[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4587":3,"related-4587":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},4587,"Sentinel-2 NDVI as an indicator of apple orchard yield","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffhort.2026.1904481","Satellite data is increasingly being used as a basis for operational crop monitoring. However, satellite technologies for monitoring perennial crops remain underdeveloped. The aim of this study was to assess the relationship between apple yield and NDVI calculated using all available Sentinel-2 data for the growing seasons (March-November) from 2017 to 2024. Totally 81 cloud-free images were analyzed. The seasonal absolute maximum and area-weighted average NDVI were calculated based on analysis of all images for each growing season for each plot. Intensively irrigated, mixed-age apple orchards located in northern Azerbaijan served as the research site. Totally 30 plots with 6 apple tree varieties (Arian, Gala, Golden, Golden Parsi, Granny Smith, and Fuji) planted from 2007 to 2017 were analyzed. Apple yield for each plot for 2018–2024 were collected. The linear regression models between NDVI (the seasonal absolute maximum and area-weighted average) and apple yield was used as the relationship criterion. An analysis of the relationship was conducted for individual apple varieties, for orchard plots, and for plots of different ages. It was found that reliable relationships between apple yield and NDVI are only observed for specific plots with a single variety of the same age (R2cv higher than 0,8 with RPIQ more than 2,1). Grouping plots of the same variety or age does not demonstrate a reliable relationship between NDVI and yield. Only for groups of middle-aged orchards does such a relationship become stronger. These results should be considered when developing methods for satellite monitoring of apple orchards.","卫星数据正日益被用作业务化作物监测的基础。然而，用于监测多年生作物的卫星技术仍不发达。本研究旨在评估苹果产量与利用2017年至2024年生长季（3—11月）所有可用Sentinel-2数据计算的NDVI之间的关系。共分析了81幅无云图像。基于对每个生长季每块样地所有图像的分析，计算了季节绝对最大值NDVI和面积加权平均NDVI。研究地点位于阿塞拜疆北部集约化灌溉的混龄苹果园。共分析了30块样地，涵盖2007年至2017年种植的6个苹果品种（Arian、Gala、Golden、Golden Parsi、Granny Smith和Fuji）。收集了2018—2024年每块样地的苹果产量。以NDVI（季节绝对最大值和面积加权平均值）与苹果产量之间的线性回归模型作为关系评价标准。分别针对单个苹果品种、果园样地以及不同树龄样地进行了关系分析。研究发现，仅在特定同一品种、同树龄的样地中才能观察到苹果产量与NDVI之间可靠的关系（R2cv高于0.8，RPIQ大于2.1）。将同一品种或同一树龄的样地分组后，NDVI与产量之间并未表现出可靠的关系。仅对中年果园分组时，这种关系才变得更强。在开发苹果园卫星监测方法时，应考虑这些结果。",null,"Frontiers in Horticulture","2026-10-09T00:00:00Z","论文",10,false,71,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},12,21,17,13,8,1,"基于2017—2024年81景Sentinel-2影像评估苹果园NDVI与产量的关系，方法扎实、结论有边界条件，对果园遥感监测有参考价值，但属细分领域研究，公共影响有限。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","产量预测","Sentinel-2","遥感监测","苹果园",{"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},[45,54,61,66],{"code":33,"score":46,"supported":47,"title":48,"abstract":51,"tags":53},25,true,[49,50],"orchard","apple",[52,49,50],"苹果",[],{"code":55,"score":56,"supported":47,"title":57,"abstract":58,"tags":60},"H3",3,[],[59],"灌溉",[],{"code":62,"score":56,"supported":14,"title":63,"abstract":64,"tags":65},"I3",[],[],[29,28,30],{"code":67,"score":22,"supported":14,"title":68,"abstract":69,"tags":70},"I1",[],[],[27],[72,73],"Sentinel-2 NDVI 苹果园 产量","阿塞拜疆 苹果园 遥感监测","Sentinel-2NDVI苹果园产量-4587",0,"10.3389\u002Ffhort.2026.1904481",{"doi":76,"openalex_id":78,"authors":79,"venue":10,"cited_by_count":75,"oa_url":86,"card":87,"direction":91,"ingested_from":93},"W7221180616",[80,82,84],{"name":81,"orcid":9},"N. Gasimzade",{"name":83,"orcid":9},"A. Radzhabov",{"name":85,"orcid":9},"I. Savin","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fhorticulture\u002Farticles\u002F10.3389\u002Ffhort.2026.1904481\u002Fpdf",{"tldr":88,"method":89,"finding":90,"direction":91,"opportunity":92},"评估Sentinel-2 NDVI与苹果园产量的关系，发现仅单一品种同龄地块存在可靠相关。","用2017-2024年81景Sentinel-2影像计算NDVI，对30个苹果园","仅单一品种同龄地块NDVI与产量可靠相关（R²cv>0.8），按品种或树龄分组则关系不可靠。","农业遥感与作物表型","多年生果园遥感估产需按品种、树龄精细分层建模，混合地块的普适性模型仍是研究空白。","openalex","2026-10-10T23:30:28.042882Z",{"total":96,"page":22,"page_size":96,"items":97},6,[98,216,284,360,428,469],{"id":99,"title":100,"url":101,"summary":102,"summary_zh":103,"content":9,"source_name":104,"source_url":101,"published_at":105,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":106,"score_detail":107,"sources":113,"tags":115,"primary_topic":119,"secondary_topics":125,"classification":131,"search_phrases":187,"slug":190,"view_count":22,"doi":191,"paper":192,"created_at":215},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":108,"substance":109,"depth":108,"authority":110,"freshness":111,"relevant":22,"comment":112},18,22,14,9,"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。",[114],{"name":104,"url":101},[27,116,28,117,118],"农业人工智能","多模态融合","遥感",{"code":120,"slug":121,"name":122,"path":123,"parent_code":124},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[126,127],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"code":62,"slug":128,"name":129,"path":130,"parent_code":124},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":40,"locked":14,"version":41,"method":42,"evidence":132},{"candidates":133,"agricultural_evidence":47},[134,143,148,154,161,168,175,181],{"code":120,"score":135,"supported":47,"title":136,"abstract":137,"tags":142},11,[],[138,139,140,141],"深度学习","机器学习","machine learning","deep learning",[116,117],{"code":33,"score":111,"supported":47,"title":144,"abstract":145,"tags":147},[],[52,146,49,50],"芒果",[],{"code":62,"score":21,"supported":47,"title":149,"abstract":150,"tags":153},[],[151,152],"无人机多光谱","multispectral",[28,118],{"code":67,"score":155,"supported":47,"title":156,"abstract":157,"tags":160},7,[],[158,159],"精准农业","precision agriculture",[27],{"code":162,"score":96,"supported":47,"title":163,"abstract":164,"tags":167},"H2",[],[165,166],"土壤","soil",[],{"code":169,"score":96,"supported":47,"title":170,"abstract":171,"tags":174},"I5",[],[172,173],"物联网","IoT",[],{"code":176,"score":56,"supported":47,"title":177,"abstract":178,"tags":180},"H6",[],[179],"农业生态",[],{"code":182,"score":56,"supported":47,"title":183,"abstract":184,"tags":186},"H7",[],[185],"气候适应",[],[188,189],"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":191,"openalex_id":193,"authors":194,"venue":104,"cited_by_count":75,"oa_url":101,"card":208,"direction":214,"ingested_from":93},"W7221795850",[195,198,200,202,204,206],{"name":196,"orcid":197},"Shabir Ahmad Mir","https:\u002F\u002Forcid.org\u002F0000-0003-2311-218X",{"name":199,"orcid":9},"Umarfarooque Momin",{"name":201,"orcid":9},"Sudeep Kumar E",{"name":203,"orcid":9},"Itfaq Ahmad Mir",{"name":205,"orcid":9},"Ab Rouf Khan",{"name":207,"orcid":9},"Ghulam Mohammad Mir",{"tldr":209,"method":210,"finding":211,"direction":212,"opportunity":213},"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":217,"title":218,"url":219,"summary":220,"summary_zh":221,"content":9,"source_name":222,"source_url":219,"published_at":223,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":224,"score_detail":225,"sources":228,"tags":230,"primary_topic":233,"secondary_topics":234,"classification":237,"search_phrases":258,"slug":261,"view_count":22,"doi":262,"paper":263,"created_at":283},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",77,{"impact":226,"substance":18,"depth":108,"authority":20,"freshness":111,"relevant":22,"comment":227},16,"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。",[229],{"name":222,"url":219},[27,231,116,30,232],"无人机","病害预警",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[235,236],{"code":120,"slug":121,"name":122,"path":123,"parent_code":124},{"code":62,"slug":128,"name":129,"path":130,"parent_code":124},{"status":40,"locked":14,"version":41,"method":42,"evidence":238},{"candidates":239,"agricultural_evidence":47},[240,245,250,254],{"code":33,"score":19,"supported":47,"title":241,"abstract":242,"tags":244},[50],[52,243,50],"葡萄",[],{"code":120,"score":246,"supported":47,"title":247,"abstract":248,"tags":249},15,[141],[138,141],[116],{"code":62,"score":17,"supported":47,"title":251,"abstract":252,"tags":253},[152],[152],[30],{"code":67,"score":155,"supported":47,"title":255,"abstract":256,"tags":257},[],[158,159],[27],[259,260],"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":262,"openalex_id":264,"authors":265,"venue":222,"cited_by_count":75,"oa_url":277,"card":278,"direction":214,"ingested_from":93},"W7221558726",[266,269,272,274],{"name":267,"orcid":268},"Batuhan Aşıroğlu","https:\u002F\u002Forcid.org\u002F0000-0003-0767-6348",{"name":270,"orcid":271},"Aydın Kağan Turkoglu","https:\u002F\u002Forcid.org\u002F0009-0001-8383-8807",{"name":273,"orcid":9},"Fatih Sinan Bir",{"name":275,"orcid":276},"Sibel Senan","https:\u002F\u002Forcid.org\u002F0000-0001-6773-0428","https:\u002F\u002Fdergipark.org.tr\u002Fen\u002Fdownload\u002Farticle-file\u002F5761152",{"tldr":279,"method":280,"finding":281,"direction":91,"opportunity":282},"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":285,"title":286,"url":287,"summary":288,"summary_zh":289,"content":9,"source_name":290,"source_url":287,"published_at":291,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":292,"score_detail":293,"sources":295,"tags":297,"primary_topic":299,"secondary_topics":300,"classification":303,"search_phrases":330,"slug":333,"view_count":56,"doi":334,"paper":335,"created_at":359},3167,"Temporal trend analysis and multi-temporal satellite feature integration for mango orchard acreage estimation using machine learning algorithms approach","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-65828-3","Accurate estimation of horticultural crop acreage is essential for agricultural planning, market forecasting and evidence-based policy formulation. The present study investigated long-term trends in mango cultivation and developed a multi-temporal remote sensing framework for mango orchard acreage estimation in Navsari District using integrated optical, SAR and machine learning approaches. Time-series (temporal) data spanning 23 years (2001–02 to 2023–24) were analyzed using polynomial regression models to evaluate trends in mango area and production. Linear regression best represented area expansion trends (Adj. R² = 0.969), whereas cubic regression better captured production variability (Adj. R² = 0.634), indicating climatic and seasonal influences on productivity. For orchard classification and acreage estimation, multi-temporal Sentinel-2 imagery acquired from November 2023 to March 2024 was processed within a phenology-guided framework. Monthly composites were generated and integrated with Sentinel-1 SAR backscatter data, vegetation indices (NDVI, GNDVI, NDRE, SAVI, EVI and NDMI) and texture metrics derived from Gray Level Co-occurrence Matrix (GLCM) analysis. A comprehensive 72-band feature stack was developed for classification. Four machine learning algorithms, namely Random Forest (RF), XGBoost (XGB), Support Vector Machine (SVM) and Multinomial Logistic Regression (MNLR) were evaluated for orchard discrimination. Among the tested models, RF achieved the highest classification performance with an Overall Accuracy of 99.80% and a Kappa coefficient of 0.997, followed by SVM (99.30%), MNLR (98.21%) and XGB (9.20%). The RF model estimated mango orchard area at 36,099.94 ha, showing the closest agreement with official horticultural statistics (34,363 ha) with only 5.05% estimation error. In contrast, SVM and MNLR overestimated orchard extent by 16.03% and 43.37%, respectively. The proposed framework provides a reliable and scalable methodology for operational horticultural monitoring, crop inventory generation and precision agricultural planning in tropical orchard ecosystems.","准确估算园艺作物种植面积对于农业规划、市场预测和循证政策制定至关重要。本研究探讨了芒果种植的长期趋势，并开发了一个多时相遥感框架，结合光学、合成孔径雷达（SAR）和机器学习方法，用于纳夫萨里县芒果园种植面积估算。利用多项式回归模型分析了跨越23年（2001—02年至2023—24年）的时间序列数据，以评估芒果面积和产量的变化趋势。线性回归最能表征面积扩张趋势（调整R² = 0.969），而三次回归更能捕捉产量变异性（调整R² = 0.634），表明气候和季节性因素对生产力具有影响。在果园分类和面积估算方面，基于物候指导框架处理了2023年11月至2024年3月获取的多时相Sentinel-2影像。生成了月度合成影像，并将其与Sentinel-1 SAR后向散射数据、植被指数（NDVI、GNDVI、NDRE、SAVI、EVI和NDMI）以及基于灰度共生矩阵（GLCM）分析提取的纹理指标进行整合。构建了一个包含72个波段的综合特征集用于分类。评估了四种机器学习算法，即随机森林（RF）、XGBoost（XGB）、支持向量机（SVM）和多项逻辑回归（MNLR），用于果园判别。在测试的模型中，RF取得了最高的分类性能，总体精度为99.80%，Kappa系数为0.997，其次是SVM（99.30%）、MNLR（98.21%）和XGB（9.20%）。RF模型估算的芒果园面积为36,099.94公顷，与官方园艺统计数据（34,363公顷）最为接近，估算误差仅为5.05%。相比之下，SVM和MNLR分别高估了果园面积16.03%和43.37%。所提出的框架为热带果园生态系统中的业务化园艺监测、作物清单生成和精准农业规划提供了一种可靠且可扩展的方法。","Scientific Reports","2026-09-22T00:00:00Z",78,{"impact":110,"substance":109,"depth":108,"authority":110,"freshness":13,"relevant":22,"comment":294},"方法扎实、数据规模大且精度高，但属区域性作物遥感估产研究，产业影响有限，可作为技术方法类精选。",[296],{"name":290,"url":287},[27,139,146,30,298],"作物估产",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[301,302],{"code":120,"slug":121,"name":122,"path":123,"parent_code":124},{"code":62,"slug":128,"name":129,"path":130,"parent_code":124},{"status":40,"locked":14,"version":41,"method":42,"evidence":304},{"candidates":305,"agricultural_evidence":47},[306,310,314,319,324],{"code":33,"score":246,"supported":47,"title":307,"abstract":308,"tags":309},[49],[146,49],[146],{"code":120,"score":246,"supported":47,"title":311,"abstract":312,"tags":313},[140],[139,140],[139],{"code":62,"score":21,"supported":47,"title":315,"abstract":316,"tags":318},[],[118,317],"remote sensing",[298,30],{"code":67,"score":320,"supported":47,"title":321,"abstract":322,"tags":323},4,[],[158],[27],{"code":325,"score":56,"supported":47,"title":326,"abstract":327,"tags":329},"J1",[],[328],"农业规划",[],[331,332],"Navsari 芒果 遥感估产","Sentinel-2 芒果 果园面积","Navsari芒果遥感估产-3167","10.1038\u002Fs41598-026-65828-3",{"doi":334,"openalex_id":336,"authors":337,"venue":290,"cited_by_count":75,"oa_url":287,"card":354,"direction":91,"ingested_from":93},"W7213920056",[338,340,343,345,347,350,352],{"name":339,"orcid":9},"V. Raju",{"name":341,"orcid":342},"Yogesh A. Garde","https:\u002F\u002Forcid.org\u002F0000-0002-0297-316X",{"name":344,"orcid":9},"Dr. V. S. Thorat",{"name":346,"orcid":9},"V. T. Shinde",{"name":348,"orcid":349},"Nitin Varshney","https:\u002F\u002Forcid.org\u002F0000-0001-9144-5475",{"name":351,"orcid":9},"Alok Shrivastava",{"name":353,"orcid":9},"A. P. Chaudhary",{"tldr":355,"method":356,"finding":357,"direction":91,"opportunity":358},"融合多时相Sentinel-1\u002F2与机器学习，估算印度芒果园面积并分析23年种植趋势。","23年时序回归分析；Sentinel-2月合成+SAR+植被指数+GLCM纹理共","RF精度最高（总体精度99.80%，Kappa 0.997），面积估算误差仅5.05%，优于SVM和","可迁移该多时相SAR-光学特征框架至其他热带果园，并探索深度学习与物候自适应特征优化。","2026-09-22T23:30:22.619289Z",{"id":361,"title":362,"url":363,"summary":364,"summary_zh":365,"content":9,"source_name":366,"source_url":363,"published_at":367,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":368,"score_detail":369,"sources":371,"tags":373,"primary_topic":376,"secondary_topics":377,"classification":378,"search_phrases":405,"slug":408,"view_count":75,"doi":409,"paper":410,"created_at":427},2122,"Heterogeneous behaviours towards precision agriculture adoption among Italian winegrowers: insights from latent class analysis","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs11119-026-10448-0","Abstract Purpose Precision Agriculture technologies including satellite data, drones, field robots and automatic guidance, are increasingly promoted as tools to improve sustainability, competitiveness, and environmental efficiency in viticulture. However, the adoption of these practices among Italian winegrowers exhibits significant heterogeneity, influenced by a combination of structural and behavioural factors. This study aims to identify distinct groups of Italian winegrowers based on their intentions to adopt PATs, examining how these intentions relate to four behavioural constructs that capture cognitive, social, and risk-related influences. Method The present study integrates a profile-based perspective by estimating a latent-class generalised structural equation model on 272 Italian winegrowers. The model of class membership is predicated upon a multifaceted conceptualisation encompassing risk perception, risk tolerance, perceived ease of use, and subjective norms and the technology-specific five-year intentions are incorporated as class-specific probit intercepts. Results Three qualitatively distinct profiles emerge: risk-sensitive sceptics, selective pragmatists and usability-oriented high adopters with sharply different adoption patterns across technologies. Participation in rural development schemes is the strongest predictor of membership in the higher-propensity latent classes, namely the selective-pragmatist and usability-oriented high-adopter profiles. In addition, familiarity with PATs, male gender and participation in consortium are positively associated with the higher-propensity class, while age shows a weak negative correlation. Conclusion These results inform the design of extension and policy for specific segments, prioritising risk-mitigation trials for cautious growers, targeted information services for select profiles, and integrated PATs bundles for those with a high propensity.","摘要 目的 精准农业技术（Precision Agriculture Technologies，PATs），包括卫星数据、无人机、田间机器人和自动导航，日益被视为提升葡萄栽培可持续性、竞争力和环境效率的工具。然而，意大利葡萄种植者对上述技术的采纳呈现出显著异质性，受到结构性因素与行为因素的共同影响。本研究旨在基于意大利葡萄种植者采纳PATs的意愿识别不同群体，并考察这些意愿如何与四个行为构念相关联，这四个构念分别捕捉认知、社会和风险相关的影响。方法 本研究整合了基于剖面的视角，对272名意大利葡萄种植者估计了潜在类别广义结构方程模型。类别归属模型建立在涵盖风险感知、风险容忍度、感知易用性和主观规范的多维概念化基础之上，并将技术特定的五年意愿作为类别特定的probit截距纳入模型。结果 研究识别出三种性质不同的剖面：风险敏感型怀疑者、选择性实用主义者和以易用性为导向的高采纳者，其在不同技术上的采纳模式差异显著。参与农村发展计划是归属于较高倾向潜在类别（即选择性实用主义者和以易用性为导向的高采纳者剖面）的最强预测因素。此外，对PATs的熟悉程度、男性性别和参与合作社与较高倾向类别呈正相关，而年龄则表现出较弱的负相关。结论 上述结果为针对特定群体的推广和政策设计提供了依据，应优先为谨慎型种植者开展风险缓解试验，为特定剖面提供有针对性的信息服务，并为高倾向群体提供整合的PATs技术组合。","Precision Agriculture","2026-09-10T00:00:00Z",79,{"impact":226,"substance":109,"depth":108,"authority":110,"freshness":111,"relevant":22,"comment":370},"基于272户意大利葡萄种植者的潜类别分析，揭示精准农业采纳的异质性行为分群，对农户分类推广与政策设计有实质参考价值。",[372],{"name":366,"url":363},[27,374,158,30,375],"农户采纳","葡萄种植",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":379},{"candidates":380,"agricultural_evidence":47},[381,385,392,396,401],{"code":67,"score":226,"supported":47,"title":382,"abstract":383,"tags":384},[159],[158,159],[27,158],{"code":386,"score":96,"supported":47,"title":387,"abstract":388,"tags":391},"G",[],[389,390],"农村发展","rural development",[],{"code":33,"score":320,"supported":47,"title":393,"abstract":394,"tags":395},[],[243],[375],{"code":397,"score":22,"supported":14,"title":398,"abstract":399,"tags":400},"G2",[],[],[374],{"code":62,"score":22,"supported":14,"title":402,"abstract":403,"tags":404},[],[],[30],[406,407],"农户采纳 智慧农业 精准农业 葡萄种植","农户采纳 智慧农业","农户采纳智慧农业精准农业葡萄种植-2122","10.1007\u002Fs11119-026-10448-0",{"doi":409,"openalex_id":411,"authors":412,"venue":366,"cited_by_count":75,"oa_url":363,"card":421,"direction":425,"ingested_from":93},"W7212151394",[413,415,418],{"name":414,"orcid":9},"Adriano Biondo",{"name":416,"orcid":417},"Antonino Galati","https:\u002F\u002Forcid.org\u002F0000-0003-0753-2934",{"name":419,"orcid":420},"Francesco Caracciolo","https:\u002F\u002Forcid.org\u002F0000-0001-9430-7529",{"tldr":422,"method":423,"finding":424,"direction":425,"opportunity":426},"基于272名意大利葡萄种植者，用潜类别分析识别精准农业技术采纳意向的异质性群体。","潜类别广义结构方程模型，纳入风险感知、风险容忍、易用性和主观规范。","分出风险敏感怀疑者、选择性实用主义者和易用性高采纳者三类，参与农村发展计划是最强预测因素。","数字乡村与农业信息化","可针对不同农户群体设计差异化推广策略，并研究政策参与如何通过行为路径影响技术采纳。","2026-09-11T23:30:02.943184Z",{"id":429,"title":430,"url":431,"summary":432,"summary_zh":9,"content":433,"source_name":434,"source_url":9,"published_at":435,"category":436,"cover_url":9,"hotness":13,"is_selected":14,"score":437,"score_detail":438,"sources":440,"tags":442,"primary_topic":446,"secondary_topics":447,"classification":448,"search_phrases":464,"slug":467,"view_count":75,"doi":9,"paper":9,"created_at":468},5516,"上海农科院葡萄团队赴银川参加第47届世界葡萄与葡萄酒大会","https:\u002F\u002Fwww.saas.sh.cn\u002Fhzjl\u002Fgjhz\u002Fcontent_57128","10月12日至16日第47届世界葡萄与葡萄酒大会在银川举办，智慧农业研究中心葡萄团队负责人奚晓军研究员作专题报告，阐明疏穗与环剥处理对果实糖、花青素及脱落酸积累的源库调控机制。团队还观摩酿酒葡萄AI综合作业机器人成果展示，与研发单位围绕葡萄智慧装备与果园智能化管理深入交流。","2026年10月12-16日，第47届世界葡萄与葡萄酒大会在银川举办，智慧农业研究中心葡萄团队负责人奚晓军研究员一行赴会交流。团队围绕“提升葡萄种植生产韧性与可持续发展能力”主题，向全球同行展示最新科研成果。\n\n会上，奚晓军作“Changes in sugar, anthocyanin and ABA accumulation in response to cluster thinning and girdling in ‘Jumeigui’grape”专题报告。报告围绕葡萄疏穗与环剥处理开展研究，阐明源库比对果实糖、花青素及脱落酸积累的调控机制，为葡萄优质栽培技术提供理论支撑，报告内容引发国内外园艺专家广泛研讨。参会期间，团队前往银川国际会展中心观摩酿酒葡萄 AI 综合作业机器人成果展示，详细了解该装备在葡萄园智能作业方面的技术特点与应用前景，并与研发单位围绕葡萄智慧装备研发、果园智能化管理等方向开展深入交流。\n\n本次参会是葡萄团队持续推进科研国际化、对标国际前沿开展研究的重要实践。","上海市农业科学院 2026-10-19","2026-10-19T00:00:00Z","报道",65,{"impact":226,"substance":19,"depth":20,"authority":20,"freshness":96,"relevant":22,"comment":439},"国际学术会议交流并涉及葡萄AI作业机器人观摩，有实质科研内容与行业参考价值，但属团队参会动态，影响面有限。",[441],{"name":434,"url":431},[27,443,243,444,445],"智能农机","栽培技术","国际交流",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":449},{"candidates":450,"agricultural_evidence":47},[451,455,459],{"code":33,"score":17,"supported":47,"title":452,"abstract":453,"tags":454},[243],[243],[243],{"code":67,"score":320,"supported":47,"title":456,"abstract":457,"tags":458},[],[27],[27],{"code":460,"score":22,"supported":14,"title":461,"abstract":462,"tags":463},"F5",[],[],[443],[465,466],"上海农科院 葡萄 银川","世界葡萄与葡萄酒大会 奚晓军","上海农科院葡萄银川-5516","2026-10-22T00:07:04.061911Z",{"id":470,"title":471,"url":472,"summary":473,"summary_zh":474,"content":9,"source_name":475,"source_url":472,"published_at":476,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":477,"score_detail":478,"sources":480,"tags":482,"primary_topic":486,"secondary_topics":487,"classification":488,"search_phrases":510,"slug":513,"view_count":75,"doi":514,"paper":515,"created_at":535},5401,"A HIERARCHICAL DISTRIBUTED EDGE AI FRAMEWORK FOR REAL-TIME APPLE LEAF DISEASE CLASSIFICATION","https:\u002F\u002Fdoi.org\u002F10.22190\u002Ffuacr260506002g","The application of artificial intelligence (AI) in agriculture has transformed crop management, particularly in the detection of plant diseases. Apple trees, a key agricultural commodity, are vulnerable to various diseases, which can severely impact crop yields. Traditional disease detection methods, often reliant on manual inspections, are time-consuming and prone to error. In response, this study proposes a novel two-stage edge AI framework for apple leaf disease classification that integrates RGB imagery with distributed edge computing. The first stage performs binary classification to distinguish between healthy and diseased leaves, achieving an F1 score of 95.50%. This optimization is achieved by utilizing lightweight models on edge devices, thereby enhancing computational efficiency. The second stage employs a consensus-based multiclass classification approach, achieving a 96.44% F1 score in identifying specific diseases. This dual-stage system, supported by an edge AI architecture, ensures real-time disease detection while minimizing resource consumption and enhancing scalability in large-scale agricultural environments. The full system achieved a 95.50% accuracy and F1 score on the special dataset. The results demonstrate the system’s efficacy in controlled laboratory conditions, offering a promising solution for precise, real-time agricultural monitoring. This study underscores the potential of distributed edge AI systems for scalable and efficient disease detection in precision agriculture.","人工智能（AI）在农业中的应用已深刻改变了作物管理方式，尤其是在植物病害检测方面。苹果树作为重要的农业经济作物，易受多种病害侵袭，严重影响作物产量。传统的病害检测方法通常依赖人工检查，耗时且易出错。为此，本研究提出了一种新颖的两阶段边缘AI框架，用于苹果叶片病害分类，该框架将RGB图像与分布式边缘计算相结合。第一阶段执行二分类以区分健康叶片与患病叶片，F1分数达到95.50%。该优化通过在边缘设备上采用轻量级模型实现，从而提升了计算效率。第二阶段采用基于共识的多类分类方法，在识别具体病害方面F1分数达到96.44%。该双阶段系统在边缘AI架构的支持下，实现了实时病害检测，同时最大限度地降低了资源消耗，并增强了在大规模农业环境中的可扩展性。完整系统在专用数据集上达到了95.50%的准确率和F1分数。结果表明，该系统在受控实验室条件下具有有效性，为精准、实时的农业监测提供了一种有前景的解决方案。本研究凸显了分布式边缘AI系统在精准农业中实现可扩展且高效病害检测的潜力。","Facta Universitatis Series Automatic Control and Robotics","2026-10-18T00:00:00Z",76,{"impact":108,"substance":18,"depth":19,"authority":17,"freshness":21,"relevant":22,"comment":479},"该研究提出两级边缘AI框架，在苹果叶片病害识别上取得95%以上F1值，方法新颖、数据可靠，对精准农业实时监测有参考价值，但尚处实验室验证阶段，产业影响有限。",[481],{"name":475,"url":472},[27,116,483,484,485],"边缘计算","作物病害识别","苹果病害",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":489},{"candidates":490,"agricultural_evidence":47},[491,495,499,504],{"code":33,"score":108,"supported":47,"title":492,"abstract":493,"tags":494},[50],[35,52,50],[485],{"code":67,"score":155,"supported":47,"title":496,"abstract":497,"tags":498},[],[158,159],[27],{"code":169,"score":155,"supported":47,"title":500,"abstract":501,"tags":503},[],[483,502],"edge computing",[483],{"code":120,"score":505,"supported":47,"title":506,"abstract":507,"tags":509},5,[],[508],"artificial intelligence",[484,116],[511,512],"苹果叶片病害 边缘AI","分布式边缘计算 病害分类","苹果叶片病害边缘AI-5401","10.22190\u002Ffuacr260506002g",{"doi":514,"openalex_id":516,"authors":517,"venue":475,"cited_by_count":75,"oa_url":472,"card":530,"direction":212,"ingested_from":93},"W7222964752",[518,521,524,527],{"name":519,"orcid":520},"Milan Grujev","https:\u002F\u002Forcid.org\u002F0009-0002-3211-6844",{"name":522,"orcid":523},"Dragan H. Stojanovic","https:\u002F\u002Forcid.org\u002F0000-0003-4893-3814",{"name":525,"orcid":526},"Miloš Ilić","https:\u002F\u002Forcid.org\u002F0000-0002-9696-2874",{"name":528,"orcid":529},"Aleksandar Milosavljević","https:\u002F\u002Forcid.org\u002F0000-0003-3057-7727",{"tldr":531,"method":532,"finding":533,"direction":214,"opportunity":534},"提出两级边缘AI框架，用RGB图像实时分类苹果叶片病害。","分布式边缘计算+轻量模型，先二分类再共识多分类。","两级系统准确率与F1均达95.50%，多分类F1为96.44%。","仅在受控实验室验证，可延伸至田间复杂光照与多作物泛化及边缘能耗优化。","2026-10-20T23:30:33.830748Z"]