here, we propose synchrosqueezing PCT (SPCT) for amplitude-modulated (AM) and FM signals with multimode, and apply it to tight sandstone gas reservoirs. First, a multikernel operator is constructed to concentrate the energy near the IF of each mode, and then an IF estimator is derived to further reassign the energy to the corresponding IF ridge. This not only achieves a highly energy-concentrated time-frequency representation, but also retains its invertibility. The synthetic signal is employed to validate the effectiveness of the SPCT. The application on field seismic data also demonstrates that the SPCT can effectively identify tight sandstone gas reservoirs.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Sloping Surface Reflectance: The Best Option for Satellite-Based Albedo
           Retrieval Over Mountainous Areas

    • Free pre-print version: Loading...

      Authors: Xingwen Lin;Shengbiao Wu;Dalei Hao;Jianguang Wen;Qing Xiao;Qinhuo Liu;
      Pages: 1 - 5
      Abstract: The estimation of satellite-based albedo highly depends on the surface reflectance (SR). In mountainous areas, three types of SRs [i.e., the virtual SR (VSR) that is retrieved from the atmospheric correction model, the topographically corrected SR (TCSR) that is retrieved from the atmospheric and topographic correction model, and the sloping SR (SSR) that is retrieved from the physically bidirectional reflectance distribution function (BRDF)-based mountain-radiative-transfer (MRT) model] are commonly used to retrieve land surface albedo (SA). However, which type of SR is the best option for SA retrieval has not yet been quantitatively addressed. This letter assessed the performance of these three types of SRs on driving SA by comparison with in situ albedo measurements over field sites in the Heihe River Basin, China. Our results show that these three types of albedos have consistent accuracy over flat sites with a root mean squared error (RMSE) smaller than 0.0320. Moreover, the sloping SA (SSA) retrieved from SSR shows the best agreement with in situ albedo measurements over rugged sites with a bias of 0.0008, RMSE of 0.0338, relative RMSE (RMSER) of 12.92%, and correlation coefficient ( $r$ ) of 0.89, followed by the topographically corrected SA (TCSA) from TCSR with a lager bias of 0.0208, RMSE of 0.0470, RMSER of 20.24%, and $r$ of 0.69. The virtual SA (VSA) retrieved from VSR shows the largest uncertainty than the other two types of albedos, with an RMSE of 0.0516. These results illustrate that SSR is the best option of reflectance for satellite-based albedo retrieval over mountainous areas.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Deep Learning-Based Building Footprint Extraction With Missing Annotations

    • Free pre-print version: Loading...

      Authors: Jian Kang;Ruben Fernandez-Beltran;Xian Sun;Jingen Ni;Antonio Plaza;
      Pages: 1 - 5
      Abstract: Most state-of-the-art deep learning-based methods for extraction of building footprints are aimed at designing proper convolutional neural network (CNN) architectures or loss functions able to effectively predict building masks from remote sensing (RS) images. To properly train such CNN models, large-scale and pixel-level building annotations are required. One common approach to obtain scalable benchmark data sets for the segmentation of buildings is to register RS images with auxiliary geospatial information data, such as those available from OpenStreetMaps (OSM). However, due to land-cover changes, urban construction, and delayed geospatial information updating, some building annotations may be missing in the corresponding ground-truth building mask layers. This will likely introduce confusion in the training of CNN models for discriminating between background and building pixels. To solve this important issue, we first formulate the problem as a long-tailed classification one. Then, we introduce a new joint loss function based on three terms: 1) logit adjusted cross entropy (LACE) loss, aimed at discriminating between building and background pixels from a long-tailed label distribution; 2) weighted dice loss, aimed at increasing the $F_{1}$ scores of the predicted building masks; and 3) boundary (BD) alignment loss, which is optimized for preserving the fine-grained structure of building boundaries. Our experiments, conducted on two benchmark building segmentation data sets, validate the effectiveness of our newly proposed loss with respect to other state-of-the-art losses commonly used for extracting building footprints. The codes of this letter will be publicly available from https://github.com/jiankang1991/GRSL_BFE_MA.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • DBRANet: Road Extraction by Dual-Branch Encoder and Regional Attention
           Decoder

    • Free pre-print version: Loading...

      Authors: Si-Bao Chen;Yu-Xin Ji;Jin Tang;Bin Luo;Wei-Qiang Wang;Ke Lv;
      Pages: 1 - 5
      Abstract: Although widely exploited in recent decades, road extraction is still a very significant and challenging research in the field of remote sensing image processing due to the complex background and road distribution. Among the existing CNN-based methods, U-shape architectures composed of encoders and decoders have shown their effectiveness. In this letter, we propose an improved encoder–decoder method, named DBRANet, for extracting roads from remote sensing images. In the encoding phase, we present a dual-branch network module (DBNM) to construct more effective features, thus improving the fusion feature maps of different scales. One branch utilizes the residual block, and the other branch utilizes the refined asymmetric block, which effectively increases the feature extraction capability of the backbone. In the decoding phase, considering the sinuous shape and the unbalanced distribution of roads in remote sensing images, we design a novel attention module, named the regional attention network module (RANM), to automatically learn the importance of each channel according to the regional information. Extensive experiments on several public remote sensing road data sets show that our DBRANet achieves higher segmentation [ $F1$ score and Intersection over Union (IoU)] and connectivity [average path length similarity (APLS)] accuracy, which verifies the effectiveness of our approach.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Landslide Inventory Mapping Method Based on Adaptive Histogram-Mean
           Distance With Bitemporal VHR Aerial Images

    • Free pre-print version: Loading...

      Authors: Tongfei Liu;Maoguo Gong;Fenlong Jiang;Yuanqiao Zhang;Hao Li;
      Pages: 1 - 5
      Abstract: Landslide inventory mapping (LIM) on the basis of change detection techniques has potential significance for landslide disaster analysis. In this letter, a novel LIM approach based on the adaptive histogram-mean distance (AHMD) is proposed, which adaptively considers spatial contextual information of different landslide regions to improve the detection performance. First, to adapt the shape, size, and distribution of various landslides, an adaptive region around a pixel is extracted by a novel adaptive region extension algorithm without parameter setting. Second, the pixels within the adaptive region are taken to construct the spectral frequency histograms, and then, the adaptive histogram mean (AHM) is developed as the feature of a histogram. Third, the AHMD is defined based on the bin-to-bin (B2B) distance to measure change magnitude between the pairwise AHMs. Finally, LIM can be obtained by a supervised threshold method called double-window flexible pace search (DFPS). Experimental results tested on two real datasets with a very high spatial resolution (VHR) demonstrate the outperformance of the proposed AHMD approach with seven comparative methods.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Richer U-Net: Learning More Details for Road Detection in Remote Sensing
           Images

    • Free pre-print version: Loading...

      Authors: Yifan Zao;Zhenwei Shi;
      Pages: 1 - 5
      Abstract: Road detection in remote sensing images has been an important research topic in the past few decades. However, with complex backgrounds and occlusion of vehicles and trees, it is difficult for most road detection methods to obtain complete and accurate results. There will be a large number of error and omission detections in such complex scenes due to the poor utilization of detailed information. Therefore, in this article, we propose a novel road detection method called Richer U-Net, which alleviates this problem by designing two detail enhancement strategies. First, considering that convolution operation will cause the loss of detailed information in the feature map, an enhanced detail recovery structure (EDRS) is introduced to make full use of those lost information. It combines the output of each convolutional layer at the same level for the detail recovery of decoding network, leading to more accurate segmentation results. Second, an edge-focused loss function is proposed to guide the network to pay more attention to the road edge area. By adding an enhancement factor, the pixels closer to edge will contribute more loss. The corresponding experiments are conducted on two public datasets, and it can be shown that our method effectively improves final detection results.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Contrasting YOLOv5, Transformer, and EfficientDet Detectors for Crop
           Circle Detection in Desert

    • Free pre-print version: Loading...

      Authors: Mohamed Lamine Mekhalfi;Carlo Nicolò;Yakoub Bazi;Mohamad Mahmoud Al Rahhal;Norah A. Alsharif;Eslam Al Maghayreh;
      Pages: 1 - 5
      Abstract: Ongoing discoveries of water reserves have fostered an increasing adoption of crop circles in the desert in several countries. Automatically quantifying and surveying the layout of crop circles in remote areas can be of great use for stakeholders in managing the expansion of the farming land. This letter compares latest deep learning models for crop circle detection and counting, namely Detection Transformers, EfficientDet and YOLOv5 are evaluated. To this end, we build two datasets, via Google Earth Pro, corresponding to two large crop circle hot spots in Egypt and Saudi Arabia. The images were drawn at an altitude of 20 km above the targets. The models are assessed in within-domain and cross-domain scenarios, and yielded plausible detection potential and inference response.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Root Zone Soil Moisture Comparisons: AirMOSS, SMERGE, and SMAP

    • Free pre-print version: Loading...

      Authors: Kenneth J. Tobin;Wade T. Crow;Marvin E. Bennett;
      Pages: 1 - 5
      Abstract: A long-standing goal in the terrestrial remote sensing community has been the development of a root-zone soil moisture (RZSM) product based on microwave radar or radiometry observations. For example, the National Aeronautics and Space Administration’s (NASA’s) Airborne Microwave Observatory of Subcanopy and Surface (AirMOSS) mission between 2012 and 2015 served as an airborne testbed for the development of RZSM estimates acquired from a 420–440 MHz (P-band) radar. Results from the AirMOSS mission suggest that P-band backscatter can be inverted to provide a direct measurement of 0- to 40-cm RZSM. However, whether AirMOSS RZSM is inherently more robust than indirect RZSM estimates including soil MERGE (SMERGE) and Soil Moisture Active Passive Level 4 (SMAP L4) is not clear. SMERGE and SMAP L4 leverage surface (2–5 cm depth), higher-frequency microwave observations (C- and L-bands) via data fusion (DFus) and data assimilation (DA) techniques, respectively. Therefore, the comparisons of these products are warranted and were based on bias, root mean square error (RMSE), and unbiased root mean standard deviation (ubRMSD) metrics. Comparisons also were made against in situ observations providing additional context. The seven AirMOSS sites within the contiguous United States (CONUS) were examined. Overall, direct AirMOSS RZSM measurements, based on the original retrieval algorithms, did not outperform indirect SMERGE and SMAP L4 RZSM estimates. These results provide insight into the viability of achieving enhanced RZSM accuracy via deployment of a spaceborne P-band radar.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • An Improved Model for Estimating the Dielectric Constant of Saline Soil in
           C-Band

    • Free pre-print version: Loading...

      Authors: Leilei Dong;Weizhen Wang;Feinan Xu;Yueru Wu;
      Pages: 1 - 5
      Abstract: Soil salinization is one of the major forms of land degradation processes from all over the world. The dielectric constant plays an important role in the process of soil salinity retrieval by using microwave remote sensing. The Dobson model has been widely used to simulate the dielectric constant of nonsaline soil, but the estimated result of the Dobson model did not perform well for saline soil. Moreover, the ions’ concentration is related to soil salinity, and the electrical conductance is a critical factor that influences the imaginary part of the dielectric constant. Therefore, the relationship between them needs to further explore. In addition, saturation is neglected in the current dielectric model of saline soil. In this letter, the relationship between the electrical conductance and ions’ concentration was analyzed based on the experimental data. The saturation as a new parameter was introduced into the Dobson model to improve the estimated accuracy of the dielectric constant of saline soil in the C-band. The comparison between the revised model, the Dobson model, the Hu Qingrong (HQR) model, and the Wu Yueru (WYR) model was presented. The results indicate that there is a significant linear relationship between the electrical conductance and ions’ concentration, with $R^{2}$ of 0.996, a slope of 0.1456, and an intercept of 0.0252. Once the new parameter is implemented, the improved dielectric model based on the C-band reproduces the dielectric constant of saline soil satisfactorily in each soil sample. The simulated results of the improved model are consistent with the laboratory measurement results, with an RMSE of 0.97 and $R^{2}$ of 0.953. Compared with other commonly used three dielectric models of the saline soil, the improved dielectric model performs -ell in simulating the imaginary part of the dielectric constant. The improved agreements between the simulations and the measurements indicate that the revised dielectric model is appropriate for simulating the dielectric constant of saline soil. The revised dielectric model of saline soil will provide a scientific foundation for the soil salinity retrieval from the microwave remote sensing technology.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Soil Moisture Retrievals Using CYGNSS Data in a Time-Series Ratio Method:
           Progress Update and Error Analysis

    • Free pre-print version: Loading...

      Authors: Mohammad M. Al-Khaldi;Joel T. Johnson;
      Pages: 1 - 5
      Abstract: A previously reported time-series ratio method for retrieving soil moisture information from Cyclone Global Navigation Satellite System (CYGNSS) measurements is updated to improve the algorithm used for excluding CYGNSS measurements from the time series, thereby improving the algorithm’s computational efficiency while eliminating the requirement for contemporary soil moisture information from Soil Moisture Active Passive (SMAP). Daily CYGNSS soil moisture estimates are retrieved and presented on a 36-km grid over the 27-month period January 2018–May 2020 and show an overall root mean square error $approx 4.46$ %, an overall correlation for all attempted retrievals of $approx 80.53$ %, and an average correlation for individual pixels of 48.61% relative to SMAP using the updated time-series algorithm. An analysis of the errors of the updated algorithm is also provided as a function of surface properties.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Development of Soil Moisture Inversion Model for Bare Soil Using
           Navigation With Indian Constellation (NavIC)

    • Free pre-print version: Loading...

      Authors: Sushant Shekhar;Rishi Prakash;Dharmendra Kumar Pandey;Anurag Vidyarthi;Shivani Tyagi;Deepak Putrevu;Arundhati Misra;
      Pages: 1 - 5
      Abstract: This letter aims to develop an inversion model to estimate soil moisture using Navigation with Indian Constellation (NavIC) L-band signal. Several research works suggest that microwave signal property gets affected after reflecting from the soil surface. The nature of the reflected microwave signal depends on the signal’s penetration depth, which is the factor of water content present in the soil surface. NavIC multipath signal can be used for the estimation of soil moisture using this property. The carrier to noise ratio $(C/N_{mathrm {o}})$ of NavIC signal is used for this purpose. The model proposed in the letter is based on the relationship of estimated multipath phase value with the volumetric moisture content present in the soil surface. The output of the developed model is highly encouraging. A linear relation relationship with a high correlation coefficient value of 0.902 and root mean square error (RMSE) of 4.03% is obtained between ground truth soil moisture and retrieved soil moisture from developed algorithm.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Phase Coherence of GPS Signal Land Reflections and its Dependence on
           Surface Characteristics

    • Free pre-print version: Loading...

      Authors: Ian Collett;Yang Wang;Rashmi Shah;Y. Jade Morton;
      Pages: 1 - 5
      Abstract: Coherent reflections of global navigation satellite system (GNSS) signals have a measurable carrier phase, enabling higher precision for certain GNSS-based Earth remote sensing applications. In this letter, we explore the dependence of coherence on three land surface characteristics: surface water, topography, and soil moisture (SM). Carrier phase measurements are obtained by tracking raw intermediate frequency data collected by the cyclone GNSS (CYGNSS) mission. In total, several hundred data collections between 2017 and 2019 are analyzed. The phase coherence, quantified using statistics of the tracked carrier phase, is compared to the corresponding land characteristics on a per-track basis and across the entire dataset. On a per-track basis, we find that the level of coherence can often be explained by the presence of surface water, with no obvious dependence on topography or SM. However, by analyzing the entire dataset, we show that topography and SM have a weak but noticeable impact on the coherence.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Temperature-Soil Moisture Dryness Index for Remote Sensing of Surface Soil
           Moisture Assessment

    • Free pre-print version: Loading...

      Authors: Mai Son Le;Yuei-An Liou;
      Pages: 1 - 5
      Abstract: Surface water availability and its temperature are fundamental factors in describing the characteristics of land surface properties. In this study, a new temperature-soil moisture dryness index (TMDI) to quantify surface soil moisture (SSM) is proposed. It is defined as a function of land surface temperature variation and its relationship to surface water availability. The spatial pattern of TMDI has been analyzed over two time points of dry and rainy seasons for the plain area of Tainan, Taiwan, using Landsat 8 Operational Land Imager (OLI)/Thermal Infrared Sensor (TIRS) image acquired on January 20 and October 19, 2014. The effectiveness of TMDI in reflecting the SSM status was then evaluated by the results of the simulated evapotranspiration (ET) and verified by the near-surface air temperature ( $T_{text {air}}$ ) and humidity (RHair) measured by the ground-based weather stations. The results indicated that TMDI exhibited a significantly negative correlation with the simulated ET and positive correlation with in situ measured $T_{text {air}}$ from seven stations ( $r = - 0.95$ and −0.9 for simulated ET and $r = 0.94$ and 0.78 for $T_{text {air}}$ corresponding to January 20 and October 19, respectively). We further compared the performance of the TMDI with the existing remotely sensed dryness assessment methods, including temperature vegetation dryness index (TVDI) and Surface Energy Balance Algorithm for Land (SEBAL) model. The advantages of the TMDI in reflecting SSM, especially in the nonvegetation area, are clearly demonstrated. It is concluded that the-TMDI is a reliable indicator for determining the SSM status with a large degree of freedom for further applications since it does not require any other ground-based measurements.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Self-Supervised Contrastive Learning for Volcanic Unrest Detection

    • Free pre-print version: Loading...

      Authors: Nikolaos Ioannis Bountos;Ioannis Papoutsis;Dimitrios Michail;Nantheera Anantrasirichai;
      Pages: 1 - 5
      Abstract: Ground deformation measured from interferometric synthetic aperture radar (InSAR) data is considered a sign of volcanic unrest, statistically linked to a volcanic eruption. Recent studies have shown the potential of using Sentinel-1 InSAR data and supervised deep learning (DL) methods for the detection of volcanic deformation signals, toward global volcanic hazard mitigation. However, detection accuracy is compromised from the lack of labeled data and class imbalance. To overcome this, synthetic data are typically used for fine-tuning DL models pretrained on the ImageNet dataset. This approach suffers from poor generalization on real InSAR data. This letter proposes the use of self-supervised contrastive learning to learn quality visual representations hidden in unlabeled InSAR data. Our approach, based on the SimCLR framework, provides a solution that does not require a specialized architecture nor a large labeled or synthetic dataset. We show that our self-supervised pipeline achieves higher accuracy with respect to the state-of-the-art methods and shows excellent generalization even for out-of-distribution test data. Finally, we showcase the effectiveness of our approach for detecting the unrest episodes preceding the recent Icelandic Fagradalsfjall volcanic eruption.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Dual-Path Morph-UNet for Road and Building Segmentation From Satellite
           Images

    • Free pre-print version: Loading...

      Authors: Moni Shankar Dey;Ushasi Chaudhuri;Biplab Banerjee;Avik Bhattacharya;
      Pages: 1 - 5
      Abstract: Building footprints and road network detection have gained significant attention for map preparation, humanitarian aid dissemination, disaster management, to name a few. Traditionally, morphological filters excel at extracting shape features from remotely sensed images and have been widely used in the literature. However, the structural element (SE) dimension selection impedes these classical and learning-based methods utilizing any morphological operators. To overcome this aspect, we propose a novel framework to extract road and building from remote sensing (RS) images by exploiting morphological networks. The method predominantly aims at learning an optimized SE to capture variably-sized building and road footprints. We substitute convolutions with 2-D morphological operations in the basic building blocks of the network architecture (Dual-path Morph-UNet) to manage the intricate task of optimizing the SE in addition to the actual segmentation task. The dual-path framework incorporates parallel residual and dense paths in an encoder-decoder architecture, which permits learning of higher-level feature representations with fewer parameters. Finally, we implement the proposed framework on the benchmarked Massachusetts roads and buildings dataset and demonstrate superior results than the state-of-the-art (SOTA). In addition, the proposed network consists of $10times $ less learnable parameters than the SOTA methods.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Robust Ground Roll Noise Suppression Based on Dictionary Learning and
           Bandpass Filtering

    • Free pre-print version: Loading...

      Authors: Zhenjie Feng;
      Pages: 1 - 5
      Abstract: Ground roll noise is a common type of seismic noise arising from land acquisition. Suppressing ground roll noise has long been a challenging problem due to the strong coupling between ground rolls and reflection signals. The easiest way to suppress ground roll noise is by a bandpass filter, which removes the low-frequency ground roll and retains the high-frequency signals. Due to the coupling issue, the bandpass filter, however, is prone to cause the removal of low-frequency signals and the existence of high-frequency noise. To combat this problem, we propose a novel dictionary learning (DL) method for decoupling the ground rolls and reflection signals in the low-frequency band. We first filter the seismic shot gather using a strong low-pass filter, by which we remove all ground rolls. Then, we apply the DL method to retrieve the leaked low-frequency reflection signals. The dictionary atoms are obtained from the high-frequency reflection signals and then used to code the low-frequency mixture between ground rolls and signals. As a result, the reflection signals in the low-frequency part are easily separated by the sparse coding process and are added back to the high-frequency signals. The final output of the proposed algorithm is the summation between the high-frequency reflections and the retrieved low-frequency reflections. We apply the proposed method to both synthetic and real shot gathers containing ground roll noise and demonstrate its promising results.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Generalized W Transform and Its Application in Gas-Bearing Reservoir
           Characterization

    • Free pre-print version: Loading...

      Authors: Rui Li;Xing Zhu;Yuzhu Zhou;Hui Chen;Xuping Chen;Ying Hu;
      Pages: 1 - 5
      Abstract: The W transform (WT), employing a Gaussian window with non-stationary dominant frequency weight, is suitable for reservoir description with high time resolution at low-frequency band. In this letter, we generalize the WT through designing a novel frequency-varying Gaussian standard deviation with a two-parameter multivariate composite exponential form of the dominant frequency, namely generalized WT (GWT), which can avoid the singularity of WT caused by the non-differentiability of its standard deviation at the dominant frequency, thus obtaining a smoother and more flexible window. Compared with the S-transform (ST) and WT, the proposed method provides a better time-frequency (TF) representation performance. The analysis results of simulated seismic trace and field seismic data illustrate that the GWT can effectively characterize gas-bearing reservoirs.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Data-Domain Traveltime Inversion of Reflected Waves Using Segment Dynamic
           Image Warping

    • Free pre-print version: Loading...

      Authors: Lu Liu;Yubing Li;Weiguang He;Yi Luo;
      Pages: 1 - 5
      Abstract: Reflection traveltime information is generally used for producing a kinematically accurate velocity model for seismic imaging. Accurately estimating the traveltime difference between the demigrated and observed data is crucial for data-domain reflection traveltime tomography. To enhance the robustness of signal’s alignment, we propose a new method of segment dynamic image warping (SDIW). It first exploits windowed polynomial fitting for signal processing and then aligns the signals based on point-wise segment-to-segment matching. Compared with the conventional point-to-point matching strategy, our method is more robust and insensitive toward strong random noise. By minimizing the traveltime difference computed by SDIW, data-domain reflection traveltime inversion (DRTI) is then used to find an accurate background velocity model. Synthetic tests show that SDIW provides reliable time shifts between the demigrated and observed data even if the signal-to-noise ratio of input data is rather low. This enables DRTI to automatically reconstruct the deep background velocity model. The subsequent full waveform inversion (FWI) gradually added short-wavelength velocity structures and finally recovers a high-resolution and high-fidelity model. The results demonstrate that the DRTI provides a kinematically accurate background velocity model sufficient for following FWI to fully retrieve the detail of the subsurface structures even when the low frequencies are missing.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Evaluation of Topographic Correction Models Based on 3-D Radiative
           Transfer Simulation

    • Free pre-print version: Loading...

      Authors: Haojing Chi;Kai Yan;Kai Yang;Shuyuan Du;Hanliang Li;Jianbo Qi;Wei Zhou;
      Pages: 1 - 5
      Abstract: The timely and accurate assessment of changes in mountain vegetation biomass and other parameters is of great importance to mountain ecosystem conservation. With the rapid development of remote sensing technology, hyperspectral remote sensing images have facilitated the large-scale and long-time series monitoring of environmental changes in mountainous areas. However, topographic effects cause remote sensing images of mountainous areas to be prone to spectral variations within the same land cover and spectral confusion among different land covers. This phenomenon seriously affects the accuracy of remote sensing inversions and hinders the development and application of remote sensing in mountainous areas. Numerous scholars have established various topographic correction models (TCMs) to eliminate the influence of topographic effects. Comparative evaluation of the performance of different TCMs allows us to better understand their characteristics. Most previous evaluation studies have directly applied in remote sensing images, which were limited by the changing conditions of the study area. Therefore, this letter used computer simulations to controllably evaluate six popular TCMs on hyperspectral images. The results showed that their performance varied with the spectral band, and overall, the best performance was achieved by the C correction model, followed by the sun-canopy-sensor (SCS) + C model. This letter provides a basis for the optimal selection of TCMs in complex terrains.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Land Surface Temperature Based Soil Moisture Dynamics Modeling for Chinese
           Mainland

    • Free pre-print version: Loading...

      Authors: Jiale Li;Yu Li;Quanhua Zhao;
      Pages: 1 - 5
      Abstract: Since remotely sensed land surface temperature (LST) and LST-derived indexes such as surface-to-air temperature gradient ( $Delta T$ ) and day-to-night LST gradient ( $Delta $ LST) all contain important soil moisture (SM) information, it is meaningful to utilize easily available and near-real-time LST data for modeling the spatiotemporal SM dynamics. However, the optimal LST-derived index to appropriately quantify SM dynamics on a large scale remains to be studied. Considering the complex and diverse climate conditions and land cover types in the Chinese mainland, this letter proposes to evaluate $Z$ -score indexes from LST-based SM dynamic modeling for the Chinese Mainland. Monthly LST and SM during April–October in 2000–2019 years are derived from the MOD11C3 (MODIS LST product) and ERA5-Land (the global reanalysis dataset), respectively. The Pearson correlation coefficients (Rs) between ZSM ( $Z$ -score of SM) and ZLST ( $Z$ -score of LST), $ZDelta T$ ( $Z$ -score of $Delta T$ ), as well as $ZDelta $ LST ( $Z$ -score of $Delta $ LST) are calculated. The average $R$ between ZS- and ZLST is 0.44 over the whole domain. It is up to 0.7 for cultivated land and grassland in semi-arid and semi-humid areas. The $R$ between ZSM and ZLST is stronger than the ones between ZSM and $ZDelta T$ and $ZDelta $ LST. Overall, ZLST can be viewed as a relatively robust and easy-to-calculate indicator for modeling SM dynamics in a large region. Even if the approach used is simple, its results are encouraging because it makes sense to actually use LST to capture SM dynamics in the Chinese mainland.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • AVO Inversion Based on Transfer Learning and Low-Frequency Model

    • Free pre-print version: Loading...

      Authors: Jinyu Meng;Shoudong Wang;Wanli Cheng;Zhiyong Wang;Liuqing Yang;
      Pages: 1 - 5
      Abstract: Amplitude variation with offset (AVO) refers to the amplitude variation with offset. This relationship can be used to analyze lithology and identify the oil and gas reservoirs in seismic exploration. Traditional AVO inversion is a typical ill-posed problem. When deep learning is directly used for seismic inversion, there are three main issues. First, the label data are insufficient. Second, a network trained for one working area is not applicable to other working areas. Third, there are spatial discontinuities and instability problems in the inversion results. In this letter, we propose the AVO inversion method that combines transfer learning and low-frequency component constraints. Transfer learning strategy is introduced to solve two main problems: The label data are insufficient to train the network, and the trained network is not applicable to other regions. Taking the low-frequency component as the constraint term makes the solution easier to converge to the true value. The experimental results of a typical example show that our method not only effectively improves the prediction accuracy and spatial continuity of the inversion results, but also reduces dependence on logging data.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Multiscale Coherence Attribute and Its Application on Seismic
           Discontinuity Description

    • Free pre-print version: Loading...

      Authors: Yihuai Lou;Haoran Zhang;Naihao Liu;Rongchang Liu;Fengyuan Sun;
      Pages: 1 - 5
      Abstract: Geologic structure characterization is a key step for seismic structure interpretation, such as fluvial channels, faults, and fractures. The coherence attribute is a widely used tool for describing seismic discontinuities, which is usually calculated based on the similarity and dissimilarity of the adjacent seismic traces. However, accurately extracting coherence attribute is a difficult task in field data applications because seismic signal is one of the typical nonstationary, non-Gaussian, and wideband signals. To describe seismic discontinuities at different scales, we propose a workflow to extract the multiscale coherence (MSC) attribute. We first decompose seismic data into several band-limited intrinsic mode functions (IMFs) with different dominant frequencies via the multichannel variational mode decomposition (MVMD). Afterward, we develop a Cauchy kernel correlation-based coherence algorithm to extract the coherence attributes at different scales based on the decomposed IMFs. Finally, we can compute the MSC attribute by utilizing the calculated coherence attributes. Field data applications demonstrate that the proposed MSC attribute characterizes seismic discontinuities, such as faults and fluvial channels, more accurately and more clearly than the traditional coherence attribute and the 1-D variational mode decomposition (VMD)-based coherence attribute.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Graph Convolution Networks for Seismic Events Classification Using Raw
           Waveform Data From Multiple Stations

    • Free pre-print version: Loading...

      Authors: Gwantae Kim;Bonhwa Ku;Jae-Kwang Ahn;Hanseok Ko;
      Pages: 1 - 5
      Abstract: This letter proposes a multiple station-based seismic event classification model using a deep convolution neural network (CNN) and graph convolution network (GCN). To classify various seismic events, such as natural earthquakes, artificial earthquakes, and noise, the proposed model consists of weight-shared convolution layers, graph convolution layers, and fully connected layers. We employed graph convolution layers in order to aggregate features from multiple stations. Representative experimental results with the Korean peninsula earthquake datasets from 2016 to 2019 showed that the proposed model is superior to the single-station based state-of the-art methods. Moreover, the proposed model significantly reduced false alarms when using continuous waveforms of long duration. The code is available at.1
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • RCEN: A Deep-Learning-Based Background Noise Suppression Method for
           DAS-VSP Records

    • Free pre-print version: Loading...

      Authors: Tie Zhong;Ming Cheng;Shaoping Lu;Xintong Dong;Yue Li;
      Pages: 1 - 5
      Abstract: Recently, distributed optical fiber acoustic sensing (DAS) is regarded as a transformative technology in seismic exploration. However, both various complex background noise and weak desired signals significantly limit its practical application. To explore an effective denoising method for the vertical seismic profile (VSP) record received by DAS, we propose an improved residual encoder–decoder deep neural network (RED-Net) enhanced by deep iterative memory block (DMB) and channel aggregation block (CAB), called residual channel aggregation encoder–decoder network (RCEN). Here, DMB uses the weight accumulation theory to improve the feature extraction ability and achieve accurate noise elimination. Meanwhile, CAB, using the multi-channel analysis architecture, enhances the weak signal retention performance. In addition, we leverage both the synthetic data obtained by forward modeling and real DAS noise data to construct a sufficient training dataset with high authenticity, thereby meeting the requirement of network training. Both the synthetic and field DAS-VSP data processing results demonstrate the advantage of RCEN compared with competing algorithms, including singular value decomposition (SVD), conventional RED-Net, and feed-forward denoising convolutional neural network (DnCNN).
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Consecutively Missing Seismic Data Interpolation Based on Coordinate
           Attention Unet

    • Free pre-print version: Loading...

      Authors: Xinze Li;Bangyu Wu;Xu Zhu;Hui Yang;
      Pages: 1 - 5
      Abstract: Missing traces interpolation is a basic step in the seismic data processing workflow. Recently, many seismic data interpolation methods based on different neural networks have been proposed. The existing research shows that when the seismic data are consecutively missing, the larger gap for missing traces, the more difficult task of interpolation, due to convolution operation in the neural network can only capture local relations. In this letter, we incorporate the coordinate attention block to the Unet for 2-D successive missing traces interpolation. The hybrid loss function combined with structural similarity (SSIM) and $text {L}_{ {1}}$ norm is used as the loss function to further improve the interpolation performance of the designed network. Comparison experiments on 2-D synthetic and field seismic data show that the interpolation results obtained by the proposed method are more accurate and reasonable compared with Unet and Unets equipped state-of-the-art similar modules.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Image Recovery of Inaccessible Rough Surfaces Profiles Having Impedance
           Boundary Condition

    • Free pre-print version: Loading...

      Authors: Ahmet Sefer;Ali Yapar;
      Pages: 1 - 5
      Abstract: This letter addresses a reconstruction algorithm of locally rough inaccessible surface profiles via the knowledge of the scattered field data under the consideration of the impedance boundary condition (IBC). To this aim, first, the synthetic scattered field data are obtained through the solution of the conventional surface integral equation (SIE) written on the rough surface. Then, the same SIE together with the data equation is solved iteratively via Newton’s method to obtain the image of the rough surface profile. In the numerical implementation, the nonlinear ill-posed inverse problem is linearized in an iterative fashion via the Newton method and regularized by Tikhonov in the least-squares sense. The feasibility of the algorithm is provided via numerical examples, which shows that the method is effective and promising.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • PS-Wave Angle-Domain Imaging With Gaussian Beam Summation in 2-D TTI Media

    • Free pre-print version: Loading...

      Authors: Jianguang Han;Qingtian Lü;Hao Zhang;Bingluo Gu;Zhiwei Liu;
      Pages: 1 - 5
      Abstract: Imaging PS-wave is essential for converted wave exploration, especially in tilted transversely isotropic (TTI) media. Compared with the relatively low imaging accuracy of anisotropic time migration for complex structures, an accurate anisotropic PS-wave depth migration approach would be preferable. As an effective depth migration technique, Gaussian beam summation (GBS) migration can provide high-precision imaging for complex geological structures. In this letter, we extend the GBS to PS-waves imaging in anisotropic media and present an angle-domain GBS migration method for converted waves in 2-D TTI media. We first introduce the anisotropic ray-tracing-based angle-domain GBS imaging condition of PS-waves in TTI media, in which the sign of the incidence angle of P-waves is applied to decide the PS-wave polarity. After calculating the propagation angles at imaging points by using the data of real-value travel time of anisotropic Gaussian beams, we can get the P-wave incidence angles and then extract the corresponding PS-wave angle-domain common-image gathers (ADCIGs). The performance of our method is verified by two numerical tests, indicating that it is an effective migration algorithm for accurately imaging converted waves in 2-D TTI media.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Validation of the ECOSTRESS Land Surface Temperature Product Using Ground
           Measurements

    • Free pre-print version: Loading...

      Authors: Xiangchen Meng;Jie Cheng;Beibei Yao;Yahui Guo;
      Pages: 1 - 5
      Abstract: The ECOsystem Spaceborne Thermal Radiometer Experiment on Space Station (ECOSTRESS) land surface temperature (LST) product provides LST data with a high-spatial resolution of 70 m $times70$ m. In this letter, the quality of ECOSTRESS LST product was assessed using ground measurements collected from 17 sites, including seven surface radiation budget network (SURFRAD) sites, seven baseline surface radiation network (BSRN) sites, and three National Tibetan Plateau/Third Pole Environment Data Center (TPDC) sites. After outlier removal using the “ $3sigma $ -Hampel identifier,” the overall bias and root mean square error (RMSE) of ECOSTRESS LST at SURFRAD, BSRN, and TPDC sites are −1.61 and 3.08 K, −0.75, and 3.50 K, and −0.82 and 4.18 K, respectively. This letter shows the accuracy and uncertainty of ECOSTRESS LST product, and will benefit research fields that require LST with high-spatial resolution.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Second-Order Horizontal Multi-Synchrosqueezing Transform for Hydrocarbon
           Reservoir Identification

    • Free pre-print version: Loading...

      Authors: Yuxia Fang;Ying Hu;Mengyuan Li;Hui Chen;Xuping Chen;Jun Li;
      Pages: 1 - 5
      Abstract: Time-frequency (TF) analysis has received considerable attention in seismic spectral anomaly detection for its superiority in significantly revealing the frequency content of seismic signals changing with time variation. In this letter, a novel method termed second-order horizontal multi-synchrosqueezing transform (SHMSST) is proposed for hydrocarbon reservoir identification. First, a Gaussian-modulated linear chirp model is constructed in the frequency domain for describing the signals with slowly or rapidly linear-varying group delay. Then, the second-order local group delay estimation of the model is deduced in the TF domain through an approach similar to the instantaneous frequency estimation in the synchrosqueezing transform (SST). Finally, the rearrangement procedure is executed iteratively to concentrate the blurry TF energy into the estimated group delay, which provides an energy-concentrated TF representation for the signals with distinct nonlinear and nonstationary features. Synthetic signal and field seismic data illustrate the effectiveness of the proposed SHMSST in time localization and direct hydrocarbon detection.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • MarkCapsNet: Road Marking Extraction From Aerial Images Using
           Self-Attention-Guided Capsule Network

    • Free pre-print version: Loading...

      Authors: Yongtao Yu;Yinyin Li;Chao Liu;Jun Wang;Changhui Yu;Xiaoling Jiang;Lanfang Wang;Zuojun Liu;Yongjun Zhang;
      Pages: 1 - 5
      Abstract: High-definition map building and map navigation systems often require detailed, complete, and up-to-date data of road markings. The real-time and accurate recognition of road markings also serves significantly to the autonomous vehicles. This letter designs a self-attention (SA)-guided high-resolution capsule network to conduct road marking extraction from aerial images. First, by combining the superiorities of capsule formulation and high-resolution network architecture, this model behaves advantageously in providing fine-grained and strong feature semantics for promoting pixel-wise marking extraction accuracy. Furthermore, boosted by the capsule-based SA and adversarial learning mechanisms, the feature encoding quality and robustness are positively enhanced. Quantitative assessments, qualitative inspections, and comparative analyses on two aerial image datasets prove the excellent feasibility and effectiveness of the proposed model in road marking extraction tasks.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Sequence-to-Sequence Learning for Prediction of Soil Temperature and
           Moisture

    • Free pre-print version: Loading...

      Authors: Xiaojie Li;Jian Tang;Chengxiang Yin;
      Pages: 1 - 5
      Abstract: Soil temperature and moisture play a significant influence on vegetation and climate. Measurements of soil temperature and moisture can now be obtained through soil temperature and moisture sensors, but the measurements can only be done for a specified period of time in the past. Predicting soil temperature and moisture for the future is of significant importance because it can provide guidance on making plant plans. With deep learning algorithms, the characteristics of soil temperature and moisture in a certain upcoming period can be predicted from data measured in the past. In this letter, we develop a sequence-to-sequence learning model for multistep ahead prediction, which features a long short-term memory (LSTM)-based encoder–decoder structure for modeling long-term temporal correlations as well as an autoencoder for modeling spatial correlations (i.e., considering data from neighboring locations). For performance evaluation, we use real data collected by the temperature and moisture sensors on soils at the Heihe River Basin in the west of China. Our experimental results show that: 1) the proposed model significantly outperforms two widely used time series analysis algorithms, autoregressive integrated moving average (ARIMA) and support vector regression (SVR), and 2) the proposed spatial encoder–decoder LSTM modeling method is indeed effective in that the root-mean-squared error (RMSE) and mean absolute error (MAE) are only 0.22 °C and 0.17 °C for 24-h (144 steps ahead) prediction of soil temperature and the values are only 0.28% and 0.23% for soil moisture.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Fast Dictionary Learning With Automatic Atom Classification for Seismic
           Data Denoising

    • Free pre-print version: Loading...

      Authors: Zhenjie Feng;
      Pages: 1 - 5
      Abstract: Seismic noise attenuation is a long-standing yet still challenging topic in seismic data processing. Dictionary learning (DL) has emerged as an effective way to attenuate spatially incoherent noise without damaging useful signals. DL can adaptively learn atoms that best represent the structure of seismic data in a fully data-driven way, and thus can be applied in arbitrarily complex seismic datasets. Due to the existence of strong noise, the dictionary atoms could be strongly affected, e.g., containing many atoms that show quite irregular structures. Here, we propose a new method for effectively rejecting those noise-contaminated atoms while maintaining the most representative atoms, so as to improve the denoising performance. Atom classification is performed by taking advantage of the statistical features of the atoms in each category, e.g., regular (for signal) and irregular (for noise). More importantly, the rejection of atoms with a high probability of noise inference is controlled easily by a threshold, below which the atom is preserved for sparse coding and denoising. An efficient dictionary updating scheme is also used to avoid the computationally expensive singular value decomposition (SVD). We demonstrate the performance of the proposed method in both synthetic and real datasets.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Learnable Maximum Amplitude Structure for Earthquake Event Classification

    • Free pre-print version: Loading...

      Authors: Shou Zhang;Bonhwa Ku;Hanseok Ko;
      Pages: 1 - 5
      Abstract: Recently, most research has been conducted to minimize damage from earthquakes by establishing an early warning system through the analysis of short seismic waves. In particular, deep learning is widely used as it allows to learn complex patterns for earthquake detection from seismic data without complex physical knowledge. In this letter, we propose an improved ConvNetQuake for earthquake event classification by adding learnable features related to the maximum amplitude of the seismic waveform. Since the maximum amplitude is a major factor representing the characteristics of an earthquake, we presented a deep learning structure that can apply this factor in the process of determining whether an earthquake occurs. In the proposed structure, the maximum amplitude is transformed into a feature learned through multi-layer perceptron (MLP) and then concatenates with features extracted through a convolutional neural network (CNN). On the STanford EArthquake Dataset (STEAD) dataset, the proposed method significantly increases the performance for an earthquake event classification than the previous state-of-the-art (SOTA) method by only adding a few parameters.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Elastic Full-Waveform Inversion With Unconverted-Wave Adjoint Propagators

    • Free pre-print version: Loading...

      Authors: Guochen Wu;Zhanyuan Liang;Xiaoyu Zhang;Lingyun Yang;
      Pages: 1 - 5
      Abstract: Elastic full-waveform inversion (EFWI) can restore high-resolution model parameters by minimizing the misfit function between the modeled and observed data. However, the coupling propagation of $P$ - and $S$ -waves will cause the crosstalk among elastic parameters and increase the nonlinearity of EFWI. The decoupled elastic wave equation can help EFWI to weaken the crosstalk effect, but it increases the computational cost of EFWI. In addition, the decomposition of the $S$ -wave stress will produce artifacts. Hence, we have developed an EFWI approach with unconverted-wave adjoint propagators to recover the high-resolution model parameters. In the new EFWI, we use the unconverted-wave equation to construct the adjoint propagators without $S$ -wave stress decomposition, which can reduce the artifacts. Since the unconverted-wave equation omits the cross term in the elastic wave equation, the computational cost of EFWI is reduced. Numerical examples have demonstrated that our EFWI can efficiently produce high-resolution models and reduce the computational cost of EFWI by about 30%.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Subspace-Based Distorted FDFD Iterative Method for Inverse Scattering

    • Free pre-print version: Loading...

      Authors: Teng-Fei Wei;Xiao-Hua Wang;Bing-Zhong Wang;
      Pages: 1 - 5
      Abstract: The distorted FDFD-based iterative method (DFIM) and subspace theory are combined to improve the efficiency of electromagnetic scattering inversion in this letter. With the help of singular value decomposition (SVD), the proposed subspace-based DFIM (S-DFIM) updates the total electric field with an increment produced by the deterministic subspace of the equivalent source. In the iterations, this increment can make the total electric field more accurate than that by the DFIM, which leads to faster convergence. In addition, a self-adapting scheme for getting the parameter of Tikhonov regularization is also proposed to improve the imaging quality. Numerical results show that the efficiency of the proposed method is greatly improved while maintaining good accuracy.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Inverse Imaging Using Total Field Measurements

    • Free pre-print version: Loading...

      Authors: Chandan Bhat;Uday K. Khankhoje;
      Pages: 1 - 5
      Abstract: Most microwave inverse imaging algorithms rely on measurements of both the total and the incident electric field in order to estimate the dielectric properties of an unknown scattering object (SO). We propose a new technique to jointly estimate the incident field and relative permittivity of a heterogeneous dielectric object from measurements of the total electric field alone. For the first task, we express the incident field as a collection of plane waves and estimate the wave coefficients from the given data by leveraging the sparsity of the plane wave spectrum and obtain the solution via a constrained reweighted $L_{1}$ norm minimization technique. Subsequently, we estimate the permittivity and geometry of the SO using a twofold subspace optimization method. We evaluate the performance of our algorithm on synthetically generated object and experimental data. For synthetic objects, the accuracy in reconstruction of the incident field and the relative permittivity is ≈93% for field measurements with a 15-dB signal-to-noise ratio, while the accuracy obtained for an experimental data set was ≈90%.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Fast Inversion of Subsurface Target Electromagnetic Induction Response
           With Deep Learning

    • Free pre-print version: Loading...

      Authors: Shiyan Li;Xiaojuan Zhang;Kang Xing;Yaoxin Zheng;
      Pages: 1 - 5
      Abstract: With the development of electromagnetic detection technology, the inversion of electromagnetic induction (EMI) response based on a 3-D orthogonal dipole model can provide an estimation of parameters of a high-conductivity target, such as the target’s position, orientation, and shape. However, the traditional inversion methods suffer from several limitations including relying on the initial value, easy to fall into the local optimal solution, and high computational complexity. To overcome these disadvantages, in this letter, we propose a deep learning (DL) inversion method of subsurface target EMI response based on deep neural network (DNN) architecture, which is combined with adaptive moment estimation (Adam) optimization algorithm and learning rate attenuation strategy to improve the model accuracy. Datasets are obtained from forward modeling in different target parameters. By limiting the range of target parameters, errors caused by the nonuniqueness of inversion results are avoided. Through simulation and field experiments, we verify the performance of this method. The experimental results show that compared with the traditional inversion algorithms, the inversion accuracy is higher and the inversion speed is three to four orders of magnitude faster.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • P-Detector: Real-Time P-Wave Detection in a Seismic Waveform Recorded on a
           Low-Cost MEMS Accelerometer Using Deep Learning

    • Free pre-print version: Loading...

      Authors: Irshad Khan;Young-Woo Kwon;
      Pages: 1 - 5
      Abstract: Recently, the Internet of Things (IoT) systems have been widely used for earthquake detection because of the easy construction of a dense seismic network, communication capabilities, and low cost of sensors. However, when utilizing MEMS sensors as seismic sensors, earthquake detection capabilities are often affected by various types of noises because such sensors are installed in heterogeneous environments. In earthquakes, P-waves first arrive, but their lengths are only a few seconds, and their amplitudes are also relatively smaller than to S-waves. As a result, it is difficult to accurately detect P-waves in IoT systems where environmental noises are always present. Furthermore, when using deep learning approaches for earthquake detection, inference time usually becomes a critical factor for real-time processing because of the complex architecture of a detection model. To that end, in this letter, we present a deep learning model that can detect P-waves in noisy environments. The model outputs the detection probability before the arrival of strong shakes. We tested our model on earthquakes recorded by the IoT-based seismic sensors deployed in South Korea. Our model can detect P-waves within 1.5–2.5 s after the first arrival of P-wave with the accuracy of 98.8%, making it applicable in real-time earthquake detection.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • A Concentrated Time-Frequency Method for Reservoir Detection Using
           Adaptive Synchrosqueezing Transform

    • Free pre-print version: Loading...

      Authors: Xinjun Mao;
      Pages: 1 - 5
      Abstract: The synchrosqueezing transform (SST) is an effective technique to concentrate the time-frequency (TF) energy and to retrieve the components of a non-stationary multicomponent signal. Therefore, it has been widely used to process and interpret seismic data. However, due to the fixed window width of the short-time Fourier transform (STFT), the STFT-based SST (FSST) is not well suitable for the characterization of the oil and gas reservoirs with varying layer thickness. Here, an adaptive SST is employed to characterize the features of the seismic signals for identifying the oil reservoirs with varying thickness. Overall, the proposed method is based on STFT with time-varying windows. For the local harmonic wave approximation and well-separated condition of a non-stationary multicomponent signal, the adaptive STFT is windowed with the Gaussian function. Compared with the conventional FSST, the adaptive FSST (AFSST) provides the TF concentration with better concentration and separates the components more accurately. In this work, both synthetic model and field seismic data are applied to validate the AFSST method, demonstrating that the AFSST method can precisely distinguish the stratigraphic characteristics.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Fast 3-D Controlled-Source Electromagnetic Modeling Combining UPML and
           Rational Krylov Method

    • Free pre-print version: Loading...

      Authors: Jiren Liu;Xiao Xiao;Jingtian Tang;Zhengyong Ren;Xiangyu Huang;Jifeng Zhang;
      Pages: 1 - 5
      Abstract: Controlled-source electromagnetic (CSEM) surveying is a critical tool for sensing and locating underground anomalies and structures. In this letter, based on uniaxial perfectly matched layer (UPML) and rational Krylov (RK) method, we propose a fast algorithm for 3-D Multifrequency CSEM modeling. We use the frequency-independent UPML to truncate the boundaries and adopt an RK method to rapidly solve the 3-D multifrequency CSEM problems. The accuracy and efficiency of our algorithm are verified by two examples, i.e., a two-layer model and a 3-D model. Numerical experiments indicate that our algorithm is computationally efficient, obtaining nearly 20-fold speedup on a laptop compared with the conventional 3-D CSEM using finite element method (3DCSEM) modeling.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Seismic Surface-Related Multiples Suppression Based on SAGAN

    • Free pre-print version: Loading...

      Authors: Liurong Tao;Haoran Ren;Yueming Ye;Jinsheng Jiang;
      Pages: 1 - 5
      Abstract: Suppressing multiples from seismic records is necessary to improve imaging quality. Deep neural networks (DNNs) can automatically mine features from data. Once a network is successfully trained, it can process data with extremely high efficiency. In this letter, a generative adversarial network (GAN) framework is proposed to remove surface-related multiples in both synthetic and field datasets, where the generator is U-Net with Markov discriminator. Adding self-attention (SA) blocks to GAN improves processing precision. Improved signal noise ratio (SNR), and accurate reverse time migration (RTM) images implemented by network’s outputs of synthetic datasets, jointly support that this network is effective on surface-related multiple suppression. Based on the results from field application, deep learning method in this letter is comparable to conventional adaptive surface-related multiple elimination (SRME) method but time-saving. By constructing an end-to-end workflow for seismic surface-related multiples suppression, small batches dataset can be used to train the network, and large batches of datasets can be processed accurately and efficiently.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • A Novel Teacher–Student Framework for Soil Moisture Retrieval by
           Combining Sentinel-1 and Sentinel-2: Application in Arid Regions

    • Free pre-print version: Loading...

      Authors: Noureddine Jarray;Ali Ben Abbes;Imed Riadh Farah;
      Pages: 1 - 5
      Abstract: Soil moisture (SM) is an important parameter used to control a broad range of environmental applications. An increasing attention has been recently given to machine learning (ML) methods for SM retrieval that provide promising performance. Nevertheless, most of them are based on a supervised learning strategies that depend on the used labeled training samples. In fact, they are unaffordable or costly. In this letter, new teacher–student for SM estimation, called (TS-SME), relying on teacher–student (TS) framework using synthetic aperture radar (SAR) and optical data, was proposed to estimate SM. The main advantage of this framework is to enroll a large amount of unlabeled data together with a small amount of labeled data. Experiments were carried out on two arid areas in southern Tunisia. The input data include the backscatter coefficient in two-mode polarization ( $sigma ^{circ }_{textrm {VV}}$ and $sigma ^{circ }_{textrm {VH}}$ ) for Sentinel-1A, normalized difference vegetation index (NDVI) and normalized difference infrared index (NDII) for Sentinel-2A and in situ measurements. Extensive experimental results demonstrated that TS-SME framework is capable of generating a well-performed student model, with the estimation accuracy is superior to all teacher models [artificial neural network (ANN), eXtreme gradient boosting (XGBoost), random forest regressor (RFR), and water cloud model (WCM)]. It was highly correlated with the in situ measurements with high Pearson’s correlation coefficient $R$ ( ${R}_{textrm {RF}} =0.86$ , ${R}_{textrm {ANN}- =0.75$ , ${R}_{textrm {XGBoost}} =0.77$ , ${R}_{textrm {WCM}} =0.77$ , ${R}_{{,,textrm {TS-SME}}} =0.96$ ) and low root mean square error (RMSE) ( $textrm {RMSE}_{textrm {RF}} =1.09$ %, $textrm {RMSE}_{textrm {ANN}} =1.49$ %, $textrm {RMSE}_{textrm {XGBoost}} =1.39$ %, $textrm {RMSE}_{textrm {WCM}} =1.12$ %, $textrm {RMSE}_{,,textrm {TS-SME{} }} =0.8$ %), respectively.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Deep-Learning-Based Calibration in Contrast Source Inversion Based
           Microwave Subsurface Imaging

    • Free pre-print version: Loading...

      Authors: Takahiro Hanabusa;Takahide Morooka;Shouhei Kidera;
      Pages: 1 - 5
      Abstract: A deep-learning (DL)-based data calibration technique applied to quantitative microwave inverse-scattering analysis is presented. This technique aims at subsurface inspection for the buried object under a concrete road or soil. The inverse-scattering analysis provides a complex permittivity profile, which is useful for object identification such as air gap or water. Contrast source inversion (CSI) is one of the most promising inverse-scattering methods. This method is capable of avoiding the iterative use of highly computational forward solvers. However, when applied to the measured data, an appropriate calibration capable of converting measured data to simulation data is required. In this work, a DL-based calibration suitable for nonlinear inverse problems is proposed. Its efficiency is experimentally demonstrated using a concrete cylinder containing water with different salinities.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • High-Throughput Phenotyping of Wheat Canopy Height Using Ultrawideband
           Radar: First Results

    • Free pre-print version: Loading...

      Authors: Daniel Gomez-Garcia;Fernando Rodriguez-Morales;Stephen Welch;Carl Leuschen;
      Pages: 1 - 5
      Abstract: This letter presents an experimental study on the use of ultrawideband (UWB) probing radar as a new type of sensor to efficiently and nondestructively measure plant structure for breeding applications, focusing here on wheat canopy height. Wheat canopy height is an important morphological and developmental phenotype that indicates plant growth and it is related to biomass. Currently, taking manual measurements of canopy height is labor-intensive and has become a bottleneck for genomic selection and breeding programs. Other recently proposed noncontact methods only sense the top of the canopy, thereby having to make assumptions about the elevation of the base of the canopy. We propose the use of UWB radar as a phenotyping sensor for measuring a variety of plant characteristics. A direct measurement of wheat canopy height is investigated with the capability of sensing both the top and the bottom of the canopy simultaneously. To test this idea, we developed a 2–18-GHz frequency-modulated-continuous-wave (FMCW) radar prototype and a mobile phenotyping platform. The sensor was tested by collecting near-nadir coherent radar measurements of wheat canopies of breeding plots at different growth stages. The performance to detect both the top and bottom of the canopy was examined at different frequency bands.
      PubDate: 2022
      Issue No: Vol. 19 (2022)
       
  • Particle Size Distribution Characteristics Within Different Regions of
           Mature Squall-Line Based on the Analysis of Global Precipitation
           Measurement Dual-Frequency Precipitation Radar Retrieval

    • Free pre-print version: Loading...