Smart agricultural technology最新文献

{"title":"Automated detection of downy mildew and powdery mildew symptoms for vineyard disease management","authors":"Luca Ghiani ,&nbsp;Salvatorica Serra ,&nbsp;Alberto Sassu ,&nbsp;Alessandro Deidda ,&nbsp;Antonio Deidda ,&nbsp;Filippo Gambella","doi":"10.1016/j.atech.2025.100877","DOIUrl":"10.1016/j.atech.2025.100877","url":null,"abstract":"<div><div>This work focuses on developing an automated system for detecting downy mildew and powdery mildew symptoms in grapevines, with particular attention to the role of data partitioning and dataset diversity in ensuring reliable model performance. Leveraging deep learning techniques, specifically the YOLO (You Only Look Once) object detection model, we aimed to provide a robust tool for disease detection, which is crucial for optimizing vineyard management, increasing crop yield, and promoting sustainable agricultural practices. Over two years, we collected and expertly annotated a large dataset of images depicting downy and powdery mildew symptoms in field conditions. The YOLO model was trained and validated on this dataset, achieving a mean Average Precision (mAP) of 0.730, demonstrating good detection accuracy. A key contribution of this study is the emphasis on the importance of proper data partitioning strategies, showing that random image partitioning can lead to an overestimation of model performance. Our findings underscore that true improvements in detection accuracy are driven not merely by increasing the number of images but by enhancing the diversity of the dataset, particularly for the areas, seasons, growth stages, and conditions in which the images are captured. This approach ensures a more realistic assessment of the system's performance, critical for deploying such systems in practical, real-world agricultural scenarios. The results highlight the potential of deep learning models to enhance vineyard management through a reliable and efficient detection of diseases in real-world conditions.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"11 ","pages":"Article 100877"},"PeriodicalIF":6.3,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143591985","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Generalization of peanut yield prediction models using artificial neural networks and vegetation indices","authors":"Jarlyson Brunno Costa Souza ,&nbsp;Samira Luns Hatum de Almeida ,&nbsp;Mailson Freire de Oliveira ,&nbsp;Vinicius dos Santos Carreira ,&nbsp;Armando Lopes de Brito Filho ,&nbsp;Adão Felipe dos Santos ,&nbsp;Rouverson Pereira da Silva","doi":"10.1016/j.atech.2025.100873","DOIUrl":"10.1016/j.atech.2025.100873","url":null,"abstract":"<div><h3>CONTEXT</h3><div>The prediction of crop yield is vital for the management and decision-making processes in agriculture. Techniques such as Remote Sensing (RS) and Artificial Neural Networks (ANN) emerge as potential tools for predicting these agronomic parameters.</div></div><div><h3>OBJECTIVE</h3><div>Therefore, the objective of this study was to combine RS data in ANN models to remotely and anticipatively predict peanut yield.</div></div><div><h3>METHODS</h3><div>The experiment was conducted in eleven commercial fields, divided into six fields in the 2020/21 season and five in the 2021/22 season. The input data for the development of the models were vegetation indices (EVI, GNDVI, MNLI, NLI, NDVI, SAVI, and SR) derived from high-resolution satellite images on five dates, from one to thirty days before the start of the peanut harvest. The Vegetation Index (VI) data from the 20/21 season were inserted into Multilayer Perceptron (MLP) and Radial Basis Function (RBF) Artificial Neural Networks (ANNs) for the calibration. Subsequently, the generated equations were applied to the fields of the subsequent season for generalizing and recalibration of the models using the dataset from both seasons. Both networks proved capable of making predictions using the VIs as input, both in validation and recalibration, where an improvement in the precision and accuracy of the models was observed.</div></div><div><h3>RESULTS AND CONCLUSION</h3><div>The validation of the models demonstrated a high potential for generalizing the variability of peanut yield in new fields. The MLP network presented the best results in this study, with an MAPE of 9.3 %, thirty days before harvest and a determination coefficient of 0.80. The VIs that stood out the most as input were EVI, SAVI, and SR. The use of RS combined with ANN is a powerful tool for predicting peanut yield and assisting the farmer in crop management.</div></div><div><h3>SIGNIFICANCE</h3><div>The results obtained highlight the importance of developing predictive models for peanut yield over the years, taking into account the interaction between genotypes and environments to enhance model robustness. Furthermore, it is essential that these models be applicable in new areas, as demonstrated by this work, which evidenced good generalization across distinct locations, even under varying management practices and cultivars.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"11 ","pages":"Article 100873"},"PeriodicalIF":6.3,"publicationDate":"2025-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143591988","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Supervised and unsupervised machine learning approaches for tree classification using multiwavelength airborne polarimetric LiDAR","authors":"Zhong Hu ,&nbsp;Songxin Tan","doi":"10.1016/j.atech.2025.100872","DOIUrl":"10.1016/j.atech.2025.100872","url":null,"abstract":"<div><div>As an active remote sensing tool, Light Detection And Ranging (LiDAR) with laser source offers many advantages over passive and radar remote sensing, enabling a wide range of applications across fields such as forestry, agriculture, urban planning, and environment. Current studies have mainly employed commercial non-polarimetric LiDAR for forest surveying and monitoring using point cloud data. A Multiwavelength Airborne Polarimetric LiDAR (MAPL) has been developed. The MAPL system has dual-wavelengths and dual-polarization, and offers full waveform recording capability. With its unique characteristics, it has been used in vegetation remote sensing for better target detection and identification. In this work, field data were collected from five different tree species, including deciduous trees (ash and maple) and coniferous trees (Austrian pine, ponderosa pine, and blue spruce). Subsequently, supervised (Decision-Tree) and unsupervised (clustering) machine learning (ML) methods were developed for tree species classification, based on the peak intensities and full width at half maxima (FWHMs) of the MAPL waveforms. The Decision-Tree approach shows a re-substitution error of 0.14 % and a k-fold loss error of 0.57 % for 2,106 tree samples; and the clustering methods provide accuracies at about 80 %. Furthermore, the results indicate that both peak intensities and FWHMs of the MAPL waveforms are potent features for the ML approaches. In addition, the supervised method has higher accuracy, while clustering is less labor intense and may be applied to large scale remote sensing. The adopted methods enable expeditious and accurate data processing and can be expanded to other classification applications.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"11 ","pages":"Article 100872"},"PeriodicalIF":6.3,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143578115","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Accurate machine vision identification of GCHD symptom using a self-attention-based CNN model with adaptive fish separation","authors":"Xiang Shen ,&nbsp;Zehui Liu ,&nbsp;Wei Qin ,&nbsp;Muchen Zhang ,&nbsp;Haibo Jiang ,&nbsp;Xiuxiang Huang ,&nbsp;Jun Xiao ,&nbsp;Jianguo Su ,&nbsp;Jiaji Pan ,&nbsp;Hao Feng","doi":"10.1016/j.atech.2025.100871","DOIUrl":"10.1016/j.atech.2025.100871","url":null,"abstract":"<div><div>Grass carp hemorrhagic disease (GCHD) caused by grass carp reovirus (GCRV) is one of the most serious transmissible diseases threatening the freshwater fish aquaculture, which asks for novel efficient and cost-effective surveillance techniques. Machine vision could provide an effective inspection allowing for the early warning of the GCHD epidemic spreading. But the detection accuracy using current deep learning algorithms are not satisfactory by testing the experimental datasets. In this study, we collected datasets of model animal Chinese rare minnow (<em>Gobiocypris rarus</em>) with GCHD symptoms and developed a self-attention-based convolutional neural network (SA-CNN) deep learning model. The SA-CNN model can accurately detect Chinese rare minnow with GCHD symptoms. After the pre-processing of the extracted images using improved <em>k</em>-means and enhanced watershed algorithms, the dense or overlapping fish in the populations can be adaptively separated which improves the recognizing precision. The SA-CNN model achieves an accuracy of 99.1 %, a recall of 97.7 %, and F1 score of 96.6 % with optimized loss function for the acquired datasets of fish with GCHD symptoms. The precision is higher than the current state-of-art you only look once (YOLO) series networks ranging from 4.9 % to 25.6 % with respect to different model series. The identification time for each image takes only 95ms demonstrating a good efficiency. The self-attention module brought an increase of 3.8 % in accuracy, 3.0 % in recall, as demonstrated by the ablation experiment. Thus, this optimized SA-CNN model provides an effective approach for the indispensable broad application of GCHD surveillance programs containing GCRV transmission, laying a foundation for the intelligent, healthy and precision aquaculture.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"11 ","pages":"Article 100871"},"PeriodicalIF":6.3,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143578063","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing wheat storage efficiency: A microcontroller-based environment control system for silo","authors":"Muhammad Mateen ,&nbsp;Zaheer Ahmed Khan ,&nbsp;Yang Minli ,&nbsp;Ma Wenqiu ,&nbsp;Abreham Arebe Tola","doi":"10.1016/j.atech.2025.100865","DOIUrl":"10.1016/j.atech.2025.100865","url":null,"abstract":"<div><div>Agricultural activities are incomplete without the proper wheat storage, and maintaining optimal storage conditions requires an effective management system. This study presents a control system designed to improve the storage conditions of wheat using an Arduino UNO, a DHT22 sensor, and a fan cooling system to manage the environment. The device continually monitors temperature and relative humidity, as well as giving a non-destructive evaluation of the moisture content of wheat kept in silos. During the study, the system confirmed its efficacy by effectively maintaining appropriate storage conditions, such as average temperature and humidity levels, which encourage safe wheat storage. The automatic fan system effectively regulates temperature fluctuations, providing ideal conditions. The study examined the system's capacity to control essential parameters such as moisture content and germination rate of preserved seeds. The results indicated that the temperature dropped by 1.25 °C per minute when the fan was activated, with a threshold activation temperature of 30 °C. The recorded temperature and humidity of the stored wheat were 34.76 °C and 43.33 %, respectively. The moisture content ranged from 15.26 % to 11.73 %, while the seed germination rate ranged from 94.27 % to 75.66 %. Compared to conventional storage methods, the system demonstrated superior performance in reducing moisture levels, stabilizing temperature fluctuations, and preserving wheat quality, ultimately lowering the risk of insect infestation and post-harvest losses. Although its success, issues of scalability, cost-effectiveness, and adaption to varied environmental circumstances were recognized. Future experimental research should concentrate on incorporating modern IoT technologies for real-time monitoring, enhancing energy efficiency, and evaluating the system in bigger storage facilities or with diverse crop varieties. Rectifying these deficiencies will augment the system's relevance and bolster rural food security and economic stability.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"11 ","pages":"Article 100865"},"PeriodicalIF":6.3,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143578065","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Recognition of multi-symptomatic rice leaf blast in dual scenarios by using convolutional neural networks","authors":"Huiru Zhou ,&nbsp;Dingzhou Cai ,&nbsp;Lijie Lin ,&nbsp;Dong Huang ,&nbsp;Bo-Ming Wu","doi":"10.1016/j.atech.2025.100867","DOIUrl":"10.1016/j.atech.2025.100867","url":null,"abstract":"<div><div>Rice blast is an airborne disease which can spread rapidly from small disease foci, and result in severe yield loss. To monitor the disease foci in the rice field effectively and timely, deep learning is applied to recognize dual-scenario images of multi-symptomatic rice leaf blast. In this study, a benchmark dataset containing chronic type and acute type of rice leaf blast over different growth stages of plants, as well as two other common rice leaf diseases and healthy rice leaves was constructed and made publicly available. Firstly, the impact of different training methods on imbalanced datasets was compared. Then six state-of-the-art convolutional neural network models were trained with the dataset by transfer learning and the hyperparameters of the outperforming models were further optimized to improve the recognition accuracy of models. The results proved that the quantity and quality of images had great impacts on the model performance, and image augmentation could greatly alleviate the problem of imbalanced inter class recognition performance. According to the experimental results, the overall performance of InceptionV3 was the best among the six models, and its highest validation accuracy was 99.78 % after parameter adjustment, and its highest test accuracy reached 99.64 %. The research demonstrated that the use of computer vision and deep learning to identify symptoms of crop diseases and to locate disease foci through the feedback frequency of infected images would be an effective method for intelligent disease monitoring in the future.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"11 ","pages":"Article 100867"},"PeriodicalIF":6.3,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143578114","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Quantifying the impact of varied NPK fertilizer levels on oil palm plants during the nursery stage: A Vis-NIR spectral reflectance analysis","authors":"Siti Anis Dalila Muhammad Zahir ,&nbsp;Mohd Faizal Jamlos ,&nbsp;Ahmad Fairuz Omar ,&nbsp;Muhammad Aqil Hafizzan Nordin ,&nbsp;Muna Ezzi Abdullah Raypah ,&nbsp;Rizalman Mamat ,&nbsp;Mohd Aminudin Jamlos ,&nbsp;Jelena Muncan","doi":"10.1016/j.atech.2025.100864","DOIUrl":"10.1016/j.atech.2025.100864","url":null,"abstract":"<div><div>The utilization of Vis-NIR spectroscopy, coupled with advanced statistical analysis methods, offers enhanced precision in monitoring the nutrient status of plants compared to traditional practices. This research aims to explore the efficacy of spectroscopy as a method for detecting and monitoring plant nutrient levels. The reflectance spectra of <em>AA Hybrida 1S</em> oil palm plants were measured in the 325–1075 nm wavelength range. Different quantities and application intervals of nitrogen, phosphorus, and potassium (NPK) fertilizers were systematically examined to assess their impact on the physical condition and reflectance of the plants. The relationship between different fertilization methods and nutrient levels is analysed using spectral index and principal component analysis (PCA), employing and testing several spectral pre-processing techniques, such as moving average smoothing, Savitzky-Golay derivatives, and standard normal variate (SNV) transformation. Spectral index calculation showed with statistical significance that 0.8 g of NPK supplied every two weeks improved the nutrient conditions in plants after five months. Moreover, PCA analysis showed that SNV pre-processing enabled the best classification between stressed and non-stressed nutrient status. Among the spectral bands analysed, the red-edge band (660–770 nm) demonstrated significantly better performance than the green band (540–560 nm) in identifying nutrient-stressed conditions. This is attributed to the strong light absorption by chlorophyll in the red region and the pronounced reflection caused by leaf cell structures in the NIR region.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"11 ","pages":"Article 100864"},"PeriodicalIF":6.3,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143591986","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Web-based nutrient management with the software webBESyD–Scientific principles, software architecture and model validation","authors":"Joseph Donauer ,&nbsp;Marco Luthardt ,&nbsp;Christiane Peter ,&nbsp;Michael Grunert ,&nbsp;Aurelia Ostermaier-Welz ,&nbsp;Frank Leßke ,&nbsp;Kurt-Jürgen Hülsbergen","doi":"10.1016/j.atech.2025.100859","DOIUrl":"10.1016/j.atech.2025.100859","url":null,"abstract":"<div><div>Efficient on-farm nutrient management is a prerequisite for achieving high crop yields, high product quality, high nutrient use efficiency, and low nutrient losses to the environment. So far, software tools are only available for individual, specific management tasks, but there is no comprehensive nutrient management system at farm level. This paper presents the concept, architecture, scientific basis and model validation of the web-based farm nutrient management system webBESyD. This software allows a comprehensive assessment of all relevant nutrient flows within farming systems and is developed specifically for use by farmers and agricultural advisors. webBESyD integrates several scientifically validated modules to calculate fertilizer requirements, nutrient balances, soil organic matter balances, nitrate leaching risks, and to provide decision support. It uses a modular, web-based architecture and interfaces for importing farm, management and geospatial data. All data concerning crop and livestock production is stored centrally in a clearly structured farm model. The modular design allows two different modes of operation: Users can utilize webBESyD directly via a graphical user interface or use specific modules from external systems via a machine-readable application interface. The performance of the modules is evaluated through field experiments, demonstrating good performance. Modeled values align well with measurements, and fertilizer recommendation systems offer economically and ecologically sound guidance. In summary, webBESyD can provide meaningful insights into farm-specific nutrient management, identify optimization potential and provide suggestions for improvement. The technical implementation ensures that webBESyD remains adaptable and compatible with future developments in agricultural technology.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"11 ","pages":"Article 100859"},"PeriodicalIF":6.3,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143735034","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The PhenoLab – an automated, high-throughput phenotyping platform for analyzing development, abiotic stress responses and pathogen infection in model and crop plants","authors":"D․B․ Amby ,&nbsp;J․C․ Westergaard ,&nbsp;D․K Großkinsky ,&nbsp;S․M․ Jensen ,&nbsp;J․ Svensgaard ,&nbsp;F․ Liu ,&nbsp;S․ Christensen ,&nbsp;T․ Roitsch","doi":"10.1016/j.atech.2025.100845","DOIUrl":"10.1016/j.atech.2025.100845","url":null,"abstract":"<div><div>Important plant stresses are drought, but also biotic stresses caused by pathogens have economically important losses to crops worldwide. Advancements in our ability to fast, sensitive and cost efficient detect stress responses by sensor based imaging are important to improve crop management practices. As a step towards this, we introduce a fully automated, high-throughput plant phenotyping platform called “PhenoLab”. It automatically ensures precise and automatic irrigation of plants and non-destructively, fast and quantitatively measure biomass, abiotic and biotic stresses via multispectral imaging. A user friendly software for supervised machine learning based spectral image analysis is used for image processing and water consumption of individual plants can be extracted from an integrated database.</div><div>As a proof of concept, we used two important crop plants for phenotyping and detecting abiotic and biotic stresses. Individual multi-spectral measurements (within 365–970 nm) and vegetation index were considered in the image processing to detect drought symptoms of maize plants. Powdery mildew of barley plants was sufficiently detected and quantified via multi-reflectance and multi-fluorescence image system during disease progression. The integrated settings for multispectral image recording, computer vision and image processing platform with customized settings and protocols are expected as practical importance for academic and translational high-throughput research. It will be notably relevant for more complex systems with additional multiple factors e.g.<em>,</em> multiple plant genotypes and their resistance and susceptibility to abiotic and biotic stresses, or treatments of beneficial microbes for sustainable improvement of general stress resiliency.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"11 ","pages":"Article 100845"},"PeriodicalIF":6.3,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143610601","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparative analysis of spectral unmixing methods for subpixel weed identification under controlled and field conditions","authors":"Inbal Ronay ,&nbsp;Ran Nisim Lati ,&nbsp;Fadi Kizel","doi":"10.1016/j.atech.2025.100835","DOIUrl":"10.1016/j.atech.2025.100835","url":null,"abstract":"<div><div>Efficient Site-Specific weed management (SSWM) practice requires high-resolution data in both spatial and spectral domains. It allows spatially locating different weed species at early growth to adjust herbicide application based on weed composition and coverage. Nonetheless, such high-resolution data is not always available, and mixed pixels are likely to exist, creating a challenge to generate accurate weed maps. In this regard, Spectral Mixture Analysis (SMA), which allows exploiting subpixel information from coarse spatial resolution spectral data, can mitigate this challenge. This study assesses the potential benefits of four SMA methods for estimating weed coverage from different botanical groups. Each of the methods examined here namely, Fully Constrained Least Squares Unmixing (FCLSU), Sparse Unmixing via variable Splitting and Augmented Lagrangian (SUnSAL), Sparse Unmixing via variable Splitting and Augmented Lagrangian and Total variation (SUnSAL-TV) and the e Vectorized Code Projected Gradient Descent Unmixing (VPGDU) suggests a distinct advantage for spectral unmixing. To compare the four methods, we first established a controlled dataset that included weed species characterized by distinct botanical groups and assessed the performance of four SMA methods in estimating weed coverage and composition at various spatial resolutions. We found that SUnSAL-TV and VPGDU outperformed FCLSU and SUnSAL, with up to 13 % lower Mean Absolute Error (MAE) values. Next, we applied the comparative analysis of these four SMA methods to a multispectral field dataset involving corn and weeds. The same results trend was observed in the field study, with VPGDU as the best-performing method, with an overall MAE value lower than 12 %. These experimental outcomes demonstrate the advantages of the total variation regularization of SUnSAL-TV and the superiority of the SAM-based method, VPGDU, over other approaches, underscoring the advantage of its objective function and the significant effect of varying illumination on the results.</div></div>","PeriodicalId":74813,"journal":{"name":"Smart agricultural technology","volume":"11 ","pages":"Article 100835"},"PeriodicalIF":6.3,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143610599","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}