Subjects -> EARTH SCIENCES (Total: 771 journals)
    - EARTH SCIENCES (527 journals)
    - GEOLOGY (94 journals)
    - GEOPHYSICS (33 journals)
    - HYDROLOGY (29 journals)
    - OCEANOGRAPHY (88 journals)

EARTH SCIENCES (527 journals)            First | 1 2 3     

Showing 401 - 371 of 371 Journals sorted alphabetically
Physical Geography     Hybrid Journal   (Followers: 8)
Physical Science International Journal     Open Access  
Physics in Medicine & Biology     Full-text available via subscription   (Followers: 15)
Physics of Life Reviews     Hybrid Journal   (Followers: 1)
Physics of Metals and Metallography     Hybrid Journal   (Followers: 18)
Physics of Plasmas     Hybrid Journal   (Followers: 10)
Physics of the Earth and Planetary Interiors     Hybrid Journal   (Followers: 34)
Physics of the Solid State     Hybrid Journal   (Followers: 4)
Physics of Wave Phenomena     Hybrid Journal  
Physics World     Full-text available via subscription   (Followers: 18)
Physik in unserer Zeit     Hybrid Journal   (Followers: 9)
Pirineos     Open Access  
Planet     Open Access   (Followers: 4)
Plasma Physics and Controlled Fusion     Hybrid Journal   (Followers: 6)
Plasma Physics Reports     Hybrid Journal   (Followers: 7)
Polar Record     Hybrid Journal   (Followers: 2)
Positioning     Open Access   (Followers: 4)
Pramana     Open Access   (Followers: 13)
Precambrian Research     Hybrid Journal   (Followers: 7)
Preview     Hybrid Journal  
Proceedings of the Geologists' Association     Full-text available via subscription   (Followers: 6)
Proceedings of the Linnean Society of New South Wales     Full-text available via subscription   (Followers: 2)
Proceedings of the Yorkshire Geological Society     Hybrid Journal   (Followers: 1)
Progress in Earth and Planetary Science     Open Access   (Followers: 15)
Pure and Applied Geophysics     Hybrid Journal   (Followers: 12)
Quarterly Journal of Engineering Geology and Hydrogeology     Hybrid Journal   (Followers: 4)
Quaternary     Open Access  
Quaternary Australasia     Full-text available via subscription  
Quaternary Geochronology     Hybrid Journal   (Followers: 8)
Quaternary International     Hybrid Journal   (Followers: 14)
Quaternary Research     Full-text available via subscription   (Followers: 19)
Quaternary Science Advances     Open Access  
Quaternary Science Reviews     Hybrid Journal   (Followers: 26)
Radiocarbon     Hybrid Journal   (Followers: 12)
Remote Sensing     Open Access   (Followers: 57)
Remote Sensing Applications : Society and Environment     Full-text available via subscription   (Followers: 9)
Remote Sensing in Earth Systems Sciences     Hybrid Journal   (Followers: 5)
Remote Sensing Letters     Hybrid Journal   (Followers: 45)
Remote Sensing Science     Open Access   (Followers: 29)
Rendiconti Lincei     Hybrid Journal  
Reports on Geodesy and Geoinformatics     Open Access   (Followers: 8)
Reports on Mathematical Physics     Full-text available via subscription   (Followers: 2)
Research & Reviews : Journal of Space Science & Technology     Full-text available via subscription   (Followers: 18)
Resource Geology     Hybrid Journal   (Followers: 6)
Resources, Environment and Sustainability     Open Access   (Followers: 1)
Results in Geochemistry     Open Access  
Results in Geophysical Sciences     Open Access  
Reviews in Mineralogy and Geochemistry     Hybrid Journal   (Followers: 4)
Reviews of Modern Physics     Full-text available via subscription   (Followers: 31)
Revista Cerrados     Open Access  
Revista de Ciências Exatas Aplicadas e Tecnológicas da Universidade de Passo Fundo : CIATEC-UPF     Open Access  
Revista de Ingenieria Sismica     Open Access  
Revista de Investigaciones en Energía, Medio Ambiente y Tecnología     Open Access  
Revista de la Academia Colombiana de Ciencias Exactas, Físicas y Naturales     Open Access  
Revista de Teledetección     Open Access  
Revista Geológica de Chile     Open Access  
Revue Française de Géotechnique     Hybrid Journal  
Rock Mechanics and Rock Engineering     Hybrid Journal   (Followers: 7)
Rocks & Minerals     Hybrid Journal   (Followers: 3)
Russian Geology and Geophysics     Hybrid Journal   (Followers: 2)
Russian Journal of Mathematical Physics     Full-text available via subscription  
Russian Journal of Pacific Geology     Hybrid Journal  
Russian Physics Journal     Hybrid Journal   (Followers: 1)
Science China Earth Sciences     Hybrid Journal   (Followers: 3)
Science News     Hybrid Journal   (Followers: 11)
Science of Remote Sensing     Open Access   (Followers: 7)
Scientific Annals of Stefan cel Mare University of Suceava. Geography Series     Open Access  
Scientific Journal of Earth Science     Open Access   (Followers: 1)
Scientific Reports     Open Access   (Followers: 85)
Sedimentary Geology     Hybrid Journal   (Followers: 20)
Sedimentology     Hybrid Journal   (Followers: 15)
Seismic Instruments     Hybrid Journal   (Followers: 1)
Seismological Research Letters     Full-text available via subscription   (Followers: 12)
Soil Dynamics and Earthquake Engineering     Hybrid Journal   (Followers: 14)
Soil Security     Open Access   (Followers: 3)
Solid Earth     Open Access   (Followers: 5)
Solid Earth Discussions     Open Access   (Followers: 1)
Solid Earth Sciences     Open Access   (Followers: 1)
South African Journal of Geomatics     Open Access   (Followers: 2)
Standort - Zeitschrift für angewandte Geographie     Hybrid Journal   (Followers: 2)
Stratigraphy and Geological Correlation     Full-text available via subscription   (Followers: 2)
Studia Geophysica et Geodaetica     Hybrid Journal   (Followers: 1)
Studia Geotechnica et Mechanica     Open Access  
Studia Universitatis Babes-Bolyai, Geologia     Open Access  
Survey Review     Hybrid Journal   (Followers: 6)
Surveys in Geophysics     Hybrid Journal   (Followers: 3)
Swiss Journal of Palaeontology     Hybrid Journal   (Followers: 4)
Tectonics     Full-text available via subscription   (Followers: 15)
Tectonophysics     Hybrid Journal   (Followers: 24)
Tellus A     Open Access   (Followers: 21)
Tellus B     Open Access   (Followers: 20)
Terra Latinoamericana     Open Access  
Terra Nova     Hybrid Journal   (Followers: 5)
The Compass : Earth Science Journal of Sigma Gamma Epsilon     Open Access  
The Holocene     Hybrid Journal   (Followers: 16)
The Leading Edge     Hybrid Journal   (Followers: 1)
Transportation Infrastructure Geotechnology     Hybrid Journal   (Followers: 8)
Turkish Journal of Earth Sciences     Open Access  
UD y la Geomática     Open Access  
Unconventional Resources     Open Access  
Underwater Technology: The International Journal of the Society for Underwater     Full-text available via subscription   (Followers: 1)
Universal Journal of Geoscience     Open Access  
Unoesc & Ciência - ACET     Open Access  
Vadose Zone Journal     Open Access   (Followers: 5)
Volcanica     Open Access  
Water     Open Access   (Followers: 10)
Water International     Hybrid Journal   (Followers: 19)
Water Resources     Hybrid Journal   (Followers: 21)
Water Resources Research     Full-text available via subscription   (Followers: 94)
Watershed Ecology and the Environment     Open Access  
Weather, Climate, and Society     Hybrid Journal   (Followers: 15)
Wiley Interdisciplinary Reviews - Climate Change     Hybrid Journal   (Followers: 33)
World Environment     Open Access   (Followers: 1)
Yearbook of the Association of Pacific Coast Geographers     Full-text available via subscription   (Followers: 2)
Yugra State University Bulletin     Open Access   (Followers: 1)
Zeitschrift der Deutschen Gesellschaft für Geowissenschaften     Full-text available via subscription   (Followers: 3)
Zeitschrift für Geomorphologie     Full-text available via subscription   (Followers: 5)
Zitteliana     Open Access  
Землеустрій, кадастр і моніторинг земель     Open Access   (Followers: 1)

  First | 1 2 3     

Similar Journals
Journal Cover
Remote Sensing
Journal Prestige (SJR): 1.386
Citation Impact (citeScore): 4
Number of Followers: 57  

  This is an Open Access Journal Open Access journal
ISSN (Print) 2072-4292
Published by MDPI Homepage  [84 journals]
  • Remote Sensing, Vol. 14, Pages 4837: Multiplicative Long Short-Term Memory
           with Improved Mayfly Optimization for LULC Classification

    • Authors: Andrzej Stateczny, Shanthi Mandekolu Bolugallu, Parameshachari Bidare Divakarachari, Kavithaa Ganesan, Jamuna Rani Muthu
      First page: 4837
      Abstract: Land Use and Land Cover (LULC) monitoring is crucial for global transformation, sustainable land control, urban planning, urban growth prediction, and the establishment of climate regulations for long-term development. Remote sensing images have become increasingly important in many environmental planning and land use surveys in recent times. LULC is evaluated in this research using the Sat 4, Sat 6, and Eurosat datasets. Various spectral feature bands are involved, but unexpectedly little consideration has been given to these characteristics in deep learning models. Due to the wide availability of RGB models in computer vision, this research mainly utilized RGB bands. Once the pre-processing is carried out for the images of the selected dataset, the hybrid feature extraction is performed using Haralick texture features, an oriented gradient histogram, a local Gabor binary pattern histogram sequence, and Harris Corner Detection to extract features from the images. After that, the Improved Mayfly Optimization (IMO) method is used to choose the optimal features. IMO-based feature selection algorithms have several advantages that include features such as a high learning rate and computational efficiency. After obtaining the optimal feature selection, the LULC classes are classified using a multi-class classifier known as the Multiplicative Long Short-Term Memory (mLSTM) network. The main functionality of the multiplicative LSTM classifier is to recall appropriate information for a comprehensive duration. In order to accomplish an improved result in LULC classification, a higher amount of remote sensing data should be processed. So, the simulation outcomes demonstrated that the proposed IMO-mLSTM efficiently classifies the LULC classes in terms of classification accuracy, recall, and precision. When compared with ConvNet and Alexnet, the proposed IMO-mLSTM method accomplished accuracies of 99.99% on Sat 4, 99.98% on Sat 6, and 98.52% on the Eurosat datasets.
      Citation: Remote Sensing
      PubDate: 2022-09-28
      DOI: 10.3390/rs14194837
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4838: Active Fault Trace Identification
           Using a LiDAR High-Resolution DEM: A Case Study of the Central Yangsan
           Fault, Korea

    • Authors: Sangmin Ha, Moon Son, Yeong Bae Seong
      First page: 4838
      Abstract: Korea has been recognized as an earthquake-safe zone, but over recent decades, several earthquakes, at a medium scale or higher, have occurred in succession in and around the major fault zones, hence there is a need for studying active faults to mitigate earthquake risks. In Korea, research on active faults has been challenging owing to urbanization, high precipitation, and erosion rates, and relatively low earthquake activity compared to the countries on plate boundaries. To overcome these difficulties, the use of aerial light detection and ranging (LiDAR) techniques providing high-resolution images and digital elevation models (DEM) that filter vegetation cover has been introduced. Multiple active fault outcrops have been reported along the Yangsan Fault, which is in the southeastern area of the Korean Peninsula. This study aimed to detect active faults by performing a detailed topographic analysis of aerial LiDAR images in the central segment of the Yangsan Fault. The aerial LiDAR image covered an area of 4.5 km by 15 km and had an average ground point density of 3.5 points per m2, which produced high-resolution images and DEMs at greater than 20 cm. Using LiDAR images and DEMs, we identified a 2–4 m high fault scarp and 50–150 m deflected streams with dextral offset. Based on the image analysis, we further conducted a trench field investigation and successfully located the active fault that cut the Quaternary deposits. The N–S to NNE-striking fault surfaces cut unconsolidated deposits comprising nine units, and the observed slickenlines indicated dextral reverse strike-slip. The optically stimulated luminescence (OSL) age dating results of the unconsolidated deposits indicate that the last earthquake occurred 3200 years ago, which is one of the most recent along the Yangsan Fault.
      Citation: Remote Sensing
      PubDate: 2022-09-28
      DOI: 10.3390/rs14194838
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4839: An Overview of Ecosystem Changes in
           Tibetan and Other Alpine Regions from Earth Observation

    • Authors: Ruyin Cao, Miaogen Shen, Bin Fu
      First page: 4839
      Abstract: Alpine ecosystems have shown sensitive responses to climate change during the past few decades [...]
      Citation: Remote Sensing
      PubDate: 2022-09-28
      DOI: 10.3390/rs14194839
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4840: Point-to-Surface Upscaling Algorithms
           for Snow Depth Ground Observations

    • Authors: Yingxu Hou, Xiaodong Huang, Lin Zhao
      First page: 4840
      Abstract: To validate the accuracy of snow depth products retrieved from passive microwave remote sensing data with a high confidence level, the verification method based on points of ground observation is subject to great uncertainty, due to the scale effect. Thus, it is necessary to use a point-to-surface scale transformation method to obtain the relative ground truth at the remote sensing pixel scale. In this study, by using the snow depth ground observations at different observation scales, the upscaling methods are conducted based on simple average (SA), geostatistical, Bayes maximum entropy (BME), and random forest (RF) algorithms. In addition, the cross-validation of the leave-one-out method is employed to validate the upscaling results. The results show that the SA algorithm is seriously inadequate for estimating snow depth variation in space, and is only suitable for regions with relatively flat terrain and small variation of snow depth. The BME algorithm can introduce prior knowledge and perform kernel smoothing on observed data, and the upscaling result is superior to geostatistical and RF algorithms, especially when the observed data is insufficient, and outliers appear. The results of the study are expected to provide a reference for developing a point-to-surface upscaling method based on snow depth ground observations, and to further solve the uncertainties caused by scale effects in snow depth and other land surface parameter inversion and validation, by using remote sensing data.
      Citation: Remote Sensing
      PubDate: 2022-09-28
      DOI: 10.3390/rs14194840
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4841: Satellite Soil Moisture Data
           Reconstruction in the Temporal and Spatial Domains: Latent Error
           Assessments and Performances for Tracing Rainstorms and Droughts

    • Authors: Yi Liu, Ruiqi Chen, Shanshui Yuan, Liliang Ren, Xiaoxiang Zhang, Changjun Liu, Qiang Ma
      First page: 4841
      Abstract: Intermittent records of satellite soil moisture data are major obstacles that constrain their hydrometeorological applications. Based on the European Space Agency Climate Change Initiative (ESA CCI) soil moisture combined product, two machine learning models were employed to reconstruct soil moisture in China during 1979–2019 in both temporal and spatial domains, and latent errors for reconstructed series, as well as their performances for tracing climate extremes, were analyzed. The results showed that with the homogeneity of available data over space, the spatial approach performed well in reproducing the spatial heterogeneity of soil moisture (with medians of the correlation coefficient (CC) above 0.8 and root mean square errors (RMSEs) ranging from 0.02 to 0.03 m3∙m−3). The temporal approach (CC values of 0.7 and RMSEs ranging between 0.02 and 0.03 m3∙m−3) was superior in capturing the seasonality features and the timely and accurate mapping of short-term soil moisture dynamics impacted by rainstorms. However, both approaches failed to identify the location and severity of droughts accurately. The findings highlight the benefits of combining the strengths of both temporal and spatial gap-filling approaches for improving the estimation of missing values and hydrometeorological applications.
      Citation: Remote Sensing
      PubDate: 2022-09-28
      DOI: 10.3390/rs14194841
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4842: Ecological Assessment of Terminal
           Lake Basins in Central Asia under Changing Landscape Patterns

    • Authors: Wei Yan, Xiaofei Ma, Yuan Liu, Kaixuan Qian, Xiuyun Yang, Jiaxin Li, Yifan Wang
      First page: 4842
      Abstract: Climate change and anthropogenic activities drive the shrinkage of terminal lakes in arid areas to varying degrees. Ecological water conveyance (EWC) projects have emerged globally to restore the ecology of terminal lakes. However, there remains a lack of qualitative evaluation of the benefits of EWC on terminal lakes. This study compared the Taitema Lake Basin with the Aral Sea Basin in Central Asia, representative of terminal lake basins with and without EWC, respectively. The results show that the water area of Taitema Lake increased by 7.23 km2/year due to EWC (2000–2019), whereas that of the Aral Sea Basin decreased by 98.21% over the entire process of natural evolution (1972–2019). Land use changes before and after the EWC (1990–2019) included an increase and decrease in desert land and water bodies in the Aral Sea Basin, and a decrease and increase in desert land and arable land in the Tarim River Basin, respectively. The normalized difference vegetation index (NDVI) and actual evaporation (ETa) are the main factors influencing the change in the water area of the Aral Sea Basin with the changing environment, while EWC is the main factor influencing the change in the water area of Taitema Lake. The results confirm that EWC is a feasible measure for achieving ecological restoration of a terminal lake watershed in an arid area.
      Citation: Remote Sensing
      PubDate: 2022-09-28
      DOI: 10.3390/rs14194842
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4843: Flood Hazard Analysis Based on
           Rainfall Fusion: A Case Study in Dazhou City, China

    • Authors: Lingxue Liu, Li Zhou, Tianqi Ao, Xing Liu, Xiaolong Shu
      First page: 4843
      Abstract: In recent years, extreme weather events caused by global climate change have occurred frequently, intensifying the frequency of flood disasters. For flood hazard analysis, high-quality data and a reasonable weight assignment of the relevant factors are critical. This study conducts four rainfall fusion methods, to fuse the Tropical Rainfall Measuring Mission (TRMM) 3B42 and the observations in Dazhou City, China. Then, the random forest was applied to obtain the weights of various factors to facilitate a comprehensive flood hazard analysis under four rainfall durations. The results show that (1) the linear regression performs best out of the four fusion methods, with a correlation coefficient of 0.56; (2) the Digital Elevation Model (DEM) is the most impact factor with a weight of more than 0.2; and (3) the proposed flood analysis system performs well, as 70% of historical flood points are distributed in high and sub-high hazard areas and more than 93% of historical flood points are distributed in medium hazard areas. This study identified the flood hazard grade and distribution in Dazhou City, which could provide a valuable methodology to contribute to flood hazard analysis and disaster management with satellite rainfall. Furthermore, the results of this paper are profound for future work on the high-resolution flood risk assessment and management in Dazhou City.
      Citation: Remote Sensing
      PubDate: 2022-09-28
      DOI: 10.3390/rs14194843
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4844: Quantifying the Influence of Climate
           Change and Anthropogenic Activities on the Net Primary Productivity of
           China’s Grasslands

    • Authors: Xiafei Zhou, Binbin Peng, Ying Zhou, Fang Yu, Xue-Chao Wang
      First page: 4844
      Abstract: As one of China’s most common vegetation types, grasslands comprise about 27.5% of its terrestrial area and 41% of its carbon storage. Since climate change (CC) and human activities (HA) have a great effect on grasslands, quantifying the contributions of CC and HA on grassland net primary productivity (NPP) is crucial in understanding the mechanisms of grassland regional carbon balances. However, current approaches, including residual trend, biophysical model and environmental background-based methods, have limitations on different scales, especially on the national scale of China. To improve assessment accuracy, modifications to the environmental background-based method were introduced in calculating the CC and HA contributions to the actual NPP (ANPP). In this study, the grassland ANPP in national nature reserves was defined as the environmental background value (PNPP), which was only affected by CC and without HA. The pixel PNPP outside the nature reserves could be replaced by the pixel PNPP in the nature reserve with the most similar habitat in the same natural ecological geographical division. The impact of HA on grassland ANPP (HNPP) could be identified by calculating the difference between PNPP and ANPP. Finally, the contributions of CC and HA to ANPP changes were assessed by the trends of ANPP, PNPP, and HNPP. The results showed that the average grassland ANPP significantly increased from 2001 to 2020. CC contributed 71.0% to ANPP change, whereas HA contributed 29.0%. Precipitation was the main contributor to grassland growth among arid and semi-arid regions, while temperature inhibited productivity in these areas. HA was the major cause of degradation in China’s grasslands, although the effects have declined over time. The research could provide support support for government decisions. It could also provide a new and feasible research method for quantitatively evaluating grasslands and other ecosystems.
      Citation: Remote Sensing
      PubDate: 2022-09-28
      DOI: 10.3390/rs14194844
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4845: Feasibility of Bi-Temporal Airborne
           Laser Scanning Data in Detecting Species-Specific Individual Tree Crown
           Growth of Boreal Forests

    • Authors: Maryam Poorazimy, Ghasem Ronoud, Xiaowei Yu, Ville Luoma, Juha Hyyppä, Ninni Saarinen, Ville Kankare, Mikko Vastaranta
      First page: 4845
      Abstract: The tree crown, with its functionality of assimilation, respiration, and transpiration, is a key forest ecosystem structure, resulting in high demand for characterizing tree crown structure and growth on a spatiotemporal scale. Airborne laser scanning (ALS) was found to be useful in measuring the structural properties associated with individual tree crowns. However, established ALS-assisted monitoring frameworks are still limited. The main objective of this study was to investigate the feasibility of detecting species-specific individual tree crown growth by means of airborne laser scanning (ALS) measurements in 2009 (T1) and 2014 (T2). Our study was conducted in southern Finland over 91 sample plots with a size of 32 × 32 m. The ALS crown metrics of width (WD), projection area (A2D), volume (V), and surface area (A3D) were derived for species-specific individually matched trees in T1 and T2. The Scots pine (Pinus sylvestris), Norway spruce (Picea abies (L.) H. Karst), and birch (Betula sp.) were the three species groups that studied. We found a high capability of bi-temporal ALS measurements in the detection of species-specific crown growth (Δ), especially for the 3D crown metrics of V and A3D, with Cohen’s D values of 1.09–1.46 (p-value < 0.0001). Scots pine was observed to have the highest relative crown growth (rΔ) and showed statistically significant differences with Norway spruce and birch in terms of rΔWD, rΔA2D, rΔV, and rΔA3D at a 95% confidence interval. Meanwhile, birch and Norway spruce had no statistically significant differences in rΔWD, rΔV, and rΔA3D (p-value < 0.0001). However, the amount of rΔ variability that could be explained by the species was only 2–5%. This revealed the complex nature of growth controlled by many biotic and abiotic factors other than species. Our results address the great potential of ALS data in crown growth detection that can be used for growth studies at large scales.
      Citation: Remote Sensing
      PubDate: 2022-09-28
      DOI: 10.3390/rs14194845
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4846: Intrinsic Calibration of Multi-Beam
           LiDARs for Agricultural Robots

    • Authors: Na Sun, Quan Qiu, Zhengqiang Fan, Tao Li, Chao Ji, Qingchun Feng, Chunjiang Zhao
      First page: 4846
      Abstract: With the advantages of high measurement accuracy and wide detection range, LiDARs have been widely used in information perception research to develop agricultural robots. However, the internal configuration of the laser transmitter layout changes with increasing sensor working duration, which makes it difficult to obtain accurate measurement with calibration files based on factory settings. To solve this problem, we investigate the intrinsic calibration of multi-beam laser sensors. Specifically, we calibrate the five intrinsic parameters of LiDAR with a nonlinear optimization strategy based on static planar models, which include measured distance, rotation angle, pitch angle, horizontal distance, and vertical distance. Firstly, we establish a mathematical model based on the physical structure of LiDAR. Secondly, we calibrate the internal parameters according to the mathematical model and evaluate the measurement accuracy after calibration. Here, we illustrate the parameter calibration with three steps: planar model estimation, objective function construction, and nonlinear optimization. We also introduce the ranging accuracy evaluation metrics, including the standard deviation of the distance from the laser scanning points to the planar models and the 3σ criterion. Finally, the experimental results show that the ranging error of calibrated sensors can be maintained within 3 cm, which verifies the effectiveness of the laser intrinsic calibration.
      Citation: Remote Sensing
      PubDate: 2022-09-28
      DOI: 10.3390/rs14194846
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4847: Analysis of the Anomalous
           Environmental Response to the 2022 Tonga Volcanic Eruption Based on GNSS

    • Authors: Maosheng Zhou, Hao Gao, Dingfeng Yu, Jinyun Guo, Lin Zhu, Lei Yang, Shunqi Pan
      First page: 4847
      Abstract: On 15 January 2022, a violent eruption and tsunami of the Hunga Tonga-Hunga Ha’apai (HTHH) volcano in Tonga, South Pacific, caused widespread international concern. In order to detect the anomalous environmental response caused by the HTHH volcanic eruption based on GNSS ionospheric data, GNSS tropospheric data and GNSS coordinate time series, a new method combining the zenith non-hydrostatic delay difference method and the extreme-point symmetric mode decomposition (ESMD) method, was proposed to detect tropospheric anomalies. The moving interquartile range method and the ESMD method were introduced to detect ionospheric anomalous and coordinate time series anomalies, respectively. The results showed that 9–10 h before the eruption of the Tonga volcano and 11–12 h after the eruption of the Tonga volcano, obvious total electron content (TEC) anomalies occurred in the volcanic eruption center and its northeast and southeast, with the maximum abnormal value of 15 TECU. Significant tropospheric anomalies were observed on the day of the HTHH volcano eruption as well as 1–3 days and 16–17 days after the eruption, and the abnormal intensity was more than 10 times that of normal. The coordinate time series in direction E showed very significant anomalies at approximately 2:45 p.m. on 14 January, at approximately 4:30 a.m.–5:40 a.m. on 15 January, and at approximately 3:45 a.m. on 16 January, with anomalies reaching a maximum of 7–8 times daily. The abnormality in the direction north (N) is not obvious. Very prominent anomalies can be observed in the direction up (U) at approximately 4:30 a.m.–5:40 a.m., with the intensity of the anomalies exceeding the normal by more than 10 times. In this study, GNSS was successfully used to detect the anomalous environmental response during this HTHH volcano eruption.
      Citation: Remote Sensing
      PubDate: 2022-09-28
      DOI: 10.3390/rs14194847
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4848: Real-Time Vehicle Sound Detection
           System Based on Depthwise Separable Convolution Neural Network and
           Spectrogram Augmentation

    • Authors: Chaoyi Wang, Yaozhe Song, Haolong Liu, Huawei Liu, Jianpo Liu, Baoqing Li, Xiaobing Yuan
      First page: 4848
      Abstract: This paper proposes a lightweight model combined with data augmentation for vehicle detection in an intelligent sensor system. Vehicle detection can be considered as a binary classification problem, vehicle or non-vehicle. Deep neural networks have shown high accuracy in audio classification, and convolution neural networks are widely used for audio feature extraction and audio classification. However, the performance of deep neural networks is highly dependent on the availability of large quantities of training data. Recordings such as tracked vehicles are limited, and data augmentation techniques can be applied to improve the overall detection accuracy. In our case, spectrogram augmentation is applied on the mel spectrogram before extracting the Mel-scale Frequency Cepstral Coefficients (MFCC) features to improve the robustness of the system. Then depthwise separable convolution is applied to the CNN network for model compression and migrated to the hardware platform of the intelligent sensor system. The proposed approach is evaluated on a dataset recorded in the field using intelligent sensor systems with microphones. The final frame-level accuracy achieved was 94.64% for the test recordings and 34% of the parameters were reduced after compression.
      Citation: Remote Sensing
      PubDate: 2022-09-28
      DOI: 10.3390/rs14194848
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4849: Particulate Matter Concentrations
           over South Korea: Impact of Meteorology and Other Pollutants

    • Authors: Shaik Allabakash, Sanghun Lim, Kyu-Soo Chong, Tomohito J. Yamada
      First page: 4849
      Abstract: Air pollution is a serious challenge in South Korea and worldwide, and negatively impacts human health and mortality rates. To assess air quality and the spatiotemporal characteristics of atmospheric particulate matter (PM), PM concentrations were compared with meteorological conditions and the concentrations of other airborne pollutants over South Korea from 2015 to 2020, using different linear and non-linear models such as linear regression, generalized additive, and multivariable linear regression models. The results showed that meteorological conditions played a significant role in the formation, transportation, and deposition of air pollutants. PM2.5 levels peaked in January, while PM10 levels peaked in April. Both were at their lowest levels in July. Further, PM2.5 was the highest during winter, followed by spring, autumn, and summer, whereas PM10 was the highest in spring followed by winter, autumn, and summer. PM concentrations were negatively correlated with temperature, relative humidity, and precipitation. Wind speed had an inverse relationship with air quality; zonal and vertical wind components were positively and negatively correlated with PM, respectively. Furthermore, CO, black carbon, SO2, and SO4 had a positive relationship with PM. The impact of transboundary air pollution on PM concentration in South Korea was also elucidated using air mass trajectories.
      Citation: Remote Sensing
      PubDate: 2022-09-28
      DOI: 10.3390/rs14194849
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4850: Test of Determining Geopotential
           Difference between Two Sites at Wuhan Based on Optical Clocks’
           Frequency Comparisons

    • Authors: Anh The Hoang, Ziyu Shen, Kuangchao Wu, An Ning, Wenbin Shen
      First page: 4850
      Abstract: Applications of optical clocks in physical geodesy for determining geopotential are of increasing interest to scientists as the accuracy of optical clocks improves and the clock size becomes more and more compact. In this study, we propose a data processing method using the ensemble empirical mode decomposition technique to determine the geopotential difference between two sites in Wuhan based on the frequency comparison of two optical clocks. We use the frequency comparison record data of two Ca+ optical clocks based on the optical fiber frequency transfer method, provided by the Innovation Academy for Precision Measurement Science and Technology, Chinese Academy of Sciences (Wuhan, China). By optical clock comparisons we obtained a geopotential difference of 42.50 ± 1.03 m2∙s−2 (equivalent to height difference of 4.33 ± 0.11 m) between the two sites, which is excellent compared to the geopotential difference of 42.56 ± 0.29 m2∙s−2 (equivalent to height difference of 4.34 ± 0.03 m) measured by a spirit leveling. The results show that the optical fiber frequency transfer method is promising in determining the geopotential and potential for unifying the world height system.
      Citation: Remote Sensing
      PubDate: 2022-09-28
      DOI: 10.3390/rs14194850
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4851: RGB-ICP Method to Calculate Ground
           Three-Dimensional Deformation Based on Point Cloud from Airborne LiDAR

    • Authors: Mengting Sang, Wei Wang, Yani Pan
      First page: 4851
      Abstract: With the rapid development of LiDAR technology in recent years, high-resolution LiDAR data possess a great capability to describe fine surface morphology in detail; thus, differencing multi-temporal datasets becomes a powerful tool to explain the surface deformation process. Compared with other differencing methods, ICP algorithms can directly estimate 3D displacements and rotations; thus, surface deformation parameters can be obtained by aligning window point clouds. However, the traditional ICP algorithm usually requires a good initial pose of the point cloud and relies on calculating the spatial distance to match the corresponding points, which can easily lead the algorithm to the local optimum. To address the above problems, we introduced the color information of the point cloud and proposed an improved ICP method that fuses RGB (RGB-ICP) to reduce the probability of matching errors by filtering color-associated point pairs, thus improving the alignment accuracy. Through simulated experiments, the ability of the two algorithms to estimate 3D deformation was compared, and the RGB-ICP algorithm could significantly reduce the deformation deviation (30%–95%) in the three-dimensional direction. In addition, the RGB-ICP algorithm was applicable to different terrain structures, especially for smooth terrain, where the improvement was the most effective in the horizontal direction. Finally, it is worth believing that the RGB-ICP algorithm can play a unique role in surface change detection and provide a reliable basis for explaining the surface motion process.
      Citation: Remote Sensing
      PubDate: 2022-09-28
      DOI: 10.3390/rs14194851
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4852: BSC-Net: Background Suppression
           Algorithm for Stray Lights in Star Images

    • Authors: Li, Niu, Sun, Xiao, Li
      First page: 4852
      Abstract: Most background suppression algorithms are weakly robust due to the complexity and fluctuation of the star image’s background. In this paper, a background suppression algorithm for stray lights in star images is proposed, which is named BSC-Net (Background Suppression Convolutional Network) and consist of two parts: “Background Suppression Part” and “Foreground Retention Part”. The former part achieves background suppression by extracting features from various receptive fields, while the latter part achieves foreground retention by merging multi-scale features. Through this two-part design, BSC-Net can compensate for blurring and distortion of the foreground caused by background suppression, which is not achievable in other methods. At the same time, a blended loss function of smooth_L1&Structure Similarity Index Measure (SSIM) is introduced to hasten the network convergence and avoid image distortion. Based on the BSC-Net and the loss function, a dataset consisting of real images will be used for training and testing. Finally, experiments show that BSC-Net achieves the best results and the largest Signal-to-Noise Ratio (SNR) improvement in different backgrounds, which is fast, practical and efficient, and can tackle the shortcomings of existing methods.
      Citation: Remote Sensing
      PubDate: 2022-09-28
      DOI: 10.3390/rs14194852
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4853: A Hybrid Classification of Imbalanced
           Hyperspectral Images Using ADASYN and Enhanced Deep Subsampled
           Multi-Grained Cascaded Forest

    • Authors: Debaleena Datta, Pradeep Kumar Mallick, Annapareddy V. N. Reddy, Mazin Abed Mohammed, Mustafa Musa Jaber, Abed Saif Alghawli, Mohammed A. A. Al-qaness
      First page: 4853
      Abstract: Hyperspectral image (HSI) analysis generally suffers from issues such as high dimensionality, imbalanced sample sets for different classes, and the choice of classifiers for artificially balanced datasets. The existing conventional data imbalance removal techniques and forest classifiers lack a more efficient approach to dealing with the aforementioned issues. In this study, we propose a novel hybrid methodology ADASYN-enhanced subsampled multi-grained cascade forest (ADA-Es-gcForest) which comprises four folds: First, we extracted the most discriminative global spectral features by reducing the vast dimensions, i.e., the redundant bands using principal component analysis (PCA). Second, we applied the subsampling-based adaptive synthetic minority oversampling method (ADASYN) to augment and balance the dataset. Third, we used the subsampled multi-grained scanning (Mg-sc) to extract the minute local spatial–spectral features by adaptively creating windows of various sizes. Here, we used two different forests—a random forest (RF) and a complete random forest (CRF)—to generate the input joint-feature vectors of different dimensions. Finally, for classification, we used the enhanced deep cascaded forest (CF) that improvised in the dimension reduction of the feature vectors and increased the connectivity of the information exchange between the forests at the different levels, which elevated the classifier model’s accuracy in predicting the exact class labels. Furthermore, the experiments were accomplished by collecting the three most appropriate, publicly available his landcover datasets—the Indian Pines (IP), Salinas Valley (SV), and Pavia University (PU). The proposed method achieved 91.47%, 98.76%, and 94.19% average accuracy scores for IP, SV, and PU datasets. The validity of the proposed methodology was testified against the contemporary state-of-the-art eminent tree-based ensembled methods, namely, RF, rotation forest (RoF), bagging, AdaBoost, extreme gradient boost, and deep multi-grained cascade forest (DgcForest), by simulating it numerically. Our proposed model achieved correspondingly higher accuracies than those classifiers taken for comparison for all the HS datasets.
      Citation: Remote Sensing
      PubDate: 2022-09-28
      DOI: 10.3390/rs14194853
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4854: Analysis of Global Sea Level Change
           Based on Multi-Source Data

    • Authors: Yongjun Jia, Kailin Xiao, Mingsen Lin, Xi Zhang
      First page: 4854
      Abstract: Global sea level rise is both a major indicator and consequence of global warming. At present, global warming is causing sea level rise in two main ways: one is the thermal expansion of sea water, and the other is the injection of large amounts of fresh water into the ocean after glaciers and ice sheets melt. In this paper, satellite altimeter data are used to study the total changes of global sea level from 2002 to 2020. Different from most previous studies, this study proposes a calculation method of sea level anomaly using only the along track altimetry data, which is similar to considering the satellite points as tide gauges, in order to avoid the error caused by interpolation in the map data. In addition, GRACE satellite data are used to calculate the changes of global sea level caused by water increase; temperature and salinity data are used to calculate the changes from ocean thermal expansion. Next, using satellite altimetry data, the calculation results show that the global sea level rise rate in the period of 2002‒2020 is 3.3 mm/a. During this period, the sea level change caused by the increase of sea water calculated with GRACE satellite data is 2.07 mm/a, and that caused by the thermal expansion of seawater is 0.62 mm/a. The sea level rise caused by the increase of water volume accounts for 62.7% of the total sea level rise.
      Citation: Remote Sensing
      PubDate: 2022-09-28
      DOI: 10.3390/rs14194854
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4855: Shortwave Infrared Multi-Angle
           Polarization Imager (MAPI) Onboard Fengyun-3 Precipitation Satellite for
           Enhanced Cloud Characterization

    • Authors: Haofei Wang, Peng Zhang, Dekui Yin, Zhengqiang Li, Huazhe Shang, Hanlie Xu, Jian Shang, Songyan Gu, Xiuqing Hu
      First page: 4855
      Abstract: Accurate measurement of the radiative properties of clouds and aerosols is of great significance to global climate change and numerical weather prediction. The multi-angle polarization imager (MAPI) onboard the Fengyun-3 precipitation satellite, planned to be launched in 2023, will provide the multi-angle, multi-shortwave infrared (SWIR) channels and multi-polarization satellite observation of clouds and aerosols. MAPI operates in a non-sun-synchronized inclined orbit and provides images with a spatial resolution of 3 km (sub-satellite) and a swath of 700 km. The observation channels of the MAPI include 1030 nm, 1370 nm, and 1640 nm polarization channels and corresponding non-polarization channels, which provide observation information from 14 angles. In-flight radiometric and polarimetric calibration strategies are introduced, aiming to achieve radiometric accuracy of 5% and polarimetric accuracy of 2%. Simulation experiments show that the MAPI has some unique advantages of characterizing clouds and aerosols. For cloud observation, the polarization phase functions of the 1030 nm and 1640 nm around the scattering angle of a cloudbow show strong sensitivity to cloud droplet radius and effective variance. In addition, the polarized observation of the 1030 nm and 1640 nm has a higher content of information for aerosol than VIS-NIR. Additionally, the unique observation geometry of non-sun-synchronous orbits can provide more radiometric and polarization information with expanded scattering angles. Thus, the multi-angle polarization measurement of the new SWIR channel onboard Fengyun-3 can optimize cloud phase state identification and cloud microphysical parameter inversion, as well as the retrieval of aerosols. The results obtained from the simulations will provide support for the design of the next generation of polarized imagers of China.
      Citation: Remote Sensing
      PubDate: 2022-09-29
      DOI: 10.3390/rs14194855
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4856: Performance Evaluation of Multi-Epoch
           Double-Differenced Pseudorange Observation Method Using GNSS Ground

    • Authors: Takuji Ebinuma, Toshiki Tanaka
      First page: 4856
      Abstract: Multi-epoch double-differenced pseudorange observation (MDPO) is a dual-satellite lunar navigation algorithm specially designed for a precursor mission, using a minimum number of lunar orbiting small satellites to realize a GNSS-like radio navigation system for the Moon. In this study, we evaluated the performance of the MDPO algorithm by using real pseudorange measurements obtained from a pair of GNSS ground stations, one of which represented a lander, and the other a rover on the Moon. It was natural that the resulting positioning accuracy varied largely by satellite geometry, but the estimated error distributions of the double-differenced pseudorange observations were consistent and agreed with the predicted value. The results showed that the MDPO algorithm worked properly with the real GNSS observables and was capable of providing the expected navigation performance for future lunar exploration missions.
      Citation: Remote Sensing
      PubDate: 2022-09-29
      DOI: 10.3390/rs14194856
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4857: FLNet: A Near-shore Ship Detection
           Method Based on Image Enhancement Technology

    • Authors: Gang Tang, Hongren Zhao, Christophe Claramunt, Shaoyang Men
      First page: 4857
      Abstract: In the past few years, Synthetic Aperture Radar (SAR) has been widely used to detect marine ships due to its ability to work in various weather conditions. However, due to the imaging mechanism of SAR, there is a lot of background information and noise information similar to ships in the images, which seriously affects the performance of ship detection models. To solve the above problems, this paper proposes a new ship detection model called Feature enhancement and Land burial Net (FLNet), which blends traditional image processing methods with object detection approaches based on deep learning. We first design a SAR image threshold segmentation method, Salient Otsu (S-Otsu), according to the difference between the object and the noise background. To better eliminate noise in SAR images, we further combine image processing methods such as Lee filtering. These constitute a Feature Enhancement Module (FEM) that mitigates the impact of noise data on the overall performance of a ship detection model. To alleviate the influence of land information on ship detection, we design a Land Burial Module (LBM) according to the morphological differences between ships and land areas. Finally, these two modules are added to You Only Look Once V5 (YOLO V5) to form our FLNet. Experimental results on the SAR Ship Detection Dataset (SSDD) dataset show that FLNet comparison with YOLO V5 accuracy when performing object detection is improved by 7% and recall rate by 6.5%.
      Citation: Remote Sensing
      PubDate: 2022-09-29
      DOI: 10.3390/rs14194857
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4858: Comparing Machine and Deep Learning
           Methods for the Phenology-Based Classification of Land Cover Types in the
           Amazon Biome Ecosystem Using Sentinel-1 Time Series

    • Authors: Ivo Augusto Lopes Magalhães, Osmar Abílio de Carvalho Júnior, Osmar Luiz Ferreira de Carvalho, Anesmar Olino de Albuquerque, Potira Meirelles Hermuche, Éder Renato Merino, Roberto Arnaldo Trancoso Gomes, Renato Fontes Guimarães
      First page: 4858
      Abstract: The state of Amapá within the Amazon biome has a high complexity of ecosystems formed by forests, savannas, seasonally flooded vegetation, mangroves, and different land uses. The present research aimed to map the vegetation from the phenological behavior of the Sentinel-1 time series, which has the advantage of not having atmospheric interference and cloud cover. Furthermore, the study compared three different sets of images (vertical–vertical co-polarization (VV) only, vertical–horizontal cross-polarization (VH) only, and both VV and VH) and different classifiers based on deep learning (long short-term memory (LSTM), Bidirectional LSTM (Bi-LSTM), Gated Recurrent Units (GRU), Bidirectional GRU (Bi-GRU)) and machine learning (Random Forest, Extreme Gradient Boosting (XGBoost), k-Nearest Neighbors, Support Vector Machines (SVMs), and Multilayer Perceptron). The time series englobed four years (2017–2020) with a 12-day revisit, totaling 122 images for each VV and VH polarization. The methodology presented the following steps: image pre-processing, temporal filtering using the Savitsky–Golay smoothing method, collection of samples considering 17 classes, classification using different methods and polarization datasets, and accuracy analysis. The combinations of the VV and VH pooled dataset with the Bidirectional Recurrent Neuron Networks methods led to the greatest F1 scores, Bi-GRU (93.53) and Bi-LSTM (93.29), followed by the other deep learning methods, GRU (93.30) and LSTM (93.15). Among machine learning, the two methods with the highest F1-score values were SVM (92.18) and XGBoost (91.98). Therefore, phenological variations based on long Synthetic Aperture Radar (SAR) time series allow the detailed representation of land cover/land use and water dynamics.
      Citation: Remote Sensing
      PubDate: 2022-09-29
      DOI: 10.3390/rs14194858
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4859: Multi-Source Time Series Remote
           Sensing Feature Selection and Urban Forest Extraction Based on Improved
           Artificial Bee Colony

    • Authors: Jin Yan, Yuanyuan Chen, Jiazhu Zheng, Lin Guo, Siqi Zheng, Rongchun Zhang
      First page: 4859
      Abstract: Urban forests maintain the ecological balance of cities and are significant in promoting the sustainable development of cities. Therefore, using advanced remote sensing technology to accurately extract forest green space in the city and monitor its change in real-time is very important. Taking Nanjing as the study area, this research extracted 55 vegetation phenological features from Sentinel-2A time series images and formed a feature set containing 81 parameters together with 26 features, including polarimetric- and texture-related information extracted from dual-polarization Sentinel-1A data. On the basis of the improved ABC (ABC-LIBSVM) feature selection method, the optimal feature subset was selected, and the forest coverage areas in the study area were accurately described. To verify the feasibility of the improved feature selection method and explore the potential for the development of multi-source time series remote sensing for urban forest feature extraction, this paper also used the random forest classification model to classify four different feature sets. The results revealed that the classification accuracy based on the feature set obtained by the ABC-LIBSVM algorithm was the highest, with an overall accuracy of 86.80% and a kappa coefficient of 0.8145. The producer accuracy and user accuracy of the urban forest were 93.21% and 82.45%, respectively. Furthermore, by combining the multi-source time series Sentinel-2A optical images with Sentinel-1A dual-polarization SAR images, urban forests can be distinguished from the perspective of phenology, and polarimetric- and texture-related features can contribute to the accurate identification of forests.
      Citation: Remote Sensing
      PubDate: 2022-09-29
      DOI: 10.3390/rs14194859
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4860: Novel Neuron-like Procedure of Weak
           Signal Detection against the Non-Stationary Noise Background with
           Application to Underwater Sound

    • Authors: Alexander Gennadievich Khobotov, Vera Igorevna Kalinina, Alexander Ivanovich Khil’ko, Alexander Igorevich Malekhanov
      First page: 4860
      Abstract: The well-known method of detecting a useful signal in the presence of noise during underwater remote sensing, based on the matched filtering of the received signal with the test signal, provides the maximum signal-to-noise ratio (SNR) at the receiver output. To do this, a correlation-type criterion function (CF) is constructed for the received and test signals. In the case of large volumes of processed data, this method requires the use of large computing resources. The search for a data processing method with lower computational costs, as well as the effective application of artificial neural networks to array signal processing, motivates the authors to propose an alternative approach to the CF construction based on the McCulloch–Pitts neuron model. Such a neuron-like CF is based on a specific nonlinear transformation of the input and test signals and uses only logical operations, which require much less computational resources. The ratio of the output signal amplitude to the input noise level is indeed the maximum with matched filtering. Studies have shown that it is not this parameter that should be considered, but statistical characteristics, on the basis of which the thresholds for detecting a signal in the presence of noise are determined. Such characteristics include the probability density distributions of correlation and neuron-like CFs in the presence and absence of noise. In this case, the signal detection thresholds will be lower for the neuron-like CF than for the conventional correlation CF. The aim of this research is to increase the accuracy of the selection of a useful signal against the intense noise background when using a processor based on the neuron-like CF and to determine the conditions when the input SNR, at which signal detection is possible, is lower compared to the correlation CF. The comparative results of stochastic modeling show the effectiveness of using a new neuron-like approach to reduce the detection threshold when a chirp signal is received against a background of unsteady Gaussian noise. The advantages of the neuron-like method become significant when the statistical distribution of the additive noise does not change, but its variance increases or decreases. In order to confirm the presence of non-stationarity in real noises, experimental data obtained from the remote sounding of bottom sediments in the Black Sea are presented. The results obtained are considered to be applicable in a wide range of practical situations related to remote sensing in non-stationary environments, long-range sonar and sea bottom exploration.
      Citation: Remote Sensing
      PubDate: 2022-09-29
      DOI: 10.3390/rs14194860
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4861: A Simple Band Ratio Library (BRL)
           Algorithm for Retrieval of Hourly Aerosol Optical Depth Using FY-4A AGRI
           Geostationary Satellite Data

    • Authors: Xingxing Jiang, Yong Xue, Chunlin Jin, Rui Bai, Yuxin Sun, Shuhui Wu
      First page: 4861
      Abstract: The Advanced Geostationary Radiation Imager (AGRI) is one of the primary payloads aboard the FY-4A geostationary meteorological satellite, which can provide high-frequency, wide coverage, and multiple spectral channel observations for China and surrounding areas. There are currently few studies on aerosol optical depth (AOD) inversion from FY-4A AGRI data. Based on AGRI data, a new land AOD retrieval algorithm called the band ratio library (BRL) algorithm was proposed in this study. The monthly average surface reflectance band ratio library was established after obtaining the relationship of band surface reflectance ratio from the MODIS combined AOD dataset. In order to calculate the hourly AOD, look-up tables (LUT) for the various aerosol models were constructed using the 6SV model. We quantitatively compared AOD produced from AGRI data with AERONET ground observations to validate the BRL algorithms to validate the BRL technique. AGRI-retrieved AOD is in good agreement with AOD measured by AERONET, which has a correlation coefficient of R is 0.84, the linear regression function is AODAGRI = 0.80 ∗ AODAERONET − 0.004, the root-mean-square error (RMSE) is 0.16, and approximately 60% of the AGRI AOD results fall within the uncertain range of AOD = ±(0.2 × AODAERONET + 0.05). A cross-comparison was made with the MODIS AOD product provided by NASA. The comparison and verification show the proposed algorithm has a good accuracy of land AOD estimation from AGRI data.
      Citation: Remote Sensing
      PubDate: 2022-09-29
      DOI: 10.3390/rs14194861
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4862: Evaluating the Effects of Climate
           Change and Human Activities on the Seasonal Trends and Spatial
           Heterogeneity of Soil Moisture

    • Authors: Ermei Zhang, Yujie Liu, Tao Pan, Qinghua Tan, Zhiang Ma
      First page: 4862
      Abstract: Soil moisture (SM), as a crucial variable in the soil–vegetation–atmosphere continuum, plays an important role in the terrestrial water cycle. Analyzing SM’s variation and driver factors is crucial to maintaining ecosystem diversity on the Tibetan Plateau (TP) and ensuring food security as well as water supply balance in developing countries. Gradual wetting of the soil has been detected and attributed to precipitation in this area. However, there is still a gap in understanding the potential mechanisms. It is unclear whether the greening, glacier melting, and different vegetation degradation caused by asymmetrical climate change and intensified human activities have significantly affected the balance of SM. Here, to test the hypothesis that heterogeneous SM caused by precipitation was subject to temperatures and anthropogenic constraints, GLDAS-2.1 (Global Land Data Assimilation System-2.1) SM products combined with the statistical downscaling and Geographic detectors were applied. The results revealed that: (1) Seasonal SM gradually increased (p < 0.05), while SM deficit frequently appeared with exposure to extreme climates, such as in the summer of 2010 and 2013, and changed into a pattern of precipitation transport to western dry lands in autumn. (2) There was a synergistic reaction between greening and local moisture in autumn. SM was dominated by low temperature (TMN) in winter, warming indirectly regulated SM by exacerbating the thawing of glaciers and permafrost. The spatial coupling between the faster rising rate of TMN and the frozen soil might further aggravate the imbalance of SM. (3) The land cover’s mutual transformation principally affected SM in spring and autumn, and degradation accelerated the loss of SM replenished by precipitation. (4) Land cover responses were different; SM in grassland was less affected by external disturbance, while degraded woodland and shrub performed adaptive feedback under dry environments, SM increased by 0.05 and 0.04 m3/(m3 10a), respectively. Our research provides a scientific basis for improving hydrological models and developing vegetation restoration strategies for long-term adaptation to TP-changing environments.
      Citation: Remote Sensing
      PubDate: 2022-09-29
      DOI: 10.3390/rs14194862
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4863: Selection of Lunar South Pole Landing
           Site Based on Constructing and Analyzing Fuzzy Cognitive Maps

    • Authors: Yutong Jia, Lei Liu, Xingchen Wang, Ningbo Guo, Gang Wan
      First page: 4863
      Abstract: The Permanently Shadowed Regions (PSRs) of the lunar south pole have never been directly sampled. To explore and discover lunar resources, the Chinese lunar south pole exploration mission is scheduled to land in direct sunlight near the PSR, where sampling and analysis will be carried out. The selection of sites for lunar landing sampling sites is one of the key steps of the mission. The main factors affecting the site selection are the distribution of PSRs, lunar surface slopes, rock distribution, light intensity, and maximum temperature. In this paper, the main factors affecting site selection are analyzed based on lunar multi-source remote sensing data. Combined with previous engineering constraints, we then propose a comprehensive multi-factor fuzzy cognition and selection model for the lunar south site selection. An analytical model based on a fuzzy cognitive map algorithm is also established. Furthermore, to make a preliminary landing area selection, we determine the evaluation index for the candidate landing areas using fuzzy reasoning. Using the proposed model and combined scoring index, we also verify and analyze the prominent impact craters at the lunar south pole. The scores of de Gerlache (88.48°S 88.34°W), Shackleton (89.67°S 129.78°E), and Amundsen (84.5°S, 82.8°E) craters are determined using fuzzy interference as 0.816, 0.814, and 0.784, respectively. Moreover, using our proposed approach, we identify feasible landing sites around the de Gerlache crater close to the PSR to facilitate discovery of water ice exposures in future missions. The proposed method is capable of evaluating alternative landing zones subject to multiple engineering constraints on the Moon or Mars based on the existing data.
      Citation: Remote Sensing
      PubDate: 2022-09-29
      DOI: 10.3390/rs14194863
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4864: Statistical Analysis of the
           Spatiotemporal Distribution of Lower Atmospheric Ducts over the Seas
           Adjacent to China, Based on the ECMWF Reanalysis Dataset

    • Authors: Yong Zhou, Yi Liu, Jiandong Qiao, Jinze Li, Chen Zhou
      First page: 4864
      Abstract: On the basis of 12 years of the European Centre for Mesoscale Weather Forecasts (ECMWF) reanalysis dataset, we statistically analyzed the spatiotemporal distribution of lower atmospheric ducts over the seas around China, and we investigated the possible generation mechanisms. The results show that the ducts’ occurrence had obvious seasonal and regional variations. Ducting events were more likely to occur in spring and summer, and the maximum occurrence rate reached 45.6%, which was closely related to the East Asian monsoon. The ducts’ altitude in continental coastal areas was lower than that far from the coast due to the dominance of surface ducts. The ducts’ thickness varied between 50 m and 450 m, and the thicker ducts were mainly concentrated in the South China Sea and the Pacific Ocean on the east side of the East China Sea near the Philippines and Taiwan. Except for a few areas, the ducts’ intensity was less than 10 M-units (an M-unit is the unit of atmospheric modified refractivity) and the diurnal variations were less pronounced. The duct formation in the lower atmosphere was related to factors such as monsoons, tropical cyclones, ocean currents, radiative cooling, and sea–land breezes.
      Citation: Remote Sensing
      PubDate: 2022-09-29
      DOI: 10.3390/rs14194864
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4865: Seasonal and Microphysical
           Characteristics of Fog at a Northern Airport in Alberta, Canada

    • Authors: Faisal S. Boudala, Di Wu, George A. Isaac, Ismail Gultepe
      First page: 4865
      Abstract: Reduction in visibility (Vis) due to fog is one of the deadliest severe weather hazards affecting aviation and public transportation. Nowcasting/forecasting of Vis reduction due to fog using current models is still problematic, with most using some type of empirical parameterization. To improve the models, further observational studies to better understand fog microphysics and seasonal variability are required. To help achieve these goals, the seasonal and microphysical characteristics of different fog types at Cold Lake airport (CYOD), Alberta, Canada were analyzed using hourly and sub-hourly METAR data. Microphysical and meteorological measurements obtained using the DMT Fog Monitor FM-120 and the Vaisala PWD22 were examined. The results showed that radiation fog (RF) dominates at CYOD in summer while precipitation, advection and cloud-base-lowering fogs mostly occur in fall and winter. All fog types usually form at night or early morning and dissipate after sunrise. The observed dense fog events (Vis < 400 m) were mainly caused by RF. The observed mean fog particle spectra () for different fog types and temperatures showed bimodal n(D) (with two modes near 4 μm and 17–25 μm; the maximum total number concentration () was 100 cm−3 and 20 cm−3, respectively, corresponding to each mode). Parameterizations of Vis as a function of liquid water content () and were developed using both the observed Vis and calculated Vis based on . It was found that the observed Vis was higher than the calculated Vis for warm fog with > 0.1 gm−3 and most of the mass was contributed by the large drops. Based on the observed Vis, the relative error of the visibility parameterization as a function of both and (32%) was slightly lower than that (34%) using alone for warm fogs.
      Citation: Remote Sensing
      PubDate: 2022-09-29
      DOI: 10.3390/rs14194865
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4866: Hyperspectral Image Classification
           with IFormer Network Feature Extraction

    • Authors: Qi Ren, Bing Tu, Sha Liao, Siyuan Chen
      First page: 4866
      Abstract: Convolutional neural networks (CNNs) are widely used for hyperspectral image (HSI) classification due to their better ability to model the local details of HSI. However, CNNs tends to ignore the global information of HSI, and thus lack the ability to establish remote dependencies, which leads to computational cost consumption and remains challenging. To address this problem, we propose an end-to-end Inception Transformer network (IFormer) that can efficiently generate rich feature maps from HSI data and extract high- and low-frequency information from the feature maps. First, spectral features are extracted using batch normalization (BN) and 1D-CNN, while the Ghost Module generates more feature maps via low-cost operations to fully exploit the intrinsic information in HSI features, thus improving the computational speed. Second, the feature maps are transferred to Inception Transformer through a channel splitting mechanism, which effectively learns the combined features of high- and low-frequency information in the feature maps and allows for the flexible modeling of discriminative information scattered in different frequency ranges. Finally, the HSI features are classified via pooling and linear layers. The IFormer algorithm is compared with other mainstream algorithms in experiments on four publicly available hyperspectral datasets, and the results demonstrate that the proposed method algorithm is significantly competitive among the HSI classification algorithms.
      Citation: Remote Sensing
      PubDate: 2022-09-29
      DOI: 10.3390/rs14194866
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4867: MS-Pansharpening Algorithm Based on
           Dual Constraint Guided Filtering

    • Authors: Xianghai Wang, Zhenhua Mu, Shifu Bai, Yining Feng, Ruoxi Song
      First page: 4867
      Abstract: The difference and complementarity of spatial and spectral information between multispectral (MS) image and panchromatic (PAN) image have laid the foundation for the fusion of the two types of images. In recent years, MS and PAN image fusion (also known as MS-Pansharpening) has gained attention as an important research area in remote sensing (RS) image processing. This paper proposes an MS-Pansharpening algorithm based on dual constraint Guided Filtering in the nonsubsampled shearlet transform (NSST) domain. The innovation is threefold. First, the dual constraint guided image filtering (DCGIF) model, based on spatial region average gradient correlation and vector correlation formed by neighborhood elements is proposed. Further, the PAN image detail information extraction scheme, based on the model, is provided, which extracts more complete and accurate detail information, thus avoiding, to some extent, the spectral distortion caused by the injection of non-adaptive information. Second, the weighted information injection model, based on the preservation of the correlation between the band spectra, is proposed. The model determines the information injection weight of each band pixel based on the spectral proportion between bands of the original MS image, which ensures the spectral correlation between bands of the fused MS image. Finally, a new MS-Pansharpening algorithm in NSST domain is proposed. The MS and PAN high frequency sub-bands of NSST are used to extract more effective spatial details. Then the proposed DCGIF model is used to extract the effective spatial detail injection information through the weighted joint method based on the regional energy matrix. Finally, the weighted information injection model is used to inject it into each band of MS to complete information fusion. Experimental results show that the proposed approach has better fusion effect than some conventional MS-Pansharpening algorithms, which can effectively improve the spatial resolution of the fused MS image and maintain the spectral characteristics of MS.
      Citation: Remote Sensing
      PubDate: 2022-09-29
      DOI: 10.3390/rs14194867
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4868: A Review of Spectral Indices for
           Mangrove Remote Sensing

    • Authors: Thuong V. Tran, Ruth Reef, Xuan Zhu
      First page: 4868
      Abstract: Mangrove ecosystems provide critical goods and ecosystem services to coastal communities and contribute to climate change mitigation. Over four decades, remote sensing has proved its usefulness in monitoring mangrove ecosystems on a broad scale, over time, and at a lower cost than field observation. The increasing use of spectral indices has led to an expansion of the geographical context of mangrove studies from local-scale studies to intercontinental and global analyses over the past 20 years. In remote sensing, numerous spectral indices derived from multiple spectral bands of remotely sensed data have been developed and used for multiple studies on mangroves. In this paper, we review the range of spectral indices produced and utilised in mangrove remote sensing between 1996 and 2021. Our findings reveal that spectral indices have been used for a variety of mangrove aspects but excluded identification of mangrove species. The included aspects are mangrove extent, distribution, mangrove above ground parameters (e.g., carbon density, biomass, canopy height, and estimations of LAI), and changes to the aforementioned aspects over time. Normalised Difference Vegetation Index (NDVI) was found to be the most widely applied index in mangroves, used in 82% of the studies reviewed, followed by the Enhanced Vegetation Index (EVI) used in 28% of the studies. Development and application of potential indices for mangrove cover characterisation has increased (currently 6 indices are published), but NDVI remains the most popular index for mangrove remote sensing. Ultimately, we identify the limitations and gaps of current studies and suggest some future directions under the topic of spectral index application in connection to time series imagery and the fusion of optical sensors for mangrove studies in the digital era.
      Citation: Remote Sensing
      PubDate: 2022-09-29
      DOI: 10.3390/rs14194868
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4869: A Radar Detection Method of
           Plasma-Sheath-Covered Target Based on the Improved Keystone Algorithm

    • Authors: Bowen Bai, Yi Ding, Xiaoping Li, Yanming Liu
      First page: 4869
      Abstract: The aerodynamic thermal ionization affects the re-entry target, and the surface will form a ‘plasma sheath (PSh).’ The PSh with fluid characteristics will produce relative motion with the re-entry target. In the radar detection of the re-entry target, the relative motion characteristics cause the echo signal to couple different intra-pulse Doppler frequency components, forming a ‘false target’ on the one-dimensional range profile. In addition, the flight velocity of the re-entry target is exceptionally high (usually greater than 10 Mach), and there will be a severe phenomenon of migration through range cells (MTRC) during the detection period, which will make the coherent integration of the multi-period radar echo signal invalid and further affect the reliable detection of the re-entry target. Aiming at the ‘false target phenomenon’ and MTRC phenomenon in the process of re-entry target detection, this paper proposes an improved keystone algorithm. Based on the traditional keystone algorithm, a reliable, coherent integration method for radar echo of the plasma-sheath-covered target is proposed by modifying the scale transformation factor and constructing the Doppler frequency compensation function. It can effectively compensate the intra-pulse Doppler frequency and inter-pulse Doppler frequency to improve the energy gain of the real target and lay a theoretical foundation for the reliable detection of the plasma-sheath-covered target.
      Citation: Remote Sensing
      PubDate: 2022-09-29
      DOI: 10.3390/rs14194869
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4870: Hydrological Drivers for the Spatial
           Distribution of Wetland Herbaceous Communities in Poyang Lake

    • Authors: Huang, Hu, Mao, Montzka, Bol, Wan, Li, Yue, Dai
      First page: 4870
      Abstract: Hydrological processes are known as major driving forces in structuring wetland plant communities, but the specific relationships are not always well understood. The recent dry conditions of Poyang Lake (i.e., the largest freshwater lake in China) are having a profound impact on its wetland vegetation, leading to the degradation of the entire wetland ecosystem. We developed an integrated framework to quantitatively investigate the relationship between the spatial distribution of major wetland herbaceous communities and the hydrological regimes of Poyang Lake. First, the wetland herbaceous community classification was built using a support-vector machine and simultaneous parameter optimization, achieving an overall accuracy of over 98%. Secondly, based on the inundation conditions since 2000, four hydrological drivers of the spatial distribution of these communities were evaluated by canonical correspondence analysis. Finally, the hydrological niches of the communities were quantified by Gaussian regression and quantile methods. The results show that there were significant interspecific differences in terms of the hydrological niche. For example, Carex cinerascens Ass was the most adaptable to inundation, while Triarrhena lutarioriparia + Phragmites australis Ass was the least. Our integrated analytical framework can contribute to hydrological management to better maintain the wetland plant community structure in the Poyang Lake area.
      Citation: Remote Sensing
      PubDate: 2022-09-29
      DOI: 10.3390/rs14194870
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4871: Interferometric Orbit Determination
           System for Geosynchronous SAR Missions: Experimental Proof of Concept

    • Authors: Jorge Nicolás-Álvarez, Xavier Carreño-Megias, Estel Ferrer, Miquel Albert-Galí, Judith Rodríguez-Tersa, Albert Aguasca, Antoni Broquetas
      First page: 4871
      Abstract: Future Geosynchronous Synthetic Aperture Radar (GEOSAR) missions will provide permanent monitoring of continental areas of the planet with revisit times of less than 24 h. Several GEOSAR missions have been studied in the USA, Europe, and China with different applications, including water cycle monitoring and early warning of disasters. GEOSAR missions require unprecedented orbit determination precision in order to form focused Synthetic Aperture Radar (SAR) images from Geosynchronous Orbit (GEO). A precise orbit determination technique based on interferometry is proposed, including a proof of concept based on an experimental interferometer using three antennas separated 10–15 m. They provide continuous orbit observations of present communication satellites operating at GEO as illuminators of opportunity. The relative phases measured between the receivers are used to estimate the satellite position. The experimental results prove the interferometer is able to track GEOSAR satellites based on the transmitted signals. This communication demonstrates the consistency and feasibility of the technique in order to foster further research with longer interferometric baselines that provide observables delivering higher orbital precision.
      Citation: Remote Sensing
      PubDate: 2022-09-29
      DOI: 10.3390/rs14194871
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4872: Remote Sensing Scene Graph and
           Knowledge Graph Matching with Parallel Walking Algorithm

    • Authors: Wei Cui, Yuanjie Hao, Xing Xu, Zhanyun Feng, Huilin Zhao, Cong Xia, Jin Wang
      First page: 4872
      Abstract: In deep neural network model training and prediction, due to the limitation of GPU memory and computing resources, massive image data must be cropped into limited-sized samples. Moreover, in order to improve the generalization ability of the model, the samples need to be randomly distributed in the experimental area. Thus, the background information is often incomplete or even missing. On this condition, a knowledge graph must be applied to the semantic segmentation of remote sensing. However, although a single sample contains only a limited number of geographic categories, the combinations of geographic objects are diverse and complex in different samples. Additionally, the involved categories of geographic objects often span different classification system branches. Therefore, existing studies often directly regard all the categories involved in the knowledge graph as candidates for specific sample segmentation, which leads to high computation cost and low efficiency. To address the above problems, a parallel walking algorithm based on cross modality information is proposed for the scene graph—knowledge graph matching (PWGM). The algorithm uses a graph neural network to map the visual features of the scene graph into the semantic space of the knowledge graph through anchors and designs a parallel walking algorithm of the knowledge graph that takes into account the visual features of complex scenes. Based on the algorithm, we propose a semantic segmentation model for remote sensing. The experiments demonstrate that our model improves the overall accuracy by 3.7% compared with KGGAT (which is a semantic segmentation model using a knowledge graph and graph attention network (GAT)), by 5.1% compared with GAT and by 13.3% compared with U-Net. Our study not only effectively improves the recognition accuracy and efficiency of remote sensing objects, but also offers useful exploration for the development of deep learning from a data-driven to a data-knowledge dual drive.
      Citation: Remote Sensing
      PubDate: 2022-09-29
      DOI: 10.3390/rs14194872
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4873: Detection of Carbon Use Efficiency
           Extremes and Analysis of Their Forming Climatic Conditions on a Global
           Scale Using a Remote Sensing-Based Model

    • Authors: Miaomiao Wang, Jian Zhao, Shaoqiang Wang
      First page: 4873
      Abstract: Carbon use efficiency (CUE) represents the proficiency of plants in transforming carbon dioxide (CO2) into carbon stock in terrestrial ecosystems. CUE extremes represent ecosystems’ extreme proficiency in carbon transformation. Studying CUE extremes and their forming climate conditions is critical for enhancing ecosystem carbon storage. However, the study of CUE extremes and their forming climate conditions on the global scale is still lacking. In this study, we used the results from the daily Boreal Ecosystem Productivity Simulator (BEPS) model to detect the positive and negative CUE extremes and analyze their forming climatic conditions on a global scale. We found grasslands have the largest potential in changing global CUE, with the contribution being approximately 32.4% to positive extremes and 30.2% to negative extremes. Spring in the Northern Hemisphere (MAM) contributed the most (30.5%) to positive CUE extremes, and summer (JJA) contributed the most (29.7%) to negative CUE extremes. The probabilities of gross primary production (GPP) extremes resulted in CUE extremes (>25.0%) being larger than autotrophic respiration (Ra), indicating CUE extremes were mainly controlled by GPP rather than Ra extremes. Positive temperature anomalies (0~1.0 °C) often accompanied negative CUE extreme events, and positive CUE extreme events attended negative temperature anomalies (−1.0~0 °C). Moreover, positive (0~20.0 mm) and negative precipitation (−20.0~0 mm) anomalies often accompanied positive and negative CUE extremes, respectively. These results suggest that cooler and wetter climate conditions could be beneficial to enhance carbon absorptions of terrestrial ecosystems. The study provides new knowledge on proficiency in carbon transformation by terrestrial ecosystems.
      Citation: Remote Sensing
      PubDate: 2022-09-29
      DOI: 10.3390/rs14194873
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4874: MSPR-Net: A Multi-Scale Features
           Based Point Cloud Registration Network

    • Authors: Jinjin Yu, Fenghao Zhang, Zhi Chen, Liman Liu
      First page: 4874
      Abstract: Point-cloud registration is a fundamental task in computer vision. However, most point clouds are partially overlapping, corrupted by noise and comprised of indistinguishable surfaces, especially for complexly distributed outdoor LiDAR point clouds, which makes registration challenging. In this paper, we propose a multi-scale features-based point cloud registration network named MSPR-Net for large-scale outdoor LiDAR point cloud registration. The main motivation of the proposed MSPR-Net is that the features of two keypoints from a true correspondence must match in different scales. From this point of view, we first utilize a multi-scale backbone to extract the multi-scale features of the keypoints. Next, we propose a bilateral outlier removal strategy to remove the potential outliers in the keypoints based on the multi-scale features. Finally, a coarse-to-fine registration way is applied to exploit the information both in feature and spatial space. Extensive experiments conducted on two large-scale outdoor LiDAR point cloud datasets demonstrate that MSPR-Net achieves state-of-the-art performance.
      Citation: Remote Sensing
      PubDate: 2022-09-29
      DOI: 10.3390/rs14194874
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4875: Optimization of Remote Sensing Image
           Segmentation by a Customized Parallel Sine Cosine Algorithm Based on the
           Taguchi Method

    • Authors: Fang Fan, Gaoyuan Liu, Jiarong Geng, Huiqi Zhao, Gang Liu
      First page: 4875
      Abstract: Affected by solar radiation, atmospheric windows, radiation aberrations, and other air and sky environmental factors, remote sensing images usually contain a large amount of noise and suffer from problems such as non-uniform image feature density. These problems bring great difficulties to the segmentation of high-precision remote sensing image. To improve the segmentation effect of remote sensing images, this study adopted an improved metaheuristic algorithm to optimize the parameter settings of pulse-coupled neural networks (PCNNs). Using the Taguchi method, the optimal parallelism scheme of the algorithm was effectively tailored for a specific target problem. The blindness in the design of the algorithm parallel structure was effectively avoided. The superiority of the customized parallel SCA based on the Taguchi method (TPSCA) was demonstrated in tests with different types of benchmark functions. In this study, simulations were performed using IKONOS, GeoEye-1, and WorldView-2 satellite remote sensing images. The results showed that the accuracy of the proposed remote sensing image segmentation model was significantly improved.
      Citation: Remote Sensing
      PubDate: 2022-09-29
      DOI: 10.3390/rs14194875
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4876: Bird-Borne Samplers for Monitoring
           CO2 and Atmospheric Physical Parameters

    • Authors: Annalisa Di Bernardino, Valeria Jennings, Giacomo Dell’Omo
      First page: 4876
      Abstract: Air quality monitoring in cities is significant for both human health and environment. Here, an innovative miniaturized active air sampler wearable by free-flying birds is presented. The device integrates a GPS logger and atmospheric calibrated sensors allowing for high spatiotemporal resolution measurements of carbon dioxide (CO2) concentration, barometric pressure, air temperature, and relative humidity. A field campaign, carried out from January to June 2021, involved the repeated release of homing pigeons (Columba livia) from downtown Rome (Italy), to sample the air on their way back to the loft, located in a rural area out of the city. The measurements suggest the importance of green urban areas in decreasing CO2 levels. Moreover, a positive relation between CO2 levels, relative humidity, and air temperature was revealed. In contrast, a negative relation with distance from the point of release, month, and time of day was found. Flight speed and the altitude of flight were related to rising CO2 levels. The easy use of such devices paves the way for the application of miniaturized air samplers to other synanthropic species (i.e., gulls), making birds convenient biomonitors for the urban environment.
      Citation: Remote Sensing
      PubDate: 2022-09-29
      DOI: 10.3390/rs14194876
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4877: Integration of Hyperspectral and
           Magnetic Data for Geological Characterization of the Niaqornarssuit
           Ultramafic Complex in West-Greenland

    • Authors: Agnieszka Kuras, Björn H. Heincke, Sara Salehi, Christian Mielke, Nicole Köllner, Christian Rogass, Uwe Altenberger, Ingunn Burud
      First page: 4877
      Abstract: The integration of imaging spectroscopy and aeromagnetics provides a cost-effective and promising way to extend the initial analysis of a mineral deposit. While imaging spectroscopy retrieves surface spectral information, magnetic responses are used to determine magnetization at both shallower and greater depths using 2D and 3D modeling. Integration of imaging spectroscopy and magnetics improves upon knowledge concerning lithology with magnetic properties, enhances understanding of the geological origin of magnetic anomalies, and is a promising approach for analyzing a prospective area for minerals having a high iron-bearing content. To combine iron diagnostic information from airborne hyperspectral and magnetic data, we (a) used an iron absorption feature ratio to model pseudo-magnetic responses and compare them with the measured magnetic data and (b) estimated the apparent susceptibility along the surface by some equivalent source modeling, and compared them with iron ratios along the surface. For this analysis, a Modified Iron Feature Depth index was developed and compared to the surface geochemistry of the rock samples in order to validate the spectral information of iron. The comparison revealed a linear increase in iron absorption feature depths with iron content. The analysis was performed by empirically modeling the statistical relationship between the diagnostic absorption features of hyperspectral (HS) image spectra of selected rock samples and their corresponding geochemistry. Our results clearly show a link between the spectral absorption features and the magnetic response from iron-bearing ultra/-mafic rocks. The iron absorption feature ratio of 𝐹𝑒3+/𝐹𝑒2+ integrated with aeromagnetic data (residual magnetic anomaly) allowed us to distinguish main rock types based on physical properties. This separation matches the lithology of the Niaqornarssuit complex, our study area in West Greenland.
      Citation: Remote Sensing
      PubDate: 2022-09-29
      DOI: 10.3390/rs14194877
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4878: Source-Independent Waveform Inversion
           Method for Ground Penetrating Radar Based on Envelope Objective Function

    • Authors: Xintong Liu, Sixin Liu, Chaopeng Luo, Hejun Jiang, Hong Li, Xu Meng, Zhihui Feng
      First page: 4878
      Abstract: For the full waveform inversion, it is necessary to provide an accurate source wavelet for forwarding modeling in the iteration. The source wavelet estimation method based on deconvolution technology can solve this problem to some extent, but we find that the estimated source wavelet is not accurate and needs to be manually corrected repeatedly in the iteration. This process is highly operator-intensive, and the update process is time-consuming and increases the potential for errors. We propose a source-independent waveform inversion (SIEWI) scheme for cross-hole GPR data, and use the envelope objective function combined with this method to effectively reduce the nonlinearity of inversion. The residual field used by SIEWI to construct the gradient inherits the characteristics of the envelope wavefield. Compared with full waveform inversion (FWI), SIEWI is more robust and less sensitive to frequency components and inaccurate source wavelet. To avoid cycle jumping, the multi-scale strategy effectively utilizes the properties of convolutional wavefields. In one iteration, the wavefield is decomposed into multiple frequency bands through multiple convolutions in the time domain to construct a multi-scale inversion strategy that preferentially inverts low-frequency information.
      Citation: Remote Sensing
      PubDate: 2022-09-29
      DOI: 10.3390/rs14194878
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4879: GPR Image Clutter Suppression Using
           Gaussian Curvature Decomposition in the PCA Domain

    • Authors: Qibin Su, Beizhen Bi, Pengyu Zhang, Liang Shen, Xiaotao Huang, Qin Xin
      First page: 4879
      Abstract: Ground penetrating radar (GPR) is one of the most generally used underground sensing equipment, but it is frequently contaminated by clutter and noise during data acquisition, which has a significant impact on the detection performance of buried targets. The purpose of this letter is to present a novel clutter suppression method based on the principal component Gaussian curvature decomposition (PCGCD). First, the GPR B-scan data are divided into different sub-components using principal component analysis (PCA). Then, a Gaussian curvature decomposition (GCD) method is proposed, which can be applied to PCA domain subspaces to recover more target structure information from random noise. The PCGCD method’s performance is evaluated using both numerical simulation and real-world GPR datasets. The visualization and quantitative results demonstrated our method’s superiority in protecting the underground target structure, removing complex random noise, and improving the detection ability of buried targets.
      Citation: Remote Sensing
      PubDate: 2022-09-29
      DOI: 10.3390/rs14194879
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4880: Cloud and Snow Identification Based
           on DeepLab V3+ and CRF Combined Model for GF-1 WFV Images

    • Authors: Zuo Wang, Boyang Fan, Zhengyang Tu, Hu Li, Donghua Chen
      First page: 4880
      Abstract: Cloud and snow identification in remote sensing images is critical for snow mapping and snow hydrology research. Aimed at the problem that the semantic segmentation model is prone to producing blurred boundaries, slicing traces and isolated small patches for cloud and snow identification in high-resolution remote sensing images, the feasibility of combining DeepLab v3+ and conditional random field (CRF) models for cloud and snow identification based on GF-1 WFV images is studied. For GF-1 WFV images, the model training and testing experiments under the conditions of different sample numbers, sample sizes and loss functions are compared. The results show that, firstly, when the number of samples is 10,000, the sample size is 256 × 256, and the loss function is the Focal function, the model accuracy is the optimal and the Mean Intersection over Union (MIoU) and the Mean Pixel Accuracy (MPA) reach 0.816 and 0.918, respectively. Secondly, after post-processing with the CRF model, the MIoU and the MPA are improved to 0.836 and 0.941, respectively, compared with those without post-processing. Moreover, the misclassifications such as blurred boundaries, slicing traces and isolated small patches are significantly reduced, which indicates that the combination of the DeepLab v3+ and CRF models has high accuracy and strong feasibility for cloud and snow identification in high-resolution remote sensing images. The conclusions can provide a reference for high-resolution snow mapping and hydrology applications using deep learning models.
      Citation: Remote Sensing
      PubDate: 2022-09-30
      DOI: 10.3390/rs14194880
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4881: Eddy Induced Cross-Shelf Exchanges in
           the Black Sea

    • Authors: Anıl Akpınar, Ehsan Sadighrad, Bettina A. Fach, Sinan Arkın
      First page: 4881
      Abstract: Cross-shelf exchanges in the Black Sea were investigated using remote sensing data and an ocean circulation model to which an eddy-tracking algorithm and Lagrangian particle tracking model was applied. An anticyclonic eddy in 1998 and a cyclonic eddy in 2000 were investigated in detail. Eddy-induced cross-shelf transport of low salinity and high Chl-a waters reached a maximum in the presence of filaments associated with these eddies. The daily mean volume transport by the eddies was comparable with the previously documented transport by eddies of similar size in the north-western shelf region. Lagrangian particle tracking results showed that 59% of particles initially released over the shelf were transported offshore within 30 days by the 1998 anticyclone and 27% by the 2000 cyclone. The net volume transport across the Black Sea shelf-break reached the maxima in winter, coinciding with the increase in wind stress curl and mean kinetic energy that is a measure of the intensity of the boundary current. Ekman transport directly influences the cross-shelf exchanges in the surface layer. The south-eastern Black Sea is presented as an important area for cross-shelf transport. The total cross-shelf transport can be divided into its “large-scale” and “eddy-induced” components. Eddy-induced transport was 34% and 37% of the total cross-shelf transport (1998–2014) in the Black Sea in the off-shelf and on-shelf directions, respectively, but these values ranged between 25% and 65% depending on the eddy activity over time.
      Citation: Remote Sensing
      PubDate: 2022-09-30
      DOI: 10.3390/rs14194881
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4882: Concrete Bridge Defects
           Identification and Localization Based on Classification Deep Convolutional
           Neural Networks and Transfer Learning

    • Authors: Hajar Zoubir, Mustapha Rguig, Mohamed El Aroussi, Abdellah Chehri, Rachid Saadane, Gwanggil Jeon
      First page: 4882
      Abstract: Conventional practices of bridge visual inspection present several limitations, including a tedious process of analyzing images manually to identify potential damages. Vision-based techniques, particularly Deep Convolutional Neural Networks, have been widely investigated to automatically identify, localize, and quantify defects in bridge images. However, massive datasets with different annotation levels are required to train these deep models. This paper presents a dataset of more than 6900 images featuring three common defects of concrete bridges (i.e., cracks, efflorescence, and spalling). To overcome the challenge of limited training samples, three Transfer Learning approaches in fine-tuning the state-of-the-art Visual Geometry Group network were studied and compared to classify the three defects. The best-proposed approach achieved a high testing accuracy (97.13%), combined with high F1-scores of 97.38%, 95.01%, and 97.35% for cracks, efflorescence, and spalling, respectively. Furthermore, the effectiveness of interpretable networks was explored in the context of weakly supervised semantic segmentation using image-level annotations. Two gradient-based backpropagation interpretation techniques were used to generate pixel-level heatmaps and localize defects in test images. Qualitative results showcase the potential use of interpretation maps to provide relevant information on defect localization in a weak supervision framework.
      Citation: Remote Sensing
      PubDate: 2022-09-30
      DOI: 10.3390/rs14194882
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4883: Deep Learning Classification by
           ResNet-18 Based on the Real Spectral Dataset from Multispectral Remote
           Sensing Images

    • Authors: Yi Zhao, Xinchang Zhang, Weiming Feng, Jianhui Xu
      First page: 4883
      Abstract: Owing to the limitation of spatial resolution and spectral resolution, deep learning methods are rarely used for the classification of multispectral remote sensing images based on the real spectral dataset from multispectral remote sensing images. This study explores the application of a deep learning model to the spectral classification of multispectral remote sensing images. To address the problem of the large workload with respect to selecting training samples during classification by deep learning, first, linear spectral mixture analysis and the spectral index method were applied to extract the pixels of impervious surfaces, soil, vegetation, and water. Second, through the Euclidean distance threshold method, a spectral dataset of multispectral image pixels was established. Third, a deep learning classification model, ResNet-18, was constructed to classify Landsat 8 OLI images based on pixels’ real spectral information. According to the accuracy assessment, the results show that the overall accuracy of the classification results can reach 0.9436, and the kappa coefficient can reach 0.8808. This study proposes a method that allows for the more optimized establishment of the actual spectral dataset of ground objects, addresses the limitations of difficult sample selection in deep learning classification and of spectral similarity in traditional classification methods, and applies the deep learning method to the classification of multispectral remote sensing images based on a real spectral dataset.
      Citation: Remote Sensing
      PubDate: 2022-09-30
      DOI: 10.3390/rs14194883
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4884: Exploring Ephemeral Features with
           Ground-Penetrating Radar: An Approach to Roman Military Camps

    • Authors: Jesús García Sánchez, José Manuel Costa-García, João Fonte, David González-Álvarez
      First page: 4884
      Abstract: This paper addresses an experimental approach to the archaeological study of Roman camps in NW Iberia using ground-penetrating radar (henceforth GPR). The main goal is to explore the capabilities of GPR to extract datasets from ephemeral features, such as temporary camps or siege works, among others. This information aims to maximise the data available before excavation, orienting it to areas that could provide good results in terms of feature detection and contrast between soil matrix and archaeological deposits. This paper explores the potential of the GPR approach and volumetric data visualisation to improve our understanding of four ephemeral sites: Alto da Raia (Montalegre, Portugal–Calvos de Randín, Spain), Sueros de Cepeda (Villamejil, Spain), Los Andinales (Villsandino, Spain), and Villa María (Sasamón, Spain). Despite the focus of this paper, other survey techniques (namely LiDAR, aerial photography, and magnetometry) were used in combination with GPR. Further excavation of the sites provided ground truthing for all data remotely gathered.
      Citation: Remote Sensing
      PubDate: 2022-09-30
      DOI: 10.3390/rs14194884
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4885: Unifying Deep ConvNet and Semantic
           Edge Features for Loop Closure Detection

    • Authors: Jie Jin, Jiale Bai, Yan Xu, Jiani Huang
      First page: 4885
      Abstract: Loop closure detection is an important component of Simultaneous Localization and Mapping (SLAM). In this paper, a novel two-branch loop closure detection algorithm unifying deep Convolutional Neural Network (ConvNet) features and semantic edge features is proposed. In detail, we use one feature extraction module to extract both ConvNet and semantic edge features simultaneously. The deep ConvNet features are subjected to a Context Feature Enhancement (CFE) module in the global feature ranking branch to generate a representative global feature descriptor. Concurrently, to reduce the interference of dynamic features, the extracted semantic edge information of landmarks is encoded through the Vector of Locally Aggregated Descriptors (VLAD) framework in the semantic edge feature ranking branch to form semantic edge descriptors. Finally, semantic, visual, and geometric information is integrated by the similarity score fusion calculation. Extensive experiments on six public datasets show that the proposed approach can achieve competitive recall rates at 100% precision compared to other state-of-the-art methods.
      Citation: Remote Sensing
      PubDate: 2022-09-30
      DOI: 10.3390/rs14194885
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4886: Comparison of S5P/TROPOMI Inferred
           NO2 Surface Concentrations with In Situ Measurements over Central Europe

    • Authors: Andreas Pseftogkas, Maria-Elissavet Koukouli, Arjo Segers, Astrid Manders, Jos van Geffen, Dimitris Balis, Charikleia Meleti, Trissevgeni Stavrakou, Henk Eskes
      First page: 4886
      Abstract: The aim of this paper is to evaluate the surface concentration of nitrogen dioxide (NO2) inferred from the Sentinel-5 Precursor Tropospheric Monitoring Instrument (S5P/TROPOMI) NO2 tropospheric column densities over Central Europe for two time periods, summer 2019 and winter 2019–2020. Simulations of the NO2 tropospheric vertical column densities and surface concentrations from the Long-Term Ozone Simulation–European Operational Smog (LOTOS-EUROS) chemical transport model are also applied in the methodology. More than two hundred in situ air quality monitoring stations, reporting to the European Environment Agency (EEA) air quality database, are used to carry out comparisons with the model simulations and the spaceborne inferred surface concentrations. Stations are separated into seven types (urban traffic, suburban traffic, urban background, suburban background, rural background, suburban industrial and rural industrial) in order to examine the strengths and shortcomings of the different air quality markers, namely the NO2 vertical column densities and NO2 surface concentrations. S5P/TROPOMI NO2 surface concentrations are inferred by multiplying the fraction of the satellite and model NO2 vertical column densities with the model surface concentrations. The estimated inferred TROPOMI NO2 surface concentrations are examined further with the altering of three influencing factors: the model vertical leveling scheme, the versions of the TROPOMI NO2 data and the air mass factors applied to the satellite and model NO2 vertical column densities. Overall, the inferred TROPOMI NO2 surface concentrations show a better correlation with the in situ measurements for both time periods and all station types, especially for the industrial stations (R > 0.6) in winter. The calculated correlation for background stations is moderate for both periods (R~0.5 in summer and R > 0.5 in winter), whereas for traffic stations it improves in the winter (from 0.20 to 0.50). After the implementation of the air mass factors from the local model, the bias is significantly reduced for most of the station types, especially in winter for the background stations, ranging from +0.49% for the urban background to +10.37% for the rural background stations. The mean relative bias in winter between the inferred S5P/TROPOMI NO2 surface concentrations and the ground-based measurements for industrial stations is about −15%, whereas for traffic urban stations it is approximately −25%. In summer, biases are generally higher for all station types, especially for the traffic stations (~−75%), ranging from −54% to −30% for the background and industrial stations.
      Citation: Remote Sensing
      PubDate: 2022-09-30
      DOI: 10.3390/rs14194886
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4887: Winter Wheat Lodging Area Extraction
           Using Deep Learning with GaoFen-2 Satellite Imagery

    • Authors: Ziqian Tang, Yaqin Sun, Guangtong Wan, Kefei Zhang, Hongtao Shi, Yindi Zhao, Shuo Chen, Xuewei Zhang
      First page: 4887
      Abstract: The timely and accurate detection of wheat lodging at a large scale is necessary for loss assessments in agricultural insurance claims. Most existing deep-learning-based methods of wheat lodging detection use data from unmanned aerial vehicles, rendering monitoring wheat lodging at a large scale difficult. Meanwhile, the edge feature is not accurately extracted. In this study, a semantic segmentation network model called the pyramid transposed convolution network (PTCNet) was proposed for large-scale wheat lodging extraction and detection using GaoFen-2 satellite images with high spatial resolutions. Multi-scale high-level features were combined with low-level features to improve the segmentation’s accuracy and to enhance the extraction sensitivity of wheat lodging areas in the proposed model. In addition, four types of vegetation indices and three types of edge features were added into the network and compared to the increment in the segmentation’s accuracy. The F1 score and the intersection over union of wheat lodging extraction reached 85.31% and 74.38% by PTCNet, respectively, outperforming other compared benchmarks, i.e., SegNet, PSPNet, FPN, and DeepLabv3+ networks. PTCNet can achieve accurate and large-scale extraction of wheat lodging, which is significant in the fields of loss assessment and agricultural insurance claims.
      Citation: Remote Sensing
      PubDate: 2022-09-30
      DOI: 10.3390/rs14194887
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4888: Using GEOBIA and Vegetation Indices
           to Assess Small Urban Green Areas in Two Climatic Regions

    • Authors: Ana Maria Popa, Diana Andreea Onose, Ionut Cosmin Sandric, Evangelos A. Dosiadis, George P. Petropoulos, Athanasios Alexandru Gavrilidis, Antigoni Faka
      First page: 4888
      Abstract: The importance of small urban green areas has increased in the context of rapid urbanization and the densification of the urban tissue. The analysis of these areas through remote sensing has been limited due to the low spatial resolution of freely available satellite images. We propose a timeseries analysis on 3 m resolution Planet images, using GEOBIA and vegetation indices, with the aim of extracting and assessing the quality of small urban green areas in two different climatic and biogeographical regions: temperate (Bucharest, Romania) and mediterranean (Athens, Greece). Our results have shown high accuracy (over 91%) regarding the extraction of small urban green areas in both cities across all the analyzed images. The timeseries analysis showed consistency with respect to location for around 55% of the identified surfaces throughout the entire period. The vegetation indices registered higher values in the temperate region due to the vegetation characteristics and city plan of the two cities. For the same reasons, the increase in the vegetation density and quality, as a result of the distance from the city center, and the decrease in the density of built-up areas, is more obvious in Athens. The proposed method provides valuable insights into the distribution and quality of small urban green areas at the city level and can represent the basis for many analyses, which is currently limited by poor spatial resolution.
      Citation: Remote Sensing
      PubDate: 2022-09-30
      DOI: 10.3390/rs14194888
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4889: Shift Pooling PSPNet: Rethinking
           PSPNet for Building Extraction in Remote Sensing Images from Entire Local
           Feature Pooling

    • Authors: Wei Yuan, Jin Wang, Wenbo Xu
      First page: 4889
      Abstract: Building extraction by deep learning from remote sensing images is currently a research hotspot. PSPNet is one of the classic semantic segmentation models and is currently adopted by many applications. Moreover, PSPNet can use not only CNN-based networks but also transformer-based networks as backbones; therefore, PSPNet also has high value in the transformer era. The core of PSPNet is the pyramid pooling module, which gives PSPNet the ability to capture the local features of different scales. However, the pyramid pooling module also has obvious shortcomings. The grid is fixed, and the pixels close to the edge of the grid cannot obtain the entire local features. To address this issue, an improved PSPNet network architecture named shift pooling PSPNet is proposed, which uses a module called shift pyramid pooling to replace the original pyramid pooling module, so that the pixels at the edge of the grid can also obtain the entire local features. Shift pooling is not only useful for PSPNet but also in any network that uses a fixed grid for downsampling to increase the receptive field and save computing, such as ResNet. A dense connection was adopted in decoding, and upsampling was gradually carried out. With two open datasets, the improved PSPNet, PSPNet, and some classic image segmentation models were used for comparative experiments. The results show that our method is the best according to the evaluation metrics, and the predicted image is closer to the label.
      Citation: Remote Sensing
      PubDate: 2022-09-30
      DOI: 10.3390/rs14194889
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4890: Spatiotemporal Prediction of Monthly
           Sea Subsurface Temperature Fields Using a 3D U-Net-Based Model

    • Authors: Nengli Sun, Zeming Zhou, Qian Li, Xuan Zhou
      First page: 4890
      Abstract: The ability to monitor and predict sea temperature is crucial for determining the likelihood that ocean-related events will occur. However, most studies have focused on predicting sea surface temperature, and less attention has been paid to predicting sea subsurface temperature (SSbT), which can reflect the thermal state of the entire ocean. In this study, we use a 3D U-Net model to predict the SSbT in the upper 400 m of the Pacific Ocean and its adjacent oceans for lead times of 12 months. Two reconstructed SSbT products are added to the training set to solve the problem of insufficient observation data. Experimental results indicate that this method can predict the ocean temperature more accurately than previous methods in most depth layers. The root mean square error and mean absolute error of the predicted SSbT fields for all lead times are within 0.5–0.7 °C and 0.3–0.45 °C, respectively, while the average correlation coefficient scores of the predicted SSbT profiles are above 0.96 for almost all lead times. In addition, a case study qualitatively demonstrates that the 3D U-Net model can predict realistic SSbT variations in the study area and, thus, facilitate understanding of future changes in the thermal state of the subsurface ocean.
      Citation: Remote Sensing
      PubDate: 2022-09-30
      DOI: 10.3390/rs14194890
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4891: Variability of Chl a Concentration of
           Priority Marine Regions of the Northwest of Mexico

    • Authors: Carlos Manuel Robles-Tamayo, Ricardo García-Morales, José Raúl Romo-León, Gudelia Figueroa-Preciado, María Cristina Peñalba-Garmendia, Luis Fernando Enríquez-Ocaña
      First page: 4891
      Abstract: Priority Marine Regions (PMR) are important areas for biodiversity conservation in the Northwest Pacific Ocean in Mexico. The oceanographic dynamics of these regions are very important to understand their variability, generate analyses, and predict climate change trends by generating an adequate management of marine resources and their ecological characterization. Chlorophyll a (Chl a) is important to quantify phytoplankton biomass, consider the main basis of the trophic web in marine ecosystems, and determine the primary productivity levels and trends of change. The objective of this research is to analyze the oceanographic variability of 24 PMR through monthly 1-km satellite image resolution Chl a data from September 1997 to October 2018. A cluster analysis of Chl a data yielded 18 regions with clear seasonal variability in the Chl a concentration in the South-Californian Pacific (maximum values in spring-summer and minimum ones in autumn-winter) and Gulf of California (maximum values in winter-spring and minimum ones in summer-autumn). Significant differences (p < 0.05) were observed in Chl a concentration analyses for each one of the regions when climate patterns—El Niño/La Niña Southern Oscillation (ENSO) and normal events—were compared for all the seasons of the year (spring, summer, autumn, and winter).
      Citation: Remote Sensing
      PubDate: 2022-09-30
      DOI: 10.3390/rs14194891
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4892: Detection and Counting of Corn Plants
           in the Presence of Weeds with Convolutional Neural Networks

    • Authors: Canek Mota-Delfin, Gilberto de Jesús López-Canteñs, Irineo Lorenzo López-Cruz, Eugenio Romantchik-Kriuchkova, Juan Carlos Olguín-Rojas
      First page: 4892
      Abstract: Corn is an important part of the Mexican diet. The crop requires constant monitoring to ensure production. For this, plant density is often used as an indicator of crop yield, since knowing the number of plants helps growers to manage and control their plots. In this context, it is necessary to detect and count corn plants. Therefore, a database of aerial RGB images of a corn crop in weedy conditions was created to implement and evaluate deep learning algorithms. Ten flight missions were conducted, six with a ground sampling distance (GSD) of 0.33 cm/pixel at vegetative stages from V3 to V7 and four with a GSD of 1.00 cm/pixel for vegetative stages V6, V7 and V8. The detectors compared were YOLOv4, YOLOv4-tiny, YOLOv4-tiny-3l, and YOLOv5 versions s, m and l. Each detector was evaluated at intersection over union (IoU) thresholds of 0.25, 0.50 and 0.75 at confidence intervals of 0.05. A strong F1-Score penalty was observed at the IoU threshold of 0.75 and there was a 4.92% increase in all models for an IoU threshold of 0.25 compared to 0.50. For confidence levels above 0.35, YOLOv4 shows greater robustness in detection compared to the other models. Considering the mode of 0.3 for the confidence level that maximizes the F1-Score metric and the IoU threshold of 0.25 in all models, YOLOv5-s obtained a mAP of 73.1% with a coefficient of determination (R2) of 0.78 and a relative mean square error (rRMSE) of 42% in the plant count, followed by YOLOv4 with a mAP of 72.0%, R2 of 0.81 and rRMSE of 39.5%.
      Citation: Remote Sensing
      PubDate: 2022-09-30
      DOI: 10.3390/rs14194892
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4893: On the Impacts of Historical and
           Future Climate Changes to the Sustainability of the Main Sardinian Forests

    • Authors: Sara Simona Cipolla, Nicola Montaldo
      First page: 4893
      Abstract: The Mediterranean Basin is affected by climate changes that may have negative effects on forests. This study aimed to evaluate the ability of 17 forests located in the Island of Sardinia to resist or adapt to the past and future climate. Sardinia is experiencing a decreasing anthropic pressure on forests, but drought-triggered dieback in trees was recently observed and confirmed by the analysis of 20 years of satellite tree-cover data (MOD44B). Significant negative trends in yearly tree cover have affected the broad-leaved vegetation, while significative positive trends were found in the bushy sclerophyllous vegetation. Vegetation behavior resulted in being related to the mean annual precipitation (MAP); for MAP < 700 mm, we found a decline in the tall broad-leaved stands and an increase in the short ones, and the opposite was found for bushy sclerophyllous vegetations. In forests with MAP > 700 mm, both stands are stable, regardless of the growing trends in the vapor-pressure deficit (VPD) and temperature. No significative correlation between bushy sclerophyllous tree cover and the climate drivers was found, while broad-leaved tree cover is positively related to MAP1990–2019 and negatively related to the growing annual VPD. We modeled those relationships, and then we used them to coarsely predict the effects of twelve future scenarios (derived from HADGEM2-AO (CMIP5) and HadGEM3-GC31-LL (CMIP6) models) on forest tree covers. All scenarios show an annual VPD increase, and the higher its increase, the higher the trees-cover loss. The future changes in precipitation were contrasting. SC6, in line with past precipitation trends, predicts a further drop in the mean annual precipitation (−7.6%), which would correspond to an average 2.1-times-greater reduction in the tree cover (−16.09%). The future changes in precipitation for CMIP6 scenarios agree on a precipitation reduction in the range of −3.4% (SC7) to −14.29% (S12). However, although the reduction in precipitation predicted in SC12 is almost double that predicted in SC6, the consequent average reduction in TC is comparable and stands at −16%. On the contrary, SC2 predicts a turnaround with an abrupt increase of precipitation (+21.5%) in the upcoming years, with a reduction in the number of forests in water-limited areas and an increase in the percentage of tree cover in almost all forests.
      Citation: Remote Sensing
      PubDate: 2022-09-30
      DOI: 10.3390/rs14194893
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4894: Flood Vulnerability Assessment and
           Mapping: A Case Study for Australia’s Hawkesbury-Nepean Catchment

    • Authors: Schwarz, Kuleshov
      First page: 4894
      Abstract: Floods are one of the most destructive natural hazards to which Australia is exposed. The frequency of extreme rainfall events and consequential floods are projected to increase into the future as a result of anthropogenic climate change. This highlights the need for more holistic risk assessments of flood affected regions. Flood risk assessments (FRAs) are used to inform decision makers and stakeholders when creating mitigation and adaptation strategies for at-risk communities. When assessing flood risk, previous FRAs from Australia’s most flood prone regions were generally focused on the flood hazard itself, and rarely considering flood vulnerability (FV). This study assessed FV in one of Australia’s most flood prone regions—the Hawkesbury-Nepean catchment, and investigated indicator-based approaches as a proxy method for Australian FV assessment instead of hydrological modelling. Four indicators were selected with the intention of representing environmental and socio-economic characteristics: elevation, degree of slope, index of relative socio-economic disadvantage (IRSD), and hydrologic soil groups (HSGs). It was found that combination of low elevation, low degree of slope, low IRSD score, and very-low infiltration soils resulted in very high levels of vulnerability. FV was shown to be at its highest in the Hawkesbury-Nepean valley flood plain region on the outskirts of Greater Western Sydney, particularly in Blacktown, Penrith, and Liverpool. This actionable risk data which resulted from the final FV index supported the practicality and serviceability of the proxy indicator-based approach. The developed methodology for FV assessment is replicable and has the potential to help inform decision makers of flood-prone communities in Australia, particularly in data scarce areas.
      Citation: Remote Sensing
      PubDate: 2022-09-30
      DOI: 10.3390/rs14194894
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4895: MAEANet: Multiscale Attention and
           Edge-Aware Siamese Network for Building Change Detection in
           High-Resolution Remote Sensing Images

    • Authors: Bingjie Yang, Yuancheng Huang, Xin Su, Haonan Guo
      First page: 4895
      Abstract: In recent years, using deep learning for large area building change detection has proven to be very efficient. However, the current methods for pixel-wise building change detection still have some limitations, such as a lack of robustness to false-positive changes and confusion about the boundary of dense buildings. To address these problems, a novel deep learning method called multiscale attention and edge-aware Siamese network (MAEANet) is proposed. The principal idea is to integrate both multiscale discriminative and edge structure information to improve the quality of prediction results. To effectively extract multiscale discriminative features, we design a contour channel attention module (CCAM) that highlights the edge of the changed region and combine it with the classical convolutional block attention module (CBAM) to construct multiscale attention (MA) module, which mainly contains channel, spatial and contour attention mechanisms. Meanwhile, to consider the structure information of buildings, we introduce the edge-aware (EA) module, which combines discriminative features with edge structure features to alleviate edge confusion in dense buildings. We conducted the experiments using LEVIR-CD and BCDD datasets. The proposed MA and EA modules can improve the F1-Score of the basic architecture by 1.13% on the LEVIR CD and by 1.39% on the BCDD with an accepted computation overhead. The experimental results demonstrate that the proposed MAEANet is effective and outperforms other state-of-the-art methods concerning metrics and visualization.
      Citation: Remote Sensing
      PubDate: 2022-09-30
      DOI: 10.3390/rs14194895
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4896: Probabilistic Tracking of Annual
           Cropland Changes over Large, Complex Agricultural Landscapes Using Google
           Earth Engine

    • Authors: Sitian Xiong, Priscilla Baltezar, Morgan A. Crowley, Michael Cecil, Stefano C. Crema, Eli Baldwin, Jeffrey A. Cardille, Lyndon Estes
      First page: 4896
      Abstract: Cropland expansion is expected to increase across sub-Saharan African (SSA) countries in the next thirty years to meet growing food needs across the continent. These land transformations will have cascading social and ecological impacts that can be monitored using novel Earth observation techniques that produce datasets complementary to national cropland surveys. In this study, we present a flexible Bayesian data synthesis workflow on Google Earth Engine (GEE) that can be used to fuse optical and synthetic aperture radar data and demonstrate its ability to track agricultural change at national scales. We adapted the previously developed Bayesian Updating of Land Cover (Unsupervised) algorithm (BULC-U) by integrating a shapelet and slope thresholding algorithm to identify the locations and dates of cropland expansion and implemented a tiling scheme to allow the processing of large volumes of imagery. We apply this approach to map annual cropland change from 2000 to 2015 for Zambia (750,000 km2), a country that is experiencing rapid growth in agricultural land. We applied our cropland mapping approach to a time series of unsupervised classifications developed from Landsat 5, 7, 8, Sentinel-1, and ALOS PALSAR within 1476 tiles covering Zambia. The annual cropland changes maps reveal active cropland expansion between 2000 to 2015 in Zambia, especially in the Southern, Central, and Eastern provinces. Our accuracy assessment estimates that we have identified 27.5% to 69.6% of the total cropland expansion from 2000 to 2015 in Zambia (commission errors between 6.1% to 37.6%), depending on the slope threshold. Our results demonstrate the usefulness of Bayesian data fusion and shapelet, slope-based thresholding to synthesize optical and synthetic aperture radar for monitoring agricultural changes in situations where training data are scarce. In addition, the annual cropland maps provide one of the first spatially continuous, annually incremented accounts of cropland growth in this region. Our flexible, cloud-based workflow using GEE enables multi-sensor, national-scale agricultural change monitoring at low cost for users.
      Citation: Remote Sensing
      PubDate: 2022-09-30
      DOI: 10.3390/rs14194896
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4897: Optimizing Management Practices to
           Reduce Sediment Connectivity between Forest Roads and Streams in a
           Mountainous Watershed

    • Authors: Qinghe Zhao, An Wang, Yaru Jing, Guiju Zhang, Zaihui Yu, Jinhai Yu, Yi Liu, Shengyan Ding
      First page: 4897
      Abstract: Forest roads often increase runoff and sediment loss, thus greatly impacting hydrological processes in mountainous watersheds. While there has been previous investigation on best management practices (BMPs) to reduce soil erosion from forest roads, few studies have attempted to optimize BMPs based on how much they can decrease sediment connectivity between forest roads and streams. To close this gap in knowledge, we analyzed the spatial relationship between forest roads and streams, presented the spatial distribution of sediment connectivity by integrating the forest roads into the calculation of the index of connectivity (IC), determined how sediment connectivity would respond to additional BMPs through simulating scenarios, and used these data to optimize the BMPs so they would intercept the greatest sediment loads. We found that forest roads and streams in the Xiangchagou watershed in the Dabie Mountain area of China tend to occur within 180 m of each other; however, within the same buffer zones, streams are more often accompanied by forest roads. IC was greatest near road–stream crossings but smaller near streams and forest roads, and it tended to decrease as the buffer distance increased. Furthermore, we found that sediment connectivity was decreased through running a variety of scenarios that used sediment basin and riparian buffers as BMPs between forest roads and streams. Specifically, within this watershed, riparian buffers should be 64 m wide, and there should be 30 sediment basins with a minimum upslope drainage area of 2 ha. At these quantities, the BMPs in this watershed would significantly affect sediment connectivity. By contrast, beyond these thresholds, increasing the width of riparian buffers or the number of sediment basins does not lead to meaningful sediment reductions. In this way, we were able to use the mean change point method to determine the optimal sediment basin quantity (30 with corresponding minimum upslope drainage area of 2 ha) and the optimal riparian buffer width (64 m) for the Xiangchagou watershed. While these results are a first approximation in a novel research area, they can guide forest managers and stakeholders to design and optimize BMPs that control the delivery of eroded sediments associated with forest roads.
      Citation: Remote Sensing
      PubDate: 2022-09-30
      DOI: 10.3390/rs14194897
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4898: Monitoring Non-Linear Ground Motion
           above Underground Gas Storage Using GNSS and PSInSAR Based on Sentinel-1

    • Authors: Juraj Struhár, Petr Rapant, Michal Kačmařík, Ivana Hlaváčová, Milan Lazecký
      First page: 4898
      Abstract: Several methods allow accurate measurement of terrain surface motions. Global navigation satellite systems (GNSSes) and interferometry with synthetic aperture radar (InSAR) stand out in terms of measurement accuracy among them. In principle, both methods make it possible to evaluate a three-dimensional vector of the motion of points on the terrain surface. In this work, we dealt with the evaluation of motions in the up–down (U–D) and east–west direction (E–W) over underground gas storage (UGS) from InSAR. One crucial step in breaking down PSInSAR line of sight (LOS) measurements to U–D and E–W components is getting time series derived from individual tracks to the same time frame. This is usually performed by interpolation, but we used an innovative approach: we analyzed individual time series using the Lomb–Scargle periodogram (LSP), which is suitable for periodic noisy and irregularly sampled data; we selected the most significant period, created LSP models, and used them instead of the original time series. Then, it was possible to derive time series values for any arbitrary time step. To validate the results, we installed one GNSS receiver in the Tvrdonice UGS test area to perform independent measurements. The results show a good agreement in the evaluation of motions by both methods. The correlation coefficient between horizontal components from both PSInSAR and GNSS was 0.95 in the case of the E–W component, with an RMSE of 1.75 mm; for U–D they were 0.78 and 2.35 mm, respectively. In addition to comparing the motions in the U–D and E–W directions, we also created a comparison by converting GNSS measurements to a line of sight of the Sentinel-1 satellite to evaluate the conformity of InSAR and GNSS measurements. Based on descending track, the correlation coefficient between LOS from both methods is, on average, 0.97, with an RMSE of 2.70 mm.
      Citation: Remote Sensing
      PubDate: 2022-09-30
      DOI: 10.3390/rs14194898
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4899: Ground Penetrating Radar in Coastal
           Hazard Mitigation Studies Using Deep Convolutional Neural Networks

    • Authors: Abhishek Kumar, Upendra Kumar Singh, Pradhan Biswajeet
      First page: 4899
      Abstract: There is a long history of coastal erosion caused by frequent storm surges in the coastal regions of Australia, which imposes great threats to communities and infrastructures alongside the beach. Old Bar Beach, New South Wales, Australia, is one such hotspot famous for its extreme coastal erosion. To apply remedial measures such as beach nourishment effectively and economically, estimating/reconstructing the subsurface hydrogeology over the coastal areas is essential. A geophysical tool such as a ground−penetrating radar (GPR) which works on the principle of reflecting electromagnetic (EM) waves, can be conveniently deployed to delineate the soil and rock profiling, water−table depth, bedrock depth, and the subsurface structural features. Here, DeepLabv3+ architecture based newly developed deep convolutional neural networks (DCNNs) were used to establish an inherent non−linear relationship between the GPR data and the EM wave velocity. The presented DCNNs have a lesser number of layers, a lesser number of trainable (learnable) parameters, a high convergence rate and, at the same time, achieve prediction accuracy comparable to that of well−established DeepLabv3+ networks, having high trainable parameters and a relatively low convergence rate. Here, firstly the DCNNs were trained and validated on small 1D datasets. Each dataset contains a 1D GPR trace and a corresponding EM velocity model. The DCNNs turned out to be quite promising in the 1D case, with training, validation, and testing accuracy of approximately 95%, 94%, and 95%, respectively. Secondly, 1D trained weights were applied to 2D synthetic GPR data for EM velocity prediction, and the accuracy of prediction achieved was approximately 95%. Seeing the excellent performance of the DCNNs in the 2D prediction case using 1D trained weights, a large amount of 1D synthetic datasets (approximately 1.2 million) were generated and gaussian noise was added to it to replicate the real field scenario. Thirdly, topographically corrected GPR data acquired over the Old Bar Beach were inverted using the DCNNs trained on 1.2 million 1D synthetic datasets to obtain the subsurface high−resolution, high−precision EM velocity, and distribution information to understand the hydrogeology over the beach. The findings presented in this paper agree well with the previous hydrogeological studies carried out using GPR. Our findings show that DCNNs, along with GPR, can be successfully used in coastal environments for the quick and accurate hydrogeological investigation required for the implementation of coastal erosion mitigation methods such as beach nourishment.
      Citation: Remote Sensing
      PubDate: 2022-09-30
      DOI: 10.3390/rs14194899
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4900: Analysis of Spatiotemporal Variation
           and Drivers of Ecological Quality in Fuzhou Based on RSEI

    • Authors: Jianwei Geng, Kunyong Yu, Zhen Xie, Gejin Zhao, Jingwen Ai, Liuqing Yang, Honghui Yang, Jian Liu
      First page: 4900
      Abstract: Background: High-speed urbanization has brought about a number of ecological and environmental problems, as well as the use of remote sensing to monitor the urban ecological environment and explore the main factors affecting its changes. It is important to promote the sustainable development of cities. Methods: In this study, we quantify the ecological quality of the study area from 2000 to 2020 based on the remote sensing ecological index (RSEI) and analyze its drivers through Geodetector and geographically weighted regression. Results: The RSEI of Fuzhou City from 2000 to 2020 showed an increasing followed by a decreasing trend, with obvious spatial autocorrelation. The main driving factors causing the spatial divergence of the RSEI were elevation (q = 0.48–0.63), slope (0.42–0.59), and GDP (0.3–0.42), and the driving effect and range of each factor changed with time. Conclusion: In this paper, we explore changes in the ecological environment in Fuzhou City over the past 20 years, as well as the scope and magnitude of the drivers, providing an important reference basis to improve the ecological environment quality of the city.
      Citation: Remote Sensing
      PubDate: 2022-09-30
      DOI: 10.3390/rs14194900
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4901: Improving the Modeling of Sea Surface
           Currents in the Persian Gulf and the Oman Sea Using Data Assimilation of
           Satellite Altimetry and Hydrographic Observations

    • Authors: Mahmoud Pirooznia, Mehdi Raoofian Naeeni, Alireza Atabati, Mohammad J. Tourian
      First page: 4901
      Abstract: Sea surface currents are often modeled using numerical models without adequately addressing the issue of model calibration at the regional scale. The aim of this study is to calibrate the MIKE 21 numerical ocean model for the Persian Gulf and the Oman Sea to improve the sea surface currents obtained from the model. The calibration was performed through data assimilation of the model with altimetry and hydrographic observations using variational data assimilation, where the weights of the objective functions were defined based on the type of observations and optimized using metaheuristic optimization methods. According to the results, the calibration of the model generally led the model results closer to the observations. This was reflected in an improvement of about 0.09 m/s in the obtained sea surface currents. It also allowed for more accurate evaluations of model parameters, such as Smagorinsky and Manning coefficients. Moreover, the root mean square error values between the satellite altimetry observations at control stations and the assimilated model varied between 0.058 and 0.085 m. We further showed that the kinetic energy produced by sea surface currents could be used for generating electricity in the Oman Sea and near Jask harbor.
      Citation: Remote Sensing
      PubDate: 2022-09-30
      DOI: 10.3390/rs14194901
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4902: A Novel Algorithm Modelling for UWB
           Localization Accuracy in Remote Sensing

    • Authors: Zhengyu Yu, Zenon Chaczko, Jiajia Shi
      First page: 4902
      Abstract: At present, the ultra-wideband (UWB) technology plays a vital role in the environment of indoor localization. As a new technology of wireless communications, UWB has many advantages, such as high accuracy, strong anti-multipath ability, and high transmission rate. However, in real-time operation, the accuracy of UWB is reduced by multi-sensor interference, antenna variations and system operation noise. We have developed a novel error modelling based on the curve fitted Kalman filter (CFKF) algorithm to solve these issues. This paper involves investigating and developing the error modelling algorithm that can calibrate the signal sensors, reduce the errors, and mitigate noise levels and interference signals. As part of the research investigation, a range of experiments was executed to validate the CFKF error modelling approach’s accuracy, reliability and viability. The experimental results indicate that this novel approach significantly improves the accuracy and precision of beacon-based localization. Validation tests also show that the CFKF error modelling method can improve the localization accuracy of UWB-based solutions.
      Citation: Remote Sensing
      PubDate: 2022-09-30
      DOI: 10.3390/rs14194902
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4903: Unbiased Area Estimation Using
           Copernicus High Resolution Layers and Reference Data

    • Authors: Luca Kleinewillinghöfer, Pontus Olofsson, Edzer Pebesma, Hanna Meyer, Oliver Buck, Carsten Haub, Beatrice Eiselt
      First page: 4903
      Abstract: Land cover area estimates can be derived via design-based approaches using a probability (random) reference sample. The collection of samples is usually costly and requires an effective sampling design. Earth-Observation-based mapping approaches do not have this requirement but can be biased in providing area estimates. Combining reference samples with remote sensing products can reduce sampling efforts and provide a more effective method to estimate land cover. The Copernicus High-Resolution Layer (HRL) provides remote-sensing-based data across Europe to support area estimation. Different methods are tested to estimate areas of imperviousness in four selected countries in Europe to demonstrate the use and shortcomings of existing reference information from the LUCAS survey program and the HRL Imperviousness products from 2015 and 2018.
      Citation: Remote Sensing
      PubDate: 2022-09-30
      DOI: 10.3390/rs14194903
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4904: Monitoring of Hydrological Resources

    • Authors: Li, Xie, Li, van der Meijde, Yan, Huang, Li, Wang
      First page: 4904
      Abstract: Satellite altimetry technology has unparalleled advantages in the monitoring of hydrological resources. After decades of development, satellite altimetry technology has achieved a perfect integration from the geometric research of geodesy to the natural resource monitoring research. Satellite altimetry technology has shown great potential, whether solid or liquid. In general, this paper systematically reviews the development of satellite altimetry technology, especially in terms of data availability and program practicability, and proposes a multi-source altimetry data fusion method based on deep learning. Secondly, in view of the development prospects of satellite altimetry technology, the challenges and opportunities in the monitoring application and expansion of surface water changes are sorted out. Among them, the limitations of the data and the redundancy of the program are emphasized. Finally, the fusion scheme of altimetry technology and deep learning proposed in this paper is presented. It is hoped that it can provide effective technical support for the monitoring and application research of hydrological resources.
      Citation: Remote Sensing
      PubDate: 2022-09-30
      DOI: 10.3390/rs14194904
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4905: Power Pylon Reconstruction from
           Airborne LiDAR Data Based on Component Segmentation and Model Matching

    • Authors: Yiya Qiao, Xiaohuan Xi, Sheng Nie, Pu Wang, Hao Guo, Cheng Wang
      First page: 4905
      Abstract: In recent years, with the rapid growth of State Grid digitization, it has become necessary to perform three-dimensional (3D) reconstruction of power elements with high efficiency and precision to achieve full coverage when simulating important transmission lines. Limited by the performance of acquisition equipment and the environment, the actual scanned point cloud usually has problems such as noise interference and data loss, presenting a great challenge for 3D reconstruction. This study proposes a model-driven 3D reconstruction method based on Airborne LiDAR point cloud data. Firstly, power pylon redirection is realized based on the Principal Component Analysis (PCA) algorithm. Secondly, the vertical and horizontal distribution characteristics of the power pylon point cloud and the graphical characteristics of the overall two-dimensional (2D) orthographic projection are analyzed to determine segmentation positions and the key segmentation position of the power pylon. The 2D alpha shape algorithm is adopted to obtain the pylon body contour points, and then the pylon feature points are extracted and corrected. Based on feature points, the components of original pylon and model pylon are registered, and the distance between the original point cloud and the model point cloud is calculated at the same time. Finally, the model with the highest matching degree is regarded as the reconstructed model of the pylon. The main advantages of the proposed method include: (1) identifying the key segmentation position according to the graphical characteristics; (2) for some pylons with much missing data, the complete model can be accurately reconstructed. The average RMSE (Root-Mean-Square Error) of all power pylon components in this study was 15.4 cm. The experimental results reveal that the effects of power pylon structure segmentation and reconstruction are satisfactory, which provides method and model support for digital management and security analysis of transmission lines.
      Citation: Remote Sensing
      PubDate: 2022-09-30
      DOI: 10.3390/rs14194905
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4906: A Simple Procedure to Preprocess and
           Ingest Level-2 Ocean Color Data into Google Earth Engine

    • Authors: Elígio de Raús Maúre, Simon Ilyushchenko, Genki Terauchi
      First page: 4906
      Abstract: Data from ocean color (OC) remote sensing are considered a cost-effective tool for the study of biogeochemical processes globally. Satellite-derived chlorophyll, for instance, is considered an essential climate variable since it is helpful in detecting climate change impacts. Google Earth Engine (GEE) is a planetary scale tool for remote sensing data analysis. Along with OC data, such tools allow an unprecedented spatial and temporal scale analysis of water quality monitoring in a way that has never been done before. Although OC data have been routinely collected at medium (~1 km) and more recently at higher (~250 m) spatial resolution, only coarse resolution (≥4 km) data are available in GEE, making them unattractive for applications in the coastal regions. Data reprojection is needed prior to making OC data readily available in the GEE. In this paper, we introduce a simple but practical procedure to reproject and ingest OC data into GEE at their native resolution. The procedure is applicable to OC swath (Level-2) data and is easily adaptable to higher-level products. The results showed consistent distributions between swath and reprojected data, building confidence in the introduced framework. The study aims to start a discussion on making OC data at native resolution readily available in GEE.
      Citation: Remote Sensing
      PubDate: 2022-09-30
      DOI: 10.3390/rs14194906
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4907: Updating Inventory, Deformation, and
           Development Characteristics of Landslides in Hunza Valley, NW Karakoram,
           Pakistan by SBAS-InSAR

    • Authors: Xiaojun Su, Yi Zhang, Xingmin Meng, Mohib Ur Rehman, Zainab Khalid, Dongxia Yue
      First page: 4907
      Abstract: The Hunza Valley, in the northwestern Karakoram Mountains, North Pakistan, is a typical region with many towns and villages, and a dense population and is prone to landslides. The present study completed landslide identification, updating a comprehensive landslide inventory and analysis. First, the ground surface deformation was detected in the Hunza Valley by SBAS-InSAR from ascending and descending datasets, respectively. Then, the locations and boundaries were interpreted and delineated, and a comprehensive inventory of 118 landslides, including the 53 most recent InSAR identified active landslides and 65 landslides cited from the literature, was completed. This study firstly named all 118 landslides, considering the demand for globally intensive research and hazard mitigation. Finally, the deformation, spatial–topographic development, and distribution characteristics in the Hunza Valley scale and three large significant landslides were analyzed. Information on 72 reported landslides was used to construct an empirical power law relationship linking landslide area (AL) to volume (VL) (VL = 0.067 × AL1.351), and this formula predicted the volume of 118 landslides in this study. We discovered that the landslides from the literature, which were interpreted from optical images, had lower levels of velocity, area, elevation, and height. The SBAS-InSAR-detected active landslide was characterized by higher velocity, larger area, higher elevation, larger slope gradient, larger NDVI (normalized difference vegetation index), and greater height. The melting glacier water and rainfall infiltration from cracks on the landslide’s upper part may promote the action of a push from gravity on the upper part. Simultaneously, the coupling of actions from river erosion and active tectonics could have an impact on the stability of the slope toe. The up-to-date comprehensive identification and understanding of the characteristics and mechanism of landslide development in this study provide a reference for the next step in landslide disaster prevention and risk assessment.
      Citation: Remote Sensing
      PubDate: 2022-09-30
      DOI: 10.3390/rs14194907
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4908: A Convolutional Neural Network for
           Large-Scale Greenhouse Extraction from Satellite Images Considering
           Spatial Features

    • Authors: Zhengchao Chen, Zhaoming Wu, Jixi Gao, Mingyong Cai, Xuan Yang, Pan Chen, Qingting Li
      First page: 4908
      Abstract: Deep learning-based semantic segmentation technology is widely applied in remote sensing and has achieved excellent performance in remote sensing image target extraction. Greenhouses play an important role in the development of agriculture in China. However, the rapid expansion of greenhouses has had a series of impacts on the environment. Therefore, the extraction of large-scale greenhouses is crucial for the sustainable development of agriculture and environmental governance. It is difficult for existing methods to acquire precise boundaries. Therefore, we propose a spatial convolutional long short-term memory structure, which can fully consider the spatial continuity of ground objects. We use multitask learning to improve the network’s ability to extract image boundaries and promote convergence through auxiliary loss. We propose a superpixel optimization module to optimize the main-branch results of network semantic segmentation using more precise boundaries obtained by advanced superpixel segmentation techniques. Compared with other mainstream methods, our proposed structure can better consider spatial information and obtain more accurate results. We chose Shandong Province, China, as the study area and used Gaofen-1 satellite remote sensing images to create a new greenhouse dataset. Our method achieved an F1 score of 77%, a significant improvement over mainstream semantic segmentation networks, and it could extract greenhouse results with more precise boundaries. We also completed large-scale greenhouse mapping for Shandong Province, and the results show that our proposed modules have great potential in greenhouse extraction.
      Citation: Remote Sensing
      PubDate: 2022-09-30
      DOI: 10.3390/rs14194908
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4909: Application of Random Forest
           Algorithm on Tornado Detection

    • Authors: Qiangyu Zeng, Zhipeng Qing, Ming Zhu, Fugui Zhang, Hao Wang, Yin Liu, Zhao Shi, Qiu Yu
      First page: 4909
      Abstract: Tornadoes are highly destructive small-scale extreme weather processes in the troposphere. The weather radar is one of the most effective remote sensing devices for the monitoring and early warning of tornadoes. The existing tornado detection algorithms based on radar data are unsupervised and have strict multi-altitude constraints, such as the tornado detection algorithm based on tornado vortex signatures (TDA-TVS), which may lead to high false alarm rates, and the performance of the detection algorithm is greatly affected by the radar data quality control algorithm. A novel TDA-RF algorithm based on the random forest (RF) classification algorithm is proposed for real-time tornado identification of the S-band China new generation of Doppler weather radar (CINRAD-SA). The TDA-RF algorithm uses velocity features to identify tornadoes and adds features related to reflectivity and velocity spectrum width in radar level-II data. Historical CINRAD-SA tornado data from 2006–2015 are used to construct the tornado dataset and train the TDA-RF model. The performance of TDA-RF is evaluated using CINRAD-SA data from five tornadoes of 2016–2020 with enhanced Fujita(EF) scale ratings ranging from EF0 to EF4 and distances from 10 to 130 km to the radar. TDA-RF performs well overall with the probability of detection (POD), false alarm ratio (FAR), and critical success index (CSI) of 71%, 29%, and 55%, respectively. Moreover, the TDA-RF improves POD and CSI, and reduces FAR compared to the TDA-TVS. The maximum tornado early-warning time of TDA-RF is 17 min, and the average is 6 min; TDA-RF can provide classification probability according to the tornado generation and development process to facilitate tracking ability.
      Citation: Remote Sensing
      PubDate: 2022-10-01
      DOI: 10.3390/rs14194909
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4910: AC−WGAN−GP: Generating
           Labeled Samples for Improving Hyperspectral Image Classification with

    • Authors: Caihao Sun, Xiaohua Zhang, Hongyun Meng, Xianghai Cao, Jinhua Zhang
      First page: 4910
      Abstract: The lack of labeled samples severely restricts the classification performance of deep learning on hyperspectral image classification. To solve this problem, Generative Adversarial Networks (GAN) are usually used for data augmentation. However, GAN have several problems with this task, such as the poor quality of the generated samples and an unstable training process. Thereby, knowing how to construct a GAN to generate high−quality hyperspectral training samples is meaningful for the small−sample classification task of hyperspectral data. In this paper, an Auxiliary Classifier based Wasserstein GAN with Gradient Penalty (AC−WGAN−GP) was proposed. The framework includes AC−WGAN−GP, an online generation mechanism, and a sample selection algorithm. The proposed method has the following distinctive advantages. First, the input of the generator is guided by prior knowledge and a separate classifier is introduced to the architecture of AC−WGAN−GP to produce reliable labels. Second, an online generation mechanism ensures the diversity of generated samples. Third, generated samples that are similar to real data are selected. Experiments on three public hyperspectral datasets show that the generated samples follow the same distribution as the real samples and have enough diversity, which effectively expands the training set. Compared to other competitive methods, the proposed framework achieved better classification accuracy with a small number of labeled samples.
      Citation: Remote Sensing
      PubDate: 2022-10-01
      DOI: 10.3390/rs14194910
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4911: Improving Estimates and Change
           Detection of Forest Above-Ground Biomass Using Statistical Methods

    • Authors: Amber E. Turton, Nicole H. Augustin, Edward T. A. Mitchard
      First page: 4911
      Abstract: Forests store approximately as much carbon as is in the atmosphere, with potential to take in or release carbon rapidly based on growth, climate change and human disturbance. Above-ground biomass (AGB) is the largest carbon pool in most forest systems, and the quickest to change following disturbance. Quantifying AGB on a global scale and being able to reliably map how it is changing, is therefore required for tackling climate change by targeting and monitoring policies. AGB can be mapped using remote sensing and machine learning methods, but such maps have high uncertainties, and simply subtracting one from another does not give a reliable indication of changes. To improve the quantification of AGB changes it is necessary to add advanced statistical methodology to existing machine learning and remote sensing methods. This review discusses the areas in which techniques used in statistical research could positively impact AGB quantification. Nine global or continental AGB maps, and a further eight local AGB maps, were investigated in detail to understand the limitations of techniques currently used. It was found that both modelling and validation of maps lacked spatial consideration. Spatial cross validation or other sampling methods, which specifically account for the spatial nature of this data, are important to introduce into AGB map validation. Modelling techniques which capture the spatial nature should also be used. For example, spatial random effects can be included in various forms of hierarchical statistical models. These can be estimated using frequentist or Bayesian inference. Strategies including hierarchical modelling, Bayesian inference, and simulation methods can also be applied to improve uncertainty estimation. Additionally, if these uncertainties are visualised using pixelation or contour maps this could improve interpretation. Improved uncertainty, which is commonly between 30% and 40%, is in addition needed to produce accurate change maps which will benefit policy decisions, policy implementation, and our understanding of the carbon cycle.
      Citation: Remote Sensing
      PubDate: 2022-10-01
      DOI: 10.3390/rs14194911
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4912: Assessment of Iran’s Mangrove
           Forest Dynamics (1990–2020) Using Landsat Time Series

    • Authors: Yousef Erfanifard, Mohsen Lotfi Nasirabad, Krzysztof Stereńczak
      First page: 4912
      Abstract: Mangrove forests distributed along the coast of southern Iran are an important resource and a vital habitat for species communities and the local people. In this study, accurate mapping and spatiotemporal change detection were conducted on Iran’s mangroves for three decades, using the Landsat imagery available for the years 1990, 2000, 2010, and 2020. Four general vegetation indices and eight mangrove-specific indices were employed for mangrove mapping in three study sites. Additionally, six important landscape metrics were implemented to quantify the spatiotemporal alteration of the mangrove forests during the study period. Our results showed the robustness of the submerged mangrove recognition index (SMRI), validated as the most effective index (AUCmangrove ≥ 0.96), which was used for mangrove identification within all nine sites. The mangrove area of southern Iran was estimated at approximately 13,000 ha in 2020, with an overall increase of 2313 ha over the whole period. A similar trend could be observed for both the landscape connectivity and complexity. Our results revealed that a stronger connectivity and higher complexity could be detected in most sites, while there was increased fragmentation and a weaker connection in some locations. This study provides an accurate map of Iran’s mangrove forests over time and space.
      Citation: Remote Sensing
      PubDate: 2022-10-01
      DOI: 10.3390/rs14194912
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4913: On the Sensitivity of a Ground-Based
           Tropospheric Lidar to Aitken Mode Particles in the Upper Troposphere

    • Authors: Matheus T. Silva, Juan Luis Guerrero-Rascado, Alexandre L. Correia, Diego A. Gouveia, Henrique M. J. Barbosa
      First page: 4913
      Abstract: Airborne observations have shown high concentrations of ultrafine aerosols in the Amazon upper troposphere (UT), which are key for replenishing the planetary boundary layer (PBL) with cloud condensation nuclei that sustain the “green ocean” clouds. Given their climatic relevance, long-term observations are needed, but aircraft measurements are only available in short-term campaigns. Alternatively, continuous observations of the aerosol vertical structure could be performed by a lidar (acronym for “light detection and ranging”) system in long-term campaigns. Here we assess whether a ground-based tropospheric lidar system could detect these ultrafine UT aerosols. To this aim, we simulated the lidar signal of a real instrument and then varied the instrument’s efficiency and the UT-particle concentration to determine under which conditions the detection is possible. Optical properties were computed with a Mie code based on the size distributions and numerical concentration profiles measured by the aircraft, and on the refractive indexes inverted from AERONET measurements. The aerosol optical depth (AOD) was retrieved by inverting the elastic lidar signal, and a statistical test was applied to evaluate the detection of the UT-aerosol layer. Our results indicate that, for the instrument we simulated, a 55-fold increase in the signal-to-noise ratio (SNR) is required for a 100% detection rate. This could be achieved by simultaneously time averaging over 30 min and spatially averaging to vertical bin lengths of 375 m, or by modifying the hardware. We repeated the analysis for under- and overestimated aerosol lidar ratio (Laer), and found that possible systematic errors did not affect the detection rate. Further studies are necessary to assess whether such long-time averages are feasible in the Amazon region (given the very high cloud cover), and to design a hardware upgrade. Although simulations and analyses here were based on a particular instrument and for the presence of new organic particles in the Amazonian upper troposphere, our methodology and results are general and applicable to other instruments and sites.
      Citation: Remote Sensing
      PubDate: 2022-10-01
      DOI: 10.3390/rs14194913
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4914: Hyperspectral Reconnaissance: Joint
           Characterization of the Spectral Mixture Residual Delineates Geologic Unit
           Boundaries in the White Mountains, CA

    • Authors: Francis J. Sousa, Daniel J. Sousa
      First page: 4914
      Abstract: We use a classic locale for geology education in the White Mountains, CA, to demonstrate a novel approach for using imaging spectroscopy (hyperspectral imaging) to generate base maps for the purpose of geologic mapping. The base maps produced in this fashion are complementary to, but distinct from, maps of mineral abundance. The approach synthesizes two concepts in imaging spectroscopy data analysis: the spectral mixture residual and joint characterization. First, the mixture residual uses a linear, generalizable, and physically based continuum removal model to mitigate the confounding effects of terrain and vegetation. Then, joint characterization distinguishes spectrally distinct geologic units by isolating residual, absorption-driven spectral features as nonlinear manifolds. Compared to most traditional classifiers, important strengths of this approach include physical basis, transparency, and near-uniqueness of result. Field validation confirms that this approach can identify regions of interest that contribute significant complementary information to PCA alone when attempting to accurately map spatial boundaries between lithologic units. For a geologist, this new type of base map can complement existing algorithms in exploiting the coming availability of global hyperspectral data for pre-field reconnaissance and geologic unit delineation.
      Citation: Remote Sensing
      PubDate: 2022-10-01
      DOI: 10.3390/rs14194914
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4915: Multibranch Unsupervised Domain
           Adaptation Network for Cross Multidomain Orchard Area Segmentation

    • Authors: Ming Liu, Dong Ren, Hang Sun, Simon X. Yang
      First page: 4915
      Abstract: Although unsupervised domain adaptation (UDA) has been extensively studied in remote sensing image segmentation tasks, most UDA models are designed based on single-target domain settings. Large-scale remote sensing images often have multiple target domains in practical applications, and the simple extension of single-target UDA models to multiple target domains is unstable and costly. Multi-target unsupervised domain adaptation (MTUDA) is a more practical scenario that has great potential for solving the problem of crossing multiple domains in remote sensing images. However, existing MTUDA models neglect to learn and control the private features of the target domain, leading to missing information and negative migration. To solve these problems, this paper proposes a multibranch unsupervised domain adaptation network (MBUDA) for orchard area segmentation. The multibranch framework aligns multiple domain features, while preventing private features from interfering with training. We introduce multiple ancillary classifiers to help the model learn more robust latent target domain data representations. Additionally, we propose an adaptation enhanced learning strategy to reduce the distribution gaps further and enhance the adaptation effect. To evaluate the proposed method, this paper utilizes two settings with different numbers of target domains. On average, the proposed method achieves a high IoU gain of 7.47% over the baseline (single-target UDA), reducing costs and ensuring segmentation model performance in multiple target domains.
      Citation: Remote Sensing
      PubDate: 2022-10-01
      DOI: 10.3390/rs14194915
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4916: Multidirectional Shift Rasterization
           (MDSR) Algorithm for Effective Identification of Ground in Dense Point

    • Authors: Štroner, Urban, Línková
      First page: 4916
      Abstract: With the ever-increasing popularity of unmanned aerial vehicles and other platforms providing dense point clouds, filters for the identification of ground points in such dense clouds are needed. Many filters have been proposed and are widely used, usually based on the determination of an original surface approximation and subsequent identification of points within a predefined distance from such surface. We presented a new filter, the multidirectional shift rasterization (MDSR) algorithm, which is based on a different principle, i.e., on the identification of just the lowest points in individual grid cells, shifting the grid along both the planar axis and subsequent tilting of the entire grid. The principle was presented in detail and both visually and numerically compared with other commonly used ground filters (PMF, SMRF, CSF, and ATIN) on three sites with different ruggedness and vegetation density. Visually, the MDSR filter showed the smoothest and thinnest ground profiles, with the ATIN the only filter comparably performing. The same was confirmed when comparing the ground filtered by other filters with the MDSR-based surface. The goodness of fit with the original cloud is demonstrated by the root mean square deviations (RMSDs) of the points from the original cloud found below the MDSR-generated surface (ranging, depending on the site, between 0.6 and 2.5 cm). In conclusion, this paper introduced a newly developed MDSR filter that outstandingly performed at all sites, identifying the ground points with great accuracy while filtering out the maximum of vegetation and above-ground points and outperforming the aforementioned widely used filters. The filter dilutes the cloud somewhat; in such dense point clouds, however, this can be perceived as a benefit rather than as a disadvantage.
      Citation: Remote Sensing
      PubDate: 2022-10-01
      DOI: 10.3390/rs14194916
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4917: An Improved RANSAC Outlier Rejection
           Method for UAV-Derived Point Cloud

    • Authors: Bahram Salehi, Sina Jarahizadeh, Amin Sarafraz
      First page: 4917
      Abstract: A common problem with matching algorithms, in photogrammetry and computer vision, is the imperfection of finding all correct corresponding points, so-called inliers, and, thus, resulting in incorrect or mismatched points, so-called outliers. Many algorithms, including the well-known randomized random sample consensus (RANSAC)-based matching, have been developed focusing on the reduction of outliers. RANSAC-based methods, however, have limitations such as increased false positive rates of outliers, and, consequently resulting in fewer inliers, an unnecessary high number of iterations, and high computational time. Such deficiencies possibly result from the random sampling process, the presence of noise, and incorrect assumptions of the initial values. This paper proposes a modified version of RANSAC-based methods, called Empowered Locally Iterative SAmple Consensus (ELISAC). ELISAC improves RANSAC by utilizing three basic modifications individually or in combination. These three modifications are (a) to increase the stability and number of inliers using two Locally Iterative Least Squares (LILS) loops (Basic LILS and Aggregated-LILS), based on the new inliers in each loop, (b) to improve the convergence rate and consequently reduce the number of iterations using a similarity termination criterion, and (c) to remove any possible outliers at the end of the processing loop and increase the reliability of results using a post-processing procedure. In order to validate our proposed method, a comprehensive experimental analysis has been done on two datasets. The first dataset contains the commonly-used computer vision image pairs on which the state-of-the-art RANSAC-based methods have been evaluated. The second dataset image pairs were captured by a drone over a forested area with various rotations, scales, and baselines (from short to wide). The results show that ELISAC finds more inliers with a faster speed (lower computational time) and lower error (outlier) rates compared to M-estimator SAmple Consensus (MSAC). This makes ELISAC an effective approach for image matching and, consequently, for 3D information extraction of very high and super high-resolution imagery acquired by space-borne, airborne, or UAV sensors. In particular, for applications such as forest 3D modeling and tree height estimations where standard matching algorithms are problematic due to spectral and textural similarity of objects (e.g., trees) on image pairs, ELISAC can significantly outperform the standard matching algorithms.
      Citation: Remote Sensing
      PubDate: 2022-10-01
      DOI: 10.3390/rs14194917
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4918: Assessment and Calibration of ERA5
           Severe Winds in The Atlantic Ocean using Satellite Data

    • Authors: Ricardo M. Campos, Carolina B. Gramcianinov, Ricardo de Camargo, Pedro L. da Silva Dias
      First page: 4918
      Abstract: In this paper, we analyze the surface winds of ECMWF ERA5 reanalysis in the Atlantic Ocean. The first part addresses a reanalysis validation, studying the spatial distribution of the errors and the performance as a function of the percentiles, with a further investigation under cyclonic conditions. The second part proposes and compares two calibration models, a simple least-squares linear regression (LR) and the quantile mapping method (QM). Our results indicate that ERA5 provides high-quality winds for non-extreme conditions, especially at the eastern boundaries, with bias between −0.5 and 0.3 m/s and RMSE below 1.5 m/s. The reanalysis errors are site-dependent, where large RMSE and severe underestimation are found in tropical latitudes and locations following the warm currents. The most extreme winds in tropical cyclones show the worst results, with RMSE above 5 m/s. Apart from these areas, the strong winds at extratropical locations are well represented. The bias-correction models have proven to be very efficient in removing systematic bias. The LR works well for low-to-mild wind intensities while the QM is better for the upper percentiles and winds above 15 m/s—an improvement of 10% in RMSE and 50% for the bias compared to the original reanalysis is reported.
      Citation: Remote Sensing
      PubDate: 2022-10-01
      DOI: 10.3390/rs14194918
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4919: Classifying Sparse Vegetation in a
           Proglacial Valley Using UAV Imagery and Random Forest Algorithm

    • Authors: Ulrich Zangerl, Stefan Haselberger, Sabine Kraushaar
      First page: 4919
      Abstract: Extreme hydro-meteorological events become an increasing risk in high mountain environments, resulting in erosion events that endanger human infrastructure and life. Vegetation is known to be an important stabilizing factor; however, little is known about the spatial patterns of species composition in glacial forelands. This investigation aims to differentiate sparse vegetation in a steep alpine environment in the Austrian part of the Central Eastern Alps using low-cost multispectral cameras on an unmanned aerial vehicle (UAV). Highly resolved imagery from a consumer-grade UAV proved an appropriate basis for the SfM-based modeling of the research area as well as for vegetation mapping. Consideration must be paid to changing light conditions during data acquisition, especially with multispectral sensors. Different approaches were tested, and the best results were obtained using the Random Forest (RF) algorithm with the target class discrimination based on the RGB orthomosaic and the DEM as supplementary dataset. Our work contributes to the field of biogeomorphic research in proglacial areas as well as to the field of small-scale remote sensing and vegetation measuring. Our findings show that the occurrence of vegetation patches differs in terms of density and diversity within this relatively recent deglaciated environment.
      Citation: Remote Sensing
      PubDate: 2022-10-01
      DOI: 10.3390/rs14194919
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4920: Multi-Modal Feature Fusion Network
           with Adaptive Center Point Detector for Building Instance Extraction

    • Authors: Qinglie Yuan, Helmi Zulhaidi Mohd Shafri
      First page: 4920
      Abstract: Building information extraction utilizing remote sensing technology has vital applications in many domains, such as urban planning, cadastral mapping, geographic information censuses, and land-cover change analysis. In recent years, deep learning algorithms with strong feature construction ability have been widely used in automatic building extraction. However, most methods using semantic segmentation networks cannot obtain object-level building information. Some instance segmentation networks rely on predefined detectors and have weak detection ability for buildings with complex shapes and multiple scales. In addition, the advantages of multi-modal remote sensing data have not been effectively exploited to improve model performance with limited training samples. To address the above problems, we proposed a CNN framework with an adaptive center point detector for the object-level extraction of buildings. The proposed framework combines object detection and semantic segmentation with multi-modal data, including high-resolution aerial images and LiDAR data, as inputs. Meanwhile, we developed novel modules to optimize and fuse multi-modal features. Specifically, the local spatial–spectral perceptron can mutually compensate for semantic information and spatial features. The cross-level global context module can enhance long-range feature dependence. The adaptive center point detector explicitly models deformable convolution to improve detection accuracy, especially for buildings with complex shapes. Furthermore, we constructed a building instance segmentation dataset using multi-modal data for model training and evaluation. Quantitative analysis and visualized results verified that the proposed network can improve the accuracy and efficiency of building instance segmentation.
      Citation: Remote Sensing
      PubDate: 2022-10-01
      DOI: 10.3390/rs14194920
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4921: Water Quality and Water Hyacinth
           Monitoring with the Sentinel-2A/B Satellites in Lake Tana (Ethiopia)

    • Authors: Tadesse Mucheye, Sara Haro, Sokratis Papaspyrou, Isabel Caballero
      First page: 4921
      Abstract: Human activities coupled with climate change impacts are becoming the main factors in decreasing inland surface water quantity and quality, leading to the disturbance of the aquatic ecological balance. Under such conditions, the introduction and proliferation of aquatic invasive alien species are more likely to occur. Hence, frequent surface water quality monitoring is required for aquatic ecosystem sustainability. The main objectives of the present study are to analyze the seasonal variation in the invasive plant species water hyacinth (Pontederia crassipes) and biogeochemical water quality parameters, i.e., chlorophyll-a (Chl-a) and total suspended matter (TSM), and to examine their relationship in Lake Tana (Ethiopia) during a one-year study period (2020). Sentinel-2A/B satellite images are used to monitor water hyacinth expansion and Chl-a and TSM concentrations in the water. The Case 2 Regional Coast Colour processor (C2RCC) is used for atmospheric and sunglint correction over inland waters, while the Sen2Cor atmospheric processor is used to calculate the normalized difference vegetation index (NDVI) for water hyacinth mapping. The water hyacinth cover and biomass are determined by NDVI values ranging from 0.60 to 0.95. A peak in cover and biomass is observed in October 2020, just a month after the peak of Chl-a (25.2 mg m−3) and TSM (62.5 g m−3) concentrations observed in September 2020 (end of the main rainy season). The influx of sediment and nutrient load from the upper catchment area during the rainy season could be most likely responsible for both Chl-a and TSM increased concentrations. This, in turn, created a fertile situation for water hyacinth proliferation in Lake Tana. Overall, the freely available Sentinel-2 satellite imagery and appropriate atmospheric correction processors are an emerging potent tool for inland water monitoring and management in large-scale regions under a global change scenario.
      Citation: Remote Sensing
      PubDate: 2022-10-01
      DOI: 10.3390/rs14194921
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4922: Simulation Performance and Case Study
           of Extreme Events in Northwest China Using the BCC-CSM2 Model

    • Authors: Minhong Song, Yufei Pei, Shaobo Zhang, Tongwen Wu
      First page: 4922
      Abstract: The BCC-CSM2 model is the second generation of the Beijing Climate Center Climate System Model developed by the National Center of China Meteorological Administration. Using the outputs of two versions of the BCC-CSM2 model with different resolutions, namely: BCC-CSM2-MR and BCC-CSM2-HR, their performance in simulating the climate characteristics of Northwest China was compared. The BCC-CSM2-HR had a better ability to simulate the detailed distribution of the average temperature and precipitation in Northwest China, and could delineate the influence of the topography in detail. The extreme events in Northwest China were evaluated further using the BCC-CSM2-HR and the observation data from China Meteorological Data Center. The BCC-CSM2-HR provided a good simulation of the spatial distribution of extreme climate events in Northwest China, and the spatial distribution of TXx, TNx, TXn, and TNn in Northwest China show closer proximity to the observation than that of TX90p, TN90p, TX10p, and TN10p, even in the case of extreme heavy precipitation. This case study of the extreme weather events showed that the BCC-CSM2-HR model had the best simulation performance for extreme high temperature events in Northwest China, followed by extreme low temperature events, and had the worst simulation ability for extreme precipitation events.
      Citation: Remote Sensing
      PubDate: 2022-10-01
      DOI: 10.3390/rs14194922
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4923: Recent Seasonal Spatiotemporal
           Variations in Alpine Glacier Surface Elevation in the Pamir

    • Authors: Weibing Du, Yanchao Zheng, Yangyang Li, Anming Bao, Junli Li, Dandan Ma, Xin Gao, Yaming Pan, Shuangting Wang
      First page: 4923
      Abstract: Climate change can lead to seasonal surface elevation variations in alpine glaciers. This study first uses DEM (Digital Elevation Model) of Pamir glaciers to develop a denoising model for laser altimetry of ICESat-2 footprints, which reduces the standard deviation of the differences between ICESat-2 footprints and corresponding datum DEM from 13.9 to 3.6 m. Second, the study constructs a calibration processing model for solving the problem that laser footprints obtained at different times have inconsistent plane positions. We calculates plane position and elevation differences between the two laser footprints in the local area of 0.05 × 0.05° from 2018 to 2021. The elevations constructed by laser footprints shows a strong correlation with the datum elevation over the different periods, and effectively preserve the time-series variation information of glacier surface elevation (GSE). Based on these two models, the spatiotemporal variations of the surface elevation of the Pamir glaciers is established as a function of seasons. There are three main conclusions: (1) The GSE in the Pamir increased slightly from 2018 to 2021 at an average rate of +0.02 ± 0.01 m/yr. The time series with elevation increase was located exactly on the glacial ablation zone, and the time series with elevation decrease occurred on the glacial accumulation zone. Both observations demonstrate the surge state of the glacier. (2) The Pamir eastern (Zone I) and northwestern (Zone III) regions had large glacier accumulation areas. GSE in these two regions has increased in recent years at yearly rates of +0.25 ± 0.13 and +0.06 ± 0.04 m/yr, respectively. In contrast, the GSE of small glaciers in Zones II and IV has decreased at a yearly rate of −0.96 ± 0.37 and −0.24 ± 0.18 m/yr, respectively. Climate was the primary factor influencing the increase in GSE in Zones I and III. The westerly circulation had been reinforced in recent years, and precipitation had increased dramatically at a rate of +0.99 mm/yr in the northwestern section of the Pamir; this was the primary cause of the increase in GSE. (3) The increased precipitation and decreased temperature were both important factors causing an overall +0.02 ± 0.01 m/yr variation of GSE in this region. The GSE in the four sub-regions showed different variation trends because of variations in temperature and precipitation. The external causes that affected the increase in GSE in the region included an average yearly temperature decrease at the rate of 0.54 ± 0.36 °C/yr and a total yearly precipitation increase of 0.46 ± 0.29 mm/yr in the study area from 2018 to 2021.
      Citation: Remote Sensing
      PubDate: 2022-10-01
      DOI: 10.3390/rs14194923
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4924: Retrieval of Chlorophyll-a
           Concentrations Using Sentinel-2 MSI Imagery in Lake Chagan Based on
           Assessments with Machine Learning Models

    • Authors: Xuming Shi, Lingjia Gu, Tao Jiang, Xingming Zheng, Wen Dong, Zui Tao
      First page: 4924
      Abstract: Chlorophyll-a (Chl-a) is an important characterized parameter of lakes. Monitoring it accurately through remote sensing is thus of great significance for early warnings of water eutrophication. Sentinel Multispectral Imager (MSI) images from May to September between 2020 and 2021 were used along with in-situ measurements to estimate Chl-a in Lake Chagan, which is located in Jilin Province, Northeast China. In this study, the extreme gradient boosting (XGBoost) and Random Forest (RF) models, which had similar performances, were generated by six single bands and six band combinations. The RF model was then selected based on the assessments (R2 = 0.79, RMSE = 2.51 μg L−1, MAPE = 9.86%), since its learning of the input features in the model conformed to the bio-optical properties of Case 2 waters. The study considered Chl-a concentrations in Lake Chagan as a seasonal pattern according to the K-Nearest-Neighbors (KNN) classification. The RF model also showed relatively stable performance for three seasons (spring, summer and autumn) and it was applied to map Chl-a in the whole lake. The research presents a more reliable machine learning (ML) model with higher precision than previous empirical models, as shown by the effects of the input features linked with the biological mechanisms of Chl-a. Its robustness was revealed by the temporal and spatial distributions of Chl-a concentrations, which were consistent with in-situ measurements in the map. This research was capable of revealing the current ecological situation in Lake Chagan and can serve as a reference in remote sensing of inland lakes.
      Citation: Remote Sensing
      PubDate: 2022-10-01
      DOI: 10.3390/rs14194924
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4925: PerDet: Machine-Learning-Based UAV
           GPS Spoofing Detection Using Perception Data

    • Authors: Xiaomin Wei, Yao Wang, Cong Sun
      First page: 4925
      Abstract: To ensure that unmanned aerial vehicle (UAV) positioning is not affected by GPS spoofing signals, we propose PerDet, a perception-data-based UAV GPS spoofing detection approach utilizing machine learning algorithms. Based on the principle of the position estimation process and attitude estimation process, we choose the data gathered by the accelerometer, gyroscope, magnetometer, GPS and barometer as features. Although these sensors have different shortcomings, their variety makes sure that the selected perception data can compensate for each other. We collect the experimental data through real flights, which make PerDet more practical. Furthermore, we run various machine learning algorithms on our dataset and select the most effective classifier as the detector. Through the performance evaluation and comparison, we demonstrate that PerDet is better than existing methods and is an effective method with a detecting rate of 99.69%. For a fair comparison, we reproduce the existing method and run it on our dataset to compare the performance between this method and our PerDet approach.
      Citation: Remote Sensing
      PubDate: 2022-10-01
      DOI: 10.3390/rs14194925
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4926: Semantic Segmentation Guided
           Coarse-to-Fine Detection of Individual Trees from MLS Point Clouds Based
           on Treetop Points Extraction and Radius Expansion

    • Authors: Xiaojuan Ning, Yishu Ma, Yuanyuan Hou, Zhiyong Lv, Haiyan Jin, Yinghui Wang
      First page: 4926
      Abstract: Urban trees are vital elements of outdoor scenes via mobile laser scanning (MLS), accurate individual trees detection from disordered, discrete, and high-density MLS is an important basis for the subsequent analysis of city management and planning. However, trees cannot be easily extracted because of the occlusion with other objects in urban scenes. In this work, we propose a coarse-to-fine individual trees detection method from MLS point cloud data (PCD) based on treetop points extraction and radius expansion. Firstly, an improved semantic segmentation deep network based on PointNet is applied to segment tree points from the scanned urban scene, which combining spatial features and dimensional features. Next, through calculating the local maximum, the candidate treetop points are located. In addition, the optimized treetop points are extracted after the tree point projection plane was filtered to locate the candidate treetop points, and a distance rule is used to eliminate the pseudo treetop points then the optimized treetop points are obtained. Finally, after the initial clustering of treetop points and vertical layering of tree points, a top-down layer-by-layer segmentation based on radius expansion to realize the complete individual extraction of trees. The effectiveness of the proposed method is tested and evaluated on five street scenes in point clouds from Oakland outdoor MLS dataset. Furthermore, the proposed method is compared with two existing individual trees segmentation methods. Overall, the precision, recall, and F-score of instance segmentation are 98.33%, 98.33%, and 98.33%, respectively. The results indicate that our method can extract individual trees effectively and robustly in different complex environments.
      Citation: Remote Sensing
      PubDate: 2022-10-01
      DOI: 10.3390/rs14194926
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4927: Factors Controlling a Synthetic
           Aperture Radar (SAR) Derived Root-Zone Soil Moisture Product over The
           Seward Peninsula of Alaska

    • Authors: Julian Dann, Katrina E. Bennett, W. Robert Bolton, Cathy J. Wilson
      First page: 4927
      Abstract: Root-zone soil moisture exerts a fundamental control on vegetation, energy balance, and the carbon cycle in Arctic ecosystems, but it is still not well understood in vast, remote, and understudied regions of discontinuous permafrost. The root-zone soil moisture product (30 m resolution) used in this analysis was retrieved from a time-series P-Band (420–440 MHz) synthetic aperture radar (SAR) backscatter observations (August 2017 & October 2017). While similar approaches have been taken to retrieve surface (0 cm to 5 cm) soil moisture from L-Band (1.2 GHz) SAR backscatter, this is one of the first known attempts at reaching the root-zone in permafrost regions. Here, we analyze secondary factors (excluding primary factors, such as precipitation) controlling summer (August) soil moisture at depths of 6 cm, 12 cm, and 20 cm over a 4500 km2 area on the Seward Peninsula of Alaska. Using a random forest model, we quantify the impact of topography, vegetation, and meteorological factors on soil moisture distributions. In developing the random forest model, we explore a variety of feature scales (30 m, 60 m, 90 m, 120 m, 180 m, and 240 m), tune hyperparameters (the structure of individual decision trees making up the ensemble including the number and depth of trees), and perform the final feature selection using cross-validated recursive feature elimination. Results suggest that root-zone soil moisture on the Seward Peninsula is primarily controlled by vegetation at 6 cm, but deeper in the soil column topography and meteorological factors, such as predominant winter wind direction and summer insolation, play a larger role. The random forest model accounts for 40% to 60% of the variation observed (R2 = 0.44 at 6 cm, R2 = 0.52 at 12 cm, R2 = 0.58 at 20 cm). These results indicate that vegetation is the dominant control on soil moisture shallow in the soil column, but the impact of vegetation does not extend to deeper layers retrieved from P-Band SAR backscatter.
      Citation: Remote Sensing
      PubDate: 2022-10-02
      DOI: 10.3390/rs14194927
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4928: Review of Ship Collision Avoidance
           Guidance Algorithms Using Remote Sensing and Game Control

    • Authors: Józef Lisowski
      First page: 4928
      Abstract: This work provides a mathematical description of a process game for the safe driving of a ship that encounters other ships. State and control constraint variables, as well as a set of acceptable ship tactics, are taken into consideration. Multi-criteria optimization operations are developed as positional and matrix games, based on cooperative, non-cooperative, and classical (non-game) optimal steering control. Adequate algorithms for ship collision avoidance, relating to the above operations, are developed and verified through digital simulation of a real navigational situation using MATLAB/Simulink.
      Citation: Remote Sensing
      PubDate: 2022-10-02
      DOI: 10.3390/rs14194928
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4929: Patterns, Dynamics, and Drivers of
           Soil Available Nitrogen and Phosphorus in Alpine Grasslands across the
           QingZang Plateau

    • Authors: Yuchuan He, Jian Sun, Junnan Xiong, Hua Shang, Xin Wang
      First page: 4929
      Abstract: Soil available nutrient contents are critical for regulating ecosystem structure and function; therefore, exploring patterns, dynamics, and drivers of soil available nutrient contents is helpful for understanding the geochemical cycle at the regional scale. However, learning the patterns and dynamics of soil available nutrients across a regional scale is quite limited, especially the soil available nitrogen (SAN) and soil available phosphorus (SAP) in alpine grasslands. In this study, we used machine learning (Random Forest) to map the SAN and SAP at a soil depth of 0–30 cm in alpine grasslands across the QingZang Plateau (QZP) in 2015. Our results showed that the current (2015) contents of the SAN and SAP in alpine grasslands on the QZP were 139.96 mg kg−1 and 2.63 mg kg−1, respectively. Compared to the 1980s, the SAN significantly increased by 18.12 mg kg−1 (14.83%, p < 0.05) and the SAP decreased by 1.71 mg kg−1 (39.40%, p < 0.05). The SAN and SAP contents of alpine meadows were higher than those of alpine steppes. The increases in SAN were not significantly (p > 0.05) different between those two grassland types, while the decrease in SAP was significantly (p < 0.05) higher in alpine meadows than in alpine grasslands. Combined with redundancy analysis, we quantified the impact of environmental drivers, and 80% of the spatial variation in SAN and SAP could be explained by environmental factors. Our findings also highlighted that in the context of global change, the increase in SAP and decrease in SAP might lead to weakening of nitrogen limitation and intensification of phosphorus limitation, especially in alpine meadows. In general, this study expanded the knowledge about the patterns and dynamics of SAN and SAP, and deepened the understanding of the driving mechanisms, which provided a basis for sustainable management of grasslands and optimization of ecological security barrier functions on the QZP.
      Citation: Remote Sensing
      PubDate: 2022-10-02
      DOI: 10.3390/rs14194929
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4930: Characterizing Spatiotemporal
           Patterns of Winter Wheat Phenology from 1981 to 2016 in North China by
           Improving Phenology Estimation

    • Authors: Shuai Wang, Jin Chen, Miaogen Shen, Tingting Shi, Licong Liu, Luyun Zhang, Qi Dong, Cong Wang
      First page: 4930
      Abstract: Phenology provides important information for wheat growth management and the estimation of wheat yield and quality. The relative threshold method has been widely used to retrieve phenological metrics from remotely sensed data owing to its simplicity. However, the thresholds vary substantially among phenological metrics and locations, hampering us from effectively detecting spatial and temporal variations in winter wheat phenology. In this study, we developed a calibrated relative threshold method based on ground phenological observations. Compared with the traditional relative threshold method, our method can minimize the bias and uncertainty caused by unreasonable thresholds in determining phenological dates. On this basis, seven key phenological dates and three growth periods of winter wheat were estimated from long-term series (1981–2016) of the remotely sensed Normalized Difference Vegetation Index for North China (106°18′–122°41′E, 28°59′–39°57′N). Results show that the pre-wintering phenological dates of winter wheat (i.e., emergence and tillering) occurred in December in the south and in mid- to late- October in the north, while the post-wintering phenological dates (i.e., green-up onset, jointing, heading, milky stage, and maturity) exhibited the opposite pattern, that is, January to May in the south and February to June in the north. Consequently, the vegetative growth period increased from 49 days in the south to 77 in the north, and the reproductive growth period decreased from 51 days to 29 days. At the regional scale, all winter wheat phenological dates predominantly advanced, with the most pronounced advancement being for green-up onset (–0.10 days/year, P > 0.1), emergence (–0.09 days/year, P > 0.1), and jointing (–0.08, P > 0.1 days/year). The vegetative growth period and reproductive growth period at the regional scale predominantly extended by 0.03 (P > 0.1) and 0.09 (P < 0.001) days/year, respectively. In general, the later phenological events (i.e., heading, milky stage, and maturity) tended to advance with higher temperature, while the earlier phenological events (i.e., emergence, tillering, green-up onset, and jointing) showed a weak correlation with temperature, suggesting that the earlier events might be mainly affected by management while later ones were more responsive to warming. These findings provide a critical reference for improving winter wheat management under the ongoing climate warming.
      Citation: Remote Sensing
      PubDate: 2022-10-02
      DOI: 10.3390/rs14194930
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4931: High-Resolution Inversion Method for
           the Snow Water Equivalent Based on the GF-3 Satellite and Optimized EQeau

    • Authors: Yichen Yang, Shifeng Fang, Hua Wu, Jiaqiang Du, Xiaohu Wang, Rensheng Chen, Yongqiang Liu, Hao Wang
      First page: 4931
      Abstract: High-resolution snow water equivalent studies are important for obtaining a clear picture of the potential of water resources in arid areas, and SAR-based sensors can achieve meter-level snow water equivalent inversion. The advanced C-band SAR satellite Gaofen-3 (GF-3) can now achieve meter-level observations of the same area within one day and has great potential for the inversion of the snow water equivalent. The EQeau model is an empirical method for snow water equivalent inversion using C-band SAR satellites, but the model has major accuracy problems. In this paper, the EQeau model is improved by using classification of underlying surface types and polarization decomposition, and the inversion of the snow water equivalent was also completed using the new data source GF-3 input model. The results found that: (1) the classification of underlying surface types can significantly improve the fit between the snow thermal resistance and the backscattering coefficient ratio; (2) the accuracy of the snow density extracted by the GF-3 satellite using the Singh–Cloude Three-Component Hybrid (S3H) decomposition is better than IDW spatial interpolation, and the overall RMSE can reach 0.005 g/cm3; (3) the accuracy of the optimized EQeau model is significantly improved, and the overall MRE is reduced from 27.4% to 10.3%. Compared with the original model, the optimized model is superior both in terms of verification accuracy and image detail. In the future, with the combination of advanced technologies such as the Internet of Things (IoT), long, gapless, all-weather, and high-resolution snow water equivalent inversion can be achieved, which is conducive to the realization of all-weather monitoring of the regional snow water equivalent.
      Citation: Remote Sensing
      PubDate: 2022-10-02
      DOI: 10.3390/rs14194931
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4932: Recognition of Sago Palm Trees Based
           on Transfer Learning

    • Authors: Sri Murniani Angelina Letsoin, Ratna Chrismiari Purwestri, Fajar Rahmawan, David Herak
      First page: 4932
      Abstract: Sago palm tree, known as Metroxylon Sagu Rottb, is one of the priority commodities in Indonesia. Based on our previous research, the potential habitat of the plant has been decreasing. On the other hand, while the use of remote sensing is now widely developed, it is rarely applied for detection and classification purposes, specifically in Indonesia. Considering the potential use of the plant, local farmers identify the harvest time by using human inspection, i.e., by identifying the bloom of the flower. Therefore, this study aims to detect sago palms based on their physical morphology from Unmanned Aerial Vehicle (UAV) RGB imagery. Specifically, this paper endeavors to apply the transfer learning approach using three deep pre-trained networks in sago palm tree detection, namely, SqueezeNet, AlexNet, and ResNet-50. The dataset was collected from nine different groups of plants based on the dominant physical features, i.e., leaves, flowers, fruits, and trunks by using a UAV. Typical classes of plants are randomly selected, like coconut and oil palm trees. As a result, the experiment shows that the ResNet-50 model becomes a preferred base model for sago palm classifiers, with a precision of 75%, 78%, and 83% for sago flowers (SF), sago leaves (SL), and sago trunk (ST), respectively. Generally, all of the models perform well for coconut trees, but they still tend to perform less effectively for sago palm and oil palm detection, which is explained by the similarity of the physical appearance of these two palms. Therefore, based our findings, we recommend improving the optimized parameters, thereby providing more varied sago datasets with the same substituted layers designed in this study.
      Citation: Remote Sensing
      PubDate: 2022-10-02
      DOI: 10.3390/rs14194932
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4933: Use of Remote Sensing Techniques to
           Estimate Plant Diversity within Ecological Networks: A Worked Example

    • Authors: Francesco Liccari, Maurizia Sigura, Giovanni Bacaro
      First page: 4933
      Abstract: As there is an urgent need to protect rapidly declining global diversity, it is important to identify methods to quickly estimate the diversity and heterogeneity of a region and effectively implement monitoring and conservation plans. The combination of remotely sensed and field-collected data, under the paradigm of the Spectral Variation Hypothesis (SVH), represents one of the most promising approaches to boost large-scale and reliable biodiversity monitoring practices. Here, the potential of SVH to capture information on plant diversity at a fine scale in an ecological network (EN) embedded in a complex landscape has been tested using two new and promising methodological approaches: the first estimates α and β spectral diversity and the latter ecosystem spectral heterogeneity expressed as Rao’s Quadratic heterogeneity measure (Rao’s Q). Both approaches are available thanks to two brand-new R packages: “biodivMapR” and “rasterdiv”. Our aims were to investigate if spectral diversity and heterogeneity provide reliable information to assess and monitor over time floristic diversity maintained in an EN selected as an example and located in northeast Italy. We analyzed and compared spectral and taxonomic α and β diversities and spectral and landscape heterogeneity, based on field-based plant data collection and remotely sensed data from Sentinel-2A, using different statistical approaches. We observed a positive relationship between taxonomic and spectral diversity and also between spectral heterogeneity, landscape heterogeneity, and the amount of alien species in relation to the native ones, reaching a value of R2 = 0.36 and R2 = 0.43, respectively. Our results confirmed the effectiveness of estimating and mapping α and β spectral diversity and ecosystem spectral heterogeneity using remotely sensed images. Moreover, we highlighted that spectral diversity values become more effective to identify biodiversity-rich areas, representing the most important diversity hotspots to be preserved. Finally, the spectral heterogeneity index in anthropogenic landscapes could be a powerful method to identify those areas most at risk of biological invasion.
      Citation: Remote Sensing
      PubDate: 2022-10-02
      DOI: 10.3390/rs14194933
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4934: Crop Water Productivity Mapping and

    • Authors: Ali Karbalaye Ghorbanpour, Isaya Kisekka, Abbas Afshar, Tim Hessels, Mahdi Taraghi, Behzad Hessari, Mohammad J. Tourian, Zheng Duan
      First page: 4934
      Abstract: Scarce water resources present a major hindrance to ensuring food security. Crop water productivity (WP), embraced as one of the Sustainable Development Goals (SDGs), is playing an integral role in the performance-based evaluation of agricultural systems and securing sustainable food production. This study aims at developing a cloud-based model within the Google Earth Engine (GEE) based on Landsat -7 and -8 satellite imagery to facilitate WP mapping at regional scales (30-m resolution) and analyzing the state of the water use efficiency and productivity of the agricultural sector as a means of benchmarking its WP and defining local gaps and targets at spatiotemporal scales. The model was tested in three major agricultural districts in the Lake Urmia Basin (LUB) with respect to five crop types, including irrigated wheat, rainfed wheat, apples, grapes, alfalfa, and sugar beets as the major grown crops. The actual evapotranspiration (ET) was estimated using geeSEBAL based on the Surface Energy Balance Algorithm for Land (SEBAL) methodology, while for crop yield estimations Monteith’s Light Use Efficiency model (LUE) was employed. The results indicate that the WP in the LUB is below its optimum targets, revealing that there is a significant degree of work necessary to ameliorate the WP in the LUB. The WP varies between 0.49–0.55 (kg/m3) for irrigated wheat, 0.27–0.34 for rainfed wheat, 1.7–2.2 for apples, 1.2–1.7 for grapes, 5.5–6.2 for sugar beets, and 0.67–1.08 for alfalfa, which could be potentially increased up to 80%, 150%, 76%, 83%, 55%, and 48%, respectively. The spatial variation of the WP and crop yield makes it feasible to detect the areas with the best and poorest on-farm practices, thereby facilitating the better targeting of resources to bridge the WP gap through water management practices. This study provides important insights into the status and potential of WP with possible worldwide applications at both farm and government levels for policymakers, practitioners, and growers to adopt effective policy guidelines and improve on-farm practices.
      Citation: Remote Sensing
      PubDate: 2022-10-02
      DOI: 10.3390/rs14194934
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4935: Combined Effects of the ENSO and the
           QBO on the Ozone Valley over the Tibetan Plateau

    • Authors: Shujie Chang, Yongchi Li, Chunhua Shi, Dong Guo
      First page: 4935
      Abstract: The El Niño–Southern Oscillation (ENSO) and the quasi-biennial oscillation (QBO) are two major interannual variations observed in the tropics, yet the joint modulation of the ENSO and QBO on the ozone valley over the Tibetan Plateau (TP) in summer has not been performed. This study investigates the combined effects of the ENSO and the QBO on the interannual variations of the ozone valley over the TP using the ERA5 reanalysis data from 1979 to 2021. The results show that the ENSO leads the zonal deviation of the total column ozone (TCO*) over the TP by about 6 months. This means the TCO* in the summer of the following year is affected by the ENSO in the current year. This is consistent with the theory of recharge oscillation. In terms of dynamic conditions, the anomalous circulation resulting from the combined effect of El Niño and the easterly phase of the QBO (EQBO) lead to strengthened and upward anomalies of the South Asian high (SAH) over the TP, followed by reduced ozone valley with more negative anomalies over the TP in summer. As to thermodynamic conditions, affected by both El Niño and the EQBO, the atmospheric stability shows positive anomalies from the lower troposphere to the upper troposphere, and the positive anomaly areas are larger than those in other conditions. These findings indicate an unstable atmosphere, where convection is more likely to cause ozone exchange. The turbulent mixing of ozone at low levels and high levels leads to the ozone valley over the TP, with more negative anomalies in the upper troposphere and lower stratosphere (UTLS).
      Citation: Remote Sensing
      PubDate: 2022-10-02
      DOI: 10.3390/rs14194935
      Issue No: Vol. 14, No. 19 (2022)
  • Remote Sensing, Vol. 14, Pages 4936: The Impact of Future Sea-Level Rise
           on Low-Lying Subsiding Coasts: A Case Study of Tavoliere Delle Puglie
           (Southern Italy)

    • Authors: Giovanni Scardino, Marco Anzidei, Paolo Petio, Enrico Serpelloni, Vincenzo De Santis, Angela Rizzo, Serena Isabella Liso, Marina Zingaro, Domenico Capolongo, Antonio Vecchio, Alberto Refice, Giovanni Scicchitano
      First page: 4936
      Abstract: Low-lying coastal zones are highly subject to coastal hazards as a result of sea-level rise enhanced by natural or anthropogenic land subsidence. A combined analysis using sea-level data and remote sensing techniques allows the estimation of the current rates of land subsidence and shoreline retreat, supporting the development of quantified relative sea-level projections and flood maps, which are appropriate for specific areas. This study focuses on the coastal plain of Tavoliere delle Puglie (Apulia, Southern Italy), facing the Adriatic Sea. In this area, land subsidence is mainly caused by long-term tectonic movements and sediment compaction driven by high anthropogenic pressure, such as groundwater exploitation and constructions of buildings. To assess the expected effects of relative sea-level rise for the next decades, we considered the following multidisciplinary source data: (i) sea-level-rise projections for different climatic scenarios, as reported in the Sixth Assessment Report of the Intergovernmental Panel on Climate Change, (ii) coastal topography from airborne and terrestrial LiDAR data, (iii) Vertical Land Movement (VLM) from the analysis of InSAR and GNSS data, and (iv) shoreline changes obtained from the analysis of orthophotos, historic maps, and satellite images. To assess the expected evolution of the coastal belt, the topographic data were corrected for VLM values, assuming that the rates of land subsidence will remain constant up to 2150. The sea-level-rise projections and expected flooded areas were estimated for the Shared Socioeconomic Pathways SSP1-2.6 and SSP5-8.5, corresponding to low and high greenhouse-gas concentrations, respectively. From our analysis, we estimate that in 2050, 2100, and 2150, up to 50.5 km2, 118.7 km2 and 147.7 km2 of the coast could be submerged, respectively, while beaches could retreat at rates of up to 5.8 m/yr. In this area, sea-level rise will be accelerated by natural and anthropogenic land subsidence at rates of up to −7.5 ± 1.7 mm/yr. Local infrastructure and residential areas are thus highly exposed to an increasing risk of severe inundation by storm surges and sea-level rise in the next decades.
      Citation: Remote Sensing
      PubDate: 2022-10-02
      DOI: 10.3390/rs14194936
      Issue No: Vol. 14, No. 19 (2022)
School of Mathematical and Computer Sciences
Heriot-Watt University
Edinburgh, EH14 4AS, UK
Tel: +00 44 (0)131 4513762

Your IP address:
Home (Search)
About JournalTOCs
News (blog, publications)
JournalTOCs on Twitter   JournalTOCs on Facebook

JournalTOCs © 2009-