[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-5243":3,"related-5243":87},{"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":57,"slug":60,"view_count":61,"doi":62,"paper":63,"created_at":86},5243,"Identificación de índices de vegetación relacionados con componentes de rendimiento de frijol común (Phaseolus vulgaris L.) mediante el uso de sensores multiespectrales","https:\u002F\u002Fdoi.org\u002F10.18845\u002Ftm.v39i4.8378","Bean production in Costa Rica supplies only 20 % of domestic consumption, requiring the importation of the remaining amount; this situation highlights the need to know in advance the actual productive capacity of local farmers to improve planning, agronomic management, and import regulation. Therefore, the objective of this study was to evaluate the use of multispectral data and vegetation indices to analyze their relationship with yield components in bean varieties cultivated in different production areas of Costa Rica and to identify the yield component with the greatest spectral association. The research was conducted at three sites located in Alajuela, Costa Rica. Multispectral reflectance data were collected during the R5 phenological stage using an airborne multispectral sensor. Subsequently, yield components were quantified per meter of crop row, including 100-grain weight, number of pods per meter, number of plants, number of grains, and total grain weight. The number of pods showed the highest association with spectral variables and was therefore identified as the yield component with the greatest potential for analysis through remote sensing. The SR (Simple Ratio) and GCI (Green Chlorophyll Index) indices showed correlations greater than 0.7 with this variable, being identified as the vegetation indices with the highest spectral association during the R5 stage of the crop.","哥斯达黎加的菜豆（bean）产量仅能满足国内消费量的20%，其余部分需要进口；这一状况凸显了提前了解当地农民实际生产能力的必要性，以改进生产规划、农艺管理和进口调控。因此，本研究旨在评估多光谱数据和植被指数（vegetation indices）的应用，分析其与哥斯达黎加不同产区菜豆品种产量构成因素（yield components）之间的关系，并确定与光谱关联性最强的产量构成因素。研究在哥斯达黎加阿拉胡埃拉（Alajuela）的三个地点开展。在R5物候期使用机载多光谱传感器采集多光谱反射率数据。随后，按每米作物行量化产量构成因素，包括百粒重、每米豆荚数、植株数、籽粒数和籽粒总重。豆荚数与光谱变量的关联性最高，因此被确定为最具遥感分析潜力的产量构成因素。SR（简单比值，Simple Ratio）和GCI（绿色叶绿素指数，Green Chlorophyll Index）与该变量的相关系数大于0.7，被确定为作物R5期光谱关联性最高的植被指数。",null,"Revista Tecnología en Marcha","2026-10-16T00:00:00Z","论文",10,false,62,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},8,18,15,12,9,1,"该研究利用机载多光谱传感器识别与菜豆产量组分相关的植被指数，方法清晰、结论具体，但属于哥斯达黎加的小区域研究，公共影响有限，可作为遥感作物监测领域的技术性资讯收录。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","产量预测","遥感","植被指数","菜豆",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",[],{"status":40,"locked":14,"version":41,"method":42,"evidence":43},"classified","2026-10-22.2","rules",{"candidates":44,"agricultural_evidence":46},[45,52],{"code":33,"score":20,"supported":46,"title":47,"abstract":48,"tags":51},true,[],[29,49,50],"remote sensing","multispectral",[28,30,29],{"code":53,"score":22,"supported":14,"title":54,"abstract":55,"tags":56},"I1",[],[],[27],[58,59],"哥斯达黎加 菜豆 多光谱 遥感","Phaseolus vulgaris 植被指数 产量","哥斯达黎加菜豆多光谱遥感-5243",0,"10.18845\u002Ftm.v39i4.8378",{"doi":62,"openalex_id":64,"authors":65,"venue":10,"cited_by_count":61,"oa_url":78,"card":79,"direction":83,"ingested_from":85},"W7222720635",[66,69,72,75],{"name":67,"orcid":68},"Guillermo Vargas-Hernández","https:\u002F\u002Forcid.org\u002F0000-0003-1410-3898",{"name":70,"orcid":71},"Eddison José Araya-Morales","https:\u002F\u002Forcid.org\u002F0009-0001-0550-414X",{"name":73,"orcid":74},"Juan Carlos Hernández","https:\u002F\u002Forcid.org\u002F0000-0002-1915-3213",{"name":76,"orcid":77},"Ignacio Mora-Cordero","https:\u002F\u002Forcid.org\u002F0009-0007-0925-0099","https:\u002F\u002Frevistas.tec.ac.cr\u002Findex.php\u002Ftec_marcha\u002Farticle\u002Fdownload\u002F8378\u002F8641",{"tldr":80,"method":81,"finding":82,"direction":83,"opportunity":84},"用机载多光谱传感器评估菜豆产量构成与植被指数的关系。","机载多光谱遥感获取R5期反射率，结合地面产量构成测定与相关分析。","豆荚数与光谱变量关联最强，SR和GCI指数与其相关系数超过0.7。","农业遥感与作物表型","可探索将SR\u002FGCI用于菜豆产量早期预测，并扩展到多品种、多生育期与无人机高光谱验证。","openalex","2026-10-18T23:30:20.259545Z",{"total":88,"page":22,"page_size":88,"items":89},6,[90,148,223,335,414,491],{"id":91,"title":92,"url":93,"summary":94,"summary_zh":95,"content":9,"source_name":96,"source_url":93,"published_at":97,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":98,"score_detail":99,"sources":103,"tags":105,"primary_topic":108,"secondary_topics":113,"classification":115,"search_phrases":132,"slug":135,"view_count":61,"doi":136,"paper":137,"created_at":147},5570,"Evaluation of Counterfactual Explanation Robustness for Computer Vision Agriculture Yield-Forecast Models Under Satellite Cloud-Mask Gaps: An Interpretability Reliability Bound for Cooperative Storage Decisions","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23545079","Counterfactual explanations are increasingly proposed as the interface through which cooperative storage managers interrogate computer-vision yield-forecast models, yet their reliability under the satellite cloud-mask gaps that routinely afflict agricultural remote sensing has not been bounded. The bound is derived from a Lipschitz continuity assumption on the forecast model and a masking-operator perturbation analysis, and it is expressed as a function of the cloud-mask gap fraction, the model's local Lipschitz constant, and the counterfactual search tolerance. A replication-based evaluation of the before-after-control-impact estimator was conducted to characterise the operating characteristics of the design under a declared variance structure (between-cluster SD = 6.0, residual SD = 4.5, intraclass correlation = 0.64), with power estimated across 2000 design cells. The reliability bound degrades non-linearly as the gap fraction rises, and that the intraclass correlation of 0.64 implies that cooperative-level aggregation of counterfactual recourse is necessary to preserve explanation stability. The contribution is a decision-relevant reliability bound that storage cooperatives can use to set a maximum tolerable cloud-mask gap before counterfactual recourse is suspended.","反事实解释日益被提出作为合作式仓储管理者质询计算机视觉产量预测模型的接口，然而在农业遥感中经常出现的卫星云掩膜缺口条件下，其可靠性尚未得到界定。该界基于预测模型上的Lipschitz连续性假设和掩膜算子扰动分析推导得出，并表示为云掩膜缺口比例、模型局部Lipschitz常数和反事实搜索容差的函数。对前后对照影响估计量进行了基于重复的评估，以表征该设计在给定方差结构（组间标准差=6.0，残差标准差=4.5，组内相关系数=0.64）下的运行特征，并在2000个设计单元中估计了检验效能。可靠性界随缺口比例上升呈非线性退化，且组内相关系数0.64意味着需要对反事实救济进行合作社层面的聚合，以保持解释的稳定性。本文的贡献在于提供了一个与决策相关的可靠性界，仓储合作社可据此设定在暂停反事实救济之前可容忍的最大云掩膜缺口。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-21T00:00:00Z",67,{"impact":17,"substance":100,"depth":101,"authority":20,"freshness":13,"relevant":22,"comment":102},20,17,"该论文提出反事实解释在卫星云掩膜缺口下的可靠性边界，方法新颖且结论可用于合作社决策，但属细分方法学研究，产业影响有限。",[104],{"name":96,"url":93},[27,106,28,29,107],"农业人工智能","可解释性",{"code":109,"slug":110,"name":111,"path":112,"parent_code":37},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",[114],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":116},{"candidates":117,"agricultural_evidence":46},[118,124,128],{"code":109,"score":20,"supported":46,"title":119,"abstract":121,"tags":123},[120],"computer vision",[122],"计算机视觉",[106],{"code":33,"score":17,"supported":46,"title":125,"abstract":126,"tags":127},[],[29,49],[28,29],{"code":53,"score":22,"supported":14,"title":129,"abstract":130,"tags":131},[],[],[27],[133,134],"农业人工智能 产量预测 可解释性 智慧农业","农业人工智能 产量预测","农业人工智能产量预测可解释性智慧农业-5570","10.5281\u002Fzenodo.23545079",{"doi":136,"openalex_id":138,"authors":139,"venue":96,"cited_by_count":61,"oa_url":93,"card":142,"direction":83,"ingested_from":85},"W7223114002",[140],{"name":141,"orcid":9},"Kadiatou Barry",{"tldr":143,"method":144,"finding":145,"direction":83,"opportunity":146},"推导卫星云掩膜缺口下反事实解释可靠性的理论界，并评估其对合作社储粮决策的影响。","基于Lipschitz连续性假设与掩膜扰动分析推导可靠性界，并用2000个设计单","缺口比例上升使可靠性非线性下降；ICC=0.64表明需合作社层级聚合以保持解释稳定。","可研究不同作物区云掩膜统计特性下的自适应解释暂停阈值与聚合策略。","2026-10-22T11:20:39.240791Z",{"id":149,"title":150,"url":151,"summary":152,"summary_zh":153,"content":9,"source_name":154,"source_url":151,"published_at":155,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":156,"score_detail":157,"sources":160,"tags":162,"primary_topic":164,"secondary_topics":169,"classification":171,"search_phrases":204,"slug":207,"view_count":61,"doi":208,"paper":209,"created_at":222},5394,"Rice Yield Prediction Using Multi-Modal Regression Learning with Optimized Ensemble Models","https:\u002F\u002Fdoi.org\u002F10.3390\u002Feng7100572","Accurate rice yield estimation is important for agricultural planning, resource allocation, and food security assessment, but yield depends on interacting climatic, vegetation, remote sensing, seasonal, and crop growth factors. This study presents a Multi-Modal Regression Learning (MMRL) framework for continuous rice yield prediction. The framework integrates rainfall, temperature, humidity, normalized difference vegetation index (NDVI), VH synthetic aperture radar (SAR) backscatter, season, rice cultivation area, and leaf wetness information. Predictor relevance is assessed before model development, and multiple regression learners are trained using a common feature set. Their validation predictions are combined through non-negative ensemble weights constrained to sum to one, thereby producing a single optimized prediction. Experiments were performed on a modeled spatio-temporal agricultural dataset representing Karnataka conditions, with 10,000 observations used for the regression comparison. The proposed MMRL ensemble achieved an R2 of 0.9515, an RMSE of 0.6334 tons\u002Fha, an MAE of 0.5075 tons\u002Fha, and an MAPE of 9.81%, outperforming the evaluated individual regression models. Diagnostic plots further indicated close agreement between predicted and reference yields across most of the evaluated range. The MMRL workflow was also evaluated on a separately reconstructed synthetic dataset generated with fully specified distributions, sampling rules, noise terms, a yield generation equation, and fixed random seeds.","准确的水稻产量估算对农业规划、资源配置和粮食安全评估具有重要意义，但产量取决于气候、植被、遥感、季节和作物生长等多种因素的相互作用。本研究提出了一种用于连续水稻产量预测的多模态回归学习（Multi-Modal Regression Learning，MMRL）框架。该框架整合了降雨量、温度、湿度、归一化植被指数（NDVI）、VH合成孔径雷达（SAR）后向散射、季节、水稻种植面积和叶片湿润信息。在模型开发之前评估预测变量的相关性，并使用共同特征集训练多个回归学习器。其验证预测结果通过约束为和等于1的非负集成权重进行组合，从而生成单一优化预测。实验在代表卡纳塔克邦条件的建模时空农业数据集上进行，使用10,000个观测值进行回归比较。所提出的MMRL集成模型实现了R²为0.9515、RMSE为0.6334吨\u002F公顷、MAE为0.5075吨\u002F公顷、MAPE为9.81%，优于所评估的各个回归模型。诊断图进一步表明，在大多数评估范围内，预测产量与参考产量高度一致。MMRL工作流程还在一个单独重建的合成数据集上进行了评估，该数据集使用完全指定的分布、采样规则、噪声项、产量生成方程和固定随机种子生成。","Eng—Advances in Engineering","2026-10-18T00:00:00Z",78,{"impact":18,"substance":158,"depth":18,"authority":20,"freshness":17,"relevant":22,"comment":159},22,"多模态回归集成方法在水稻估产上取得较高精度，方法新颖、数据规模明确，对农业信息化有参考价值，但属学术论文且数据集为模拟数据，产业影响有限。",[161],{"name":154,"url":151},[27,106,163,28,29],"水稻",{"code":165,"slug":166,"name":163,"path":167,"parent_code":168},"A1","rice","\u002Ftopic\u002Ffield-crops\u002Frice","A",[170],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":172},{"candidates":173,"agricultural_evidence":46},[174,178,182,189,196,200],{"code":165,"score":19,"supported":46,"title":175,"abstract":176,"tags":177},[166],[163,166],[163],{"code":33,"score":17,"supported":46,"title":179,"abstract":180,"tags":181},[],[29,49],[28,29],{"code":183,"score":88,"supported":46,"title":184,"abstract":185,"tags":188},"A8",[],[186,187],"粮食安全","food security",[],{"code":190,"score":191,"supported":46,"title":192,"abstract":193,"tags":195},"J1",3,[],[194],"农业规划",[],{"code":53,"score":22,"supported":14,"title":197,"abstract":198,"tags":199},[],[],[27],{"code":109,"score":22,"supported":14,"title":201,"abstract":202,"tags":203},[],[],[106],[205,206],"水稻 产量预测 多模态","NDVI SAR 水稻估产","水稻产量预测多模态-5394","10.3390\u002Feng7100572",{"doi":208,"openalex_id":210,"authors":211,"venue":154,"cited_by_count":61,"oa_url":151,"card":217,"direction":83,"ingested_from":85},"W7222942064",[212,214],{"name":213,"orcid":9},"Nayana Venkatesh",{"name":215,"orcid":216},"Evangelin Geetha Devaraj","https:\u002F\u002Forcid.org\u002F0000-0002-7253-4314",{"tldr":218,"method":219,"finding":220,"direction":83,"opportunity":221},"构建多模态回归学习框架，融合气候、遥感与作物因子，实现水稻产量连续预测。","融合降雨、温度、NDVI、SAR后向散射等多源特征，用非负权重集成多个回归器。","集成模型R²达0.9515，RMSE为0.6334吨\u002F公顷，优于各单一回归模型。","可引入真实田间多时相遥感与深度时序模型，验证合成数据结论在真实产区的泛化性。","2026-10-20T23:30:19.292634Z",{"id":224,"title":225,"url":226,"summary":227,"summary_zh":228,"content":9,"source_name":229,"source_url":226,"published_at":230,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":231,"score_detail":232,"sources":235,"tags":237,"primary_topic":239,"secondary_topics":240,"classification":248,"search_phrases":306,"slug":309,"view_count":22,"doi":310,"paper":311,"created_at":334},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":18,"substance":158,"depth":18,"authority":233,"freshness":21,"relevant":22,"comment":234},14,"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。",[236],{"name":229,"url":226},[27,106,28,238,29],"多模态融合",{"code":109,"slug":110,"name":111,"path":112,"parent_code":37},[241,247],{"code":242,"slug":243,"name":244,"path":245,"parent_code":246},"B2","fruit","果树","\u002Ftopic\u002Fhorticulture\u002Ffruit","B",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":249},{"candidates":250,"agricultural_evidence":46},[251,260,268,273,280,287,294,300],{"code":109,"score":252,"supported":46,"title":253,"abstract":254,"tags":259},11,[],[255,256,257,258],"深度学习","机器学习","machine learning","deep learning",[106,238],{"code":242,"score":21,"supported":46,"title":261,"abstract":262,"tags":267},[],[263,264,265,266],"苹果","芒果","orchard","apple",[],{"code":33,"score":17,"supported":46,"title":269,"abstract":270,"tags":272},[],[271,50],"无人机多光谱",[28,29],{"code":53,"score":274,"supported":46,"title":275,"abstract":276,"tags":279},7,[],[277,278],"精准农业","precision agriculture",[27],{"code":281,"score":88,"supported":46,"title":282,"abstract":283,"tags":286},"H2",[],[284,285],"土壤","soil",[],{"code":288,"score":88,"supported":46,"title":289,"abstract":290,"tags":293},"I5",[],[291,292],"物联网","IoT",[],{"code":295,"score":191,"supported":46,"title":296,"abstract":297,"tags":299},"H6",[],[298],"农业生态",[],{"code":301,"score":191,"supported":46,"title":302,"abstract":303,"tags":305},"H7",[],[304],"气候适应",[],[307,308],"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":310,"openalex_id":312,"authors":313,"venue":229,"cited_by_count":61,"oa_url":226,"card":327,"direction":333,"ingested_from":85},"W7221795850",[314,317,319,321,323,325],{"name":315,"orcid":316},"Shabir Ahmad Mir","https:\u002F\u002Forcid.org\u002F0000-0003-2311-218X",{"name":318,"orcid":9},"Umarfarooque Momin",{"name":320,"orcid":9},"Sudeep Kumar E",{"name":322,"orcid":9},"Itfaq Ahmad Mir",{"name":324,"orcid":9},"Ab Rouf Khan",{"name":326,"orcid":9},"Ghulam Mohammad Mir",{"tldr":328,"method":329,"finding":330,"direction":331,"opportunity":332},"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":336,"title":337,"url":338,"summary":339,"summary_zh":340,"content":9,"source_name":341,"source_url":338,"published_at":342,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":343,"score_detail":344,"sources":348,"tags":350,"primary_topic":353,"secondary_topics":358,"classification":360,"search_phrases":384,"slug":387,"view_count":22,"doi":388,"paper":389,"created_at":413},4598,"Seasonal compatibility of RGB and multispectral vegetation indices in Amazon Cacao","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs12518-026-00815-x","Abstract Precision agriculture in cacao cultivation is constrained by multispectral sensor costs, limiting accessibility for smallholder farmers. This study evaluated the seasonal compatibility between RGB-derived visible reflectance and multispectral vegetation indices (NDVI, GNDVI, NDRE) to establish a low-cost monitoring approach for Eastern Amazon cacao plantations. We collected spectral data from 1,431 random sampling points across a 0.9-ha commercial cacao plantation during four seasonal periods (February, May, August, and November 2025) using UAV-mounted RGB and multispectral sensors. Pearson correlations and linear regression models assessed relationships between mean visible reflectance [(R + G+B)\u002F3] and multispectral indices. Geostatistical analysis characterized spatial dependence structure across seasons. GNDVI demonstrated superior compatibility across all seasons (mean R² = 59.3%; range: 52.5–62.9%), outperforming NDRE (44.2%) and NDVI (40.8%) by 15–19% points. Temporal stability was 2.9× higher for GNDVI (SD = 4.7 pp) than NDRE (14.1 pp) and NDVI (12.7 pp). Peak compatibility occurred in May (R² = 62.9%) during wet-to-dry transition. The conversion equation (GNDVI = 0.509–0.000012 × Visible Reflectance; RMSE = 0.077) enables reliable estimation, retaining 59% of multispectral information. Strong spatial dependence (Co\u002F(Co + C) \u003C 10%) was confirmed across all periods, with August providing optimal structure (range = 11.4 m) for management zone delineation. GNDVI is the most reliable RGB proxy for cacao monitoring, democratizing precision agriculture access through affordable technology while maintaining robust spatial and temporal performance year-round.","摘要 可可种植中的精准农业受到多光谱传感器成本的制约，限制了小农户的可及性。本研究评估了RGB衍生的可见光反射率与多光谱植被指数（NDVI、GNDVI、NDRE）之间的季节性兼容性，以建立一种面向东亚马逊可可种植园的低成本监测方法。我们使用无人机搭载的RGB和多光谱传感器，在四个季节时段（2025年2月、5月、8月和11月）从一片0.9公顷商业可可种植园的1，431个随机采样点采集了光谱数据。采用Pearson相关分析和线性回归模型评估平均可见光反射率[（R + G + B）\u002F3]与多光谱指数之间的关系。地统计学分析刻画了各季节的空间依赖结构。GNDVI在所有季节均表现出最优兼容性（平均R² = 59.3%；范围：52.5–62.9%），较NDRE（44.2%）和NDVI（40.8%）高出15–19个百分点。GNDVI的时间稳定性（SD = 4.7个百分点）是NDRE（14.1个百分点）和NDVI（12.7个百分点）的2.9倍。最高兼容性出现在5月（R² = 62.9%），即湿季向干季过渡期。转换方程（GNDVI = 0.509–0.000012 × 可见光反射率；RMSE = 0.077）可实现可靠估算，保留了59%的多光谱信息。所有时期均确认存在强空间依赖性（Co\u002F(Co + C) \u003C 10%），其中8月提供了最优结构（变程 = 11.4 m），适合用于管理分区划分。GNDVI是可可监测中最可靠的RGB替代指标，通过可负担的技术使精准农业更广泛可及，同时全年保持稳健的空间和时间性能。","Applied Geomatics","2026-10-08T00:00:00Z",68,{"impact":17,"substance":345,"depth":101,"authority":346,"freshness":21,"relevant":22,"comment":347},21,13,"以低成本RGB替代多光谱监测亚马逊可可，数据扎实、结论明确，对精准农业降本有参考价值，但属细分作物研究，公共影响有限。",[349],{"name":341,"url":338},[27,29,30,351,352],"可可种植","无人机监测",{"code":354,"slug":355,"name":356,"path":357,"parent_code":246},"B3","tea-coffee","茶叶与咖啡","\u002Ftopic\u002Fhorticulture\u002Ftea-coffee",[359],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":361},{"candidates":362,"agricultural_evidence":46},[363,369,373,377],{"code":354,"score":233,"supported":46,"title":364,"abstract":366,"tags":368},[365],"cacao",[367,365],"可可",[],{"code":33,"score":346,"supported":46,"title":370,"abstract":371,"tags":372},[50],[50],[30,29],{"code":53,"score":274,"supported":46,"title":374,"abstract":375,"tags":376},[],[277,278],[27],{"code":378,"score":88,"supported":46,"title":379,"abstract":380,"tags":383},"G2",[],[381,382],"小农户","smallholder",[],[385,386],"亚马逊 可可 无人机 遥感","GNDVI RGB 植被指数 可可","亚马逊可可无人机遥感-4598","10.1007\u002Fs12518-026-00815-x",{"doi":388,"openalex_id":390,"authors":391,"venue":341,"cited_by_count":61,"oa_url":407,"card":408,"direction":83,"ingested_from":85},"W7221039911",[392,395,398,401,404],{"name":393,"orcid":394},"Charlyngton da Silva e Silva","https:\u002F\u002Forcid.org\u002F0009-0003-9332-4302",{"name":396,"orcid":397},"Luiz Antônio Soares Cardoso","https:\u002F\u002Forcid.org\u002F0000-0001-6868-7847",{"name":399,"orcid":400},"Ronilson de Souza Santos","https:\u002F\u002Forcid.org\u002F0000-0002-2683-456X",{"name":402,"orcid":403},"Carlos Rodrigo Tanajura Caldeira","https:\u002F\u002Forcid.org\u002F0000-0001-7102-7735",{"name":405,"orcid":406},"Norberto Cornejo Noronha","https:\u002F\u002Forcid.org\u002F0000-0001-7216-8687","https:\u002F\u002Flink.springer.com\u002Fcontent\u002Fpdf\u002F10.1007\u002Fs12518-026-00815-x.pdf",{"tldr":409,"method":410,"finding":411,"direction":83,"opportunity":412},"评估RGB与多光谱植被指数在亚马逊可可园的季节性兼容性，以低成本监测替代多光谱传感器。","无人机RGB与多光谱传感器采集1431个样点，用相关、回归和地统计分析四季数据。","GNDVI兼容性最佳（R²=59.3%），时空稳定性最高，5月表现最优，可保留59%多光谱信息。","可探索RGB代理指数在其他热带作物和不同冠层结构下的普适性，并优化低成本管理分区方法。","2026-10-10T23:30:31.142887Z",{"id":415,"title":416,"url":417,"summary":418,"summary_zh":419,"content":9,"source_name":96,"source_url":417,"published_at":420,"category":12,"cover_url":9,"hotness":421,"is_selected":14,"score":422,"score_detail":423,"sources":425,"tags":429,"primary_topic":430,"secondary_topics":431,"classification":434,"search_phrases":475,"slug":478,"view_count":61,"doi":479,"paper":480,"created_at":490},4310,"Comprehensive remote sensing and machine learning framework for multi-regional rice yield forecasting under hydroclimatic variability in Sahelian Niger","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23149579","It is crucial to forecast rice yields effectively in order to improve agricultural planning and resilience to climate change in the Sahel, where production is greatly affected by hydroclimatic variability. This research has developed an integrated framework combining remote sensing analysis and machine learning to assess the variability in rice production in Niamey, Dosso, Tillaberi and Diffa, in Niger, over the period 2010–2025. They combined Landsat-derived NDVI and EVI with parameters such as evapotranspiration, precipitation, temperature, humidity, solar radiation, soil moisture, cultivated area, year and season. We processed and harmonised the datasets using Google Earth Engine and Python. We then evaluated four regression algorithms separately, Random Forest (RF), k-nearest neighbours (KNN), support vector regression (SVR) and XGBoost (XGB), for each region. The correlation analysis revealed modest positive links between rice yield and the NDVI (r = 0.27) and the EVI (r = 0.14), while a strong correlation was observed between the NDVI and the EVI (r = 0.80). The vegetation indices showed marked seasonal and interannual variability, generally exhibiting higher values during the wet season. Model performance varied considerably from one region to another","在萨赫勒地区，有效预测水稻产量对于改善农业规划和增强气候变化适应能力至关重要，因为该地区的生产在很大程度上受到水文气候变率的制约。本研究开发了一个集成框架，将遥感分析与机器学习相结合，以评估尼日尔尼亚美、多索、蒂拉贝里和迪法在2010—2025年期间水稻产量的变异性。研究将基于Landsat的归一化植被指数（NDVI）和增强型植被指数（EVI）与蒸散发、降水、温度、湿度、太阳辐射、土壤水分、耕地面积、年份和季节等参数相结合。利用Google Earth Engine和Python对数据集进行了处理和协调。随后，针对每个地区分别评估了四种回归算法：随机森林（RF）、k近邻（KNN）、支持向量回归（SVR）和XGBoost（XGB）。相关分析显示，水稻产量与NDVI（r = 0.27）和EVI（r = 0.14）之间存在弱正相关，而NDVI与EVI之间则观察到强相关（r = 0.80）。植被指数表现出明显的季节性和年际变异性，通常在湿季呈现较高值。模型性能在不同地区之间差异显著。","2026-10-05T00:00:00Z",25,72,{"impact":20,"substance":345,"depth":101,"authority":346,"freshness":21,"relevant":22,"comment":424},"基于Landsat植被指数与四种机器学习模型的多区域水稻产量预测研究，方法扎实、数据跨度长，但属区域性学术成果，对国内农业信息化有方法借鉴价值。",[426,427],{"name":96,"url":417},{"name":96,"url":428},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23149580",[27,106,163,28,29],{"code":165,"slug":166,"name":163,"path":167,"parent_code":168},[432,433],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"code":109,"slug":110,"name":111,"path":112,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":435},{"candidates":436,"agricultural_evidence":46},[437,442,446,450,454,461,467,471],{"code":33,"score":438,"supported":46,"title":439,"abstract":440,"tags":441},16,[49],[29,49],[28,29],{"code":165,"score":19,"supported":46,"title":443,"abstract":444,"tags":445},[166],[163,166],[163],{"code":109,"score":19,"supported":46,"title":447,"abstract":448,"tags":449},[257],[256,257],[106],{"code":281,"score":88,"supported":46,"title":451,"abstract":452,"tags":453},[],[284,285],[],{"code":455,"score":88,"supported":46,"title":456,"abstract":457,"tags":460},"H3",[],[458,459],"蒸散发","evapotranspiration",[],{"code":301,"score":88,"supported":46,"title":462,"abstract":463,"tags":466},[],[464,465],"气候变化","climate change",[],{"code":190,"score":191,"supported":46,"title":468,"abstract":469,"tags":470},[],[194],[],{"code":53,"score":22,"supported":14,"title":472,"abstract":473,"tags":474},[],[],[27],[476,477],"尼日尔 水稻 遥感 产量预测","Landsat NDVI 水稻 机器学习","尼日尔水稻遥感产量预测-4310","10.5281\u002Fzenodo.23149579",{"doi":479,"openalex_id":481,"authors":482,"venue":96,"cited_by_count":61,"oa_url":417,"card":485,"direction":83,"ingested_from":85},"W7220391503",[483],{"name":484,"orcid":9},"Battula Vijaya Saradhi Halarou Saidou Souley",{"tldr":486,"method":487,"finding":488,"direction":83,"opportunity":489},"结合遥感植被指数与机器学习，预测尼日尔萨赫勒四地区2010–2025年水稻产量。","Landsat NDVI\u002FEVI 加气象土壤变量，GEE与Python处理，比较","NDVI\u002FEVI与产量仅弱相关，模型精度区域差异大，植被指数呈明显季节与年际波动。","可引入时序深度学习与迁移学习，解决跨区域泛化差及植被指数解释力弱的问题。","2026-10-06T23:30:20.077977Z",{"id":492,"title":493,"url":494,"summary":495,"summary_zh":496,"content":9,"source_name":497,"source_url":494,"published_at":498,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":499,"score_detail":500,"sources":502,"tags":504,"primary_topic":507,"secondary_topics":512,"classification":514,"search_phrases":530,"slug":533,"view_count":191,"doi":534,"paper":535,"created_at":545},3838,"Forecasting Cotton Productivity in the Mil-Mugan Economic Region using Climate Variables and Remote Sensing Data","https:\u002F\u002Fdoi.org\u002F10.52171\u002Fherald.342","Satellite imagery is considered as one of the most valuable and functional data sources for evaluating and forecasting production in agricultural systems. This study aims to forecast productivity in cotton fields within the Mil-Mugan economic region by incorporating vegetation indices and climatic variables. NDVI indicators were derived from Sentinel-2 data, temperature (T) was obtained from ERA5-Land data, and precipitation (R) was collected from the CHIRPS database. The data were analyzed using Google Earth Engine, ArcGIS Pro, and Python environments, consolidating them into an integrated temporal-spatial dimension. The correlation and regression analysis assessed the link among NDVI, temperature, precipitation, and productivity, leading to the development of a multivariate model. The findings derived from the model indicate that NDVI is the primary factor influencing productivity. The model developed for one region was implemented in the other three locations, and the correlation between the actual and predicted indicators was assessed using R² and RMSE metrics. The results indicate that the model's forecast accuracy fluctuates within the 90% range, considered appropriate for predicting regional cotton yield. The study's findings are significant for enhancing operational monitoring and planning of agrotechnical decisions with satellite data.","卫星影像被认为是评估和预测农业系统产量最有价值且最实用的数据来源之一。本研究旨在通过整合植被指数与气候变量，预测米尔-穆甘经济区棉田的生产力。NDVI指标源自Sentinel-2数据，温度（T）取自ERA5-Land数据，降水（R）来自CHIRPS数据库。数据在Google Earth Engine、ArcGIS Pro和Python环境中进行分析，并将其整合为统一的时空维度。通过相关性与回归分析评估了NDVI、温度、降水与生产力之间的关系，进而构建了多变量模型。模型结果表明，NDVI是影响生产力的主要因素。将为某一区域开发的模型应用于其他三个地点，并使用R²和RMSE指标评估实际值与预测值之间的相关性。结果表明，模型的预测精度在90%范围内波动，被认为适用于预测区域棉花产量。本研究结果对于利用卫星数据加强农艺决策的业务化监测与规划具有重要意义。","Herald of the Azerbaijan Engineering Academy","2026-09-29T00:00:00Z",63,{"impact":17,"substance":100,"depth":438,"authority":13,"freshness":21,"relevant":22,"comment":501},"基于Sentinel-2与气候变量的棉花产量预测模型，方法扎实、精度达90%，但属区域案例研究，公共影响有限。",[503],{"name":497,"url":494},[27,28,505,29,506],"棉花","NDVI",{"code":508,"slug":509,"name":510,"path":511,"parent_code":168},"A6","cash-crops","棉麻糖与特色经作","\u002Ftopic\u002Ffield-crops\u002Fcash-crops",[513],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":515},{"candidates":516,"agricultural_evidence":46},[517,522,526],{"code":508,"score":19,"supported":46,"title":518,"abstract":520,"tags":521},[519],"cotton",[505,519],[505],{"code":33,"score":252,"supported":46,"title":523,"abstract":524,"tags":525},[49],[],[506,28,29],{"code":53,"score":22,"supported":14,"title":527,"abstract":528,"tags":529},[],[],[27],[531,532],"Mil-Mugan 棉花 遥感","Sentinel-2 NDVI 棉花产量","Mil-Mugan棉花遥感-3838","10.52171\u002Fherald.342",{"doi":534,"openalex_id":536,"authors":537,"venue":497,"cited_by_count":61,"oa_url":494,"card":540,"direction":83,"ingested_from":85},"W7214748696",[538],{"name":539,"orcid":9},"B.H. Babashli",{"tldr":541,"method":542,"finding":543,"direction":83,"opportunity":544},"结合Sentinel-2 NDVI与气候变量，构建多元模型预测米尔-穆甘地区棉花产量。","Sentinel-2 NDVI、ERA5-Land温度、CHIRPS降水，GEE","NDVI是产量主控因子，模型跨区预测精度约90%，可用于区域估产。","可引入多时相NDVI与机器学习，提升跨区域迁移性和极端气候下的估产鲁棒性。","2026-09-30T23:30:27.786044Z"]