[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2617":3,"related-2617":112},{"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":45,"search_phrases":72,"slug":75,"view_count":76,"doi":77,"paper":78,"created_at":111},2617,"Dynamic ROI-constrained UAV multispectral estimation of single-plant LAI in trellis-trained kiwifruit","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112437","Leaf area index (LAI) is a key biophysical parameter for characterizing orchard canopy structure and growth status, and it is closely associated with crop productivity. In trellis-trained orchards, severe branch overlap and persistent background interference make it difficult to delineate single-plant observation boundaries, while radiometric drift across multi-temporal observations further reduces feature comparability. To address these issues, this study proposes a dynamic ROI-constrained framework for single-plant LAI estimation from UAV multispectral imagery. First, relative radiometric calibration based on pseudo-invariant features was applied to reduce inter-date spectral bias and establish a unified radiometric baseline for multi-temporal analysis. Second, a dynamic ROI extraction algorithm was developed using dual constraints from the spatial distance percentile (P) and the local spectral purity threshold (Q). Parameter ablation results showed that the P90_Q70 combination achieved the best balance between retaining core canopy information and suppressing background noise. Compared with the best fixed-radius strategy (3.00 m), this scheme improved R 2 from 0.700 to 0.766 and reduced RMSE to 0.122. On this basis, spectral vegetation indices and near-infrared texture features were integrated to construct a multidimensional feature set. The gradient boosting decision tree (GBDT) model achieved the best predictive performance, with R 2 = 0.772, RMSE = 0.120, and RPD = 2.094, and was further used to generate high-resolution LAI maps of the orchard. These results indicate that the combination of dynamic boundary constraints and spectral purity screening can improve the robustness of single-plant feature extraction in trellis-trained kiwifruit orchards and provide a practical reference for quantitative remote sensing of other densely closed orchard systems.","叶面积指数（LAI）是表征果园冠层结构与生长状态的关键生物物理参数，与作物生产力密切相关。在棚架式栽培果园中，严重的枝条重叠和持续的背景干扰使得单株观测边界难以界定，而多时相观测间的辐射漂移进一步降低了特征可比性。为解决上述问题，本研究提出了一种基于无人机多光谱影像的单株LAI估算动态ROI约束框架。首先，采用基于伪不变特征的相对辐射校正以减小日期间的光谱偏差，为多时相分析建立统一的辐射基准。其次，利用空间距离百分位数（P）和局部光谱纯度阈值（Q）的双重约束，开发了动态ROI提取算法。参数消融结果表明，P90_Q70组合在保留核心冠层信息与抑制背景噪声之间取得了最佳平衡。与最优固定半径策略（3.00 m）相比，该方案将R²从0.700提升至0.766，并将RMSE降至0.122。在此基础上，融合光谱植被指数与近红外纹理特征构建多维特征集。梯度提升决策树（GBDT）模型取得了最佳预测性能，R²=0.772，RMSE=0.120，RPD=2.094，并进一步用于生成果园高分辨率LAI分布图。上述结果表明，动态边界约束与光谱纯度筛选相结合可提高棚架式猕猴桃果园单株特征提取的鲁棒性，并为其他密集郁闭果园系统的定量遥感提供实践参考。",null,"Computers and Electronics in Agriculture","2026-09-15T00:00:00Z","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,"提出动态ROI约束与辐射校正结合的无人机多光谱单株LAI估测框架，方法新颖、指标提升明确，对密植果园定量遥感有实用参考价值。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","无人机","农业遥感","猕猴桃","叶面积指数",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},"B2","fruit","果树","\u002Ftopic\u002Fhorticulture\u002Ffruit","B",[39],{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",{"status":46,"locked":14,"version":47,"method":48,"evidence":49},"classified","2026-10-22.2","rules",{"candidates":50,"agricultural_evidence":53},[51,61,67],{"code":40,"score":52,"supported":53,"title":54,"abstract":56,"tags":60},19,true,[55],"multispectral",[57,58,59,55],"遥感","无人机多光谱","remote sensing",[29,31],{"code":33,"score":19,"supported":53,"title":62,"abstract":64,"tags":66},[63],"kiwifruit",[30,65,63],"orchard",[30],{"code":68,"score":22,"supported":14,"title":69,"abstract":70,"tags":71},"I1",[],[],[27],[73,74],"叶面积指数 农业遥感 智慧农业 无人机","叶面积指数 农业遥感","叶面积指数农业遥感智慧农业无人机-2617",4,"10.1016\u002Fj.compag.2026.112437",{"doi":77,"openalex_id":79,"authors":80,"venue":10,"cited_by_count":103,"oa_url":6,"card":104,"direction":108,"ingested_from":110},"W7213243341",[81,83,85,87,90,92,94,96,98,101],{"name":82,"orcid":9},"Wenjie Li",{"name":84,"orcid":9},"Hongen Liu",{"name":86,"orcid":9},"Linghuan Ouyang",{"name":88,"orcid":89},"Qian Chen","https:\u002F\u002Forcid.org\u002F0000-0002-7916-1370",{"name":91,"orcid":9},"Tianqi Lv",{"name":93,"orcid":9},"Jiali Li",{"name":95,"orcid":9},"Xintao Lin",{"name":97,"orcid":9},"Chen Yao",{"name":99,"orcid":100},"Yongqiang Zheng","https:\u002F\u002Forcid.org\u002F0000-0003-3246-2800",{"name":102,"orcid":9},"Jianping Qian",0,{"tldr":105,"method":106,"finding":107,"direction":108,"opportunity":109},"提出动态ROI约束框架，用无人机多光谱影像估算棚架猕猴桃单株LAI。","伪不变特征辐射校正、动态ROI提取（P90_Q70）、植被指数与纹理特征、GBD","动态ROI优于固定半径，GBDT最优（R²=0.772，RMSE=0.120，RPD=2.094）。","农业遥感与作物表型","可迁移至其他密植果园，探索多时相辐射校正与动态边界约束的普适性及轻量化模型。","openalex","2026-09-16T23:30:02.136941Z",{"total":113,"page":22,"page_size":113,"items":114},6,[115,199,298,372,441,528],{"id":116,"title":117,"url":118,"summary":119,"summary_zh":120,"content":9,"source_name":121,"source_url":118,"published_at":122,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":123,"score_detail":124,"sources":128,"tags":130,"primary_topic":134,"secondary_topics":135,"classification":142,"search_phrases":172,"slug":175,"view_count":22,"doi":176,"paper":177,"created_at":198},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":17,"substance":125,"depth":19,"authority":126,"freshness":21,"relevant":22,"comment":127},21,13,"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。",[129],{"name":121,"url":118},[27,28,131,132,133],"农业人工智能","遥感监测","病害预警",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[136,141],{"code":137,"slug":138,"name":139,"path":140,"parent_code":44},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},{"status":46,"locked":14,"version":47,"method":48,"evidence":143},{"candidates":144,"agricultural_evidence":53},[145,153,160,165],{"code":33,"score":146,"supported":53,"title":147,"abstract":149,"tags":152},17,[148],"apple",[150,151,148],"苹果","葡萄",[],{"code":137,"score":154,"supported":53,"title":155,"abstract":157,"tags":159},15,[156],"deep learning",[158,156],"深度学习",[131],{"code":40,"score":161,"supported":53,"title":162,"abstract":163,"tags":164},12,[55],[55],[132],{"code":68,"score":166,"supported":53,"title":167,"abstract":168,"tags":171},7,[],[169,170],"精准农业","precision agriculture",[27],[173,174],"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":176,"openalex_id":178,"authors":179,"venue":121,"cited_by_count":103,"oa_url":191,"card":192,"direction":197,"ingested_from":110},"W7221558726",[180,183,186,188],{"name":181,"orcid":182},"Batuhan Aşıroğlu","https:\u002F\u002Forcid.org\u002F0000-0003-0767-6348",{"name":184,"orcid":185},"Aydın Kağan Turkoglu","https:\u002F\u002Forcid.org\u002F0009-0001-8383-8807",{"name":187,"orcid":9},"Fatih Sinan Bir",{"name":189,"orcid":190},"Sibel Senan","https:\u002F\u002Forcid.org\u002F0000-0001-6773-0428","https:\u002F\u002Fdergipark.org.tr\u002Fen\u002Fdownload\u002Farticle-file\u002F5761152",{"tldr":193,"method":194,"finding":195,"direction":108,"opportunity":196},"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。","智慧农业 \u002F 农业物联网","2026-10-13T23:30:10.242467Z",{"id":200,"title":201,"url":202,"summary":203,"summary_zh":204,"content":9,"source_name":205,"source_url":202,"published_at":206,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":207,"score_detail":208,"sources":210,"tags":212,"primary_topic":215,"secondary_topics":216,"classification":219,"search_phrases":270,"slug":273,"view_count":22,"doi":274,"paper":275,"created_at":297},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":19,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":209},"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。",[211],{"name":205,"url":202},[27,131,213,214,57],"产量预测","多模态融合",{"code":137,"slug":138,"name":139,"path":140,"parent_code":44},[217,218],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},{"status":46,"locked":14,"version":47,"method":48,"evidence":220},{"candidates":221,"agricultural_evidence":53},[222,229,234,239,243,250,257,264],{"code":137,"score":223,"supported":53,"title":224,"abstract":225,"tags":228},11,[],[158,226,227,156],"机器学习","machine learning",[131,214],{"code":33,"score":21,"supported":53,"title":230,"abstract":231,"tags":233},[],[150,232,65,148],"芒果",[],{"code":40,"score":235,"supported":53,"title":236,"abstract":237,"tags":238},8,[],[58,55],[213,57],{"code":68,"score":166,"supported":53,"title":240,"abstract":241,"tags":242},[],[169,170],[27],{"code":244,"score":113,"supported":53,"title":245,"abstract":246,"tags":249},"H2",[],[247,248],"土壤","soil",[],{"code":251,"score":113,"supported":53,"title":252,"abstract":253,"tags":256},"I5",[],[254,255],"物联网","IoT",[],{"code":258,"score":259,"supported":53,"title":260,"abstract":261,"tags":263},"H6",3,[],[262],"农业生态",[],{"code":265,"score":259,"supported":53,"title":266,"abstract":267,"tags":269},"H7",[],[268],"气候适应",[],[271,272],"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":274,"openalex_id":276,"authors":277,"venue":205,"cited_by_count":103,"oa_url":202,"card":291,"direction":197,"ingested_from":110},"W7221795850",[278,281,283,285,287,289],{"name":279,"orcid":280},"Shabir Ahmad Mir","https:\u002F\u002Forcid.org\u002F0000-0003-2311-218X",{"name":282,"orcid":9},"Umarfarooque Momin",{"name":284,"orcid":9},"Sudeep Kumar E",{"name":286,"orcid":9},"Itfaq Ahmad Mir",{"name":288,"orcid":9},"Ab Rouf Khan",{"name":290,"orcid":9},"Ghulam Mohammad Mir",{"tldr":292,"method":293,"finding":294,"direction":295,"opportunity":296},"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。","2026-10-15T23:30:08.750140Z",{"id":299,"title":300,"url":301,"summary":302,"summary_zh":303,"content":9,"source_name":304,"source_url":301,"published_at":305,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":306,"score_detail":307,"sources":309,"tags":311,"primary_topic":313,"secondary_topics":314,"classification":317,"search_phrases":342,"slug":345,"view_count":259,"doi":346,"paper":347,"created_at":371},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":20,"substance":18,"depth":19,"authority":20,"freshness":13,"relevant":22,"comment":308},"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。",[310],{"name":304,"url":301},[27,226,232,132,312],"作物估产",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[315,316],{"code":137,"slug":138,"name":139,"path":140,"parent_code":44},{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},{"status":46,"locked":14,"version":47,"method":48,"evidence":318},{"candidates":319,"agricultural_evidence":53},[320,324,328,332,336],{"code":33,"score":154,"supported":53,"title":321,"abstract":322,"tags":323},[65],[232,65],[232],{"code":137,"score":154,"supported":53,"title":325,"abstract":326,"tags":327},[227],[226,227],[226],{"code":40,"score":235,"supported":53,"title":329,"abstract":330,"tags":331},[],[57,59],[312,132],{"code":68,"score":76,"supported":53,"title":333,"abstract":334,"tags":335},[],[169],[27],{"code":337,"score":259,"supported":53,"title":338,"abstract":339,"tags":341},"J1",[],[340],"农业规划",[],[343,344],"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":346,"openalex_id":348,"authors":349,"venue":304,"cited_by_count":103,"oa_url":301,"card":366,"direction":108,"ingested_from":110},"W7213920056",[350,352,355,357,359,362,364],{"name":351,"orcid":9},"V. Raju",{"name":353,"orcid":354},"Yogesh A. Garde","https:\u002F\u002Forcid.org\u002F0000-0002-0297-316X",{"name":356,"orcid":9},"Dr. V. S. Thorat",{"name":358,"orcid":9},"V. T. Shinde",{"name":360,"orcid":361},"Nitin Varshney","https:\u002F\u002Forcid.org\u002F0000-0001-9144-5475",{"name":363,"orcid":9},"Alok Shrivastava",{"name":365,"orcid":9},"A. P. Chaudhary",{"tldr":367,"method":368,"finding":369,"direction":108,"opportunity":370},"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":373,"title":374,"url":375,"summary":376,"summary_zh":377,"content":9,"source_name":378,"source_url":375,"published_at":379,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":380,"score_detail":381,"sources":384,"tags":386,"primary_topic":389,"secondary_topics":390,"classification":392,"search_phrases":419,"slug":422,"view_count":423,"doi":424,"paper":425,"created_at":440},2874,"Laboratory Evaluation of Multispectral Grape Quality Grade Prediction with Compensation for Controlled Illumination Variation","https:\u002F\u002Fdoi.org\u002F10.1088\u002F2631-8695\u002Faea952","Abstract Accurate fruit quality assessment is important for selective harvesting in agricultural robotics, where multispectral sensing provides a non-destructive approach but remains sen- sitive to variability in illumination conditions. This study presents a controlled laboratory evaluation conducted in a dark box under halogen illumination with fixed sensor and sam- ple geometry, in which illumination variation was simulated by adjusting lamp intensity. Prediction models for visually assigned grape quality grades were first established under fixed illumination using an AS7265x multispectral sensor with 18 channels from 410 to 940 nm, covering the visible and part of the near-infrared range. Spectral data were prepro- cessed using standard normal variate transformation, standardization, variable importance in projection feature selection, and mixup interpolation. Three machine learning meth- ods, partial least squares regression, support vector regression, and random forest, were evaluated with nested cross-validation, out-of-fold prediction, and 2000-iteration bootstrap resampling. Support vector regression achieved the best performance, with R² = 0.9084 [95% CI: 0.851–0.945], RMSE = 0.3352, and MAE = 0.2374. To address illumination vari- ability, three compensation methods, direct standardization, extended multiplicative scatter correction, and a polynomial per-band fitting method, were implemented and compared across five lamp intensity levels from 20% to 100% of rated power. The three methods and the uncompensated condition reached similar mean accuracy across the five levels, with the exception of extended multiplicative scatter correction, which was lower at every level. Di- rect standardization reduced the spread of the five predictions obtained for the same berry by about 31% relative to no compensation, and gave the highest grade-level accuracy of the four conditions. These results provide laboratory feasibility evidence that direct standard- ization can improve the consistency of grade prediction across controlled illumination levels, and establish a basis for further validation under natural field illumination toward future robotic harvesting applications.","摘要 准确的水果品质评估对于农业机器人中的选择性采收至关重要，其中多光谱传感提供了一种非破坏性方法，但仍对光照条件的变化较为敏感。本研究提出了一种在暗箱中、卤素灯照明下、传感器与样品几何构型固定的受控实验室评估方法，通过调节灯强度来模拟光照变化。首先在固定光照条件下，使用AS7265x多光谱传感器（具有410至940 nm范围内的18个通道，覆盖可见光及部分近红外波段）建立了视觉 assigned 葡萄品质等级的预测模型。光谱数据采用标准正态变量变换、标准化、投影变量重要性特征选择以及mixup插值进行预处理。采用嵌套交叉验证、折外预测和2000次迭代自助重采样，对偏最小二乘回归、支持向量回归和随机森林三种机器学习方法进行了评估。支持向量回归取得了最佳性能，R² = 0.9084 [95% CI: 0.851–0.945]，RMSE = 0.3352，MAE = 0.2374。为解决光照变化问题，实施了直接标准化、扩展多元散射校正和逐波段多项式拟合三种补偿方法，并在额定功率20%至100%的五个灯强度水平下进行了比较。三种方法及未补偿条件在五个水平下达到了相似的平均准确率，但扩展多元散射校正除外，其在每个水平下均较低。与未补偿相比，直接标准化使同一浆果五次预测结果的离散度降低了约31%，并在四种条件中给出了最高的等级准确率。这些结果为直接标准化能够提高受控光照水平下等级预测的一致性提供了实验室可行性证据，并为未来机器人采收应用中在自然田间光照下进一步验证奠定了基础。","Engineering Research Express","2026-09-17T00:00:00Z",66,{"impact":235,"substance":382,"depth":146,"authority":126,"freshness":235,"relevant":22,"comment":383},20,"实验室条件下多光谱葡萄品质分级与光照补偿研究，方法扎实、结论可靠，但属实验室可行性验证，产业影响有限。",[385],{"name":378,"url":375},[27,131,151,387,388],"多光谱检测","水果品质分级",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[391],{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},{"status":46,"locked":14,"version":47,"method":48,"evidence":393},{"candidates":394,"agricultural_evidence":53},[395,400,404,408,415],{"code":33,"score":154,"supported":53,"title":396,"abstract":398,"tags":399},[397],"grape",[151,397],[151],{"code":40,"score":223,"supported":53,"title":401,"abstract":402,"tags":403},[55],[55],[],{"code":137,"score":166,"supported":53,"title":405,"abstract":406,"tags":407},[],[226,227],[131],{"code":409,"score":113,"supported":53,"title":410,"abstract":411,"tags":414},"F6",[],[412,413],"农业机器人","robotic harvesting",[],{"code":68,"score":22,"supported":14,"title":416,"abstract":417,"tags":418},[],[],[27],[420,421],"多光谱 葡萄 品质分级","AS7265x 多光谱传感器","多光谱葡萄品质分级-2874",2,"10.1088\u002F2631-8695\u002Faea952",{"doi":424,"openalex_id":426,"authors":427,"venue":378,"cited_by_count":103,"oa_url":375,"card":435,"direction":295,"ingested_from":110},"W7213509882",[428,430,432],{"name":429,"orcid":9},"Guodong Xiu",{"name":431,"orcid":9},"Sára Strakošová",{"name":433,"orcid":434},"Ikuo Mizuuchi","https:\u002F\u002Forcid.org\u002F0000-0003-4657-2613",{"tldr":436,"method":437,"finding":438,"direction":108,"opportunity":439},"在暗箱中评估多光谱葡萄品质分级预测，并比较三种光照补偿方法。","AS7265x多光谱传感器、SNV与VIP预处理、SVR\u002FRF建模、直接标准化等","SVR预测最佳（R²=0.9084）；直接标准化使同果预测离散度降低约31%。","可延伸至自然田间光照下的验证，并融合机器人采摘的实时多光谱分级系统。","2026-09-18T23:30:52.790038Z",{"id":442,"title":443,"url":444,"summary":445,"summary_zh":446,"content":9,"source_name":447,"source_url":444,"published_at":448,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":449,"score_detail":450,"sources":452,"tags":454,"primary_topic":457,"secondary_topics":458,"classification":464,"search_phrases":493,"slug":496,"view_count":22,"doi":497,"paper":498,"created_at":527},1312,"Accurate diagnosis of soil moisture and canopy water content in citrus orchards based on synergistic multi-source remote sensing","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.agwat.2026.110725","Accurate prediction of soil moisture is essential for precise agricultural irrigation decision-making and regional water resource optimal scheduling. However, regional soil moisture inversion commonly suffers from three major limitations, including overreliance on single remote sensing data sources, fixed canopy parameters adopted in conventional physical models, and severe cloud contamination in the cloudy mountainous areas of Southwest China. In this study, a synergistic multi-source remote sensing framework integrating Landsat-8\u002F9, Sentinel-2, and Sentinel-1A datasets was established to improve the traditional water cloud model by introducing phenology-driven dynamic canopy parameters. Specifically, canopy coverage and canopy water content of late-maturing citrus across different growth stages were accurately retrieved from Landsat-8\u002F9 and Sentinel-2 imagery to optimize the simulation of canopy backscattering signals. The all-weather C-band radar data effectively mitigate the persistent cloud-cover limitations prevalent in the hilly regions of Southwest China. The results indicated that the vegetation water content in large-scale citrus orchards retrieved by optical remote sensing exhibits significant spatial variability, mainly distributed in the range of 1.65–5.71 kg·m −2 and 1.55–5.78 kg·m −2 , respectively. The soil moisture inversion results using multi-temporal Sentinel-1A data in VV polarization outperformed those in VH polarization, with R² ranges of 0.785–0.854 and 0.515–0.759, RMSE ranges of 6.125–8.351% and 6.942–8.412%, respectively. The two polarizations data have the highest inversion accuracy in citrus fruit maturation stage, with R² ranges of 0.811–0.842 and 0.682–0.711, RMSE ranges of 6.125–6.132% and 6.942–7.025%, respectively. This study proposes a novel methodology for high-resolution and precision inversion of surface soil moisture at the regional farmland scale.","土壤水分的精准预测对于精准农业灌溉决策和区域水资源优化调度至关重要。然而，区域土壤水分反演普遍面临三大局限，包括对单一遥感数据源的过度依赖、传统物理模型中采用固定冠层参数，以及中国西南多云山区严重的云污染问题。本研究构建了一种融合Landsat-8\u002F9、Sentinel-2和Sentinel-1A数据集的协同多源遥感框架，通过引入物候驱动的动态冠层参数对传统水云模型进行改进。具体而言，利用Landsat-8\u002F9和Sentinel-2影像精确反演了不同生长阶段晚熟柑橘的冠层覆盖度和冠层含水量，以优化冠层后向散射信号的模拟。全天候C波段雷达数据有效缓解了西南丘陵地区普遍存在的持续云覆盖限制。结果表明，光学遥感反演的大规模柑橘园植被含水量表现出显著的空间变异性，主要分布在1.65–5.71 kg·m⁻²和1.55–5.78 kg·m⁻²范围内。使用多时相Sentinel-1A VV极化的土壤水分反演结果优于VH极化，R²范围分别为0.785–0.854和0.515–0.759，RMSE范围分别为6.125–8.351%和6.942–8.412%。两种极化数据在柑橘果实成熟期反演精度最高，R²范围分别为0.811–0.842和0.682–0.711，RMSE范围分别为6.125–6.132%和6.942–7.025%。本研究提出了一种在区域农田尺度上实现地表土壤水分高分辨率精准反演的新方法。","Agricultural Water Management","2026-08-31T00:00:00Z",75,{"impact":19,"substance":18,"depth":19,"authority":20,"freshness":259,"relevant":22,"comment":451},"提出多源遥感协同反演土壤水分的新方法，对丘陵山地精准灌溉有参考价值，但时效性一般。",[453],{"name":447,"url":444},[27,57,455,456],"土壤墒情","柑橘",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[459,463],{"code":244,"slug":248,"name":460,"path":461,"parent_code":462},"土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},{"status":46,"locked":14,"version":47,"method":48,"evidence":465},{"candidates":466,"agricultural_evidence":53},[467,472,476,480,489],{"code":33,"score":154,"supported":53,"title":468,"abstract":470,"tags":471},[469],"citrus",[456,469],[456],{"code":244,"score":154,"supported":53,"title":473,"abstract":474,"tags":475},[248],[247,248],[455],{"code":40,"score":154,"supported":53,"title":477,"abstract":478,"tags":479},[59],[57,59],[57],{"code":481,"score":21,"supported":53,"title":482,"abstract":483,"tags":488},"H3",[],[484,485,486,487],"灌溉","水资源","irrigation","water resource",[],{"code":68,"score":76,"supported":53,"title":490,"abstract":491,"tags":492},[],[169],[27],[494,495],"土壤墒情 智慧农业 柑橘 遥感","土壤墒情 智慧农业","土壤墒情智慧农业柑橘遥感-1312","10.1016\u002Fj.agwat.2026.110725",{"doi":497,"openalex_id":499,"authors":500,"venue":447,"cited_by_count":103,"oa_url":444,"card":522,"direction":108,"ingested_from":110},"W7204808715",[501,503,505,507,510,513,516,518,520],{"name":502,"orcid":9},"Zongjun Wu",{"name":504,"orcid":9},"Bin Zhu",{"name":506,"orcid":9},"Ningbo Cui",{"name":508,"orcid":509},"Wei Zhao","https:\u002F\u002Forcid.org\u002F0000-0003-0215-8584",{"name":511,"orcid":512},"Yanjun Wang","https:\u002F\u002Forcid.org\u002F0000-0001-5286-6269",{"name":514,"orcid":515},"Liwen Xing","https:\u002F\u002Forcid.org\u002F0000-0003-0007-3560",{"name":517,"orcid":9},"Quanshan Liu",{"name":519,"orcid":9},"Shenglin Wen",{"name":521,"orcid":9},"Bihang Fan",{"tldr":523,"method":524,"finding":525,"direction":108,"opportunity":526},"融合多源遥感数据改进水云模型，实现柑橘园土壤水分和冠层含水量高精度反演。","集成Landsat-8\u002F9、Sentinel-2和Sentinel-1A数据，引","VV极化反演精度优于VH，果实成熟期精度最高，R²达0.842。","可探索将动态冠层参数方法应用于其他作物或区域，结合更高分辨率数据提升反演精度。","2026-09-01T23:30:20.097045Z",{"id":529,"title":530,"url":531,"summary":532,"summary_zh":533,"content":9,"source_name":534,"source_url":531,"published_at":535,"category":12,"cover_url":9,"hotness":536,"is_selected":14,"score":537,"score_detail":538,"sources":540,"tags":544,"primary_topic":547,"secondary_topics":548,"classification":549,"search_phrases":561,"slug":564,"view_count":259,"doi":565,"paper":566,"created_at":577},3498,"DRON VA MASOFADAN MONITORING TEXNOLOGIYALARIGA OID AGRAR TERMINLARNING INGLIZ TILIDAN O'ZBEK TILIGA KIRIB KELISH MEXANIZMLARI","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22942951","Ushbu maqolada dron va masofadan monitoring texnologiyalari bilan bog‘liq zamonaviy agrar terminlarning ingliz tilidan o‘zbek tiliga kirib kelish mexanizmlari leksik-semantik va tarjimashunoslik nuqtayi nazaridan tahlil qilinadi. Tadqiqot materiali sifatida precision agriculture, drone, unmanned aerial vehicle, remote sensing, crop monitoring, multispectral imaging, hyperspectral imaging, thermal imaging, vegetation index, orthomosaic, georeferencing, payload, flight planning, variable-rate application singari xalqaro ilmiy-texnik birliklar va ularning o‘zbekcha qo‘llanish shakllari tanlandi. Tahlil natijasida o‘zlashishning besh asosiy modeli: bevosita fonetik-grafik o‘zlashtirish, kalkalash, tavsifiy-ekvivalent tarjima, qisqartmalarni saqlash hamda gibrid termin hosil qilish faol ekanligi aniqlandi. Agrar raqamlashtirish tezlashgani sari inglizcha terminlarning o‘zbek tiliga kirib kelishi faqat lug‘aviy jarayon emas, balki texnologik transfer, professional kommunikatsiya va terminologik me’yorlash bilan uzviy bog‘liq jarayon sifatida namoyon bo‘lmoqda. Maqolada variantdorlikni kamaytirish, o‘zbek tilining so‘z yasash imkoniyatlaridan oqilona foydalanish va xalqaro qisqartmalar bilan milliy ekvivalentlar o‘rtasida funksional muvozanatni ta’minlash bo‘yicha takliflar ilgari suriladi.","本文从词汇语义学和翻译学的角度，分析了与无人机和遥感监测技术相关的现代涉农术语从英语进入乌兹别克语的机制。研究以precision agriculture（精准农业）、drone（无人机）、unmanned aerial vehicle（无人驾驶飞行器）、remote sensing（遥感）、crop monitoring（作物监测）、multispectral imaging（多光谱成像）、hyperspectral imaging（高光谱成像）、thermal imaging（热成像）、vegetation index（植被指数）、orthomosaic（正射影像图）、georeferencing（地理配准）、payload（有效载荷）、flight planning（飞行规划）、variable-rate application（变量施用）等国际科技统一术语及其乌兹别克语使用形式为材料。分析结果表明，借入的五种主要模式较为活跃：直接语音—字形借入、仿译、描述—等值翻译、保留缩略语以及混合术语构词。随着农业数字化加速，英语术语进入乌兹别克语不仅是一个词汇过程，而且表现为与工艺转移、专业交流和术语规范化密切相关的过程。文中就减少变体现象、合理利用乌兹别克语的构词能力以及在国标缩略语与民族语对应词之间保持功能平衡提出了建议。","Zenodo (CERN European Organization for Nuclear Research)","2026-09-24T00:00:00Z",25,62,{"impact":235,"substance":19,"depth":154,"authority":161,"freshness":21,"relevant":22,"comment":539},"论文系统分析无人机与遥感农业术语从英语进入乌兹别克语的五种借入机制，属农业信息化语言标准化研究，专业性强但影响面偏窄。",[541,542],{"name":534,"url":531},{"name":534,"url":543},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22942950",[27,28,29,545,546],"农业术语","乌兹别克语",{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},[],{"status":46,"locked":14,"version":47,"method":48,"evidence":550},{"candidates":551,"agricultural_evidence":53},[552,557],{"code":40,"score":13,"supported":53,"title":553,"abstract":554,"tags":556},[],[57,59,55,555],"hyperspectral",[29],{"code":68,"score":166,"supported":53,"title":558,"abstract":559,"tags":560},[],[169,170],[27],[562,563],"乌兹别克语 农业术语 农业遥感 智慧农业","乌兹别克语 农业术语","乌兹别克语农业术语农业遥感智慧农业-3498","10.5281\u002Fzenodo.22942951",{"doi":565,"openalex_id":567,"authors":568,"venue":534,"cited_by_count":103,"oa_url":531,"card":571,"direction":108,"ingested_from":110},"W7214177750",[569],{"name":570,"orcid":9},"Qodirova Gulbahor Turdiyevna",{"tldr":572,"method":573,"finding":574,"direction":575,"opportunity":576},"分析无人机与遥感农业术语从英语借入乌兹别克语的五种机制。","选取精准农业等15个术语，做词汇语义与翻译学分析。","借入机制含音译、仿译、描述翻译、缩写保留和混合构词五类。","数字乡村与农业信息化","可构建多语言农业术语库，研究术语标准化对技术扩散的影响。","2026-09-25T23:30:30.787630Z"]