|
Precision Agriculture
Journal Prestige (SJR): 0.778  Citation Impact (citeScore): 3 Number of Followers: 10  Hybrid journal (It can contain Open Access articles)ISSN (Print) 1573-1618 - ISSN (Online) 1385-2256 Published by Springer-Verlag  [2468 journals]
|
- Using UAV-based multispectral remote sensing imagery combined with DRIS
method to diagnose leaf nitrogen nutrition status in a fertigated apple
orchard-
Free pre-print version: Loading...
Abstract: Abstract Monitoring plant growth information by timely and effective approaches, such as UAV remote sensing, is crucial to achieve the precise nutrient management. The study investigated that the effects of irrigation levels (Full irrigation and deficit irrigation) and nitrogen rates (0, 120, 240 and 360 kg N ha−1) on leaf nutrient (NPK) content and mainly assessed the capacity of UAV-based multispectral imagery to quantify the leaf NPK content. The UAV multi-spectral indices were used to perform ordinary linear regression (OLR), multivariate stepwise regression (MSR) and ridge regression (RR) inversion model on leaf NPK content, and further combining the diagnosis and recommendation integrated system (DRIS) with the optimal inversion model of leaf NPK content to diagnose the leaf nitrogen (N) nutrition status. The results indicated that three inversion models of LNC at a single stage had indicated that it was suitable to use UAV-based multispectral imagery to assess LNC before the early fruit expansion stage (R2 = 0.52–0.76), but not stages after that (R2 < 0.5). the MSR and RR inversion models with pooling data from multiple stages of the LPC (R2 = 0.67 and 0.69) and LKC (R2 = 0.76 and 0.76) produced better performance, while that of LNC was poor (R2 = 0.49 and 0.50). The DRIS analysis shown that the LNC of 360 kg ha−1 under two irrigation levels was not deficient in shoot growth stage and early fruit enlargement stage, while it was deficient in young fruit. Moreover, the LNC of other treatments was deficient in three growth stages. Combining the remote-sensed models for assessing leaf NPK content and DRIS method to diagnose leaf N nutrition status has the potential to guide precise N application in fertigated apple orchards.
PubDate: 2023-12-01
-
- Impact of soil electrical conductivity-based site-specific seeding and
uniform rate seeding methods on winter wheat yield parameters and economic
benefits-
Free pre-print version: Loading...
Abstract: Abstract Precision seeding which exploits the variability of soil properties in the field, is one of the most important agrotechnological solutions for smart agriculture, making it possible to increase the agronomic and economic efficiency of the production of one of the world’s most popular crops—winter wheat. The aim of this work was to investigate the impact of the site-specific-seeding (SSS) method on winter wheat yield and its productivity parameters and economic benefits compared with the conventional uniform rate seeding (URS) method. The experimental studies were carried out in a 22.4 ha field, which was divided into 5 soil management zones (MZs) based on the measured apparent electrical conductivity (ECa) with an electromagnetic induction sensor. These included MZ1 representing the highest soil ECa zone, MZ2, MZ3, and MZ4 as the medium-high, medium, and medium-low zones, respectively, and finally MZ5 as the lowest ECa zone with the lightest soil texture. The studies were carried out using two seeding methods. Under the conventional URS method, the same seeding rate of 180 kg ha−1 was applied in all MZs, while under the precision SSS method different seeding rates ranging from 146 kg ha−1 (MZ1) to 214 kg ha−1 (MZ5) were applied. Results showed that the SSS method overcome the URS in providing higher average grain yield and its yield components (e.g., the number of ears per square meter, the number of grains per ear, and the weight of 1000 grains). A particularly strong effect of seeding methods was found in the poorest soil fertility zone MZ5, where a significant difference between SSS and URS was obtained concerning plant height, straw-to-grain ratio, number of grains per ear, weight of 1000 grains, and grain yield. The cost-benefit analysis showed that the SSS approach resulted in an 8.3% higher gross margin than the URS approach. Future research is necessary to validate the results obtained in a larger number of fields having different degrees of spatial variability.
PubDate: 2023-12-01
-
- Small-target weed-detection model based on YOLO-V4 with improved backbone
and neck structures-
Free pre-print version: Loading...
Abstract: Abstract In field weed detection tasks, achieving accurate identification of crops and weeds is the primary target. However, since small target weeds among crops are not easily detected, this undoubtedly increases the difficulty of detection. In order to solve this problem, based on the YOLO-V4 network, this paper modifies the residual block of the backbone network into a Res2block residual block with a hierarchical residual mode, and constructs a new backbone network Csp2Darknet53 to enhance fine-grained feature detection; In addition, receptive field enlargement and multi-scale fusion are achieved by using the I-SPP structure with multi-branch structure and dilated convolution; Finally, a depthwise separable convolution block with residual mode (IDSC-X) is proposed to replace the original 5-time convolution block in the path aggregation network (PANet) to ensure that the original features are not completely lost and reduce the amount of parameters. Compared with FasterR-CNN, SSD, MaskR-CNN, YOLO-V3 and YOLO-V4, the improved network detection accuracy is significantly better than other networks. Compared with YOLO-V4, the AP value of small target weeds increased by 15.1%, the mAP value increased by 4.2%, and the model parameters and training weight file size decreased by 34%. The results show that the method is feasible to improve the accurate detection of small target weeds, and can be extended to weed detection tasks of different crops.
PubDate: 2023-12-01
-
- Monitoring corn nitrogen nutrition index from optical and synthetic
aperture radar satellite data and soil available nitrogen-
Free pre-print version: Loading...
Abstract: Abstract Nitrogen (N) nutrition index (NNI) is a reliable indicator of plant N status for field crops, but its determination is both labor- and cost-intensive. The utilization of remote sensing approaches for monitoring N, mainly in relevant crops such as of corn (Zea mays L.), will be critical for enhancing effective use of this nutrient. Therefore, the aim of this study was to assess NNI predicted from optical and C-band Synthetic Aperture Radar (C-SAR) satellite data and available soil N (Nav) at different vegetative growth stages for corn crop. Eleven field studies were conducted in the Pampas region (Argentina), applying five fertilizer N rates (0, 60, 120, 180, and 240 kg N ha−1), all at sowing time. Plant samples were collected at sixth-leaf (V6), tenth-leaf (V10), fourteen-leaf (V14), and flowering (R1). Using linear regression models, NNI was best predicted using only optical satellite data from V6 to V14, and integrating optical with C-SAR plus Nav at R1. The best monitoring model integrated vegetation spectral indices, C-SAR and Nav data at V10 with an adjusted R2 of 0.75 achieved during calibration in the northern Pampa. During validation, it predicted NNI with an RMSE of 0.14 and a MAPE of 12% in the southeastern Pampa. The red-edge spectrum and Local Incidence Angle of C-SAR were necessary to monitor the corn N status via prediction of NNI. Thus, this study provided empirical models to remotely sensed corn N status within fields during vegetative period, serving as a foundational data for guiding future N management.
PubDate: 2023-12-01
-
- Monitoring leaf nitrogen content in rice based on information fusion of
multi-sensor imagery from UAV-
Free pre-print version: Loading...
Abstract: Abstract Timely and accurately monitoring leaf nitrogen content (LNC) is essential for evaluating crop nutrition status. Currently, Unmanned Aerial Vehicles (UAV) imagery is becoming a potentially powerful tool of assessing crop nitrogen status in fields, but most of crop nitrogen estimates based on UAV remote sensing usually use single type imagery, the fusion information from different types of imagery has rarely been considered. In this study, the fusion images were firstly made from the simultaneously acquired digital RGB and multi-spectral images from UAV at three growth stages of rice, and then couple the selecting methods of optimal features with machine learning algorithms for the fusion images to estimate LNC in rice. Results showed that the combination with different types of features could improve the models’ accuracy effectively, the combined inputs with bands, vegetation indices (VIs) and Grey Level Co-occurrence Matrices (GLCMs) have the better performance. The LNC estimation of using fusion images was improved more obviously than multispectral those, and there was the best estimation at jointing stage based on Lasso Regression (LR), with R2 of 0.66 and RMSE of 11.96%. Gaussian Process Regression (GPR) algorithm used in combination with one feature-screening method of Minimum Redundancy Maximum Correlation (mRMR) for the fusion images, showed the better improvement to LNC estimation, with R2 of 0.68 and RMSE of 11.45%. It indicates that the information fusion from UAV multi-sensor imagery can significantly improve crop LNC estimates and the combination with multiple types of features also has a great potential for evaluating LNC in crops.
PubDate: 2023-12-01
-
- Toward automated irrigation management with integrated crop water stress
index and spatial soil water balance-
Free pre-print version: Loading...
Abstract: Abstract Decision support systems intended for precision irrigation aim at reducing irrigation applications while optimizing crop yield to achieve maximum crop water productivity (CWP). These systems incorporate on-site sensor data, remote sensing inputs, and advanced algorithms with spatial and temporal characteristics to compute precise crop water needs. The availability of variable rate irrigation (VRI) systems enables irrigation applications at a sub-field scale. The combination of an appropriate VRI system along with a precise decision support system would be ideal for improved CWP. The objective of this study was to compare and evaluate two decision support systems in terms of seasonal applied irrigation, crop yield, and CWP. This study implemented the Spatial EvapoTranspiration Modeling Interface (SETMI) model and the Irrigation Scheduling Supervisory Control and Data Acquisition (ISSCADA) system for management of a center pivot irrigation system in a 58-ha maize-soybean field during the 2020 and 2021 growing seasons. The irrigation scheduling methods included: ISSCADA plant feedback, ISSCADA hybrid, common practice, and SETMI. These methods were applied at irrigation levels of 0, 50, 100, and 150% of the full irrigation prescribed by the respective irrigation scheduling method. Data from infrared thermometers (IRTs), soil water sensors, weather stations, and satellites were used in the irrigation methods. Mean seasonal irrigation prescribed was different among the irrigation levels and methods for the 2 years. The ISSCADA plant feedback prescribed the least irrigation among the methods for majority of the cases. The common practice prescribed the largest seasonal irrigation depth among the methods for three crop-year cases. The maize yield in rainfed was found to be significantly lower than the irrigated levels in 2020 since 2020 was a dry year. No significant differences were observed in crop yield among the different irrigation methods for both years. The CWP among the different irrigation methods ranged between 2.72 and 3.15 kg m−3 for 2020 maize, 1.03 and 1.13 kg m−3 for 2020 soybean, 3.57 and 4.24 kg m−3 for 2021 maize, and 1.19 and 1.48 kg m−3 for 2021 soybean. Deficit level (50%) had the largest irrigation water productivity in all crop-year cases in this study. The ISSCADA and SETMI systems were found to reduce irrigation applications as compared to the common practice while maintaining crop yield. This study was the first to implement the newly developed integrated crop water stress index (iCWSI) thresholds and the ISSCADA system for site-specific irrigation of maize and soybean in Nebraska.
PubDate: 2023-12-01
-
- Machine learning as a tool to predict potassium concentration in soybean
leaf using hyperspectral data-
Free pre-print version: Loading...
Abstract: Abstract The soybean grain yield is affected by several factors, among them, the nutritional deficiency caused by low levels of potassium (K+) is one of the main responsible for the reduction in grain yield both in Brazil and worldwide. Traditional methods of nutrient determination involve leaf collection and laboratory procedures with toxic reagents, which is a destructive, time-consuming, expensive, and environmentally unfriendly method. In this context, the use of hyperspectral data and machine learning regression models can be a powerful tool in the nutritional diagnosis of plants. However, the comparison among different machine learning algorithms for K+ estimation in soybean leaves from hyperspectral reflectance data is yet to be reported. From this, the goal of this research was to obtain K+ prediction models in soybean leaves at different stages of development using hyperspectral data and machine learning regression models with wavelength selection algorithms. The experiment was carried out at the National Soybean Research Centre (Embrapa Soja) in the 2017/2018, 2018/2019 and 2019/2020 soybean crop season, at the stages of development V4–V5, R1–R2, R3–R4 and R5.1–R5.3. The experimental plots were managed to obtain different conditions of K+ availability for the plants, from severe deficiency level to the appropriate level of nutrient, under the following experimental treatments: severe potassium deficiency, moderate potassium deficiency and adequate supply of potassium. Spectral data were obtained by the ASD Fieldspec 3 Jr. hyperspectral sensor in the visible/near-infrared spectral range (400–1000 nm) and correlated to leaf K+ through ten machine learning methods: Partial Least Square Regression (PLSR), interval Partial Least Squares (iPLS), Genetics Algorithm (GA), Competitive Adaptive Reweighted Sampling (CARS), Random Frog (RF, Frog), Variable combination population analysis (VCPA), Principal Component Regression (PCR), Support Vector Machine (SVM), Successive projections algorithm (SPA), and Stepwise. The results showed that K+ deficiency significantly reduce grain yield and nutrient content in the leaf, making enabling the clustering separation of all treatments by Tukey’s test. Among the 601 wavelengths obtained by the sensor, the algorithms selected from 1 to 33.28%, largely distributed in the regions of red, green, blue, red-edge and NIR. In all stages of development, it was possible to quantify the nutrient with high accuracy (R2 ≅ 0.88). The multivariate regression models from the selection of variables contributed to increase the accuracy (R2) in about 7.65% for the calibration step and 6.45% for the cross-validation step, when compared to the model using the full spectra. The results obtained demonstrate that the monitoring of K+ in soybean leaves is possible and has the potential to determine the nutritional content in the early stages of plant development.
PubDate: 2023-12-01
-
- Fully automated proximal hyperspectral imaging system for high-resolution
and high-quality in vivo soybean phenotyping-
Free pre-print version: Loading...
Abstract: Abstract Hyperspectral imaging (HSI) is a prevalent method in crop phenotyping. Nevertheless, current HSI remote sensing techniques are compromised by changing ambient lighting conditions, long imaging distances, and comparatively low resolutions. Proximal HSI sensors such as LeafSpec were developed to improve the imaging quality. However, the application of proximal sensors remains contrained by their low throughput and intensive labor costs. Moreover, few automation solutions were available to use LeafSpec in phenotyping dicot plants. In this paper, a novel robotic system is presented as a sensor platform to operate LeafSpec to collect leaf-level hyperspectral images for in vivo phenotyping of soybean. A machine vision algorithm was developed to detect the top mature trifoliate and estimate the poses of the leaflets. A control and motion planning algorithm was developed for an articulated robotic manipulator to grasp the target leaflets. An experiment was conducted in March 2021 in a greenhouse with 64 soybean plants of 2 genotypes and 2 nitrogen treatments. The machine vision detected the target leaflets with a first trial success rate of 84.13% and an overall success rate of 90.66%. The robotic manipulator operated LeafSpec to image the target leaflets with a first trial success rate of 87.30% and an overall success rate of 93.65%. The average cycle time for one soybean plant was 63.20 s. The PLS predictions from the robot-collected data had an R2 of 0.84 with the measured nitrogen content and an R2 of 0.82 with the predictions from human-collected data. The results demonstrated the potential of applying the system for automated in vivo leaf-level HSI for soybean phenotyping in the field.
PubDate: 2023-12-01
-
- Minimizing active canopy sensor differences in nitrogen status diagnosis
and in-season nitrogen recommendation for maize with multi-source data
fusion and machine learning-
Free pre-print version: Loading...
Abstract: Abstract Active canopy sensors (ACSs) are great tools for diagnosing crop nitrogen (N) status and grain yield prediction to support precision N management strategies. Different commercial ACSs are available and their performances in crop N status diagnosis and recommendation may vary. The objective of this study was to determine the potential to minimize the differences of two commonly used ACSs (GreenSeeker and Crop Circle ACS-430) in maize (Zea mays L.) N status diagnosis and recommendation with multi-source data fusion and machine learning. The regression model was based on simple regression or machine learning regression including ancillary information of soil properties, weather conditions, and crop management information. Results of simple regression models indicated that Crop Circle ACS-430 with red-edge based vegetation indices performed better than GreenSeeker in estimating N nutrition index (NNI) (R2 = 0.63 vs. 0.50–0.51) and predicting grain yield (R2 = 0.56–0.57 vs. 0.49). The random forest regression (RFR) models using vegetation indices and ancillary data greatly improved the prediction of NNI (R2 = 0.81–0.82) and grain yield (R2 = 0.87–0.89), regardless of the sensor type or the vegetation index used. Using RFR models, moderate degree of accuracy in N status diagnosis was achieved based on either GreenSeeker or Crop Circle ACS-430. In comparison, using simple regression models based on spectral data only, the accuracy was significantly lower. When these two ACSs were used independently, they performed similarly in N fertilizer recommendation (R2 = 0.57–0.60). Hybrid RFR models were established using vegetation indices from both ACSs and ancillary data, which could be used to diagnose maize N status (moderate accuracy) and make side-dress N recommendations (R2 = 0.62–0.67) using any of the two ACSs. It is concluded that the use of multi-source data fusion with machine learning model could improve the accuracy of ACS-based N status diagnosis and recommendation and minimize the performance differences of different active sensors. The results of this research indicated the potential to develop machine learning models using multi-sensor and multi-source data fusion for more universal applications.
PubDate: 2023-12-01
-
- Factors affecting farmer perceived challenges towards precision
agriculture-
Free pre-print version: Loading...
Abstract: Abstract Precision Agriculture (PA) manages field heterogeneities and enables informed site-specific management. While PA helps improve farming efficiency and profitability, challenges prior to and following PA adoption can prevent many farmers from widely using it. This paper aims to understand producers’ challenge perceptions using 1119 survey responses from U.S. Midwest farmers. The majority (59%) of respondents have adopted at least one PA technology, while the minority (14%) had not adopted any PA technologies. Cost (equipment and service fee), brand compatibility, and data privacy concerns topped other concerns from the average producer’s point of view. Among all producers, 60% regarded PA equipment and service fee as too high, followed by 50% who viewed brand compatibility and data privacy as their major concerns. Producers at more advanced adoption stage indicated reduced concerns in most categories. Yet, there were similar concerns towards data privacy issue regardless of the adoption status. Furthermore, brand compatibility issue is more of a concern for adopters than for non-adopters. Estimation results from partial proportional odds (PPO) models show that factors that frequently affect producers’ perceived challenges include adoption status, cropland acres, age, education, information sources, farming goals, soil characteristics, and region variables. Findings from this study can aid PA stakeholders in identifying target groups, tailoring future development, research, and outreach efforts, and ultimately promoting efficient PA usage on a broader scale.
PubDate: 2023-12-01
-
- Coupling continuous wavelet transform with machine learning to improve
water status prediction in winter wheat-
Free pre-print version: Loading...
Abstract: Abstract Water is one of the essential factors for crop growth and development. Rapid and non-destructive monitoring of winter wheat water status is crucial for water diagnosis and irrigation management. Wavelet analysis has been widely used to process hyperspectral reflectance data for remote sensing monitoring of crop water status. However, most studies utilized only a single wavelet feature, and the potential of combined wavelet features remains unclear. This study aimed to use the combination of machine learning algorithms with wavelet analysis to make full use of the spectral information and improve the performance of wavelet analysis in winter wheat water status monitoring. Field experiments under four water and two nitrogen treatments were carried out from 2020 to 2022. Crop water status indicators and canopy reflectance spectra of winter wheat were acquired and analyzed. Wavelet index models and prediction models based on two-band wavelet features and multi-sensitive wavelet features were constructed by employing machine learning algorithms including multiple linear regression (MLR), random forest (RF), and support vector machine (SVM). The results showed that the best prediction of canopy water content, plant water content, and canopy equivalent water thickness was produced by RF (R2 = 0.92, RMSE = 2.39%), SVM (R2 = 0.93, RMSE = 2.12%) and SVM (R2 = 0.79, RMSE = 99.31 μm) based on multiple sensitive wavelet features, respectively. In addition, the wavelet index model also showed a good monitoring ability (R2 = 0.71–0.82). The machine learning models based on multiple sensitive wavelet features after feature selection avoided collinearity between features, made full use of spectral information, and improved the monitoring performance of wavelet transform for winter wheat water status. The findings will be helpful to the water stress diagnosis and accurate irrigation management of winter wheat.
PubDate: 2023-12-01
-
- Estimation of the economic impacts and operational limitations imposed on
unmanned aerial systems by poor sky conditions-
Free pre-print version: Loading...
Abstract: Abstract Cloudy skies reduce image quality obtained from unmanned aerial vehicles (UAV) due to variable lighting conditions imposed on the surface. This study provides a novel approach for identifying temporal windows of opportunity that show promise for avoiding such reductions. The total available hours for flight within a growing season were determined based on an hourly assessment of sky condition. In the study region, this represents total hours from 9 AM to 3 PM, March 1 through September 30. The most promising windows were early and late season, and early morning and late afternoon. Monthly windows were well aligned with crop decision making for emergence. An economic case study was conducted to determine the impact of sky condition on per hectare custom rate for agricultural applications of UAV. Both full-season and early-season-only operational scenarios were investigated. Use of UAV was financially favorable despite the frequent presence of poor sky conditions thought to reduce image quality (60% of total hours). A custom rate of < US$3.65 ha−1 for three flights accommodated a range of acceptable returns on investment over a 3 year period. Poor sky conditions increased the average custom rate by at most US$0.89 ha−1 in the early-season-only scenario and US$0.77 ha−1 over the full season. These rates are competitive with manned aircraft for average fields in the study region (80 ha). Although the initial perception was that clouds would reduce the potential for UAV operations when high image quality is required, economic analyses did not support this preliminary assumption.
PubDate: 2023-12-01
-
- The potential of image segmentation applied to sampling design for
improving farm-level multi-soil property mapping accuracy-
Free pre-print version: Loading...
Abstract: Abstract Sampling design plays a critical role in farm-level digital soil mapping (DSM). In many cases, a soil mapping model may not have been decided upon at the sample design stage. Design-based sampling may be more appropriate than model-based sampling because it is independent of subsequent soil mapping models. However, existing sampling methods optimize the sample size and locations in geographical space or feature space without considering the impacts of environmental similarity in local geographical space. In this paper, a novel sampling design method based on local environmental similarity was developed. Image segmentation was introduced into the sampling design by partitioning agricultural soil into subregions with good spatial continuity, within-region homogeneity, and between-region heterogeneity to determine the optimal sample size and locations. First, the environmental similarity between adjacent soils was calculated. Second, the merging process was iteratively conducted, and a series of segmentations was generated. Finally, the optimal sample size and locations were determined based on the optimal segmentation results. To validate the proposed method, it was compared with stratified random sampling, k-means sampling, and spatially balanced sampling methods. Two mapping models, ordinary kriging and sandwich estimation, were employed to map five soil properties, including pH, soil organic matter, total nitrogen, available phosphorus, and available potassium. These comparative experiments showed that the proposed method had better potential to generate farm-level muti-soil property mapping results with good accuracy than the competing sampling methods. In conclusion, consideration of local environmental similarity and the use of image segmentation for soil sampling were helpful in determining the optimal sample size and key sample locations.
PubDate: 2023-12-01
-
- Within-field spatial variability and potential for profitability of
variable rate applications-
Free pre-print version: Loading...
Abstract: Abstract Since literature is not unanimous about profitability of variable rate application (VRA), a systematic analysis is essential to determine when, where and how to increase the production profits. This paper examines the relationship between the within-field spatial variability of soil fertility and profitability of variable rate fertilisation (VRF) and VR seeding (VRS). Within-field spatial variability was determined using high resolution data of key soil attributes, subjected to a modified Cambardella Index (CI). Profitability was determined as the net revenue over the VRA input, which is an adjusted form of the contribution margin. Results showed that the contribution margin of VRAs ranged from 847 to 6624 EUR per ha. Variations in the adjusted contribution margin were positively correlated with the adjusted Cambardella index, confirming the assumption that VRA is more profitable in fields with a higher spatial variability. Findings are interpreted in a production-theoretical framework, which discussed whether, when and under which circumstances, the observed potential for profit will effectively lead to profitability increases.
PubDate: 2023-12-01
-
- The economic performances of different trial designs in on-farm precision
experimentation: a Monte Carlo evaluation-
Free pre-print version: Loading...
Abstract: Abstract On-farm precision experimentation (OFPE) has expanded rapidly over the past few years. While the importance of OFPE trial design efficiency has been recognized, existing studies have primarily used statistical measures of that efficiency to compare designs. The current article is motivated by the surety that farmers are more interested in economic results than statistical results; Monte Carlo simulations of corn-to-nitrogen (N) response OFPEs were used to compare economic performances of 13 different types of OFPE trial design. Each design type’s economic efficiency was measured by the monetary profits resulting from applying the site-specific economically optimal N rates estimated from the data generated by the design type. Results showed that trial design affects the economic performance of OFPE. Overall, the best design was the Latin square design with a special pattern of limited N rate “jump,” which had the highest average profit and lowest profit variation in almost all simulation scenarios. A particular type of patterned strip design also performed well, generating average profits only slightly lower than those from the best design. In contrast, designs with gradual trial rate changes over space were less profitable in most situations and should be avoided. Results were similar under various scenarios of nitrogen-to-corn price ratios, yield response estimation models, and field sizes used in the simulations. It was also found that the designs’ economic performances were roughly correlated with the spatial property measures of trial designs in existing literature, though much remains unexplained.
PubDate: 2023-12-01
-
- A pooling module with multidirectional and multi-scale spatial information
and its application on semantic segmentation of leaf lesions-
Free pre-print version: Loading...
Abstract: Abstract Timely and accurate identification of apple leaf diseases provides an important basis for the early warning and precise control of apple leaf diseases. It was of great significance to reduce the economic losses caused by diseases. In order to improve the accuracy of apple leaf lesion segmentation by using the deep neural networks, this paper proposed a twill pooling method and combined it with strip pooling to propose the double cross pooling method. The pooling method could contract multidirectional and multi-scale spatial context information. Then, on the constructed apple leaf disease dataset, these modules were combined with existing deep semantic segmentation networks to perform disease lesion semantic segmentation. These three constructed modules were added to the fully convolutional network respectively, and the universality of the constructed modules was further verified on other semantic segmentation networks. Experimental results showed that the proposed modules could improve the mean intersection over union of fully convolutional network by 7.69%, up to 80.44% on the collected apple leaf disease dataset. Furthermore, when adding the proposed pooling modules to DeepLabV3 + , PSPNet and U-Net, the mean intersection over union improved by varying degrees when adding any of the proposed modules alone. The performance of the improved fully convolutional network, DeepLabV3 + , PSPNet and U-Net were compared. The DeepLabV3 + with the double cross pooling module had the best segmentation performance whose mean pixel accuracy, mean intersection over union, leaf disease classification accuracy and leaf disease degree diagnosis accuracy were 99.07%, 82.1%, 99.52% and 77.65% respectively.
PubDate: 2023-12-01
-
- Precision nitrogen management in rainfed durum wheat cultivation:
exploring synergies and trade-offs via energy analysis, life cycle
assessment, and monetization-
Free pre-print version: Loading...
Abstract: Fertilization with variable rate technology (VRT) is a pivotal technique of precision agriculture proposed for eco-friendly farming practices. Yet the magnitude of environmental benefits is often not well known or is highly variable. This study used a multi-indicator model and life cycle-based indicators to compare the performance of rain-fed durum wheat production using uniform (UA) and variable N fertilization (VRT). Two functional units were used: 1 ha of cultivated wheat and 1 ton of wheat produced. The energy analysis indicated that VRT increases energy use efficiency and productivity by 13.3%, reduces specific energy and total energy input by 11.7%, and increases net energy gain by 15.3%. The life cycle assessment (LCA) analysis indicated that for some environmental impacts, VRT had minor negative effects due to the comparable yield performance with UA. Yet, the VRT had a noteworthy positive impact on global warming, fine particulate matter formation, stratospheric ozone depletion, terrestrial acidification, and marine eutrophication, generating a final environmental benefit of 12.2% for 1 ton of product and 13.3% for 1 ha of land. Economic valuation or monetization of LCA results using monetization weighting factors indicated indirect economic benefits of VRT can be up to 6.6% for 1 ton of product and 7.7% for 1 ha of land. Our findings support the use of nitrogen fertilization with VRT for sustainable extensification and improved eco-efficiency of wheat production in a Mediterranean context. As a result of our research, we conclude that future case studies on annual crops with moderate land requirements should employ multiple metrics and functional units, as well as the concepts of monetization and life cycle assessment, to investigate trade-offs between yield, economic, and environmental benefits and to aid decision-making about the true sustainability of proposed farming technologies. Graphical abstract
PubDate: 2023-12-01
-
- Exploring 20-year applications of geostatistics in precision agriculture
in Brazil: what’s next'-
Free pre-print version: Loading...
Abstract: In the last decades, geostatistics has been widely used for precision agriculture (PA) producing quite exciting results. Research on this topic is important for sustainable agriculture growth in Brazil. The objective of the review is an attempt to outline the current state of using geostatistical tools for PA applications in Brazil in the last 20 years (2002–2022), but not to provide an exhaustive review of models. We analyzed the scientific literature on this field in Brazil to identify their merits and weaknesses in the present, and to conjecture on future developments. We analyzed 151 proceeding papers and 144 peer-reviewed journal articles regarding applications of geostatistics in PA in Brazil from 2002 to 2022 using bibliometric techniques to reveal current research trends and hotspots. We detected using geostatistics for PA has been limited, mostly for univariate interpolation purposes. The co-citation analysis reveals four broad research clusters in the literature: (i) spatial variability, semivariogram, soil management, (ii) soil fertility, ordinary kriging, spatial dependence, (iii) coffee plant, coffee, Coffea arabica, and (iv) glycine max, zea mays, management zones. The presented review is a springboard to future modeling developments useful for geostatistics applications to PA in Brazil. We suggest expanding the use of geostatistics for smart agricultural technology by adding new potential approaches in new research. Combined with other approaches, such as machine learning, uncertainty modeling, efforts for more geostatistical training, and data fusion from multi-sensor and multi-source are a new frontier to be explored more often by the Brazilian PA community. Graphical abstract
PubDate: 2023-12-01
-
- In vivo sensing to monitor tomato plants in field conditions and optimize
crop water management-
Free pre-print version: Loading...
Abstract: Abstract Irrigation is key to increasing crop yield and meeting the global demand for food. This study reports the assessment of tomato water consumption by bioristor, a new in vivo an Organic ElectroChemical Transistor-based biosensor. Bioristor enables direct, real-time acquisition of biophysical information about the plant’s water requirements directly from the plant sap, and thus the water input can be adjusted accordingly. The aim of this study is to demonstrate the efficacy of bioristor in rapidly detecting changes in the plant’s water status enhancing water use and irrigation efficiency in tomato cultivation with significant savings in the water supply. To this end, experiments were carried out in 2018 and 2020 in Parma (Italy) in tomato fields under different water regimes. The sensor response index (R) produced by bioristor recorded the real time plant health status, highlighting an excess in the water supplied as well as the occurrence of drought stress during the growing season. In both years, bioristor showed that the amount of water supplied could have been reduced by 36% or more. Bioristor also measured the timing and duration of leaf wetting: 438 h and 409 h in 2018 and 2020, respectively. These results open up new perspectives in irrigation efficiency and in more sustainable approaches to pesticide application procedures.
PubDate: 2023-12-01
-
- European stakeholders’ perspectives on implementation potential of
precision weed control: the case of autonomous vehicles with laser
treatment-
Free pre-print version: Loading...
Abstract: Abstract Weed control is a basic agricultural practice, typically achieved through herbicides and mechanical weeders. Because of the negative environmental impacts of these tools, alternative solutions are being developed and adopted worldwide. Following recent technical developments, an autonomous laser-based weeding system (ALWS) now offers a possible solution for sustainable weed control. However, beyond recent proof of performance, little is known about the adoption potential of such a system. This study assesses the adoption potential of ALWS, using a mixed-method approach. First, six macro-environmental factors regarding the adoption of ALWS were determined. This assessment is referred to as a Political, Economic, Social, Technological, Legal, Environmental (PESTLE) analysis and is conducted in a form of a literature review initiated by expert consultations. Second, a range of European stakeholders’ perceptions of ALWS was evaluated in four focus-group discussions (n = 55), using a strengths, weaknesses, opportunities, threats (SWOT) analysis. The factors identified in the PESTLE and SWOT analyses were subsequently merged to provide a comprehensive overview of the adoption potential of ALWS. Labour reduction, precision treatment and environmental sustainability were found to be the most important advantages of ALWS. High costs and performance uncertainty were identified as the main weaknesses. To promote the adoption of ALWS, this study recommends the following: (1) Concrete performance results, both technical and economic, should be communicated to farmers. (2) Farmers’ knowledge of precision agriculture should be improved. (3) Advantage should be taken of policies that are favourable towards non-chemical methods and the high demand for organic products. This article also extensively discusses regulatory barriers, the risks posed to the safety of both humans and the machines involved, technological challenges and requirements, and policy recommendations related to ALWS adoption.
PubDate: 2023-12-01
-
