[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-5561":3,"related-5561":95},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":24,"tags":26,"primary_topic":32,"secondary_topics":38,"classification":39,"search_phrases":71,"slug":74,"view_count":75,"doi":76,"paper":77,"created_at":94},5561,"Growth Stage and Cultivar Influence the Interpretation of UAV-Derived NDVI for Potato Yield Assessment","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs11540-026-10161-5","Abstract Single-date UAV vegetation indices are widely used to assess potato crop performance and estimate yield. However, whether their biological interpretation remains consistent across cultivars and growth stages is rarely examined. This study investigated how the relationships between UAV-derived multispectral and thermal canopy indicators and potato yield changed during crop development under contrasting irrigation in two cultivars with contrasting maturity classes (Anouk and Celandine). UAV surveys were conducted in July and August, and canopy metrics were related to final yield and tuber traits. The relationship between NDVI and yield differed markedly between cultivars and growth stages. In the early-maturing cultivar Anouk, July NDVI showed a strong positive correlation with yield ( r = 0.87, p = 0.002), whereas August NDVI was not informative. In the late-maturing cultivar Celandine, the relationship reversed from a positive correlation in July ( r = 0.56) to a strong negative correlation in August ( r = −0.80, p = 0.009), indicating that greater late-season canopy greenness was associated with lower yield. Exploratory LOOCV Random Forest models achieved the highest yield prediction accuracy using July features for Anouk ( R 2 = 0.72) and August features for Celandine ( R 2 = 0.47), while multi-temporal features provided similar predictive performance. Greater temporal declines in NDVI were associated with higher yield in both cultivars, consistent with the change in canopy greenness acting as a phenological indicator of the transition from vegetative growth to tuber bulking. These results demonstrate that the interpretation of UAV-derived vegetation indices is strongly dependent on cultivar maturity and growth stage. A single UAV acquisition may therefore provide misleading assessments of crop performance when canopy phenology is not considered. Rather than serving as fixed proxies for yield, canopy vegetation indices should be interpreted within cultivar-specific and temporal contexts when used for potato monitoring and agronomic decision-making.","摘要 单期无人机植被指数被广泛用于评估马铃薯作物表现和估算产量。然而，其生物学解释在不同品种和生育期之间是否保持一致，鲜有研究加以检验。本研究探讨了在两种成熟性类别不同的品种（Anouk和Celandine）中，不同灌溉条件下，无人机获取的多光谱与热红外冠层指标与马铃薯产量之间的关系在作物发育过程中如何变化。无人机调查于7月和8月进行，并将冠层指标与最终产量及块茎性状进行关联分析。NDVI与产量之间的关系在品种和生育期之间差异显著。在早熟品种Anouk中，7月NDVI与产量呈强正相关（r = 0.87，p = 0.002），而8月NDVI则不具有指示意义。在晚熟品种Celandine中，该关系由7月的正相关（r = 0.56）转变为8月的强负相关（r = −0.80，p = 0.009），表明后期冠层绿度越高与产量越低相关。探索性留一交叉验证（LOOCV）随机森林模型在使用Anouk的7月特征（R² = 0.72）和Celandine的8月特征（R² = 0.47）时取得了最高的产量预测精度，而多时相特征提供了相似的预测表现。两个品种中NDVI随时间下降幅度越大均与产量越高相关，这与冠层绿度变化作为从营养生长向块茎膨大转变的物候指示相一致。这些结果表明，无人机获取的植被指数的解释强烈依赖于品种成熟性和生育期。因此，在未考虑冠层物候的情况下，单次无人机采集可能对作物表现作出误导性评估。冠层植被指数不应作为产量的固定替代指标，而应在品种特异性和时间背景下加以解释，方可用于马铃薯监测和农艺决策。",null,"Potato Research","2026-10-20T00:00:00Z","论文",10,false,79,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},16,22,18,14,9,1,"该研究揭示UAV-NDVI与马铃薯产量的关系随品种熟期和生育阶段而反转，对智慧农业遥感监测具有实质方法学与决策参考价值。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","马铃薯","产量预测","遥感","作物表型",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},"A5","tubers-grains","薯类与杂粮","\u002Ftopic\u002Ffield-crops\u002Ftubers-grains","A",[],{"status":40,"locked":14,"version":41,"method":42,"evidence":43},"classified","2026-10-22.2","rules",{"candidates":44,"agricultural_evidence":47},[45,52,60,66],{"code":33,"score":46,"supported":47,"title":48,"abstract":50,"tags":51},15,true,[49],"potato",[28,49],[28],{"code":53,"score":54,"supported":47,"title":55,"abstract":56,"tags":59},"H3",6,[],[57,58],"灌溉","irrigation",[],{"code":61,"score":54,"supported":47,"title":62,"abstract":63,"tags":65},"I3",[],[64],"multispectral",[29,31,30],{"code":67,"score":22,"supported":14,"title":68,"abstract":69,"tags":70},"I1",[],[],[27],[72,73],"UAV NDVI 马铃薯 产量","马铃薯 品种 生育期 遥感","UAVNDVI马铃薯产量-5561",0,"10.1007\u002Fs11540-026-10161-5",{"doi":76,"openalex_id":78,"authors":79,"venue":10,"cited_by_count":75,"oa_url":85,"card":86,"direction":92,"ingested_from":93},"W7223067378",[80,83],{"name":81,"orcid":82},"Jiangsan Zhao","https:\u002F\u002Forcid.org\u002F0000-0003-3916-7388",{"name":84,"orcid":9},"Jaroslaw S. Grodek","https:\u002F\u002Flink.springer.com\u002Fcontent\u002Fpdf\u002F10.1007\u002Fs11540-026-10161-5.pdf",{"tldr":87,"method":88,"finding":89,"direction":90,"opportunity":91},"研究不同品种和生育期下无人机NDVI与马铃薯产量的关系差异。","两个熟期品种、多时相无人机多光谱与热红外冠层指标，结合随机森林建模。","NDVI与产量的关系随品种和时期反转，晚熟品种8月NDVI与产量强负相关。","农业遥感与作物表型","可构建融合品种熟期与冠层物候期的时相自适应产量估算模型，避免单次飞行误判。","智慧农业 \u002F 农业物联网","openalex","2026-10-22T11:20:21.975818Z",{"total":54,"page":22,"page_size":54,"items":96},[97,155,217,289,392,487],{"id":98,"title":99,"url":100,"summary":101,"summary_zh":102,"content":9,"source_name":103,"source_url":100,"published_at":104,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":105,"score_detail":106,"sources":110,"tags":112,"primary_topic":115,"secondary_topics":116,"classification":117,"search_phrases":133,"slug":136,"view_count":108,"doi":137,"paper":138,"created_at":154},1589,"Pre-symptomatic detection of late blight in potatoes using field spectroscopy and backpropagation neural networks","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112339","Pre-symptomatic detection of late blight in potatoes using field spectroscopy and backpropagation neural networks。Computers and Electronics in Agriculture","利用田间光谱学与反向传播神经网络实现马铃薯晚疫病的症状前检测。《农业计算机与电子》","Computers and Electronics in Agriculture","2026-09-04T00:00:00Z",62,{"impact":107,"substance":19,"depth":17,"authority":20,"freshness":108,"relevant":22,"comment":109},12,2,"研究利用田间光谱与神经网络实现马铃薯晚疫病症状前检测，方法新颖，数据可靠，对精准农业有参考价值，但时效性较低。",[111],{"name":103,"url":100},[27,28,30,113,114],"病虫害监测","神经网络",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":118},{"candidates":119,"agricultural_evidence":47},[120,125,129],{"code":33,"score":121,"supported":47,"title":122,"abstract":123,"tags":124},4,[],[28],[28],{"code":67,"score":22,"supported":14,"title":126,"abstract":127,"tags":128},[],[],[27],{"code":61,"score":22,"supported":14,"title":130,"abstract":131,"tags":132},[],[],[30],[134,135],"病虫害监测 智慧农业 神经网络 马铃薯","病虫害监测 智慧农业","病虫害监测智慧农业神经网络马铃薯-1589","10.1016\u002Fj.compag.2026.112339",{"doi":137,"openalex_id":139,"authors":140,"venue":103,"cited_by_count":75,"oa_url":9,"card":149,"direction":90,"ingested_from":93},"W7207614551",[141,143,146],{"name":142,"orcid":9},"Keren Salinas",{"name":144,"orcid":145},"Ran Nisim Lati","https:\u002F\u002Forcid.org\u002F0000-0002-2896-857X",{"name":147,"orcid":148},"Anna Brook","https:\u002F\u002Forcid.org\u002F0000-0002-3205-6581",{"tldr":150,"method":151,"finding":152,"direction":90,"opportunity":153},"利用田间光谱和BP神经网络在马铃薯晚疫病症状出现前进行检测。","田间光谱测量结合反向传播神经网络分类。","可在症状出现前检测到晚疫病，实现早期预警。","可探索多光谱\u002F高光谱影像结合深度学习，实现大范围早期病害预警。","2026-09-04T23:30:01.531043Z",{"id":156,"title":157,"url":158,"summary":159,"summary_zh":9,"content":9,"source_name":160,"source_url":9,"published_at":161,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":162,"score_detail":163,"sources":167,"tags":169,"primary_topic":173,"secondary_topics":174,"classification":175,"search_phrases":203,"slug":206,"view_count":184,"doi":9,"paper":207,"created_at":216},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":46,"substance":164,"depth":165,"authority":21,"freshness":13,"relevant":22,"comment":166},20,17,"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。",[168],{"name":160,"url":158},[27,170,28,171,172],"农业人工智能","边缘计算","病害识别",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":176},{"candidates":177,"agricultural_evidence":47},[178,182,189,194,198],{"code":33,"score":107,"supported":47,"title":179,"abstract":180,"tags":181},[49],[28],[28],{"code":183,"score":184,"supported":47,"title":185,"abstract":186,"tags":188},"A8",3,[],[187],"粮食安全",[],{"code":190,"score":108,"supported":14,"title":191,"abstract":192,"tags":193},"I2",[],[],[170,172],{"code":67,"score":22,"supported":14,"title":195,"abstract":196,"tags":197},[],[],[27],{"code":199,"score":22,"supported":14,"title":200,"abstract":201,"tags":202},"I5",[],[],[171],[204,205],"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":9,"openalex_id":9,"authors":208,"venue":9,"cited_by_count":75,"oa_url":9,"card":209,"direction":213,"ingested_from":215},[],{"tldr":210,"method":211,"finding":212,"direction":213,"opportunity":214},"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。","农业人工智能与决策模型","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":218,"title":219,"url":220,"summary":221,"summary_zh":222,"content":9,"source_name":223,"source_url":220,"published_at":224,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":225,"score_detail":226,"sources":230,"tags":232,"primary_topic":235,"secondary_topics":236,"classification":242,"search_phrases":260,"slug":263,"view_count":75,"doi":264,"paper":265,"created_at":288},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":227,"substance":164,"depth":17,"authority":228,"freshness":227,"relevant":22,"comment":229},8,13,"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。",[231],{"name":223,"url":220},[27,170,28,233,234],"病虫害识别","精准农业",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[237],{"code":190,"slug":238,"name":239,"path":240,"parent_code":241},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":40,"locked":14,"version":41,"method":42,"evidence":243},{"candidates":244,"agricultural_evidence":47},[245,251,255],{"code":190,"score":17,"supported":47,"title":246,"abstract":248,"tags":250},[247],"machine learning",[249,247],"机器学习",[170,233],{"code":33,"score":46,"supported":47,"title":252,"abstract":253,"tags":254},[49],[28,49],[28],{"code":67,"score":227,"supported":47,"title":256,"abstract":257,"tags":259},[],[234,258],"precision agriculture",[27,234],[261,262],"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":264,"openalex_id":266,"authors":267,"venue":223,"cited_by_count":75,"oa_url":282,"card":283,"direction":92,"ingested_from":93},"W7221546496",[268,271,273,276,279],{"name":269,"orcid":270},"Cihan Ünal","https:\u002F\u002Forcid.org\u002F0000-0002-5255-4078",{"name":272,"orcid":9},"Cengizhan Tumer",{"name":274,"orcid":275},"Elham Tahsin Yasin","https:\u002F\u002Forcid.org\u002F0000-0003-3246-6000",{"name":277,"orcid":278},"İlkay Çınar","https:\u002F\u002Forcid.org\u002F0000-0003-0611-3316",{"name":280,"orcid":281},"Murat Köklü","https:\u002F\u002Forcid.org\u002F0000-0002-2737-2360","https:\u002F\u002Fdergipark.org.tr\u002Fen\u002Fdownload\u002Farticle-file\u002F5487015",{"tldr":284,"method":285,"finding":286,"direction":213,"opportunity":287},"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":290,"title":291,"url":292,"summary":293,"summary_zh":294,"content":9,"source_name":295,"source_url":292,"published_at":296,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":297,"score_detail":298,"sources":301,"tags":303,"primary_topic":308,"secondary_topics":309,"classification":310,"search_phrases":361,"slug":364,"view_count":121,"doi":365,"paper":366,"created_at":391},3995,"Determinants of farmers’ willingness to adopt technologies for the agroecological and precision management of potato pests and diseases in Rwanda","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffsufs.2026.1930171","Introduction Potato ( Solanum tuberosum L. ) production in Rwanda is limited by pests and diseases, resulting in significant yield losses and increased use of synthetic pesticides. Despite growing interest in sustainable agriculture, few studies provide empirical evidence on farmers’ knowledge of agroecological pest management practices and precision agriculture in Rwanda. This study assessed farmers’ management practices, awareness and perceptions of agroecological practices and precision agriculture technologies, as well as factors that may influence the willingness to adopt precision agriculture tools in smallholder potato systems. Methods A farm household survey using a semi-structured questionnaire was conducted among 223 potato farmers in three districts of Rwanda (i.e., Rubavu, Gicumbi, and Nyamagabe) in July 2025. Descriptive statistics, Chi square tests, and Fisher’s exact tests were used to analyze farmers’ practices and perceptions. A Firth-penalized logistic regression model, constructed based on a purposeful selection of covariates strategy, was used to identify factors associated with farmers’ willingness to adopt precision agriculture technologies. Results Findings revealed that pests and diseases were the main production constraints, with bacterial wilt, viruses, late blight, and whiteflies being the most frequently cited. Farmers primarily used synthetic pesticides to manage aerial pests and foliar diseases, while preventive agronomic practices were used to manage soil-borne pests and diseases. The use of biopesticides remained extremely limited and farmers were aware of the negative impacts of pesticide misuse and expressed a strong willingness to adopt better pest management practices. Knowledge of precision agriculture technologies was mainly limited (79%). Farmers associated precision agriculture primarily with mechanization, whereas awareness of drones, sensors and digital decision-support tools was limited. They demonstrated highly positive perceptions toward precision agriculture (90%) and a strong willingness to learn more (87%). The results of the logistic regression showed that mobile phone usage (OR = 20.58, p \u003C 0.01) and the willingness to adopt agroecological practices (OR = 67.73, p \u003C 0.001) were associated with a higher likelihood of expressing willingness to adopt precision agriculture technologies. Discussion These results highlight the opportunity to integrate precision agroecology approaches in Rwanda. Mobile-based advisory systems and low-cost digital technologies could serve as effective entry points for promoting sustainable potato production systems among smallholder farmers.","引言 卢旺达的马铃薯（Solanum tuberosum L.）生产受到病虫害的制约，导致显著的产量损失以及合成农药使用量的增加。尽管可持续农业日益受到关注，但鲜有研究提供关于卢旺达农民对农业生态病虫害管理实践和精准农业认知的实证证据。本研究评估了农民的管理实践、对农业生态实践和精准农业技术的认知与看法，以及可能影响小农马铃薯生产体系采用精准农业工具意愿的因素。方法 于2025年7月在卢旺达三个地区（即鲁巴武、吉孔比和尼亚马加贝）对223名马铃薯种植户开展了采用半结构化问卷的农户调查。采用描述性统计、卡方检验和Fisher精确检验分析农民的做法和看法。基于有目的协变量选择策略构建Firth惩罚逻辑回归模型，用于识别与农民采用精准农业技术意愿相关的因素。结果 研究结果显示，病虫害是主要的生产制约因素，其中青枯病、病毒病、晚疫病和烟粉虱被提及的频率最高。农民主要使用合成农药来防治地上害虫和叶部病害，而采用预防性农艺措施来防治土传病虫害。生物农药的使用仍然极为有限，农民已意识到农药滥用的负面影响，并表达了采用更好病虫害管理实践的强烈意愿。对精准农业技术的了解主要有限（79%）。农民主要将精准农业与机械化联系在一起，而对无人机、传感器和数字决策支持工具的认知有限。他们对精准农业表现出高度积极的看法（90%）和强烈的进一步学习意愿（87%）。逻辑回归结果表明，手机使用（OR = 20.58，p \u003C 0.01）和采用农业生态实践的意愿（OR = 67.73，p \u003C 0.001）与表达采用精准农业技术意愿的较高可能性相关。讨论 这些结果凸显了在卢旺达整合精准农业生态方法的机会。基于移动端的咨询服务","Frontiers in Sustainable Food Systems","2026-10-01T00:00:00Z",72,{"impact":107,"substance":299,"depth":165,"authority":228,"freshness":21,"relevant":22,"comment":300},21,"基于223户农户调查的实证研究，揭示手机使用与生态农业意愿对精准农业技术采纳的显著影响，对数字植保与小农户技术推广有参考价值，但属区域性研究，公共影响有限。",[302],{"name":295,"url":292},[27,28,304,305,306,307],"病虫害防控","小农户","数字植保","卢旺达",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":311},{"candidates":312,"agricultural_evidence":47},[313,317,322,329,336,343,349,355],{"code":33,"score":46,"supported":47,"title":314,"abstract":315,"tags":316},[49],[28,49],[28],{"code":67,"score":318,"supported":47,"title":319,"abstract":320,"tags":321},7,[],[234,258],[27],{"code":323,"score":54,"supported":47,"title":324,"abstract":325,"tags":328},"F4",[],[326,327],"农药","pesticide",[],{"code":330,"score":54,"supported":47,"title":331,"abstract":332,"tags":335},"H6",[],[333,334],"农业生态","agroecology",[],{"code":337,"score":54,"supported":47,"title":338,"abstract":339,"tags":342},"H8",[],[340,341],"可持续农业","sustainable agriculture",[],{"code":344,"score":121,"supported":47,"title":345,"abstract":346,"tags":348},"G2",[],[347],"smallholder",[305],{"code":350,"score":184,"supported":47,"title":351,"abstract":352,"tags":354},"F5",[],[353],"机械化",[],{"code":356,"score":184,"supported":47,"title":357,"abstract":358,"tags":360},"H2",[],[359],"soil",[],[362,363],"卢旺达 马铃薯 病虫害","卢旺达 精准农业 采纳意愿","卢旺达马铃薯病虫害-3995","10.3389\u002Ffsufs.2026.1930171",{"doi":365,"openalex_id":367,"authors":368,"venue":295,"cited_by_count":75,"oa_url":292,"card":385,"direction":389,"ingested_from":93},"W7215069280",[369,371,373,376,379,382],{"name":370,"orcid":9},"Judicael S. O. Ganta",{"name":372,"orcid":9},"Antoine Karangwa",{"name":374,"orcid":375},"Peace Bamurigire","https:\u002F\u002Forcid.org\u002F0000-0002-9884-9787",{"name":377,"orcid":378},"Nicodème V. Fassinou Hotegni","https:\u002F\u002Forcid.org\u002F0000-0001-5826-3688",{"name":380,"orcid":381},"Enoch Gbenato Achigan-Dako","https:\u002F\u002Forcid.org\u002F0000-0002-5493-0516",{"name":383,"orcid":384},"Vincent de Paul Bigirimana","https:\u002F\u002Forcid.org\u002F0009-0003-0097-2555",{"tldr":386,"method":387,"finding":388,"direction":389,"opportunity":390},"调查卢旺达223户马铃薯种植户，分析其采纳精准农业技术的意愿及影响因素。","农户问卷调查，描述统计、卡方检验与Firth惩罚逻辑回归。","手机使用和愿采纳生态农业实践显著提升精准农业技术采纳意愿。","数字乡村与农业信息化","可研究手机端决策支持工具如何与生态农业实践结合，推动小农户精准病虫害管理。","2026-10-02T23:30:09.816615Z",{"id":393,"title":394,"url":395,"summary":396,"summary_zh":397,"content":9,"source_name":398,"source_url":395,"published_at":399,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":400,"score_detail":401,"sources":403,"tags":405,"primary_topic":407,"secondary_topics":408,"classification":416,"search_phrases":459,"slug":462,"view_count":121,"doi":463,"paper":464,"created_at":486},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":107,"substance":164,"depth":17,"authority":228,"freshness":227,"relevant":22,"comment":402},"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。",[404],{"name":398,"url":395},[27,170,234,30,406],"高粱",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[409,410],{"code":190,"slug":238,"name":239,"path":240,"parent_code":241},{"code":411,"slug":412,"name":413,"path":414,"parent_code":415},"F3","fertilizers","肥料与水肥一体化","\u002Ftopic\u002Finputs-equipment\u002Ffertilizers","F",{"status":40,"locked":14,"version":41,"method":42,"evidence":417},{"candidates":418,"agricultural_evidence":47},[419,424,428,435,440,444,449,455],{"code":33,"score":46,"supported":47,"title":420,"abstract":422,"tags":423},[421],"sorghum",[406,421],[406],{"code":190,"score":46,"supported":47,"title":425,"abstract":426,"tags":427},[247],[249,247],[170],{"code":411,"score":21,"supported":47,"title":429,"abstract":430,"tags":434},[],[431,432,433],"施肥","养分管理","fertilizer",[],{"code":53,"score":21,"supported":47,"title":436,"abstract":437,"tags":439},[],[57,438,58],"水资源",[],{"code":67,"score":227,"supported":47,"title":441,"abstract":442,"tags":443},[],[234,258],[27,234],{"code":356,"score":54,"supported":47,"title":445,"abstract":446,"tags":448},[],[447,359],"土壤",[],{"code":450,"score":184,"supported":47,"title":451,"abstract":452,"tags":454},"A7",[],[453],"间作",[],{"code":61,"score":22,"supported":14,"title":456,"abstract":457,"tags":458},[],[],[30],[460,461],"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":463,"openalex_id":465,"authors":466,"venue":398,"cited_by_count":75,"oa_url":395,"card":481,"direction":213,"ingested_from":93},"W7214994063",[467,469,472,474,477,479],{"name":468,"orcid":9},"Anoop Valiya Veettil",{"name":470,"orcid":471},"Ripendra Awal","https:\u002F\u002Forcid.org\u002F0000-0002-2453-2592",{"name":473,"orcid":9},"Ali Fares",{"name":475,"orcid":476},"Binita Thapa","https:\u002F\u002Forcid.org\u002F0000-0001-7093-4915",{"name":478,"orcid":9},"Almoutaz Elhassan",{"name":480,"orcid":9},"Atikur Rahman",{"tldr":482,"method":483,"finding":484,"direction":90,"opportunity":485},"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。","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":488,"title":489,"url":490,"summary":491,"summary_zh":492,"content":9,"source_name":493,"source_url":490,"published_at":399,"category":12,"cover_url":9,"hotness":494,"is_selected":14,"score":495,"score_detail":496,"sources":498,"tags":506,"primary_topic":508,"secondary_topics":509,"classification":511,"search_phrases":533,"slug":536,"view_count":184,"doi":537,"paper":538,"created_at":548},3912,"An Integrated Computer Vision and Machine Learning Framework for Sorghum Disease Severity Assessment and Yield Prediction","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23054047","An Integrated Computer Vision and Machine Learning Framework for Sorghum Disease Severity Assessment and Yield Prediction presents a technology-driven approach for automated crop health monitoring and yield estimation in sorghum cultivation. The study integrates computer vision techniques and machine learning algorithms to identify and quantify disease severity from crop images and to predict potential yield based on relevant visual and agronomic characteristics. The framework aims to reduce the limitations of conventional manual disease assessment, which can be time-consuming and subject to human variability. Image processing and feature extraction techniques are employed to capture disease-related characteristics, while machine learning models support classification, severity estimation, and yield prediction. By combining disease assessment with yield forecasting, the proposed framework provides a comprehensive approach to precision agriculture and data-driven crop management. The work demonstrates the potential of artificial intelligence and computer vision to support timely decision-making, improve crop monitoring, and contribute to sustainable and efficient sorghum production.","一个集成的计算机视觉与机器学习框架用于高粱病害严重度评估与产量预测，提出了一种技术驱动的方法，用于高粱种植中的自动化作物健康监测与产量估算。该研究整合了计算机视觉技术和机器学习算法，从作物图像中识别和量化病害严重度，并基于相关视觉和农艺特征预测潜在产量。该框架旨在减少传统人工病害评估的局限性，传统方法可能耗时且受人为变异影响。研究采用图像处理和特征提取技术捕捉病害相关特征，同时机器学习模型支持分类、严重度估计和产量预测。通过将病害评估与产量预测相结合，所提出的框架为精准农业和数据驱动的作物管理提供了一种综合方法。该工作展示了人工智能和计算机视觉在支持及时决策、改善作物监测以及促进可持续和高效高粱生产方面的潜力。","International Journal of Emerging Technologies and Innovative Research",55,56,{"impact":107,"substance":17,"depth":20,"authority":54,"freshness":227,"relevant":22,"comment":497},"论文提出计算机视觉与机器学习结合的高粱病害严重度评估与产量预测框架，方法有一定新意但期刊权威性一般，属细分领域技术进展。",[499,500,502,504],{"name":493,"url":490},{"name":493,"url":501},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23054048",{"name":493,"url":503},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23053752",{"name":493,"url":505},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23053753",[27,170,507,29,406,172],"计算机视觉",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[510],{"code":190,"slug":238,"name":239,"path":240,"parent_code":241},{"status":40,"locked":14,"version":41,"method":42,"evidence":512},{"candidates":513,"agricultural_evidence":47},[514,521,525,529],{"code":190,"score":515,"supported":47,"title":516,"abstract":518,"tags":520},28,[247,517],"computer vision",[249,507,247,519,517],"artificial intelligence",[170,172,507],{"code":33,"score":46,"supported":47,"title":522,"abstract":523,"tags":524},[421],[406,421],[406],{"code":67,"score":318,"supported":47,"title":526,"abstract":527,"tags":528},[],[234,258],[27],{"code":61,"score":22,"supported":14,"title":530,"abstract":531,"tags":532},[],[],[29],[534,535],"高粱 病害识别 产量预测","计算机视觉 作物病害评估","高粱病害识别产量预测-3912","10.5281\u002Fzenodo.23054047",{"doi":537,"openalex_id":539,"authors":540,"venue":493,"cited_by_count":75,"oa_url":490,"card":543,"direction":213,"ingested_from":93},"W7214900332",[541],{"name":542,"orcid":9},"Anantjit Publication",{"tldr":544,"method":545,"finding":546,"direction":213,"opportunity":547},"融合计算机视觉与机器学习，实现高粱病害严重度评估与产量预测。","图像处理与特征提取结合机器学习分类回归模型。","该框架可自动量化病害严重度并预测产量，减少人工评估偏差。","可探索多作物迁移学习与田间实时轻量化部署，提升泛化性。","2026-10-01T23:30:48.742698Z"]