[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4081":3,"related-4081":126},{"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":87,"slug":90,"view_count":22,"doi":91,"paper":92,"created_at":125},4081,"Aerial Phenotyping of Coffee Flowering Using Deep Learning for Early Yield Prediction","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fplants15193019","Early yield estimation is important for improving decision-making and management practices in coffee production systems. However, approaches that use aerial imagery to characterize flowering and relate it to subsequent yield remain limited. This study evaluated the potential of RGB imagery acquired by remotely piloted aircraft (RPA) combined with Deep Learning techniques to classify coffee plants according to three levels of a flowering proxy and to investigate its relationship with yield. A dataset comprising 1593 segmented RGB images was classified into Low, Medium, and High flowering levels using a custom convolutional neural network and three transfer learning architectures: VGG16, ResNet50V2, and MobileNetV2. ResNet50V2 was selected for final evaluation based on its validation performance and achieved 92.12% accuracy, 92.40% macro-precision, 91.81% macro-recall, and 92.06% macro-F1 on the test dataset. The flowering proxy showed a positive association with field-observed yield, with Spearman’s ρ = 0.701 (p \u003C 0.001) and R2 = 0.528 for the combined dataset of Arara and Mundo Novo. In consolidated out-of-sample predictions, the model achieved R2 = 0.489, MAE = 1.03 kg plant−1, and RMSE = 1.18 kg plant−1. Performance differed between cultivars, with consolidated R2 values of 0.567 for Arara and 0.329 for Mundo Novo. Spatial analysis also showed correspondence between the distribution of flowering levels derived from RGB imagery and the subsequent spatial distribution of yield. These findings indicate that RPA-based RGB imagery and Deep Learning can provide spatialized information related to coffee flowering and its productive performance, with potential applications in precision agriculture. Further evaluation across production cycles, cultivars, and environmental conditions is needed to assess the robustness and generalization of the approach.","早期产量估测对于改善咖啡生产系统中的决策与管理实践具有重要意义。然而，利用航空影像表征开花并将其与后续产量相关联的方法仍然有限。本研究评估了由遥控驾驶航空器（RPA）获取的RGB影像结合深度学习技术，根据开花代理指标的三个水平对咖啡植株进行分类，并探讨其与产量之间关系的潜力。利用自定义卷积神经网络和三种迁移学习架构——VGG16、ResNet50V2和MobileNetV2，将包含1593张分割RGB图像的数据集分类为低、中、高开花水平。基于验证性能，选择ResNet50V2进行最终评估，其在测试数据集上达到了92.12%的准确率、92.40%的宏精确率、91.81%的宏召回率和92.06%的宏F1值。开花代理指标与田间观测产量呈正相关，Arara和Mundo Novo合并数据集的Spearman's ρ = 0.701（p \u003C 0.001），R² = 0.528。在合并的样本外预测中，模型达到了R² = 0.489、MAE = 1.03 kg plant⁻¹和RMSE = 1.18 kg plant⁻¹。不同品种间的表现存在差异，Arara和Mundo Novo的合并R²值分别为0.567和0.329。空间分析还表明，由RGB影像得出的开花水平分布与后续产量的空间分布之间存在对应关系。这些发现表明，基于RPA的RGB影像和深度学习能够提供与咖啡开花及其生产性能相关的空间化信息，在精准农业中具有应用潜力。需要在不同生产周期、品种和环境条件下进行进一步评估，以检验该方法的稳健性和泛化能力。",null,"Plants","2026-10-02T00:00:00Z","论文",10,false,78,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},16,22,18,13,9,1,"该研究将无人机RGB影像与深度学习结合用于咖啡花期分类和早期产量预测，方法新颖、数据扎实、结论可靠，对智慧农业和精准农业有参考价值，但属于细分作物研究，影响范围有限。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业人工智能","产量预测","遥感","咖啡种植",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},"B3","tea-coffee","茶叶与咖啡","\u002Ftopic\u002Fhorticulture\u002Ftea-coffee","B",[39],{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":46,"locked":14,"version":47,"method":48,"evidence":49},"classified","2026-10-22.2","rules",{"candidates":50,"agricultural_evidence":53},[51,59,65,73,81],{"code":33,"score":52,"supported":53,"title":54,"abstract":56,"tags":58},15,true,[55],"coffee",[57,55],"咖啡",[31],{"code":40,"score":52,"supported":53,"title":60,"abstract":62,"tags":64},[61],"deep learning",[63,61],"深度学习",[28],{"code":66,"score":67,"supported":53,"title":68,"abstract":69,"tags":72},"I1",7,[],[70,71],"精准农业","precision agriculture",[27],{"code":74,"score":75,"supported":53,"title":76,"abstract":77,"tags":80},"I4",6,[],[78,79],"空间分析","spatial analysis",[],{"code":82,"score":83,"supported":14,"title":84,"abstract":85,"tags":86},"I3",2,[],[],[29,30],[88,89],"无人机 RGB 咖啡 花期 产量预测","ResNet50V2 咖啡 深度学习","无人机RGB咖啡花期产量预测-4081","10.3390\u002Fplants15193019",{"doi":91,"openalex_id":93,"authors":94,"venue":10,"cited_by_count":117,"oa_url":6,"card":118,"direction":122,"ingested_from":124},"W7216244707",[95,97,100,103,105,108,111,114],{"name":96,"orcid":9},"Elias Horácio Zavala",{"name":98,"orcid":99},"Gabriel Araújo e Silva Ferraz","https:\u002F\u002Forcid.org\u002F0000-0001-6403-2210",{"name":101,"orcid":102},"Felipe Andrés Obando Vega","https:\u002F\u002Forcid.org\u002F0000-0001-7241-7065",{"name":104,"orcid":9},"Mirian de Lourdes Oliveira",{"name":106,"orcid":107},"Milene Alves de Figueiredo Carvalho","https:\u002F\u002Forcid.org\u002F0000-0001-6138-8182",{"name":109,"orcid":110},"Samuel Henrique Braga da Cunha","https:\u002F\u002Forcid.org\u002F0000-0002-8783-0378",{"name":112,"orcid":113},"Andrea Pagliai","https:\u002F\u002Forcid.org\u002F0000-0002-0455-7426",{"name":115,"orcid":116},"Daniele Sarri","https:\u002F\u002Forcid.org\u002F0000-0001-6990-7573",0,{"tldr":119,"method":120,"finding":121,"direction":122,"opportunity":123},"用无人机RGB影像和深度学习对咖啡开花分级，实现早期产量预测。","1593张分割RGB图，自定义CNN与VGG16\u002FResNet50V2\u002FMobi","ResNet50V2开花分级准确率92.12%，开花等级与产量正相关（ρ=0.701）。","农业遥感与作物表型","可跨生产周期、品种和环境验证模型泛化性，并融合多源遥感提升早期产量预测稳健性。","openalex","2026-10-03T23:30:27.930711Z",{"total":75,"page":22,"page_size":75,"items":127},[128,219,275,327,433,516],{"id":129,"title":130,"url":131,"summary":132,"summary_zh":133,"content":9,"source_name":134,"source_url":131,"published_at":135,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":136,"score_detail":137,"sources":142,"tags":144,"primary_topic":147,"secondary_topics":148,"classification":150,"search_phrases":179,"slug":182,"view_count":183,"doi":184,"paper":185,"created_at":218},3165,"Explainable growth stage classification of cacao (Theobroma cacao L.) leaves and key feature visualization using vision transformer and transfer learning","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffpls.2026.1885906","Accurate and objective plant phenotyping is crucial for optimizing agricultural practices, understanding plant development, and enabling rapid responses to environmental changes. Traditional methods, often relying on visual observation, can be subjective, time-consuming, and may overlook subtle but important differences. This study demonstrates the power of combining digital imaging with deep learning to classify plant material with high accuracy, even when visual differences are minimal. We focused on differentiating between stage D (light green) and stage E (dark green) leaves of cacao ( Theobroma cacao L. ), which are visually very similar in size and overall structure. Using cleared and stained leaves of the SCA 6 genotype to highlight the venation network, we trained a Vision Transformer (ViT) model, a deep learning architecture, on image patches. At the patch level, the model achieved an overall accuracy of 97.03% on an independent test set, with a recall of 96.0% for stage D and 98.3% for stage E. At the whole-leaf level, majority voting correctly classified 14 of 15 independent test leaves (93.3%). Attention maps indicated that image regions containing the midrib and primary lateral veins contributed strongly to classification. These attention maps identify discriminative image regions, but they do not by themselves determine the biological mechanism underlying the signal. The major-vein signal may reflect developmental differences in vein-associated structure, stage-associated differences in Safranin O uptake or optical density, tissue thickness, or a combination of these factors. Because vascular anatomy, lignification, hydraulic conductance, phloem loading, and source–sink status were not directly measured, these mechanisms are treated as hypotheses requiring future anatomical, histochemical, and physiological validation. Thus, this study provides a proof-of-concept for interpretable image-based classification of stage D and stage E leaves within greenhouse-grown SCA 6 cacao. Extension to other cacao genotypes, field-grown plants, independent seasons, staining batches, stress detection, species identification, genotype discrimination, or precision-agriculture deployment will require external validation.","准确、客观的植物表型分析对于优化农业实践、理解植物发育以及快速响应环境变化至关重要。传统方法通常依赖视觉观察，可能具有主观性、耗时，并且可能忽略细微但重要的差异。本研究展示了将数字成像与深度学习相结合，即使在视觉差异极小的情况下，也能以高精度对植物材料进行分类。我们聚焦于区分可可（Theobroma cacao L.）的D期（浅绿色）和E期（深绿色）叶片，这些叶片在大小和整体结构上视觉上非常相似。利用SCA 6基因型的透明染色叶片以突出脉序网络，我们在图像块上训练了Vision Transformer（ViT）模型，一种深度学习架构。在图像块水平上，该模型在独立测试集上达到了97.03%的总体准确率，D期的召回率为96.0%，E期为98.3%。在整叶水平上，多数投票正确分类了15片独立测试叶片中的14片（93.3%）。注意力图表明，包含中脉和初级侧脉的图像区域对分类贡献显著。这些注意力图识别了具有判别力的图像区域，但它们本身并不能确定信号背后的生物学机制。主脉信号可能反映了脉相关结构的发育差异、番红O摄取或光密度的阶段相关差异、组织厚度，或这些因素的组合。由于未直接测量维管解剖结构、木质化、水力导度、韧皮部装载和源–库状态，这些机制被视为假设，需要未来的解剖学、组织化学和生理学验证。因此，本研究为温室种植的SCA 6可可中D期和E期叶片的可解释图像分类提供了概念验证。扩展到其他可可基因型、田间种植植株、独立季节、染色批次、胁迫检测、物种鉴定、基因型区分或精准农业部署将需要外部验证。","Frontiers in Plant Science","2026-09-21T00:00:00Z",71,{"impact":138,"substance":139,"depth":140,"authority":20,"freshness":21,"relevant":22,"comment":141},12,20,17,"方法新颖、数据可靠的可解释作物表型概念验证研究，但属实验室小样本，产业影响有限。",[143],{"name":134,"url":131},[27,28,63,145,146],"可可","作物表型",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[149],{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},{"status":46,"locked":14,"version":47,"method":48,"evidence":151},{"candidates":152,"agricultural_evidence":53},[153,158,163,170,175],{"code":33,"score":52,"supported":53,"title":154,"abstract":156,"tags":157},[155],"cacao",[145,155],[145],{"code":40,"score":159,"supported":53,"title":160,"abstract":161,"tags":162},8,[],[63,61],[28,63],{"code":164,"score":75,"supported":53,"title":165,"abstract":166,"tags":169},"B7",[],[167,168],"温室","greenhouse",[],{"code":66,"score":171,"supported":53,"title":172,"abstract":173,"tags":174},4,[],[70],[27],{"code":82,"score":22,"supported":14,"title":176,"abstract":177,"tags":178},[],[],[146],[180,181],"可可 叶片 生长阶段 分类","Vision Transformer 作物表型","可可叶片生长阶段分类-3165",5,"10.3389\u002Ffpls.2026.1885906",{"doi":184,"openalex_id":186,"authors":187,"venue":134,"cited_by_count":117,"oa_url":131,"card":213,"direction":122,"ingested_from":124},"W7213901640",[188,190,193,195,197,199,202,205,208,210],{"name":189,"orcid":9},"Ezekiel Ahn",{"name":191,"orcid":192},"Eun-Sung Park","https:\u002F\u002Forcid.org\u002F0000-0001-6826-2865",{"name":194,"orcid":9},"Moon S. Kim",{"name":196,"orcid":9},"Hangi Kim",{"name":198,"orcid":9},"Lalit M. Kandpal",{"name":200,"orcid":201},"Sunchung Park","https:\u002F\u002Forcid.org\u002F0000-0002-7398-9476",{"name":203,"orcid":204},"Seunghyun Lim","https:\u002F\u002Forcid.org\u002F0000-0003-3023-4863",{"name":206,"orcid":207},"Lyndel W. Meinhardt","https:\u002F\u002Forcid.org\u002F0000-0001-8299-2629",{"name":209,"orcid":9},"Byoung-Kwan Cho",{"name":211,"orcid":212},"Insuck Baek","https:\u002F\u002Forcid.org\u002F0000-0003-1044-349X",{"tldr":214,"method":215,"finding":216,"direction":122,"opportunity":217},"用ViT和迁移学习对可可叶D、E期进行可解释分类，准确率达97%。","透明染色叶片图像块训练ViT，注意力图可视化关键区域。","模型准确区分D\u002FE期，中脉和主侧脉区域贡献最大。","可扩展到多基因型、田间、胁迫检测，并验证脉信号生物学机制。","2026-09-22T23:30:19.972949Z",{"id":220,"title":221,"url":222,"summary":223,"summary_zh":9,"content":9,"source_name":224,"source_url":9,"published_at":225,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":226,"score_detail":227,"sources":229,"tags":231,"primary_topic":235,"secondary_topics":236,"classification":242,"search_phrases":262,"slug":265,"view_count":22,"doi":9,"paper":266,"created_at":274},1367,"基于无人机多源遥感特征的茶树生长与氮素状况深度学习监测","https:\u002F\u002Fwww.mdpi.com\u002F2072-4292\u002F18\u002F17\u002F2923","南京农业大学园艺学院团队提出融合光谱、纹理与谐波特征的多域融合指标，结合无人机数据与深度学习模型，用于茶树生物量与氮素积累量估算。实验表明多域融合指数显著优于传统光谱指标，可实现对茶园生物量与氮素状况的高精度反演，为近实时茶园监测提供工具。","Remote Sensing · MDPI · 2026-09-01","2026-08-31T16:00:00Z",72,{"impact":52,"substance":139,"depth":19,"authority":138,"freshness":67,"relevant":22,"comment":228},"研究提出多域融合指标，提升茶树氮素监测精度，对智慧茶园有实用价值。",[230],{"name":224,"url":222},[27,232,30,233,234],"无人机","氮素监测","茶树",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[237,238],{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},{"code":82,"slug":239,"name":240,"path":241,"parent_code":44},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":46,"locked":14,"version":47,"method":48,"evidence":243},{"candidates":244,"agricultural_evidence":53},[245,250,254,258],{"code":33,"score":246,"supported":53,"title":247,"abstract":248,"tags":249},11,[234],[234],[],{"code":40,"score":246,"supported":53,"title":251,"abstract":252,"tags":253},[63],[63],[],{"code":82,"score":21,"supported":53,"title":255,"abstract":256,"tags":257},[30],[],[30],{"code":66,"score":22,"supported":14,"title":259,"abstract":260,"tags":261},[],[],[27],[263,264],"智慧农业 氮素监测 无人机 茶树","智慧农业 氮素监测","智慧农业氮素监测无人机茶树-1367",{"doi":9,"openalex_id":9,"authors":267,"venue":9,"cited_by_count":117,"oa_url":9,"card":268,"direction":122,"ingested_from":273},[],{"tldr":269,"method":270,"finding":271,"direction":122,"opportunity":272},"融合无人机多源遥感特征与深度学习，高精度估算茶树生物量与氮素积累量。","融合光谱、纹理、谐波特征的多域融合指标，结合无人机数据与深度学习模型。","多域融合指数显著优于传统光谱指标，实现茶园生物量与氮素高精度反演。","可探索多域融合特征在其他作物或不同生长阶段的适用性，或结合时序数据预测氮素动态。","agent","2026-09-02T00:05:07.021728Z",{"id":276,"title":277,"url":278,"summary":279,"summary_zh":280,"content":9,"source_name":281,"source_url":278,"published_at":282,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":283,"score_detail":284,"sources":286,"tags":288,"primary_topic":290,"secondary_topics":291,"classification":293,"search_phrases":311,"slug":314,"view_count":117,"doi":315,"paper":316,"created_at":326},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":159,"substance":139,"depth":140,"authority":138,"freshness":13,"relevant":22,"comment":285},"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。",[287],{"name":281,"url":278},[27,28,29,30,289],"可解释性",{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},[292],{"code":82,"slug":239,"name":240,"path":241,"parent_code":44},{"status":46,"locked":14,"version":47,"method":48,"evidence":294},{"candidates":295,"agricultural_evidence":53},[296,302,307],{"code":40,"score":138,"supported":53,"title":297,"abstract":299,"tags":301},[298],"computer vision",[300],"计算机视觉",[28],{"code":82,"score":159,"supported":53,"title":303,"abstract":304,"tags":306},[],[30,305],"remote sensing",[29,30],{"code":66,"score":22,"supported":14,"title":308,"abstract":309,"tags":310},[],[],[27],[312,313],"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":315,"openalex_id":317,"authors":318,"venue":281,"cited_by_count":117,"oa_url":278,"card":321,"direction":122,"ingested_from":124},"W7223114002",[319],{"name":320,"orcid":9},"Kadiatou Barry",{"tldr":322,"method":323,"finding":324,"direction":122,"opportunity":325},"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":328,"title":329,"url":330,"summary":331,"summary_zh":332,"content":9,"source_name":134,"source_url":330,"published_at":333,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":334,"score_detail":335,"sources":338,"tags":340,"primary_topic":342,"secondary_topics":343,"classification":350,"search_phrases":404,"slug":407,"view_count":22,"doi":408,"paper":409,"created_at":432},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","2026-10-14T00:00:00Z",81,{"impact":19,"substance":18,"depth":19,"authority":336,"freshness":21,"relevant":22,"comment":337},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。",[339],{"name":134,"url":330},[27,28,29,341,30],"多模态融合",{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},[344,349],{"code":345,"slug":346,"name":347,"path":348,"parent_code":37},"B2","fruit","果树","\u002Ftopic\u002Fhorticulture\u002Ffruit",{"code":82,"slug":239,"name":240,"path":241,"parent_code":44},{"status":46,"locked":14,"version":47,"method":48,"evidence":351},{"candidates":352,"agricultural_evidence":53},[353,359,367,373,377,384,391,398],{"code":40,"score":246,"supported":53,"title":354,"abstract":355,"tags":358},[],[63,356,357,61],"机器学习","machine learning",[28,341],{"code":345,"score":21,"supported":53,"title":360,"abstract":361,"tags":366},[],[362,363,364,365],"苹果","芒果","orchard","apple",[],{"code":82,"score":159,"supported":53,"title":368,"abstract":369,"tags":372},[],[370,371],"无人机多光谱","multispectral",[29,30],{"code":66,"score":67,"supported":53,"title":374,"abstract":375,"tags":376},[],[70,71],[27],{"code":378,"score":75,"supported":53,"title":379,"abstract":380,"tags":383},"H2",[],[381,382],"土壤","soil",[],{"code":385,"score":75,"supported":53,"title":386,"abstract":387,"tags":390},"I5",[],[388,389],"物联网","IoT",[],{"code":392,"score":393,"supported":53,"title":394,"abstract":395,"tags":397},"H6",3,[],[396],"农业生态",[],{"code":399,"score":393,"supported":53,"title":400,"abstract":401,"tags":403},"H7",[],[402],"气候适应",[],[405,406],"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":408,"openalex_id":410,"authors":411,"venue":134,"cited_by_count":117,"oa_url":330,"card":425,"direction":431,"ingested_from":124},"W7221795850",[412,415,417,419,421,423],{"name":413,"orcid":414},"Shabir Ahmad Mir","https:\u002F\u002Forcid.org\u002F0000-0003-2311-218X",{"name":416,"orcid":9},"Umarfarooque Momin",{"name":418,"orcid":9},"Sudeep Kumar E",{"name":420,"orcid":9},"Itfaq Ahmad Mir",{"name":422,"orcid":9},"Ab Rouf Khan",{"name":424,"orcid":9},"Ghulam Mohammad Mir",{"tldr":426,"method":427,"finding":428,"direction":429,"opportunity":430},"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":434,"title":435,"url":436,"summary":437,"summary_zh":438,"content":9,"source_name":281,"source_url":436,"published_at":439,"category":12,"cover_url":9,"hotness":440,"is_selected":14,"score":226,"score_detail":441,"sources":444,"tags":448,"primary_topic":450,"secondary_topics":455,"classification":458,"search_phrases":500,"slug":503,"view_count":117,"doi":504,"paper":505,"created_at":515},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,{"impact":138,"substance":442,"depth":140,"authority":20,"freshness":21,"relevant":22,"comment":443},21,"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。",[445,446],{"name":281,"url":436},{"name":281,"url":447},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23149580",[27,28,449,29,30],"水稻",{"code":451,"slug":452,"name":449,"path":453,"parent_code":454},"A1","rice","\u002Ftopic\u002Ffield-crops\u002Frice","A",[456,457],{"code":82,"slug":239,"name":240,"path":241,"parent_code":44},{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},{"status":46,"locked":14,"version":47,"method":48,"evidence":459},{"candidates":460,"agricultural_evidence":53},[461,465,469,473,477,484,490,496],{"code":82,"score":17,"supported":53,"title":462,"abstract":463,"tags":464},[305],[30,305],[29,30],{"code":451,"score":52,"supported":53,"title":466,"abstract":467,"tags":468},[452],[449,452],[449],{"code":40,"score":52,"supported":53,"title":470,"abstract":471,"tags":472},[357],[356,357],[28],{"code":378,"score":75,"supported":53,"title":474,"abstract":475,"tags":476},[],[381,382],[],{"code":478,"score":75,"supported":53,"title":479,"abstract":480,"tags":483},"H3",[],[481,482],"蒸散发","evapotranspiration",[],{"code":399,"score":75,"supported":53,"title":485,"abstract":486,"tags":489},[],[487,488],"气候变化","climate change",[],{"code":491,"score":393,"supported":53,"title":492,"abstract":493,"tags":495},"J1",[],[494],"农业规划",[],{"code":66,"score":22,"supported":14,"title":497,"abstract":498,"tags":499},[],[],[27],[501,502],"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":504,"openalex_id":506,"authors":507,"venue":281,"cited_by_count":117,"oa_url":436,"card":510,"direction":122,"ingested_from":124},"W7220391503",[508],{"name":509,"orcid":9},"Battula Vijaya Saradhi Halarou Saidou Souley",{"tldr":511,"method":512,"finding":513,"direction":122,"opportunity":514},"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":517,"title":518,"url":519,"summary":520,"summary_zh":521,"content":9,"source_name":281,"source_url":519,"published_at":282,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":522,"score_detail":523,"sources":525,"tags":527,"primary_topic":530,"secondary_topics":531,"classification":532,"search_phrases":558,"slug":561,"view_count":117,"doi":562,"paper":563,"created_at":573},5588,"Certified Temporal Fusion of Artificial Intelligence Climate Analytics for Crop Failure Early Warning Under Sparse Agricultural Sensors: Error Bounds and Famine Relief Targeting","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23545489","Sparse agricultural sensor networks across sub-Saharan Africa leave crop-failure early-warning systems with too little ground observation to support reliable famine relief targeting. The framework treats sensor sparsity as a missing-data problem with a known observation operator and propagates climate-analytics uncertainty through a temporal Kalman-Buys filter whose gain is constrained by a certified risk envelope. Using NASA POWER monthly reanalysis for Accra, Ghana (2000-2023, 312 observations), the analysis establishes a mean temperature of 26.521 C and a warming trend of 0.1622 C per decade, which calibrates the climate-analytics prior. The derived bounds show that relief-targeting error scales with the square root of sensor density and with the Lipschitz constant of the crop-response function, yielding an explicit sensor-placement rule for a target misclassification rate. The contribution is a certified, assumption-explicit bridge between climate analytics and famine relief targeting that states the conditions under which early warning is trustworthy.","撒哈拉以南非洲稀疏的农业传感器网络使得作物歉收预警系统缺乏足够的地面观测数据，难以支撑可靠的饥荒救援目标定位。该框架将传感器稀疏性视为具有已知观测算子的缺失数据问题，并通过时间Kalman-Buys滤波器传播气候分析不确定性，该滤波器的增益受经认证的风险包络约束。利用NASA POWER对加纳阿克拉的月度再分析数据（2000—2023年，312个观测值），分析确定了平均气温为26.521°C、每十年0.1622°C的增暖趋势，据此校准了气候分析先验。推导出的界限表明，救援目标定位误差随传感器密度的平方根以及作物响应函数的Lipschitz常数缩放，从而为目标误分类率给出了明确的传感器布设规则。该研究的贡献在于构建了一个经认证的、假设明确的气候分析与饥荒救援目标定位之间的桥梁，阐明了早期预警可信赖的条件。",74,{"impact":138,"substance":18,"depth":19,"authority":138,"freshness":13,"relevant":22,"comment":524},"该研究提出一种带误差界认证的时序融合方法，用于稀疏传感器条件下的作物歉收预警与饥荒救援瞄准，方法新颖、结论明确，但案例局限于加纳阿克拉，产业影响有限，适合作为技术前沿条目收录。",[526],{"name":281,"url":519},[27,28,528,30,529],"粮食安全","气候分析",{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},[],{"status":46,"locked":14,"version":47,"method":48,"evidence":533},{"candidates":534,"agricultural_evidence":53},[535,540,545,550,554],{"code":40,"score":21,"supported":53,"title":536,"abstract":538,"tags":539},[537],"artificial intelligence",[],[28],{"code":385,"score":393,"supported":53,"title":541,"abstract":542,"tags":544},[],[543],"农业传感",[],{"code":546,"score":22,"supported":14,"title":547,"abstract":548,"tags":549},"A8",[],[],[528],{"code":66,"score":22,"supported":14,"title":551,"abstract":552,"tags":553},[],[],[27],{"code":82,"score":22,"supported":14,"title":555,"abstract":556,"tags":557},[],[],[30],[559,560],"NASA POWER 加纳 气候分析","作物歉收 早期预警 传感器","NASAPOWER加纳气候分析-5588","10.5281\u002Fzenodo.23545489",{"doi":562,"openalex_id":564,"authors":565,"venue":281,"cited_by_count":117,"oa_url":519,"card":568,"direction":429,"ingested_from":124},"W7223111766",[566],{"name":567,"orcid":9},"Fatima-Zahra El Khattabi",{"tldr":569,"method":570,"finding":571,"direction":122,"opportunity":572},"提出带误差界的时间融合框架，在稀疏传感器下用气候分析预警作物歉收。","卡尔曼-布西滤波+NASA POWER再分析数据，风险包络约束增益。","救济瞄准误差随传感器密度平方根和作物响应Lipschitz常数缩放，给出布点规则。","可将该认证误差界框架扩展到多作物多区域，结合卫星遥感弥补地面传感器稀疏。","2026-10-22T11:21:02.682497Z"]