[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-1303":3,"related-1303":115},{"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":23,"tags":25,"primary_topic":31,"secondary_topics":37,"classification":38,"search_phrases":60,"slug":63,"view_count":64,"doi":65,"paper":66,"created_at":114},1303,"PhenoStream: A Cyberinfrastructure for Automated and AI-Based Crop Trait Extraction from Aerial Imagery","https:\u002F\u002Fdoi.org\u002F10.64898\u002F2026.08.26.747008","The integration of digital technologies for high-throughput field phenotyping is critical for accelerating crop improvement in agriculture. However, extracting traits from remote sensing data remains constrained by fragmented workflows, manual intervention, and limited interoperability among existing tools, resulting in delays that hinder timely biological insight and decision-making. To address these challenges, we present PhenoStream (Phenotyping Streaming), a scalable, end-to-end cyberinfrastructure designed to automate the full lifecycle of aerial imagery-based phenotyping, from data acquisition to plot- and genotype-level inference. The framework integrates automated data ingestion from distributed field sites, geospatial processing, and AI-enabled trait extraction within a unified, user-accessible graphical interface. Its modular and extensible architecture supports adaptable trait modeling and seamless integration of new data sources, enabling deployment across diverse crops, environments, and experimental designs. We demonstrate the system across a large multi-location field trial network of bioenergy crops, where it enables high-throughput characterization of spatiotemporal growth dynamics, genotype-by-environment (GxE) interactions, and predictive modeling of key agronomic traits. By significantly reducing processing latency and manual effort, the platform facilitates near-real-time analysis and reproducible workflows. This work establishes a generalizable and scalable pathway for operationalizing very-high-spatial resolution aerial phenotyping in agricultural research. By bridging data acquisition and analytics, the end-to-end cyberinfrastructure provides a foundation for integrating heterogeneous and unstructured data streams--including remote sensing, environmental, and management data--toward data-driven decision making in agriculture.","将数字技术整合用于高通量田间表型分析，对于加速农业作物改良至关重要。然而，从遥感数据中提取性状仍受制于碎片化的工作流程、人工干预以及现有工具间有限的互操作性，导致处理延迟，阻碍了及时的生物学洞察与决策制定。为应对这些挑战，我们提出了PhenoStream（表型流），一种可扩展的端到端网络基础设施，旨在自动化基于航空影像的表型分析全生命周期，从数据采集到小区及基因型水平推断。该框架在统一且用户友好的图形界面中集成了来自分布式田间站点的自动化数据摄取、地理空间处理及人工智能驱动的性状提取。其模块化和可扩展架构支持适应性性状建模及新数据源的无缝整合，使其能够部署于多种作物、环境及实验设计之中。我们在一个大型多地点生物能源作物田间试验网络中展示了该系统，实现了时空生长动态的高通量表征、基因型-环境（GxE）互作分析以及关键农艺性状的预测建模。通过显著降低处理延迟和人工投入，该平台支持近实时分析和可重复的工作流程。本研究为农业研究中超高空间分辨率航空表型分析的操作化提供了一条通用且可扩展的路径。通过连接数据采集与分析，该端到端网络基础设施为整合异构和非结构化数据流——包括遥感、环境及管理数据——奠定了面向农业数据驱动决策的基础。",null,"bioRxiv (Cold Spring Harbor Laboratory)","2026-08-30T00:00:00Z","论文",10,false,82,{"impact":17,"substance":17,"depth":18,"authority":19,"freshness":20,"relevant":21,"comment":22},22,18,12,8,1,"提出端到端自动化表型提取平台，显著提升效率，具推广价值。",[24],{"name":10,"url":6},[26,27,28,29,30],"智慧农业","农业人工智能","遥感","作物表型","田间表型",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",[],{"status":39,"locked":14,"version":40,"method":41,"evidence":42},"classified","2026-10-22.2","rules",{"candidates":43,"agricultural_evidence":45},[44,50,55],{"code":32,"score":20,"supported":45,"title":46,"abstract":47,"tags":49},true,[],[28,48],"remote sensing",[29,28],{"code":51,"score":21,"supported":14,"title":52,"abstract":53,"tags":54},"I1",[],[],[26],{"code":56,"score":21,"supported":14,"title":57,"abstract":58,"tags":59},"I2",[],[],[27],[61,62],"农业人工智能 作物表型 智慧农业 田间表型","农业人工智能 作物表型","农业人工智能作物表型智慧农业田间表型-1303",2,"10.64898\u002F2026.08.26.747008",{"doi":65,"openalex_id":67,"authors":68,"venue":10,"cited_by_count":104,"oa_url":105,"card":106,"direction":112,"ingested_from":113},"W7204800500",[69,72,74,77,79,81,83,85,88,90,93,95,97,99,101],{"name":70,"orcid":71},"Sebastián Varela","https:\u002F\u002Forcid.org\u002F0000-0001-8064-3636",{"name":73,"orcid":9},"Jeremy Ruhter",{"name":75,"orcid":76},"Erik J. Sacks","https:\u002F\u002Forcid.org\u002F0000-0001-7537-4558",{"name":78,"orcid":9},"Xuying Zheng",{"name":80,"orcid":9},"Dylan Allen",{"name":82,"orcid":9},"Anna Hale",{"name":84,"orcid":9},"Cory Landry",{"name":86,"orcid":87},"Xianyan Kuang","https:\u002F\u002Forcid.org\u002F0000-0002-5978-647X",{"name":89,"orcid":9},"B. J. Long",{"name":91,"orcid":92},"Yan Zhu","https:\u002F\u002Forcid.org\u002F0000-0002-5804-8926",{"name":94,"orcid":9},"Shatabdi Proma",{"name":96,"orcid":9},"Sehijpreet Kaur",{"name":98,"orcid":9},"Diego Jarquin",{"name":100,"orcid":9},"Jesse Morrison",{"name":102,"orcid":103},"Andrew D. B. Leakey","https:\u002F\u002Forcid.org\u002F0000-0001-6251-024X",0,"https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2026\u002F08\u002F30\u002F2026.08.26.747008.full.pdf",{"tldr":107,"method":108,"finding":109,"direction":110,"opportunity":111},"提出 PhenoStream 网络基础设施，自动化航空影像作物性状提取全流程。","集成数据采集、地理空间处理与 AI 性状提取的模块化架构。","在多地点生物能源作物试验中实现高通量表型分析，显著降低延迟。","农业人工智能与决策模型","可扩展至多源数据融合与实时决策，探索跨作物通用性状模型及边缘计算部署。","智慧农业 \u002F 农业物联网","openalex","2026-09-01T23:30:11.619805Z",{"total":116,"page":21,"page_size":116,"items":117},6,[118,196,258,310,379,458],{"id":119,"title":120,"url":121,"summary":122,"summary_zh":123,"content":9,"source_name":124,"source_url":121,"published_at":125,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":126,"score_detail":127,"sources":131,"tags":133,"primary_topic":135,"secondary_topics":140,"classification":146,"search_phrases":173,"slug":176,"view_count":64,"doi":177,"paper":178,"created_at":195},3164,"Spatiotemporal Deep Learning for Rice Plant Height Estimation from Multi-Temporal UAV RGB Imagery","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fagriculture16182034","Accurate plant height estimation is important for monitoring crop growth and supporting precision agricultural management. Manual measurements are labor-intensive, while LiDAR-based methods are expensive and require complex processing. UAV photogrammetry provides a lower-cost alternative but remains challenging in flooded rice paddies because of canopy deformation and difficulties in terrain extraction. This study proposes Rice-STNet, a spatiotemporal deep learning framework for end-to-end rice plant height estimation using multi-temporal UAV RGB imagery. Rice-STNet integrates a convolutional neural network for spatial feature extraction, Time2Vec for temporal encoding, and a gated recurrent unit network for modeling temporal dependencies across observation dates. The framework was evaluated using field data collected from rice paddies over two growing seasons. Rice-STNet achieved an R2 of 0.97, a root mean squared error of 1.97 cm, and a mean absolute error of 1.14 cm. It outperformed random forest, support vector regression, a CNN-only baseline, and a UAV photogrammetry-based point-cloud approach. In addition, the framework generated high-resolution plant height maps for field-scale analysis of spatial growth variability. These results underscore the importance of jointly modeling spatial and temporal characteristics for continuously evolving crop traits. The proposed framework offers an accurate, scalable, and non-destructive solution for large-scale crop phenotyping and precision agriculture.","准确的株高估算对于监测作物生长和支持精准农业管理具有重要意义。人工测量劳动强度大，而基于激光雷达（LiDAR）的方法成本高昂且需要复杂的处理。无人机摄影测量提供了一种成本较低的替代方案，但在淹水稻田中仍面临挑战，原因在于冠层变形和地形提取困难。本研究提出了Rice-STNet，一种时空深度学习框架，用于利用多时相无人机RGB影像进行端到端水稻株高估算。Rice-STNet集成了用于空间特征提取的卷积神经网络、用于时间编码的Time2Vec，以及用于建模观测日期之间时间依赖关系的门控循环单元网络。该框架利用两个生长季从稻田采集的田间数据进行了评估。Rice-STNet取得了R²为0.97、均方根误差为1.97 cm、平均绝对误差为1.14 cm的结果。其性能优于随机森林、支持向量回归、仅使用CNN的基线方法以及基于无人机摄影测量的点云方法。此外，该框架生成了高分辨率株高图，用于田块尺度空间生长变异性分析。这些结果凸显了联合建模空间与时间特征对于持续变化的作物性状的重要性。所提出的框架为大规模作物表型分析和精准农业提供了一种准确、可扩展且非破坏性的解决方案。","Agriculture","2026-09-21T00:00:00Z",80,{"impact":18,"substance":17,"depth":18,"authority":128,"freshness":129,"relevant":21,"comment":130},13,9,"提出时空深度学习框架Rice-STNet，用多时相无人机RGB影像实现水稻株高高精度估算，方法新颖、数据跨两个生长季，对作物表型与精准农业有实用价值。",[132],{"name":124,"url":121},[26,27,134,28,29],"水稻",{"code":136,"slug":137,"name":134,"path":138,"parent_code":139},"A1","rice","\u002Ftopic\u002Ffield-crops\u002Frice","A",[141,145],{"code":56,"slug":142,"name":143,"path":144,"parent_code":36},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":39,"locked":14,"version":40,"method":41,"evidence":147},{"candidates":148,"agricultural_evidence":45},[149,154,161,166],{"code":136,"score":18,"supported":45,"title":150,"abstract":151,"tags":153},[137],[134,152,137],"稻田",[134],{"code":56,"score":155,"supported":45,"title":156,"abstract":158,"tags":160},15,[157],"deep learning",[159,157],"深度学习",[27],{"code":32,"score":20,"supported":45,"title":162,"abstract":163,"tags":165},[],[29,164],"crop phenotyping",[29,28],{"code":51,"score":167,"supported":45,"title":168,"abstract":169,"tags":172},7,[],[170,171],"精准农业","precision agriculture",[26],[174,175],"无人机 RGB 水稻株高","Rice-STNet 水稻表型","无人机RGB水稻株高-3164","10.3390\u002Fagriculture16182034",{"doi":177,"openalex_id":179,"authors":180,"venue":124,"cited_by_count":104,"oa_url":121,"card":189,"direction":193,"ingested_from":113},"W7213887432",[181,184,186],{"name":182,"orcid":183},"Weiguo Wang","https:\u002F\u002Forcid.org\u002F0009-0003-4028-9363",{"name":185,"orcid":9},"Noboru Noguchi",{"name":187,"orcid":188},"Liangliang Yang","https:\u002F\u002Forcid.org\u002F0000-0002-5055-3987",{"tldr":190,"method":191,"finding":192,"direction":193,"opportunity":194},"提出Rice-STNet时空深度学习框架，用多时相无人机RGB影像估算水稻株高。","CNN提取空间特征，Time2Vec编码时间，GRU建模时序依赖，两季稻田数据验","R²达0.97、RMSE 1.97cm，优于随机森林、SVR、纯CNN及点云方法。","农业遥感与作物表型","可迁移至其他作物与多源遥感融合，探索轻量化模型及实时田间部署。","2026-09-22T23:30:18.545958Z",{"id":197,"title":198,"url":199,"summary":200,"summary_zh":201,"content":9,"source_name":202,"source_url":203,"published_at":204,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":205,"score_detail":206,"sources":211,"tags":213,"primary_topic":215,"secondary_topics":216,"classification":217,"search_phrases":232,"slug":235,"view_count":236,"doi":237,"paper":238,"created_at":257},2781,"Evaluating Mesh Reconstruction Methods for Crop Phenotyping","https:\u002F\u002Fdoi.org\u002F10.48550\u002Farxiv.2609.16926","Phenotyping an agricultural crop is crucial for studying its entire life cycle, as it provides vital insights to improve yield and, ultimately, food production. Doing the same for crops grown on remote sites is a challenge for the specialists who cannot be available on-site. 3D reconstruction techniques offer a promising solution to this problem by enabling crop digitization, allowing specialists to access the resulting 3D crop models from anywhere at any time. In this work, we evaluate recent 3D reconstruction pipelines for crop phenotyping. We focus on 7 mesh reconstruction pipelines and measure the fidelity and consistency of their outputs qualitatively and quantitatively. Our results suggest that the meshes produced by the GGGS, PGSR, and 2DGS are preferable to the other pipelines, owing to their quantitative metrics and visually pleasing outputs. The GGGS pipeline is better than the second-best pipeline (2DGS) by about 27\\% on the radar chart with 5 dimensions, namely, User ratings, Chamfer distance, LPIPS, PSNR, and SSIM.","对农作物进行表型分析对于研究其整个生命周期至关重要，因为它为提高产量并最终提升粮食生产提供了关键见解。对于生长在偏远地区的作物而言，由于专家无法亲临现场，开展同样的表型分析是一项挑战。三维重建技术通过实现作物数字化，使专家能够随时随地访问生成的作物三维模型，从而为这一问题提供了有前景的解决方案。在本研究中，我们评估了近期用于作物表型分析的三维重建流程。我们聚焦于7种网格重建流程，并对其输出的保真度和一致性进行了定性和定量评估。结果表明，GGGS、PGSR和2DGS生成的网格在定量指标和视觉输出方面优于其他流程。在包含5个维度（用户评分、倒角距离、LPIPS、PSNR和SSIM）的雷达图上，GGGS流程比排名第二的2DGS流程高出约27%。","arXiv (Cornell University)","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.16926","2026-09-15T00:00:00Z",74,{"impact":207,"substance":208,"depth":209,"authority":128,"freshness":20,"relevant":21,"comment":210},16,20,17,"系统评测7种网格重建流程用于作物表型数字化，结论明确、指标可量化，对远程作物表型与三维数字化研究有实质参考价值。",[212],{"name":202,"url":203},[26,27,28,29,214],"三维重建",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":14,"version":40,"method":41,"evidence":218},{"candidates":219,"agricultural_evidence":45},[220,224,228],{"code":32,"score":207,"supported":45,"title":221,"abstract":222,"tags":223},[164],[29,164],[29,28],{"code":56,"score":64,"supported":14,"title":225,"abstract":226,"tags":227},[],[],[214,27],{"code":51,"score":21,"supported":14,"title":229,"abstract":230,"tags":231},[],[],[26],[233,234],"农业人工智能 三维重建 作物表型 智慧农业","农业人工智能 三维重建","农业人工智能三维重建作物表型智慧农业-2781",4,"10.48550\u002Farxiv.2609.16926",{"doi":237,"openalex_id":239,"authors":240,"venue":202,"cited_by_count":104,"oa_url":251,"card":252,"direction":193,"ingested_from":113},"W7213397688",[241,244,246,249],{"name":242,"orcid":243},"Karanvir Singh","https:\u002F\u002Forcid.org\u002F0009-0003-0484-119X",{"name":245,"orcid":9},"Theo Morales",{"name":247,"orcid":248},"Binh‐Son Hua","https:\u002F\u002Forcid.org\u002F0000-0002-5706-8634",{"name":250,"orcid":9},"Mukesh Saini","https:\u002F\u002Farxiv.org\u002Fpdf\u002F2609.16926",{"tldr":253,"method":254,"finding":255,"direction":193,"opportunity":256},"评估7种网格重建流程在作物表型三维数字化中的保真度与一致性。","对比7种3D重建流程，用Chamfer距离、LPIPS、PSNR、SSIM及用户","GGGS、PGSR和2DGS输出更优，GGGS在五维雷达图上比2DGS高约27%。","可探索轻量化、田间实时三维重建，并建立作物表型专用网格质量评价标准。","2026-09-17T23:30:27.096274Z",{"id":259,"title":260,"url":261,"summary":262,"summary_zh":263,"content":9,"source_name":264,"source_url":261,"published_at":265,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":266,"score_detail":267,"sources":269,"tags":271,"primary_topic":274,"secondary_topics":275,"classification":277,"search_phrases":294,"slug":297,"view_count":104,"doi":298,"paper":299,"created_at":309},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":20,"substance":208,"depth":209,"authority":19,"freshness":13,"relevant":21,"comment":268},"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。",[270],{"name":264,"url":261},[26,27,272,28,273],"产量预测","可解释性",{"code":56,"slug":142,"name":143,"path":144,"parent_code":36},[276],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":39,"locked":14,"version":40,"method":41,"evidence":278},{"candidates":279,"agricultural_evidence":45},[280,286,290],{"code":56,"score":19,"supported":45,"title":281,"abstract":283,"tags":285},[282],"computer vision",[284],"计算机视觉",[27],{"code":32,"score":20,"supported":45,"title":287,"abstract":288,"tags":289},[],[28,48],[272,28],{"code":51,"score":21,"supported":14,"title":291,"abstract":292,"tags":293},[],[],[26],[295,296],"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":298,"openalex_id":300,"authors":301,"venue":264,"cited_by_count":104,"oa_url":261,"card":304,"direction":193,"ingested_from":113},"W7223114002",[302],{"name":303,"orcid":9},"Kadiatou Barry",{"tldr":305,"method":306,"finding":307,"direction":193,"opportunity":308},"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":311,"title":312,"url":313,"summary":314,"summary_zh":315,"content":9,"source_name":316,"source_url":313,"published_at":317,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":318,"score_detail":319,"sources":321,"tags":323,"primary_topic":324,"secondary_topics":325,"classification":327,"search_phrases":360,"slug":363,"view_count":104,"doi":364,"paper":365,"created_at":378},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":17,"depth":18,"authority":19,"freshness":20,"relevant":21,"comment":320},"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。",[322],{"name":316,"url":313},[26,27,134,272,28],{"code":136,"slug":137,"name":134,"path":138,"parent_code":139},[326],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":39,"locked":14,"version":40,"method":41,"evidence":328},{"candidates":329,"agricultural_evidence":45},[330,334,338,345,352,356],{"code":136,"score":155,"supported":45,"title":331,"abstract":332,"tags":333},[137],[134,137],[134],{"code":32,"score":20,"supported":45,"title":335,"abstract":336,"tags":337},[],[28,48],[272,28],{"code":339,"score":116,"supported":45,"title":340,"abstract":341,"tags":344},"A8",[],[342,343],"粮食安全","food security",[],{"code":346,"score":347,"supported":45,"title":348,"abstract":349,"tags":351},"J1",3,[],[350],"农业规划",[],{"code":51,"score":21,"supported":14,"title":353,"abstract":354,"tags":355},[],[],[26],{"code":56,"score":21,"supported":14,"title":357,"abstract":358,"tags":359},[],[],[27],[361,362],"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":364,"openalex_id":366,"authors":367,"venue":316,"cited_by_count":104,"oa_url":313,"card":373,"direction":193,"ingested_from":113},"W7222942064",[368,370],{"name":369,"orcid":9},"Nayana Venkatesh",{"name":371,"orcid":372},"Evangelin Geetha Devaraj","https:\u002F\u002Forcid.org\u002F0000-0002-7253-4314",{"tldr":374,"method":375,"finding":376,"direction":193,"opportunity":377},"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":380,"title":381,"url":382,"summary":383,"summary_zh":384,"content":9,"source_name":385,"source_url":382,"published_at":386,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":387,"score_detail":388,"sources":391,"tags":393,"primary_topic":396,"secondary_topics":397,"classification":405,"search_phrases":432,"slug":435,"view_count":104,"doi":436,"paper":437,"created_at":457},5006,"Mapping Soil Salinity in Arid Agricultural Regions Using Multi-Source Remote Sensing and a Long-Range Dependency-Enhanced Deep Learning Framework","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fland15101966","Soil salinity estimation across arid agricultural regions is challenging due to pronounced environmental heterogeneity and complex dependencies among multi-source variables. This study proposes a Long-Range Dependency-Enhanced Network (LRD-Net) for regional-scale soil salinity estimation in multiple agricultural oasis regions using multi-source remote sensing and environmental covariates. A dataset comprising 180 field samples from three agricultural oasis regions in Xinjiang, China, was constructed with 25 covariates derived from spectral, topographic, climatic, and soil property data. LRD-Net consists of three stages: a multi-scale feature fusion backbone based on depthwise separable convolutions and cross-scale interaction; a Long-Range Dependency Enhancement Module (LDEM) with an asymmetric dual-branch architecture that captures forward and reverse-aware dependencies through reverse alignment and cross-directional fusion; and multi-scale attention refinement with a regression head for continuous salinity estimation. Under the region-stratified random-split evaluation, LRD-Net achieved an R2 of 0.905, an RMSE of 1.207 g·kg−1, and an MAE of 0.868 g·kg−1. Performance decreased under more spatially independent validation, with an R2 of 0.874 under spatial cross-validation and LORO test R2 values ranging from 0.739 to 0.801, indicating that prediction across spatially and geographically independent samples is more challenging than region-stratified random-split evaluation. The proposed framework effectively integrates multi-source information and captures complementary long-range dependencies, providing a potential approach for regional-scale soil salinity estimation within the studied arid agricultural oasis environments and supporting soil salinization monitoring and sustainable land management in the study region.","干旱农业区域土壤盐分估算面临显著的环境异质性和多源变量间复杂依赖关系的挑战。本研究提出了一种长程依赖增强网络（LRD-Net），利用多源遥感与环境协变量对多个农业绿洲区域进行区域尺度土壤盐分估算。研究构建了包含中国新疆三个农业绿洲区域180个野外样本的数据集，并衍生出25个协变量，涵盖光谱、地形、气候和土壤属性数据。LRD-Net由三个阶段组成：基于深度可分离卷积和跨尺度交互的多尺度特征融合骨干网络；具有非对称双分支架构的长程依赖增强模块（LDEM），通过反向对齐和跨方向融合捕获前向与反向感知依赖关系；以及多尺度注意力细化与回归头，用于连续盐分估算。在区域分层随机划分评估下，LRD-Net取得了R²为0.905、RMSE为1.207 g·kg⁻¹、MAE为0.868 g·kg⁻¹的性能。在空间独立性更强的验证下性能有所下降，空间交叉验证R²为0.874，留一区域测试R²范围为0.739至0.801，表明跨空间和地理独立样本的预测比区域分层随机划分评估更具挑战性。所提出的框架有效整合了多源信息并捕获了互补的长程依赖关系，为研究区干旱农业绿洲环境下的区域尺度土壤盐分估算提供了潜在方法，并支持研究区土壤盐渍化监测与可持续土地管理。","Land","2026-10-14T00:00:00Z",72,{"impact":19,"substance":389,"depth":209,"authority":128,"freshness":129,"relevant":21,"comment":390},21,"方法新颖、数据扎实的遥感土壤盐渍化估算研究，对干旱区盐碱地监测与治理有参考价值，但属细分领域学术进展，公共影响有限。",[392],{"name":385,"url":382},[26,27,28,394,395],"土壤盐渍化","新疆农业",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[398,404],{"code":399,"slug":400,"name":401,"path":402,"parent_code":403},"H2","soil","土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",{"code":56,"slug":142,"name":143,"path":144,"parent_code":36},{"status":39,"locked":14,"version":40,"method":41,"evidence":406},{"candidates":407,"agricultural_evidence":45},[408,412,418,422,428],{"code":32,"score":155,"supported":45,"title":409,"abstract":410,"tags":411},[48],[28,48],[28],{"code":399,"score":413,"supported":45,"title":414,"abstract":415,"tags":417},14,[400],[416,400],"土壤",[],{"code":56,"score":129,"supported":45,"title":419,"abstract":420,"tags":421},[157],[],[27],{"code":423,"score":347,"supported":45,"title":424,"abstract":425,"tags":427},"H7",[],[426],"干旱",[],{"code":51,"score":21,"supported":14,"title":429,"abstract":430,"tags":431},[],[],[26],[433,434],"新疆 农业绿洲 土壤盐渍化 遥感","LRD-Net 土壤盐分 估算","新疆农业绿洲土壤盐渍化遥感-5006","10.3390\u002Fland15101966",{"doi":436,"openalex_id":438,"authors":439,"venue":385,"cited_by_count":104,"oa_url":382,"card":452,"direction":193,"ingested_from":113},"W7221816183",[440,442,445,447,449],{"name":441,"orcid":9},"Mingjie Qian",{"name":443,"orcid":444},"Liangjun Wang","https:\u002F\u002Forcid.org\u002F0009-0006-8718-8326",{"name":446,"orcid":9},"Peng Wang",{"name":448,"orcid":9},"Hangyuan Liu",{"name":450,"orcid":451},"Weitao Chen","https:\u002F\u002Forcid.org\u002F0000-0002-6272-1618",{"tldr":453,"method":454,"finding":455,"direction":193,"opportunity":456},"提出LRD-Net深度学习框架，融合多源遥感与环境协变量，估算新疆干旱绿洲区土壤盐分。","构建180个样点、25个协变量的数据集，设计含长程依赖增强模块的多尺度网络。","区域分层随机划分下R²达0.905，但空间独立验证R²降至0.739-0.874，跨区域预测更难。","可探索跨区域迁移学习与不确定性量化，提升空间独立场景下盐分制图泛化能力。","2026-10-15T23:30:29.667342Z",{"id":459,"title":460,"url":461,"summary":462,"summary_zh":463,"content":9,"source_name":464,"source_url":461,"published_at":386,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":465,"score_detail":466,"sources":468,"tags":470,"primary_topic":472,"secondary_topics":473,"classification":481,"search_phrases":531,"slug":534,"view_count":21,"doi":535,"paper":536,"created_at":557},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",81,{"impact":18,"substance":17,"depth":18,"authority":413,"freshness":129,"relevant":21,"comment":467},"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。",[469],{"name":464,"url":461},[26,27,272,471,28],"多模态融合",{"code":56,"slug":142,"name":143,"path":144,"parent_code":36},[474,480],{"code":475,"slug":476,"name":477,"path":478,"parent_code":479},"B2","fruit","果树","\u002Ftopic\u002Fhorticulture\u002Ffruit","B",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":39,"locked":14,"version":40,"method":41,"evidence":482},{"candidates":483,"agricultural_evidence":45},[484,491,499,505,509,513,520,526],{"code":56,"score":485,"supported":45,"title":486,"abstract":487,"tags":490},11,[],[159,488,489,157],"机器学习","machine learning",[27,471],{"code":475,"score":129,"supported":45,"title":492,"abstract":493,"tags":498},[],[494,495,496,497],"苹果","芒果","orchard","apple",[],{"code":32,"score":20,"supported":45,"title":500,"abstract":501,"tags":504},[],[502,503],"无人机多光谱","multispectral",[272,28],{"code":51,"score":167,"supported":45,"title":506,"abstract":507,"tags":508},[],[170,171],[26],{"code":399,"score":116,"supported":45,"title":510,"abstract":511,"tags":512},[],[416,400],[],{"code":514,"score":116,"supported":45,"title":515,"abstract":516,"tags":519},"I5",[],[517,518],"物联网","IoT",[],{"code":521,"score":347,"supported":45,"title":522,"abstract":523,"tags":525},"H6",[],[524],"农业生态",[],{"code":423,"score":347,"supported":45,"title":527,"abstract":528,"tags":530},[],[529],"气候适应",[],[532,533],"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":535,"openalex_id":537,"authors":538,"venue":464,"cited_by_count":104,"oa_url":461,"card":552,"direction":112,"ingested_from":113},"W7221795850",[539,542,544,546,548,550],{"name":540,"orcid":541},"Shabir Ahmad Mir","https:\u002F\u002Forcid.org\u002F0000-0003-2311-218X",{"name":543,"orcid":9},"Umarfarooque Momin",{"name":545,"orcid":9},"Sudeep Kumar E",{"name":547,"orcid":9},"Itfaq Ahmad Mir",{"name":549,"orcid":9},"Ab Rouf Khan",{"name":551,"orcid":9},"Ghulam Mohammad Mir",{"tldr":553,"method":554,"finding":555,"direction":110,"opportunity":556},"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。","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"]