[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-1205":3,"related-1205":98},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":8,"source_name":9,"source_url":6,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":15,"sources":22,"tags":24,"primary_topic":30,"secondary_topics":36,"classification":37,"search_phrases":64,"slug":67,"view_count":59,"doi":68,"paper":69,"created_at":97},1205,"Lightweight real-time detection of sweet potato virus disease by a hybrid CNN–Transformer network","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112319","Timely and precise detection of sweet potato virus disease (SPVD) is essential for ensuring crop health and improving yield quality in precision agriculture. However, conventional deep learning models often struggle to capture subtle lesion features under complex field conditions. This paper proposes Swin-SPVDNet, a hybrid CNN-Transformer detection framework with task-specific architectural enhancements that combines convolutional neural networks (CNNs) with a modified Swin Transformer to effectively integrate local spatial details and global contextual information. Unlike conventional hybrid models that simply stack convolutional and transformer blocks, the proposed network introduces three key structural designs: (1) A C2PSA-enhanced convolutional backbone for improved local feature sensitivity. (2) A C3STR module that tightly integrates convolutional operations with Swin Transformer blocks for joint local–global feature interaction. (3) A Residual Attention Block (RAB) that refines feature representations while stabilizing gradient propagation. A field-collected SPVD image dataset was constructed using handheld RGB imaging under real agricultural conditions. Extensive experiments and ablation studies demonstrate that Swin-SPVDNet achieves competitive performance compared with representative state-of-the-art detectors while providing a favorable balance between detection accuracy and deployment efficiency, attaining a mean Average Precision (mAP@0.5) of 86.8%, a precision of 85.1%, and a recall of 75.6%. Compared to Yolov5-v11 models, our approach demonstrates improved robustness in detecting small and irregular lesions, particularly under occlusion and lighting variability. These results confirm the practical value of Swin-SPVDNet for real-time field deployment and support its application in intelligent disease monitoring.",null,"Computers and Electronics in Agriculture","2026-08-25T00:00:00Z","论文",10,false,73,{"impact":16,"substance":17,"depth":16,"authority":18,"freshness":19,"relevant":20,"comment":21},18,22,13,2,1,"提出轻量级混合CNN-Transformer模型用于甘薯病毒病实时检测，方法新颖且实验数据详实，对智能植保有参考价值。",[23],{"name":9,"url":6},[25,26,27,28,29],"智慧农业","农业人工智能","作物病害","深度学习","甘薯",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},"A5","tubers-grains","薯类与杂粮","\u002Ftopic\u002Ffield-crops\u002Ftubers-grains","A",[],{"status":38,"locked":13,"version":39,"method":40,"evidence":41},"classified","2026-10-22.2","rules",{"candidates":42,"agricultural_evidence":45},[43,50,57],{"code":31,"score":44,"supported":45,"title":46,"abstract":48,"tags":49},12,true,[47],"potato",[47],[29],{"code":51,"score":52,"supported":45,"title":53,"abstract":54,"tags":56},"I2",5,[],[55],"deep learning",[26,28],{"code":58,"score":59,"supported":45,"title":60,"abstract":61,"tags":63},"I1",4,[],[62],"precision agriculture",[25],[65,66],"农业人工智能 作物病害 智慧农业 深度学习","农业人工智能 作物病害","农业人工智能作物病害智慧农业深度学习-1205","10.1016\u002Fj.compag.2026.112319",{"doi":68,"openalex_id":70,"authors":71,"venue":9,"cited_by_count":89,"oa_url":6,"card":90,"direction":94,"ingested_from":96},"W7204154634",[72,75,78,81,83,85,87],{"name":73,"orcid":74},"Ru Han","https:\u002F\u002Forcid.org\u002F0009-0000-5128-1314",{"name":76,"orcid":77},"Lei Shu","https:\u002F\u002Forcid.org\u002F0000-0002-6700-9347",{"name":79,"orcid":80},"Grzegorz Cielniak","https:\u002F\u002Forcid.org\u002F0000-0002-6299-8465",{"name":82,"orcid":8},"Yan Zhu",{"name":84,"orcid":8},"Xing Yang",{"name":86,"orcid":8},"Fan Yang",{"name":88,"orcid":8},"Kai Huang",0,{"tldr":91,"method":92,"finding":93,"direction":94,"opportunity":95},"提出Swin-SPVDNet混合CNN-Transformer网络，实现甘薯病毒病轻量级实时检测。","结合C2PSA卷积骨干、C3STR模块和残差注意力块，使用手持RGB图像数据集。","mAP达86.8%，精度85.1%，召回75.6%，优于YOLOv5-v11，鲁棒性强。","农业人工智能与决策模型","可探索将混合网络应用于其他作物病害检测，或优化模型以适应更多复杂田间环境。","openalex","2026-09-01T04:03:02.220802Z",{"total":99,"page":20,"page_size":99,"items":100},6,[101,171,227,286,352,455],{"id":102,"title":103,"url":104,"summary":105,"summary_zh":106,"content":8,"source_name":9,"source_url":104,"published_at":107,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":108,"score_detail":109,"sources":115,"tags":117,"primary_topic":120,"secondary_topics":121,"classification":122,"search_phrases":142,"slug":145,"view_count":19,"doi":146,"paper":147,"created_at":170},1709,"EOL-DQN: An intelligent cutting decision of potato seed tubers based on improved deep reinforcement learning","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112372","EOL-DQN: An intelligent cutting decision of potato seed tubers based on improved deep reinforcement learning。Computers and Electronics in Agriculture","EOL-DQN：基于改进深度强化学习的马铃薯种薯智能切块决策。Computers and Electronics in Agriculture","2026-09-05T00:00:00Z",75,{"impact":110,"substance":111,"depth":16,"authority":112,"freshness":113,"relevant":20,"comment":114},15,20,14,8,"提出基于改进深度强化学习的马铃薯种薯切块决策方法，属于智慧农业细分领域的技术创新，对种业智能化有参考价值。",[116],{"name":9,"url":104},[25,26,118,119,28],"马铃薯","种业",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":13,"version":39,"method":40,"evidence":123},{"candidates":124,"agricultural_evidence":45},[125,129,133,138],{"code":31,"score":110,"supported":45,"title":126,"abstract":127,"tags":128},[47],[118,47],[118],{"code":51,"score":19,"supported":13,"title":130,"abstract":131,"tags":132},[],[],[26,28],{"code":134,"score":20,"supported":13,"title":135,"abstract":136,"tags":137},"F1",[],[],[119],{"code":58,"score":20,"supported":13,"title":139,"abstract":140,"tags":141},[],[],[25],[143,144],"农业人工智能 智慧农业 深度学习 马铃薯","农业人工智能 智慧农业","农业人工智能智慧农业深度学习马铃薯-1709","10.1016\u002Fj.compag.2026.112372",{"doi":146,"openalex_id":148,"authors":149,"venue":9,"cited_by_count":89,"oa_url":8,"card":165,"direction":94,"ingested_from":96},"W7208757680",[150,152,154,156,158,160,162],{"name":151,"orcid":8},"Xuyang Wang",{"name":153,"orcid":8},"Yun Liu",{"name":155,"orcid":8},"Tianshuo Su",{"name":157,"orcid":8},"Yulu Sun",{"name":159,"orcid":8},"Binheng Huang",{"name":161,"orcid":8},"Yangqian Zhang",{"name":163,"orcid":164},"Wanzhi Zhang","https:\u002F\u002Forcid.org\u002F0000-0002-6196-8037",{"tldr":166,"method":167,"finding":168,"direction":94,"opportunity":169},"提出EOL-DQN改进深度强化学习模型，用于马铃薯种薯切块智能决策。","改进深度强化学习（DQN），结合视觉识别与决策模型。","EOL-DQN能有效提高切块决策的准确性和效率。","可探索将强化学习应用于其他农产品加工或农业机器人操作，优化决策策略。","2026-09-05T23:30:01.927676Z",{"id":172,"title":173,"url":174,"summary":175,"summary_zh":8,"content":8,"source_name":176,"source_url":174,"published_at":177,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":178,"score_detail":179,"sources":182,"tags":184,"primary_topic":185,"secondary_topics":186,"classification":192,"search_phrases":208,"slug":210,"view_count":59,"doi":211,"paper":212,"created_at":226},1404,"Explainable Deep Learning-Based Potato Leaf Disease Detection and Severity Assessment for Smart Agriculture in Bangladesh","https:\u002F\u002Fdoi.org\u002F10.21203\u002Frs.3.rs-10879535\u002Fv1","Explainable Deep Learning-Based Potato Leaf Disease Detection and Severity Assessment for Smart Agriculture in Bangladesh。Research Square","Research Square","2026-09-01T00:00:00Z",53,{"impact":113,"substance":110,"depth":110,"authority":113,"freshness":180,"relevant":20,"comment":181},7,"针对孟加拉国马铃薯病害的可解释深度学习检测研究，方法新颖但地域性强，影响有限。",[183],{"name":176,"url":174},[25,26,118,27],{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[187],{"code":51,"slug":188,"name":189,"path":190,"parent_code":191},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":38,"locked":13,"version":39,"method":40,"evidence":193},{"candidates":194,"agricultural_evidence":45},[195,199,204],{"code":31,"score":44,"supported":45,"title":196,"abstract":197,"tags":198},[47],[47],[118],{"code":58,"score":44,"supported":45,"title":200,"abstract":202,"tags":203},[201],"smart agriculture",[201],[25],{"code":51,"score":44,"supported":45,"title":205,"abstract":206,"tags":207},[55],[55],[26],[209,66],"农业人工智能 作物病害 智慧农业 马铃薯","农业人工智能作物病害智慧农业马铃薯-1404","10.21203\u002Frs.3.rs-10879535\u002Fv1",{"doi":211,"openalex_id":213,"authors":214,"venue":176,"cited_by_count":89,"oa_url":224,"card":8,"direction":225,"ingested_from":96},"W7204884709",[215,218,221],{"name":216,"orcid":217},"Kazi Abdul Mannan","https:\u002F\u002Forcid.org\u002F0000-0002-7123-132X",{"name":219,"orcid":220},"Sinha Nafiz Hasan","https:\u002F\u002Forcid.org\u002F0009-0007-8906-4586",{"name":222,"orcid":223},"Ahmed Shafin","https:\u002F\u002Forcid.org\u002F0009-0000-4162-6913","https:\u002F\u002Fwww.researchsquare.com\u002Farticle\u002Frs-10879535\u002Flatest.pdf","智慧农业 \u002F 农业物联网","2026-09-02T23:30:10.900822Z",{"id":228,"title":229,"url":230,"summary":231,"summary_zh":8,"content":8,"source_name":232,"source_url":8,"published_at":233,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":234,"score_detail":235,"sources":239,"tags":241,"primary_topic":244,"secondary_topics":245,"classification":246,"search_phrases":273,"slug":276,"view_count":255,"doi":8,"paper":277,"created_at":285},5064,"Detection of Potato Plant Leaf Diseases using Convolutional Neural Networks","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.20544","Haimanot Bitew Alemayehu、Simachew Melaku Ayalew、Chilotie Desalew Mengesha、Ayisheshim Almaw Bogale、Anteneh Birhan Yenew、Abrham Tegegne Bogale在arXiv 2026-10-15上传的预印本,面向埃塞俄比亚粮食安全作物马铃薯,提出可部署于边缘设备的轻量卷积神经网络,完成健康、早疫病、晚疫病三类分类。模型在PlantVillage(2,215张图像)训练,测试准确率98.66%;在埃塞俄比亚Banja镇田间独立采集的247张图像测试中准确率为90.28%,体现独立田间验证相较受控基准更接近真实部署条件。模型仅含446,787个可训练参数、约1.70MB,训练周期较VGG16和MobileNetV2更短。【预印本未审稿;仅在埃塞俄比亚一地进行田间验证,跨地区泛化能力未测】","arXiv preprint 2026-10-15","2026-10-15T00:00:00Z",71,{"impact":110,"substance":111,"depth":236,"authority":237,"freshness":12,"relevant":20,"comment":238},17,9,"预印本提出仅1.7MB的轻量CNN实现马铃薯早疫病、晚疫病识别，含独立田间验证，方法扎实但尚未审稿、泛化性待验证，属细分领域技术进展。",[240],{"name":232,"url":230},[25,26,118,242,243],"边缘计算","病害识别",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":13,"version":39,"method":40,"evidence":247},{"candidates":248,"agricultural_evidence":45},[249,253,260,264,268],{"code":31,"score":44,"supported":45,"title":250,"abstract":251,"tags":252},[47],[118],[118],{"code":254,"score":255,"supported":45,"title":256,"abstract":257,"tags":259},"A8",3,[],[258],"粮食安全",[],{"code":51,"score":19,"supported":13,"title":261,"abstract":262,"tags":263},[],[],[26,243],{"code":58,"score":20,"supported":13,"title":265,"abstract":266,"tags":267},[],[],[25],{"code":269,"score":20,"supported":13,"title":270,"abstract":271,"tags":272},"I5",[],[],[242],[274,275],"埃塞俄比亚 马铃薯 晚疫病 检测","轻量CNN 马铃薯 叶片病害","埃塞俄比亚马铃薯晚疫病检测-5064",{"doi":8,"openalex_id":8,"authors":278,"venue":8,"cited_by_count":89,"oa_url":8,"card":279,"direction":94,"ingested_from":284},[],{"tldr":280,"method":281,"finding":282,"direction":94,"opportunity":283},"提出轻量CNN实现马铃薯早疫病与晚疫病三分类，并在埃塞俄比亚田间验证。","轻量卷积神经网络，PlantVillage 2215张训练，Banja镇247张","测试集准确率98.66%，独立田间测试降至90.28%，模型仅1.70MB。","可研究跨地区\u002F多作物泛化、田间复杂背景鲁棒性及边缘设备实时部署优化。","agent","2026-10-16T00:14:01.369956Z",{"id":287,"title":288,"url":289,"summary":290,"summary_zh":291,"content":8,"source_name":292,"source_url":289,"published_at":293,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":294,"score_detail":295,"sources":298,"tags":300,"primary_topic":303,"secondary_topics":304,"classification":306,"search_phrases":323,"slug":326,"view_count":89,"doi":327,"paper":328,"created_at":351},4818,"Hybrid Deep Feature Extraction and Ensemble Machine Learning for Potato Leaf Disease Classification in Uncontrolled Field Conditions","https:\u002F\u002Fdoi.org\u002F10.15832\u002Fankutbd.1837896","Early and accurate diagnosis of potato leaf diseases is critical for preventing yield losses under real field conditions. This study proposes a hybrid deep feature–based machine learning framework that combines transfer learning and ensemble classifiers to automatically identify seven potato leaf disease classes from images. A total of 4,260 images from the publicly available Potato Leaf Disease Dataset were organized into seven categories: Bacteria, Virus, Pest, Fungi, Nematode, Phytophthora, and Healthy. Real-time image augmentation was performed using Keras ImageDataGenerator to improve strength to field variability. Deep feature vectors were extracted from three pre-trained convolutional neural networks (ResNet50, EfficientNetB0, and MobileNetV2), each followed by a lightweight dense head, and concatenated into 768-dimensional feature representations. After standardization, dimensionality reduction was applied via principal component analysis, and class imbalance in the training set was addressed using the SMOTE-ENN hybrid resampling method. On these deep features, 32 classical machine learning and ensemble models including SVMs, tree-based methods, boosting algorithms, multilayer perceptrons, and four ensemble schemes, were trained. Model performance was assessed by three-fold cross-validation on the training set and final evaluation on the held-out validation set using accuracy, precision, recall, and macro F1-score. Ensemble models outperformed individual classifiers. The best performance was obtained with the StackingClassifier_L2 model, which combines XGBoost, LightGBM, Random Forest, SVM with RBF kernel, and Extra Trees within a stacking framework. This model achieved an accuracy of 81.34% and a macro F1-score of 81.74% on the validation set. The proposed hybrid system, which integrates multi-backbone deep feature extraction with comprehensive classical and ensemble classifiers, provides a robust and practical solution for automatic potato leaf disease classification in uncontrolled field conditions. The results suggest that stacking-based ensembles on top of deep features can capture complex visual patterns more effectively than single models and may support decision-making in precision agriculture.","在马铃薯实际田间条件下，早期准确地诊断叶片病害对于防止产量损失至关重要。本研究提出了一种基于混合深度特征的机器学习框架，该框架结合迁移学习和集成分类器，从图像中自动识别七类马铃薯叶片病害。来自公开可用的马铃薯叶片病害数据集的4,260张图像被分为七个类别：细菌（Bacteria）、病毒（Virus）、害虫（Pest）、真菌（Fungi）、线虫（Nematode）、疫霉（Phytophthora）和健康（Healthy）。使用Keras ImageDataGenerator进行实时图像增强，以提高对田间变异的鲁棒性。从三个预训练的卷积神经网络（ResNet50、EfficientNetB0和MobileNetV2）中提取深度特征向量，每个网络后接一个轻量级密集头，并将其拼接为768维特征表示。经过标准化后，通过主成分分析进行降维，并使用SMOTE-ENN混合重采样方法解决训练集中的类别不平衡问题。在这些深度特征上，训练了32种经典机器学习和集成模型，包括支持向量机、基于树的方法、提升算法、多层感知机以及四种集成方案。通过训练集上的三折交叉验证和保留验证集上的最终评估，使用准确率、精确率、召回率和宏F1分数评估模型性能。集成模型优于单个分类器。最佳性能由StackingClassifier_L2模型获得，该模型在堆叠框架内结合了XGBoost、LightGBM、随机森林、带RBF核的支持向量机和极端随机树。该模型在验证集上达到了81.34%的准确率和81.74%的宏F1分数。所提出的混合系统将多骨干深度特征提取与全面的经典分类器和集成分类器相结合，为无控制田间条件下的马铃薯叶片病害自动分类提供了一种稳健且实用的解决方案。结果表明，基于深度特征的堆叠集成能够比单一模型更有效地捕捉复杂的视觉模式，并可能支持精准农业中的决策。","Tarım Bilimleri Dergisi","2026-10-12T00:00:00Z",65,{"impact":113,"substance":111,"depth":296,"authority":18,"freshness":113,"relevant":20,"comment":297},16,"方法组合较全面、数据规模明确，但验证集准确率仅81.34%，属细分领域技术进展，可作主题聚合素材而非头条精选。",[299],{"name":292,"url":289},[25,26,118,301,302],"病虫害识别","精准农业",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[305],{"code":51,"slug":188,"name":189,"path":190,"parent_code":191},{"status":38,"locked":13,"version":39,"method":40,"evidence":307},{"candidates":308,"agricultural_evidence":45},[309,315,319],{"code":51,"score":296,"supported":45,"title":310,"abstract":312,"tags":314},[311],"machine learning",[313,311],"机器学习",[26,301],{"code":31,"score":110,"supported":45,"title":316,"abstract":317,"tags":318},[47],[118,47],[118],{"code":58,"score":113,"supported":45,"title":320,"abstract":321,"tags":322},[],[302,62],[25,302],[324,325],"马铃薯 叶片病害 深度学习","Potato Leaf Disease Dataset 集成学习","马铃薯叶片病害深度学习-4818","10.15832\u002Fankutbd.1837896",{"doi":327,"openalex_id":329,"authors":330,"venue":292,"cited_by_count":89,"oa_url":345,"card":346,"direction":225,"ingested_from":96},"W7221546496",[331,334,336,339,342],{"name":332,"orcid":333},"Cihan Ünal","https:\u002F\u002Forcid.org\u002F0000-0002-5255-4078",{"name":335,"orcid":8},"Cengizhan Tumer",{"name":337,"orcid":338},"Elham Tahsin Yasin","https:\u002F\u002Forcid.org\u002F0000-0003-3246-6000",{"name":340,"orcid":341},"İlkay Çınar","https:\u002F\u002Forcid.org\u002F0000-0003-0611-3316",{"name":343,"orcid":344},"Murat Köklü","https:\u002F\u002Forcid.org\u002F0000-0002-2737-2360","https:\u002F\u002Fdergipark.org.tr\u002Fen\u002Fdownload\u002Farticle-file\u002F5487015",{"tldr":347,"method":348,"finding":349,"direction":94,"opportunity":350},"融合三种CNN深度特征与集成学习，实现田间马铃薯叶片七类病害分类。","ResNet50\u002FEfficientNetB0\u002FMobileNetV2特征拼接+","StackingClassifier_L2最优，验证集准确率81.34%、宏F1为81.74%。","可探索轻量化模型与多模态数据融合，提升非受控田间小样本病害识别鲁棒性。","2026-10-13T23:30:16.021066Z",{"id":353,"title":354,"url":355,"summary":356,"summary_zh":357,"content":8,"source_name":358,"source_url":355,"published_at":359,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":360,"score_detail":361,"sources":363,"tags":365,"primary_topic":368,"secondary_topics":369,"classification":377,"search_phrases":426,"slug":429,"view_count":59,"doi":430,"paper":431,"created_at":454},3918,"UAV-based RGB imagery and supervised–unsupervised machine learning for estimating sorghum biomass and grain yield under water and nitrogen stress","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffenvs.2026.1928610","Precision agriculture emerged as a key strategy for rational management of water and nutrients amid growing food demand driven by global population expansion. Therefore, timely monitoring of field crops is crucial in maintaining adequate nutrient and water levels in the crop fields. Vegetation indices are increasingly being studied for their use in plant nutrient management and in guiding fertilizer recommendations. However, these indices were not adequately evaluated for nutrient management of crops grown with different water and nitrogen application levels. This study investigated the potential application of RGB imagery from low-cost Unmanned Aerial Vehicles (UAVs), combined with machine learning techniques, for quantifying water and nutrient stress in sorghum [ Sorghum bicolor (L.) Moench] crop performance. The field experimental setup at Prairie View A&M University, located in Southeast Texas, applied four irrigation levels (0, 75, 100, and 125% of irrigation; the 100% irrigation level is a fully irrigated treatment with no water stress) and four nitrogen application rates (0, 90, 180, and 360 kg N ha −1 ). The RGB images were captured before harvesting the grain sorghum. Image segmentation for filtering sorghum crops from soil and weeds was performed using K-means clustering and a Convolutional Neural Network (CNN). The vegetation indices, including the Green-Red Vegetation Index (GRVI), Green Leaf Index (GLI), and Excess Green Index (ExG), derived from the segmented images were used to predict sorghum grain and biomass yields using multiple linear regression, Partial least squares regression, Ridge regression, and XGBoost. The results indicated that no single model consistently outperformed the others across both segmentation approaches and response variables, suggesting that the predictive information in the RGB indices is meaningful with selected ML approaches. For example, biomass prediction using ridge regression yielded a Pearson correlation coefficient (r) of 0.65 and an RMSE of 0.72 for K-means clustering-derived indices. The models exhibited moderate, stage-specific predictive performance, with no single regression method consistently outperforming the others across both segmentation approaches and response variables. Because imagery was acquired only once during the late reproductive period, the RGB indices primarily reflected canopy condition, maturity, and senescence at that time. The findings demonstrate the feasibility of a low-cost, single-date UAV RGB workflow for late-season sorghum assessment, while emphasizing the need for multi-temporal imagery and independent validation before application to season-long stress diagnosis or operational yield forecasting.","精准农业已成为在水资源与养分合理管理中的关键策略，以应对全球人口增长所驱动的日益增长的粮食需求。因此，及时监测田间作物对于维持作物田块中适宜的养分和水分水平至关重要。植被指数在植物养分管理和指导施肥推荐中的应用正日益受到研究。然而，这些指数尚未在不同水分和氮素施用水平下对作物养分管理进行充分评估。本研究探讨了来自低成本无人机（UAV）的RGB影像结合机器学习技术在量化高粱[Sorghum bicolor (L.) Moench]作物表现中水分和养分胁迫方面的潜在应用。位于德克萨斯州东南部的Prairie View A&M大学的田间试验设置了四个灌溉水平（灌溉量的0%、75%、100%和125%；100%灌溉水平为充分灌溉处理，无水分胁迫）和四个氮素施用量（0、90、180和360 kg N ha⁻¹）。RGB图像在收获籽粒高粱前采集。使用K-means聚类和卷积神经网络（CNN）进行图像分割，以将高粱作物与土壤和杂草分离。从分割图像中提取的植被指数，包括绿红植被指数（GRVI）、绿叶指数（GLI）和过量绿指数（ExG），被用于通过多元线性回归、偏最小二乘回归、岭回归和XGBoost预测高粱籽粒和生物量产量。结果表明，在两种分割方法和响应变量下，没有单一模型始终优于其他模型，这表明RGB指数中的预测信息在所选机器学习方法下具有意义。例如，使用岭回归进行生物量预测时，基于K-means聚类所得指数的Pearson相关系数（r）为0.65，RMSE为0.72。这些模型表现出中等、特定阶段的预测性能，在两种分割方法和响应变量下，没有单一回归方法始终优于其他方法。由于影像仅在生殖后期采集一次，RGB指数主要反映当时的冠层状况、成熟度和衰老程度。研究结果证明了低成本、","Frontiers in Environmental Science","2026-09-30T00:00:00Z",69,{"impact":44,"substance":111,"depth":296,"authority":18,"freshness":113,"relevant":20,"comment":362},"低成本无人机RGB影像结合机器学习估算高粱生物量与产量的方法学研究，结论审慎，对精准农业养分水分管理有参考价值，但属单点单期试验，影响范围有限。",[364],{"name":358,"url":355},[25,26,302,366,367],"遥感","高粱",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[370,371],{"code":51,"slug":188,"name":189,"path":190,"parent_code":191},{"code":372,"slug":373,"name":374,"path":375,"parent_code":376},"F3","fertilizers","肥料与水肥一体化","\u002Ftopic\u002Finputs-equipment\u002Ffertilizers","F",{"status":38,"locked":13,"version":39,"method":40,"evidence":378},{"candidates":379,"agricultural_evidence":45},[380,385,389,396,404,408,415,421],{"code":31,"score":110,"supported":45,"title":381,"abstract":383,"tags":384},[382],"sorghum",[367,382],[367],{"code":51,"score":110,"supported":45,"title":386,"abstract":387,"tags":388},[311],[313,311],[26],{"code":372,"score":237,"supported":45,"title":390,"abstract":391,"tags":395},[],[392,393,394],"施肥","养分管理","fertilizer",[],{"code":397,"score":237,"supported":45,"title":398,"abstract":399,"tags":403},"H3",[],[400,401,402],"灌溉","水资源","irrigation",[],{"code":58,"score":113,"supported":45,"title":405,"abstract":406,"tags":407},[],[302,62],[25,302],{"code":409,"score":99,"supported":45,"title":410,"abstract":411,"tags":414},"H2",[],[412,413],"土壤","soil",[],{"code":416,"score":255,"supported":45,"title":417,"abstract":418,"tags":420},"A7",[],[419],"间作",[],{"code":422,"score":20,"supported":13,"title":423,"abstract":424,"tags":425},"I3",[],[],[366],[427,428],"Prairie View A&M University 高粱 无人机","高粱 生物量 产量 无人机 RGB","PrairieViewAMUniversity高粱无人机-3918","10.3389\u002Ffenvs.2026.1928610",{"doi":430,"openalex_id":432,"authors":433,"venue":358,"cited_by_count":89,"oa_url":355,"card":448,"direction":94,"ingested_from":96},"W7214994063",[434,436,439,441,444,446],{"name":435,"orcid":8},"Anoop Valiya Veettil",{"name":437,"orcid":438},"Ripendra Awal","https:\u002F\u002Forcid.org\u002F0000-0002-2453-2592",{"name":440,"orcid":8},"Ali Fares",{"name":442,"orcid":443},"Binita Thapa","https:\u002F\u002Forcid.org\u002F0000-0001-7093-4915",{"name":445,"orcid":8},"Almoutaz Elhassan",{"name":447,"orcid":8},"Atikur Rahman",{"tldr":449,"method":450,"finding":451,"direction":452,"opportunity":453},"用无人机RGB影像与机器学习估算水分氮胁迫下高粱生物量和产量。","低成本无人机RGB影像，K-means与CNN分割，多种回归模型预测。","单一模型未持续最优，RGB指数在特定时期具中等预测能力。","农业遥感与作物表型","可研究多时相RGB影像与深度学习融合，提升胁迫下作物产量预测精度。","2026-10-01T23:30:54.379150Z",{"id":456,"title":457,"url":458,"summary":459,"summary_zh":460,"content":8,"source_name":461,"source_url":458,"published_at":359,"category":11,"cover_url":8,"hotness":462,"is_selected":13,"score":108,"score_detail":463,"sources":465,"tags":469,"primary_topic":472,"secondary_topics":473,"classification":475,"search_phrases":501,"slug":504,"view_count":255,"doi":505,"paper":506,"created_at":516},3913,"Lightweight Edge-AI Model for Real-Time Sorghum Disease Detection on Resource-Constrained Mobile Devices","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23054218","Lightweight Edge-AI Model for Real-Time Sorghum Disease Detection on Resource-Constrained Mobile Devices presents an efficient artificial intelligence approach for identifying sorghum diseases directly on mobile and edge-computing platforms. The study focuses on developing a lightweight machine learning model capable of performing rapid and accurate disease detection while operating under limited computational resources, memory, and power constraints. Computer vision and deep learning techniques are used to analyse sorghum leaf images and distinguish healthy plants from diseased conditions. Model optimization strategies are considered to reduce computational complexity and improve inference speed without substantially compromising detection performance. The proposed approach supports real-time, on-device disease diagnosis, reducing dependence on cloud connectivity and enabling timely intervention in agricultural environments. The work highlights the potential of Edge AI and mobile computing to make intelligent crop monitoring more accessible, practical, and scalable, particularly for farmers and agricultural users operating in resource-constrained settings.","面向资源受限移动设备的实时高粱病害检测轻量级边缘人工智能模型提出了一种高效的人工智能方法，用于直接在移动和边缘计算平台上识别高粱病害。该研究聚焦于开发一种轻量级机器学习模型，能够在有限的计算资源、内存和功耗约束下进行快速、准确的病害检测。研究采用计算机视觉和深度学习技术分析高粱叶片图像，区分健康植株与患病状态。研究考虑了模型优化策略，以降低计算复杂度并提高推理速度，同时不过度损害检测性能。所提出的方法支持实时、设备端病害诊断，减少了对云连接的依赖，并能够在农业环境中实现及时干预。该工作凸显了边缘人工智能和移动计算在使智能作物监测更加可及、实用和可扩展方面的潜力，特别是对于在资源受限环境中作业的农民和农业用户而言。","Zenodo (CERN European Organization for Nuclear Research)",25,{"impact":296,"substance":111,"depth":236,"authority":18,"freshness":237,"relevant":20,"comment":464},"面向资源受限移动端的轻量边缘AI高粱病害实时检测研究，方法实用、契合智慧农业场景，但属细分作物技术进展，影响力有限。",[466,467],{"name":461,"url":458},{"name":461,"url":468},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23054219",[25,26,242,470,471],"作物监测","高粱病害",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[474],{"code":51,"slug":188,"name":189,"path":190,"parent_code":191},{"status":38,"locked":13,"version":39,"method":40,"evidence":476},{"candidates":477,"agricultural_evidence":45},[478,482,489,493,497],{"code":31,"score":112,"supported":45,"title":479,"abstract":480,"tags":481},[382],[367,382],[],{"code":51,"score":12,"supported":45,"title":483,"abstract":484,"tags":488},[],[28,313,485,311,55,486,487],"计算机视觉","artificial intelligence","computer vision",[26],{"code":269,"score":59,"supported":45,"title":490,"abstract":491,"tags":492},[],[242],[242],{"code":58,"score":20,"supported":13,"title":494,"abstract":495,"tags":496},[],[],[25],{"code":422,"score":20,"supported":13,"title":498,"abstract":499,"tags":500},[],[],[470],[502,503],"高粱病害 边缘AI 检测","高粱叶片 病害识别 移动端","高粱病害边缘AI检测-3913","10.5281\u002Fzenodo.23054218",{"doi":505,"openalex_id":507,"authors":508,"venue":461,"cited_by_count":89,"oa_url":458,"card":511,"direction":94,"ingested_from":96},"W7214912247",[509],{"name":510,"orcid":8},"Anantjit Publication",{"tldr":512,"method":513,"finding":514,"direction":94,"opportunity":515},"开发轻量级边缘AI模型，在资源受限移动设备上实时检测高粱病害。","计算机视觉与深度学习分析高粱叶片图像，并做模型轻量化优化。","轻量模型可在移动端实时准确识别病害，减少对云连接依赖。","可探索多作物、多病害通用轻量模型及田间复杂光照下的鲁棒性。","2026-10-01T23:30:48.902282Z"]