[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2284":3,"related-2284":98},{"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":67,"slug":70,"view_count":71,"doi":72,"paper":73,"created_at":97},2284,"Lightweight nighttime citrus fruit detection in UAV imagery using an enhanced NightNet","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112378","Lightweight nighttime citrus fruit detection in UAV imagery using an enhanced NightNet。Computers and Electronics in Agriculture","基于增强型NightNet的无人机图像轻量化夜间柑橘果实检测。《计算机与电子农业》",null,"Computers and Electronics in Agriculture","2026-09-11T00:00:00Z","论文",10,false,77,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},16,21,17,14,9,1,"核心期刊论文，提出轻量化夜间柑橘检测方法，方法新颖且面向无人机夜间作业场景，具备细分领域参考价值。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","无人机","农业人工智能","遥感","柑橘",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},"B2","fruit","果树","\u002Ftopic\u002Fhorticulture\u002Ffruit","B",[],{"status":40,"locked":14,"version":41,"method":42,"evidence":43},"classified","2026-10-22.2","rules",{"candidates":44,"agricultural_evidence":47},[45,52,57,62],{"code":33,"score":46,"supported":47,"title":48,"abstract":50,"tags":51},15,true,[49],"citrus",[31,49],[31],{"code":53,"score":22,"supported":14,"title":54,"abstract":55,"tags":56},"I1",[],[],[27],{"code":58,"score":22,"supported":14,"title":59,"abstract":60,"tags":61},"I2",[],[],[29],{"code":63,"score":22,"supported":14,"title":64,"abstract":65,"tags":66},"I3",[],[],[30],[68,69],"农业人工智能 智慧农业 无人机 柑橘","农业人工智能 智慧农业","农业人工智能智慧农业无人机柑橘-2284",2,"10.1016\u002Fj.compag.2026.112378",{"doi":72,"openalex_id":74,"authors":75,"venue":10,"cited_by_count":89,"oa_url":9,"card":90,"direction":94,"ingested_from":96},"W7212284586",[76,78,81,83,85,87],{"name":77,"orcid":9},"Zhixian Wu",{"name":79,"orcid":80},"Juntao Xiong","https:\u002F\u002Forcid.org\u002F0000-0002-1095-812X",{"name":82,"orcid":9},"Zhen Liu",{"name":84,"orcid":9},"Sitong Li",{"name":86,"orcid":9},"Jingru Peng",{"name":88,"orcid":9},"Sidi Chen",0,{"tldr":91,"method":92,"finding":93,"direction":94,"opportunity":95},"提出增强NightNet实现无人机夜间柑橘果实轻量检测。","基于NightNet改进的轻量网络，用于无人机夜间图像。","增强NightNet在夜间无人机图像中实现轻量且准确的柑橘检测。","农业遥感与作物表型","夜间无人机果实检测的轻量化与低照度增强可进一步结合多光谱或时序信息。","openalex","2026-09-13T23:30:02.020275Z",{"total":99,"page":22,"page_size":99,"items":100},6,[101,220,287,339,408,452],{"id":102,"title":103,"url":104,"summary":105,"summary_zh":106,"content":9,"source_name":107,"source_url":104,"published_at":108,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":109,"score_detail":110,"sources":114,"tags":116,"primary_topic":119,"secondary_topics":124,"classification":130,"search_phrases":191,"slug":194,"view_count":22,"doi":195,"paper":196,"created_at":219},4988,"Hierarchical cross-modal spatiotemporal attention network for crop yield prediction in complex Himalayan agroecosystems","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffpls.2026.1933033","Introduction Accurate crop yield prediction is essential for precision agriculture, climate-resilient farm management, and timely decision-making. However, yield prediction remains challenging because of complex, nonlinear, and multi-scale interactions among crop physiology, soil conditions, weather variability, and management practices. Conventional statistical, machine learning, and deep learning approaches, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and long short-term memory (LSTM) networks, often have limitations in capturing long-range temporal dependencies, hierarchical spatial relationships, heterogeneous data modalities, and predictive uncertainty. Methods This study proposes a Hierarchical Cross-Modal Spatio-Temporal Attention Network (HCM-STAN) for crop yield prediction using a unified attention-based framework for integrating heterogeneous agro-environmental data. The architecture incorporates four principal components: (i) hierarchical spatio-temporal attention operating across tree, block, orchard, and regional scales; (ii) a cross-modal attention module for adaptive fusion of IoT-based soil sensor observations, weather data, plant physiological measurements, and drone-based multispectral imagery; (iii) a soil-aware attention head that explicitly models soil memory, hysteresis effects, and root-zone dynamics; and (iv) an uncertainty-aware prediction module combining Monte Carlo dropout and quantile regression to generate calibrated prediction intervals. The framework was evaluated using a multi-source dataset collected from Himalayan apple orchards during 2023–2026, comprising 1,247 monitored trees across three commercial orchards. Results The proposed HCM-STAN achieved an R 2 of 0.89 for four-week-ahead crop yield prediction, representing a 15.6% improvement over the CNN-LSTM baseline. Furthermore, zero-shot transfer to mango orchards achieved an R 2 of 0.67, corresponding to approximately 75% of the performance obtained under full training. Discussion The results demonstrate that integrating hierarchical spatio-temporal representation learning, cross-modal attention, soil-aware modelling, and uncertainty estimation can effectively address the heterogeneous and dynamic nature of crop yield prediction in complex mountain agroecosystems. The observed zero-shot transfer performance further indicates the potential of HCM-STAN to generalize across crop systems without crop-specific retraining. Overall, the proposed framework provides a promising foundation for reliable, uncertainty-aware yield forecasting and can support precision agriculture, climate-smart farm management, and data-driven decision-making in heterogeneous agroecosystems.","引言 准确的作物产量预测对于精准农业、气候适应性农场管理以及及时决策至关重要。然而，由于作物生理、土壤条件、天气变异和管理措施之间复杂、非线性且多尺度的相互作用，产量预测仍然具有挑战性。传统的统计方法、机器学习以及深度学习方法，包括卷积神经网络（CNN）、循环神经网络（RNN）和长短期记忆（LSTM）网络，在捕捉长程时间依赖关系、层次化空间关系、异构数据模态以及预测不确定性方面往往存在局限。方法 本研究提出了一种用于作物产量预测的层次化跨模态时空注意力网络（HCM-STAN），采用统一的基于注意力的框架来整合异构农业环境数据。该架构包含四个主要组成部分：（i）在树、地块、果园和区域尺度上运行的层次化时空注意力；（ii）用于自适应融合基于物联网的土壤传感器观测、天气数据、植物生理测量和无人机多光谱影像的跨模态注意力模块；（iii）显式建模土壤记忆、滞后效应和根区动态的土壤感知注意力头；（iv）结合蒙特卡洛 dropout 和分位数回归以生成校准预测区间的不确定性感知预测模块。该框架使用2023—2026年在喜马拉雅苹果园采集的多源数据集进行了评估，该数据集包含三个商业果园中1，247棵监测树木。结果 所提出的 HCM-STAN 在提前四周作物产量预测中达到了0.89的 R²，相较于 CNN-LSTM 基线提升了15.6%。此外，零样本迁移至芒果园达到了0.67的 R²，相当于完整训练下所获性能的约75%。讨论 结果表明，整合层次化时空表征学习、跨模态注意力、土壤感知建模和不确定性估计，能够有效应对复杂山地农业生态系统中作物产量预测的异构性和动态性。观察到的零样本迁移性能进一步表明，HCM-STAN 具有在无需作物特定再训练的情况下跨作物系统泛化的潜力。总体而言，该 p","Frontiers in Plant Science","2026-10-14T00:00:00Z",81,{"impact":111,"substance":112,"depth":111,"authority":20,"freshness":21,"relevant":22,"comment":113},18,22,"提出分层跨模态时空注意力网络，融合物联网土壤传感、气象、生理与无人机多光谱数据，苹果园四周产量预测R²达0.89并实现芒果园零样本迁移，方法新颖、数据扎实，对智慧农业产量预报有参考价值。",[115],{"name":107,"url":104},[27,29,117,118,30],"产量预测","多模态融合",{"code":58,"slug":120,"name":121,"path":122,"parent_code":123},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[125,126],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"code":63,"slug":127,"name":128,"path":129,"parent_code":123},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":40,"locked":14,"version":41,"method":42,"evidence":131},{"candidates":132,"agricultural_evidence":47},[133,142,150,157,164,171,178,185],{"code":58,"score":134,"supported":47,"title":135,"abstract":136,"tags":141},11,[],[137,138,139,140],"深度学习","机器学习","machine learning","deep learning",[29,118],{"code":33,"score":21,"supported":47,"title":143,"abstract":144,"tags":149},[],[145,146,147,148],"苹果","芒果","orchard","apple",[],{"code":63,"score":151,"supported":47,"title":152,"abstract":153,"tags":156},8,[],[154,155],"无人机多光谱","multispectral",[117,30],{"code":53,"score":158,"supported":47,"title":159,"abstract":160,"tags":163},7,[],[161,162],"精准农业","precision agriculture",[27],{"code":165,"score":99,"supported":47,"title":166,"abstract":167,"tags":170},"H2",[],[168,169],"土壤","soil",[],{"code":172,"score":99,"supported":47,"title":173,"abstract":174,"tags":177},"I5",[],[175,176],"物联网","IoT",[],{"code":179,"score":180,"supported":47,"title":181,"abstract":182,"tags":184},"H6",3,[],[183],"农业生态",[],{"code":186,"score":180,"supported":47,"title":187,"abstract":188,"tags":190},"H7",[],[189],"气候适应",[],[192,193],"喜马拉雅 苹果园 产量预测","HCM-STAN 作物产量预测","喜马拉雅苹果园产量预测-4988","10.3389\u002Ffpls.2026.1933033",{"doi":195,"openalex_id":197,"authors":198,"venue":107,"cited_by_count":89,"oa_url":104,"card":212,"direction":218,"ingested_from":96},"W7221795850",[199,202,204,206,208,210],{"name":200,"orcid":201},"Shabir Ahmad Mir","https:\u002F\u002Forcid.org\u002F0000-0003-2311-218X",{"name":203,"orcid":9},"Umarfarooque Momin",{"name":205,"orcid":9},"Sudeep Kumar E",{"name":207,"orcid":9},"Itfaq Ahmad Mir",{"name":209,"orcid":9},"Ab Rouf Khan",{"name":211,"orcid":9},"Ghulam Mohammad Mir",{"tldr":213,"method":214,"finding":215,"direction":216,"opportunity":217},"提出分层跨模态时空注意力网络HCM-STAN，融合多源农业数据预测喜马拉雅山区苹果产量。","用IoT土壤、气象、生理和无人机多光谱数据，结合分层时空与跨模态注意力及不确定性","四周前产量预测R²达0.89，比CNN-LSTM提升15.6%，零样本迁移芒果R²为0.67。","农业人工智能与决策模型","可探索跨作物零样本迁移的领域自适应机制，并验证模型在更多山地农业生态系统的泛化能力。","智慧农业 \u002F 农业物联网","2026-10-15T23:30:08.750140Z",{"id":221,"title":222,"url":223,"summary":224,"summary_zh":225,"content":9,"source_name":226,"source_url":223,"published_at":227,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":228,"sources":231,"tags":233,"primary_topic":236,"secondary_topics":237,"classification":240,"search_phrases":261,"slug":264,"view_count":22,"doi":265,"paper":266,"created_at":286},4808,"Early Detection of Apple Scab in Orchards and Mildew in Vineyards Using A Novel Deep Learning Model and Multispectral Imagery","https:\u002F\u002Fdoi.org\u002F10.15832\u002Fankutbd.1898342","Agricultural diseases are a significant problem for growers as they cause substantial damage to fruits and leaves, leading to yield losses. Therefore, developing systems for early detection of plant diseases is a crucial issue. In this study, a new deep learning-based hybrid model is presented for the detection and segmentation of plant diseases, specifically apple scab disease in apple orchards and mildew disease in vineyards. Multispectral imagery data collected in agricultural areas of Tekirdag province in Turkey via drones between May 2023 and December 2024 were used in developing the early disease detection system. The datasets contain 3625 images of apple orchards and 5625 images of vineyards. DJI Phantom 4 Multispectral drone, equipped with five spectral bands (Blue, Green, Red, Red Edge, and Near Infrared), was utilized to capture both spectral richness and temporal progression. This study introduces a novel deep learning architecture developed specifically for time series-based disease detection and segmentation using multispectral drone imagery. Changes in plants over time provide important information about the occurrence of plant diseases. For this reason, time series were used in this study to extract features from the changes in plants over time. The proposed model architecture was specifically designed to leverage time series information, enabling robust tracking of crop health changes over time. The model trained with the dataset collected for apple diseases achieved an average Intersection Over Unit (IoU) value of 82.05%, while the model trained with the dataset collected for vineyard diseases reached an IoU value of 79.67%. The findings highlight the effectiveness of integrating drone-acquired multispectral time-series data with advanced deep learning models for scalable, accurate, and timely plant disease detection in precision agriculture.","农业病害是种植者面临的重大问题，会对果实和叶片造成严重损害，导致产量损失。因此，开发植物病害早期检测系统是一个至关重要的问题。本研究提出了一种基于深度学习的新型混合模型，用于植物病害的检测与分割，具体针对苹果园中的苹果黑星病和葡萄园中的霜霉病。该早期病害检测系统的开发使用了2023年5月至2024年12月期间通过无人机在土耳其泰基尔达省农业区域采集的多光谱影像数据。数据集包含3625幅苹果园图像和5625幅葡萄园图像。所用DJI Phantom 4多光谱无人机配备五个光谱波段（蓝、绿、红、红边和近红外），用于捕捉光谱丰富度和时间变化过程。本研究提出了一种专门开发的深度学习架构，用于基于时间序列的多光谱无人机影像病害检测与分割。植物随时间的变化提供了关于植物病害发生的重要信息。因此，本研究使用时间序列从植物随时间的变化中提取特征。所提出的模型架构专门设计以利用时间序列信息，从而能够稳健地跟踪作物健康状况随时间的变化。使用苹果病害数据集训练的模型达到了82.05%的平均交并比（IoU）值，而使用葡萄园病害数据集训练的模型达到了79.67%的IoU值。研究结果凸显了将无人机获取的多光谱时间序列数据与先进深度学习模型相结合，在精准农业中实现可扩展、准确且及时的植物病害检测方面的有效性。","Tarım Bilimleri Dergisi","2026-10-12T00:00:00Z",{"impact":17,"substance":18,"depth":111,"authority":229,"freshness":21,"relevant":22,"comment":230},13,"该研究提出基于多光谱时序影像的新型深度学习模型，实现果园与葡萄园病害早期检测，数据规模大、方法新颖，对精准农业病害预警具有参考价值。",[232],{"name":226,"url":223},[27,28,29,234,235],"遥感监测","病害预警",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[238,239],{"code":58,"slug":120,"name":121,"path":122,"parent_code":123},{"code":63,"slug":127,"name":128,"path":129,"parent_code":123},{"status":40,"locked":14,"version":41,"method":42,"evidence":241},{"candidates":242,"agricultural_evidence":47},[243,248,252,257],{"code":33,"score":19,"supported":47,"title":244,"abstract":245,"tags":247},[148],[145,246,148],"葡萄",[],{"code":58,"score":46,"supported":47,"title":249,"abstract":250,"tags":251},[140],[137,140],[29],{"code":63,"score":253,"supported":47,"title":254,"abstract":255,"tags":256},12,[155],[155],[234],{"code":53,"score":158,"supported":47,"title":258,"abstract":259,"tags":260},[],[161,162],[27],[262,263],"苹果黑星病 无人机 多光谱","葡萄园 霜霉病 深度学习","苹果黑星病无人机多光谱-4808","10.15832\u002Fankutbd.1898342",{"doi":265,"openalex_id":267,"authors":268,"venue":226,"cited_by_count":89,"oa_url":280,"card":281,"direction":218,"ingested_from":96},"W7221558726",[269,272,275,277],{"name":270,"orcid":271},"Batuhan Aşıroğlu","https:\u002F\u002Forcid.org\u002F0000-0003-0767-6348",{"name":273,"orcid":274},"Aydın Kağan Turkoglu","https:\u002F\u002Forcid.org\u002F0009-0001-8383-8807",{"name":276,"orcid":9},"Fatih Sinan Bir",{"name":278,"orcid":279},"Sibel Senan","https:\u002F\u002Forcid.org\u002F0000-0001-6773-0428","https:\u002F\u002Fdergipark.org.tr\u002Fen\u002Fdownload\u002Farticle-file\u002F5761152",{"tldr":282,"method":283,"finding":284,"direction":94,"opportunity":285},"提出一种基于无人机多光谱时序影像的深度学习混合模型，实现苹果黑星病和葡萄霉病的早期检测与分割。","DJI Phantom 4多光谱无人机采集时序影像，构建时序深度学习分割模型。","苹果病IoU达82.05%，葡萄病达79.67%，验证多光谱时序数据有效性。","可探索多作物、多病害的时序多光谱通用模型，并融合气象与地面数据提升早期预警能力。","2026-10-13T23:30:10.242467Z",{"id":288,"title":289,"url":290,"summary":291,"summary_zh":9,"content":9,"source_name":292,"source_url":9,"published_at":293,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":294,"score_detail":295,"sources":298,"tags":300,"primary_topic":303,"secondary_topics":304,"classification":305,"search_phrases":325,"slug":328,"view_count":329,"doi":9,"paper":330,"created_at":338},3962,"华中农业大学柑橘类果实泛化识别与定位研究——YOLOv8n-Light轻量化部署","https:\u002F\u002Fnews.foodmate.net\u002F2026\u002F10\u002Fwap_754150.html","华中农业大学工学院马京奥、刘洁副教授团队研究YOLOv8n-Light模型在柑橘类果实识别中的应用，模型可同时识别橙、橘、柚三种果实，计算量较原始YOLOv8降低58%，工作站CPU推理速度提升45.9%（达15.35FPS），树莓派4B推理速度提升38.2%（达0.76FPS）；多轴机械臂采摘作业控制中，果实中心坐标X、Y、Z方向平均误差均控制在10mm内，半径误差小于6mm。312次果园采摘测试验证高兼容性与实用性。研究得到国家重点研发计划、国家柑橘产业技术体系资助。","食品伙伴网·2026年10月01日","2026-10-01T00:00:00Z",82,{"impact":111,"substance":112,"depth":296,"authority":229,"freshness":13,"relevant":22,"comment":297},19,"高校团队提出轻量化柑橘识别模型并完成果园实测，方法新颖、数据扎实，对智能采摘装备有参考价值。",[299],{"name":292,"url":290},[27,29,301,31,302],"采摘机器人","轻量化模型",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":306},{"candidates":307,"agricultural_evidence":47},[308,312,316,321],{"code":33,"score":253,"supported":47,"title":309,"abstract":310,"tags":311},[31],[31],[31],{"code":58,"score":71,"supported":14,"title":313,"abstract":314,"tags":315},[],[],[29,302],{"code":317,"score":22,"supported":14,"title":318,"abstract":319,"tags":320},"F6",[],[],[301],{"code":53,"score":22,"supported":14,"title":322,"abstract":323,"tags":324},[],[],[27],[326,327],"华中农业大学 柑橘 采摘机器人","YOLOv8n-Light 柑橘识别","华中农业大学柑橘采摘机器人-3962",5,{"doi":9,"openalex_id":9,"authors":331,"venue":9,"cited_by_count":89,"oa_url":9,"card":332,"direction":218,"ingested_from":337},[],{"tldr":333,"method":334,"finding":335,"direction":218,"opportunity":336},"提出YOLOv8n-Light轻量化模型，实现橙橘柚三种柑橘果实泛化识别与定位，并部署于树莓派和采摘","改进YOLOv8n轻量化模型，工作站与树莓派4B部署，多轴机械臂采摘测试312次","计算量降58%，工作站CPU推理15.35FPS，果实中心坐标误差\u003C10mm，半径误差\u003C6mm。","可探索多品种泛化模型在边缘设备上的精度-速度权衡，及跨季节、遮挡场景下的鲁棒性提升。","agent","2026-10-02T11:53:16.558461Z",{"id":340,"title":341,"url":342,"summary":343,"summary_zh":9,"content":9,"source_name":344,"source_url":9,"published_at":345,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":346,"score_detail":347,"sources":349,"tags":351,"primary_topic":354,"secondary_topics":355,"classification":362,"search_phrases":396,"slug":399,"view_count":71,"doi":9,"paper":400,"created_at":407},3250,"农机化研究2026(11)：基于多源感知与语义分割的果树行识别与路径跟踪控制——郑州工业应用技术学院许洋洋等 DeepLabv3+ F1达0.94","http:\u002F\u002Fwww.qikanvip.com\u002Fqkml\u002F166268.html","农机化研究2026年第11期发表郑州工业应用技术学院许洋洋、柴亚珂、王莹、牛瑞利团队论文：针对果园中裸露土壤、遮蔽物干扰和冠层阴影等因素导致导航路径难以稳定提取的问题，提出融合多源感知与语义分割的自走式植保机果树识别与路径控制方法。首先利用无人机获取多光谱影像并生成正射影像（DOM）与数字表面模型（DSM），计算归一化差异绿度指数（NDGI），增强果树冠层与背景的可分性；然后采用U-Net\u002FDeepLabv3+语义分割网络在保留空间上下文信息的同时实现果树行\u002F背景端到端分割。田间对比试验结果表明，DeepLabv3+整体分割F1可达0.94，每样区生成导航线断裂1.2次，且转向工况下横向误差RMSE为0.11 m，显著优于传统阈值分割和SVM方法。","农机化研究","2026-09-22T00:00:00Z",79,{"impact":17,"substance":112,"depth":111,"authority":229,"freshness":13,"relevant":22,"comment":348},"多源遥感与语义分割结合的果园导航研究，F1达0.94且横向误差0.11米，方法新颖、数据扎实，具备行业参考价值。",[350],{"name":344,"url":342},[27,29,352,30,353],"农机导航","果园植保",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[356],{"code":357,"slug":358,"name":359,"path":360,"parent_code":361},"F5","machinery","农机装备与机械化","\u002Ftopic\u002Finputs-equipment\u002Fmachinery","F",{"status":40,"locked":14,"version":41,"method":42,"evidence":363},{"candidates":364,"agricultural_evidence":47},[365,370,374,380,384,388,392],{"code":357,"score":253,"supported":47,"title":366,"abstract":368,"tags":369},[367],"农机",[367],[352],{"code":33,"score":134,"supported":47,"title":371,"abstract":372,"tags":373},[35],[35],[],{"code":375,"score":180,"supported":47,"title":376,"abstract":377,"tags":379},"F4",[],[378],"植保",[],{"code":165,"score":180,"supported":47,"title":381,"abstract":382,"tags":383},[],[168],[],{"code":53,"score":22,"supported":14,"title":385,"abstract":386,"tags":387},[],[],[27],{"code":58,"score":22,"supported":14,"title":389,"abstract":390,"tags":391},[],[],[29],{"code":63,"score":22,"supported":14,"title":393,"abstract":394,"tags":395},[],[],[30],[397,398],"郑州工业应用技术学院 果树行识别","DeepLabv3 果园导航 路径跟踪","郑州工业应用技术学院果树行识别-3250",{"doi":9,"openalex_id":9,"authors":401,"venue":9,"cited_by_count":89,"oa_url":9,"card":402,"direction":94,"ingested_from":337},[],{"tldr":403,"method":404,"finding":405,"direction":94,"opportunity":406},"提出融合无人机多光谱与语义分割的果树行识别与路径跟踪方法，实现植保机自主导航。","无人机多光谱DOM\u002FDSM与NDGI，U-Net\u002FDeepLabv3+语义分割，","DeepLabv3+分割F1达0.94，导航线断裂1.2次，转向横向误差RMSE 0.11 m，优于","可探索多光谱与DSM特征融合的轻量化分割模型，并迁移至多树种、多季节果园导航。","2026-09-23T00:04:33.496233Z",{"id":409,"title":410,"url":411,"summary":412,"summary_zh":9,"content":9,"source_name":413,"source_url":9,"published_at":414,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":294,"score_detail":415,"sources":417,"tags":419,"primary_topic":422,"secondary_topics":423,"classification":424,"search_phrases":439,"slug":442,"view_count":443,"doi":9,"paper":444,"created_at":451},2270,"华中农大实现柑橘黄龙病早期无损诊断 提LLM辅助拉曼光谱相似度融合框架","https:\u002F\u002Fwww.toutiao.com\u002Farticle\u002F7682626369448165922","华中农业大学工学院联合园艺林学学院在Agriculture Communications发表研究,提出LLM辅助的多通道光谱相似度融合框架(LAMSSF),依托少量经qPCR验证的参考样本,实现柑橘HLB早期无损诊断,降低模型对大规模标注数据的依赖。","华中农业大学 Agriculture Communications","2026-09-06T16:00:00Z",{"impact":112,"substance":112,"depth":111,"authority":20,"freshness":99,"relevant":22,"comment":416},"华中农大提出LLM辅助拉曼光谱融合框架，实现柑橘黄龙病早期无损诊断，方法新颖且降低标注依赖，具备行业推广价值。",[418],{"name":413,"url":411},[27,29,420,31,421],"病害检测","光谱遥感",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":425},{"candidates":426,"agricultural_evidence":47},[427,431,435],{"code":33,"score":253,"supported":47,"title":428,"abstract":429,"tags":430},[31],[31],[31],{"code":53,"score":22,"supported":14,"title":432,"abstract":433,"tags":434},[],[],[27],{"code":58,"score":22,"supported":14,"title":436,"abstract":437,"tags":438},[],[],[29],[440,441],"农业人工智能 光谱遥感 智慧农业 病害检测","农业人工智能 光谱遥感","农业人工智能光谱遥感智慧农业病害检测-2270",4,{"doi":9,"openalex_id":9,"authors":445,"venue":9,"cited_by_count":89,"oa_url":9,"card":446,"direction":216,"ingested_from":337},[],{"tldr":447,"method":448,"finding":449,"direction":216,"opportunity":450},"提出LLM辅助多通道光谱相似度融合框架，实现柑橘黄龙病早期无损诊断。","拉曼光谱多通道相似度融合，LLM辅助，少量qPCR验证参考样本。","少量标注样本即可实现HLB早期无损诊断，降低对大规模标注数据依赖。","可探索LLM辅助光谱融合在更多作物病害早期诊断中的迁移与少样本泛化能力。","2026-09-13T00:04:04.913308Z",{"id":453,"title":454,"url":455,"summary":456,"summary_zh":9,"content":9,"source_name":457,"source_url":9,"published_at":458,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":346,"score_detail":459,"sources":462,"tags":464,"primary_topic":466,"secondary_topics":467,"classification":468,"search_phrases":487,"slug":490,"view_count":71,"doi":9,"paper":491,"created_at":498},1704,"AI Drones Unlock Hidden Avocado & Hazelnut Secrets（Information Processing in Agriculture）","https:\u002F\u002Fagritechinsights.com\u002Findex.php\u002F2026\u002F09\u002F03\u002Fai-drones-unlock-hidden-avocado-hazelnut-secrets","西蒙弗雷泽大学 Xizhi Xia（机电系统工程学校）发表于《Information Processing in Agriculture》。研究开发了基于 AI 的无人机系统，将原始航拍图像转化为可操作的洞察，无需昂贵的训练数据或复杂的数字地形模型（DTM）。研究将无人机映射与加权 K-means、DBSCAN 和聚类分离三种无监督算法相结合，创建逐步分割过程。在田间试验中，该系统在牛油果树木上实现了树高 R² = 0.967、冠层体积 R² = 0.91 的准确度，结果可与许多监督方法相媲美甚至超越。","Agritech Insights","2026-09-03T00:00:00Z",{"impact":460,"substance":112,"depth":111,"authority":253,"freshness":158,"relevant":22,"comment":461},20,"研究提出无监督AI无人机分割方法，在果树表型测量上达到监督学习精度，为低成本精准农业提供新路径。",[463],{"name":457,"url":455},[28,29,161,30,465],"牛油果",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":469},{"candidates":470,"agricultural_evidence":47},[471,475,479,483],{"code":33,"score":443,"supported":47,"title":472,"abstract":473,"tags":474},[],[35],[465],{"code":53,"score":22,"supported":14,"title":476,"abstract":477,"tags":478},[],[],[161],{"code":58,"score":22,"supported":14,"title":480,"abstract":481,"tags":482},[],[],[29],{"code":63,"score":22,"supported":14,"title":484,"abstract":485,"tags":486},[],[],[30],[488,489],"农业人工智能 精准农业 无人机 牛油果","农业人工智能 精准农业","农业人工智能精准农业无人机牛油果-1704",{"doi":9,"openalex_id":9,"authors":492,"venue":9,"cited_by_count":89,"oa_url":9,"card":493,"direction":94,"ingested_from":337},[],{"tldr":494,"method":495,"finding":496,"direction":94,"opportunity":497},"开发基于AI的无人机系统，用无监督算法从航拍图像估算果树高度和冠层体积。","无人机航拍结合加权K-means、DBSCAN和聚类分离的无监督分割方法。","树高R²=0.967，冠层体积R²=0.91，媲美监督方法且无需昂贵训练数据。","无监督方法在多种作物和复杂地形下的泛化能力，以及结合时间序列监测果树生长动态。","2026-09-05T00:04:40.788850Z"]