[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-5157":3,"related-5157":101},{"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":9,"secondary_topics":32,"classification":33,"search_phrases":77,"slug":80,"view_count":81,"doi":82,"paper":83,"created_at":100},5157,"Digital twin forestry as an informatics framework integrating remote sensing ecosystem modelling and data assimilation","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs44564-026-00029-8","Forests are essential to the Earth system, regulating carbon, water, and biodiversity cycles while underpinning ecosystem resilience. Yet they face mounting pressures from climate and land-use change, requiring integrative informatics approaches that link high-resolution observations with advanced ecosystem models. This systematic review defines Digital Twin Forestry (DTF) as an emerging paradigm that continuously couples multisensor Earth Observation data with ecosystem models through data assimilation, enabling dynamic, uncertainty-aware forecasting and adaptive decision support. Following PRISMA 2020 guidelines, we synthesized 57 peer-reviewed studies published between 2016 and 2025 that combined EO datasets with ecosystem modeling and assimilation frameworks. Demonstrated advances include CubeSat constellations, spaceborne LiDAR, UAV hyperspectral systems, and hybrid machine-learning surrogates. Data assimilation methods such as Ensemble Kalman Filters and Particle Filters serve as computational bridges between multi-temporal observations and dynamic model states. Results reveal uneven biome representation, with tropical and boreal forests underrepresented compared to temperate zones, underscoring equity concerns in biodiversity-rich regions. While most forestry digital twins remain at prototype or early operational stages, continuous coupling of sensing platforms to models demonstrates the potential for near-real-time forecasting that extends beyond static inventories. Future priorities include physics-informed machine learning, FAIR-compliant cloud-native workflows, and expanded monitoring in underrepresented ecosystems. Embedding biodiversity and resilience monitoring into near-real-time, uncertainty-aware workflows will be critical, enabling DTF to evolve into operational systems that provide adaptive, policy-relevant decision support for climate-resilient forest management. This review offers an integrative roadmap for advancing DTF, contributing to global sustainability and supporting the United Nations Sustainable Development Goals, including Climate Action (SDG 13) and Life on Land (SDG 15).","森林对地球系统至关重要，调节着碳、水和生物多样性循环，同时支撑着生态系统韧性。然而，森林面临气候和土地利用变化日益增大的压力，需要将高分辨率观测与先进生态系统模型相联系的综合性信息学方法。本系统综述将数字孪生林业（Digital Twin Forestry, DTF）定义为一个新兴范式，即通过数据同化将多传感器地球观测数据与生态系统模型持续耦合，从而实现动态的、具有不确定性感知的预测和适应性决策支持。遵循PRISMA 2020指南，我们综合了2016年至2025年间发表的57项同行评审研究，这些研究将地球观测数据集与生态系统建模和数据同化框架相结合。已展示的进展包括立方星（CubeSat）星座、星载激光雷达、无人机高光谱系统和混合机器学习代理模型。集合卡尔曼滤波和粒子滤波等数据同化方法充当多时相观测与动态模型状态之间的计算桥梁。结果显示生物群系代表性不均衡，热带和寒带森林相对于温带地区代表性不足，凸显了生物多样性丰富地区的公平性问题。尽管大多数林业数字孪生仍处于原型或早期运行阶段，但传感平台与模型的持续耦合展示了超越静态资源清查的近实时预测潜力。未来优先方向包括物理信息机器学习、符合FAIR原则的云原生工作流程，以及扩大代表性不足生态系统的监测。将生物多样性和韧性监测嵌入近实时、不确定性感知的工作流程将至关重要，使DTF能够发展为可操作的系统，为气候韧性森林管理提供适应性、政策相关的决策支持。本综述为推进DTF提供了综合性路线图，助力全球可持续发展并支持联合国可持续发展目标，包括气候行动（SDG 13）和陆地生物（SDG 15）。",null,"Discover Informatics","2026-10-15T00:00:00Z","论文",10,false,79,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},18,22,19,12,8,1,"系统综述提出数字孪生林业框架，方法新颖、结论有据，对农业信息化中的遥感与生态建模有参考价值，但属学术综述而非产业级事件。",[25],{"name":10,"url":6},[27,28,29,30,31],"数字孪生","遥感","森林监测","数据同化","生态系统建模",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":37},"needs_review","2026-10-22.2","rules",{"candidates":38,"agricultural_evidence":14,"reason":76},[39,47,54,63,71],{"code":40,"score":41,"supported":42,"title":43,"abstract":45,"tags":46},"I1",15,true,[44],"digital twin",[27,44],[27],{"code":48,"score":20,"supported":42,"title":49,"abstract":51,"tags":53},"I3",[50],"remote sensing",[52],"hyperspectral",[28],{"code":55,"score":56,"supported":42,"title":57,"abstract":58,"tags":62},"I2",9,[],[59,60,61],"机器学习","machine learning","decision support",[],{"code":64,"score":65,"supported":42,"title":66,"abstract":67,"tags":70},"H6",6,[],[68,69],"生物多样性","biodiversity",[],{"code":72,"score":22,"supported":14,"title":73,"abstract":74,"tags":75},"I5",[],[],[30],"农业相关性需要复核",[78,79],"遥感 数据同化 森林","生态系统建模 数字孪生 数据同化 森林监测","遥感数据同化森林-5157",0,"10.1007\u002Fs44564-026-00029-8",{"doi":82,"openalex_id":84,"authors":85,"venue":10,"cited_by_count":81,"oa_url":91,"card":92,"direction":98,"ingested_from":99},"W7221993112",[86,89],{"name":87,"orcid":88},"Niamjit Das","https:\u002F\u002Forcid.org\u002F0000-0001-7619-8306",{"name":90,"orcid":9},"Kevin Andrew","https:\u002F\u002Flink.springer.com\u002Fcontent\u002Fpdf\u002F10.1007\u002Fs44564-026-00029-8.pdf",{"tldr":93,"method":94,"finding":95,"direction":96,"opportunity":97},"系统综述数字孪生林业，提出遥感与生态模型同化耦合框架。","PRISMA 2020 综述 57 篇文献，整合多源遥感、生态模型与数据同化。","多数林业数字孪生仍处原型阶段，热带与寒带森林代表性不足。","农业遥感与作物表型","可探索物理知情机器学习与云原生工作流，填补热带、寒带森林近实时同化监测空白。","智慧农业 \u002F 农业物联网","openalex","2026-10-17T23:30:10.474821Z",{"total":65,"page":22,"page_size":65,"items":102},[103,183,248,349,407,466],{"id":104,"title":105,"url":106,"summary":107,"summary_zh":108,"content":9,"source_name":109,"source_url":106,"published_at":110,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":111,"score_detail":112,"sources":117,"tags":119,"primary_topic":122,"secondary_topics":128,"classification":129,"search_phrases":154,"slug":157,"view_count":158,"doi":159,"paper":160,"created_at":182},4360,"Assessment of bias correction techniques for satellite soil moisture data assimilation in the dry season of Southeastern South America","https:\u002F\u002Fdoi.org\u002F10.1175\u002Fjhm-d-26-0062.1","Abstract Estimation of surface soil moisture (SSM) is fundamental for hydrological monitoring and agricultural management, particularly in drought-prone regions such as central–northeastern Argentina. Data assimilation provides a robust approach for estimating SSM by integrating land surface models with remote sensing data. Satellite missions such as SMAP and SMOS deliver global SSM products; however, these observations often exhibit systematic biases arising from instrument noise, indirect measurements, and temporal and spatial heterogeneities. Since standard data assimilation techniques assume unbiased observations, bias correction is required to ensure optimal assimilation. This work evaluates off-line observation bias-correction methods within a land data assimilation framework based on the Noah-MP land surface model and an ensemble Kalman filter, focusing on the 2022 dry season in the endorheic Pampas region. During dry conditions, SSM probability density functions differ significantly among soil textures within the bin. To address sampling errors in cumulative distribution function (CDF) matching, we propose an approach in which climatological statistics are computed using homogeneous soil texture pixels, and a 45-day moving temporal window is applied to smooth CDF evolution. The proposed method is compared with standard CDF matching and normal deviate scaling. Results indicate that improved statistical sampling in CDF matching produces a measurable impact on SSM estimates, particularly during dry periods. It shows better agreement with independent in-situ soil measurements than standard CDF matching, provided that the soil texture classifications at the in-situ site and in the model grid cell are consistent.","摘要 地表土壤水分（SSM）估算对于水文监测和农业管理至关重要，尤其是在阿根廷中东北部等干旱易发地区。数据同化通过将陆面模型与遥感数据相结合，为估算SSM提供了一种稳健的方法。SMAP和SMOS等卫星任务可提供全球SSM产品；然而，这些观测往往因仪器噪声、间接测量以及时空异质性而存在系统性偏差。由于标准数据同化技术假设观测无偏，因此需要进行偏差校正以确保最优同化。本研究在基于Noah-MP陆面模型和集合卡尔曼滤波的陆面数据同化框架内，评估了离线观测偏差校正方法，重点关注内流潘帕斯地区2022年旱季。在干旱条件下，同一分箱内不同土壤质地的SSM概率密度函数存在显著差异。为解决累积分布函数（CDF）匹配中的采样误差问题，我们提出了一种方法：利用均质土壤质地像元计算气候统计量，并应用45天滑动时间窗口以平滑CDF演变。将所提方法与标准CDF匹配和正态偏差缩放进行了比较。结果表明，CDF匹配中改进的统计采样对SSM估算产生了可测量的影响，尤其是在干旱时期。与原位站点和模型网格单元土壤质地分类一致的前提下，该方法与原位土壤实测数据的吻合程度优于标准CDF匹配。","Journal of Hydrometeorology","2026-10-06T00:00:00Z",69,{"impact":21,"substance":113,"depth":114,"authority":115,"freshness":56,"relevant":22,"comment":116},21,17,14,"面向干旱区卫星土壤水分同化的偏差校正方法研究，方法有新意但属区域尺度学术成果，对国内农业遥感墒情监测有参考价值。",[118],{"name":109,"url":106},[28,120,121,30],"农业气象","土壤墒情",{"code":123,"slug":124,"name":125,"path":126,"parent_code":127},"H2","soil","土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",[],{"status":130,"locked":14,"version":35,"method":36,"evidence":131},"classified",{"candidates":132,"agricultural_evidence":42},[133,138,146,150],{"code":123,"score":41,"supported":42,"title":134,"abstract":135,"tags":137},[124],[136,124],"土壤",[121],{"code":139,"score":140,"supported":42,"title":141,"abstract":142,"tags":145},"H7",7,[],[143,144],"干旱","drought",[120],{"code":48,"score":140,"supported":42,"title":147,"abstract":148,"tags":149},[],[28,50],[28],{"code":72,"score":22,"supported":14,"title":151,"abstract":152,"tags":153},[],[],[30],[155,156],"SMAP SMOS 土壤水分 同化","南美 潘帕斯 土壤湿度 偏差校正","SMAPSMOS土壤水分同化-4360",4,"10.1175\u002Fjhm-d-26-0062.1",{"doi":159,"openalex_id":161,"authors":162,"venue":109,"cited_by_count":81,"oa_url":9,"card":177,"direction":96,"ingested_from":99},"W7220742830",[163,166,168,171,174],{"name":164,"orcid":165},"Fabricio Matías Obregón","https:\u002F\u002Forcid.org\u002F0009-0005-9861-1356",{"name":167,"orcid":9},"Lucini Magdalena",{"name":169,"orcid":170},"Omar Vicente Müller","https:\u002F\u002Forcid.org\u002F0000-0001-9943-8368",{"name":172,"orcid":173},"Romina Carla Ruscica","https:\u002F\u002Forcid.org\u002F0000-0003-0127-9579",{"name":175,"orcid":176},"Manuel Pulido","https:\u002F\u002Forcid.org\u002F0000-0003-3992-8044",{"tldr":178,"method":179,"finding":180,"direction":96,"opportunity":181},"评估南美干旱季卫星土壤湿度同化中的偏差校正方法，提出基于均质土壤纹理和滑动窗口的改进CDF匹配。","Noah-MP模型与集合卡尔曼滤波同化框架，对比标准CDF匹配和正态偏差缩放。","改进CDF匹配在干旱期对土壤湿度估计更准确，与实测数据吻合更好，但需土壤纹理分类一致。","可探索不同气候区与土壤类型下偏差校正的普适性，并耦合作物模型提升干旱监测能力。","2026-10-07T23:30:26.212164Z",{"id":184,"title":185,"url":186,"summary":187,"summary_zh":188,"content":9,"source_name":189,"source_url":186,"published_at":190,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":191,"score_detail":192,"sources":196,"tags":198,"primary_topic":9,"secondary_topics":202,"classification":203,"search_phrases":221,"slug":224,"view_count":22,"doi":225,"paper":226,"created_at":247},2173,"Integrating Satellite Data into Near-Term, Iterative Water Temperature Forecasting Workflows Improves the Scalability of Freshwater Forecasts","https:\u002F\u002Fdoi.org\u002F10.22541\u002Fessoar.15008569\u002Fv1","Freshwater ecosystems are experiencing rapid changes and increased variability due to human activities. Near-term iterative forecasting has been shown to be a valuable tool to predict how these ecosystems will change in the future, and can be used to improve both water management and ecosystem understanding. Many freshwater forecasting systems require high-frequency in situ sensor data as input, which limits their scalability to only sites with existing sensor monitoring infrastructure. To scale these forecasting methods to waterbodies with little or no in situ data, new tools are needed. Here, we evaluated how the assimilation of satellite data into a process-based hydrodynamic model using the open-source Forecasting Lake And Reservoir Ecosystems (FLARE) system affected forecast performance for 10 lakes across the US. We forecasted water temperature across water column depths every week for 1- to 14-days ahead over two years with forecast model initial conditions and parameters updated from the assimilation of the Landsat-8\u002F9 Surface Temperature product. Comparisons of forecasts with satellite data assimilation vs. forecasts with no data assimilation reveal that satellite data can improve forecast performance across 1- to 14-day horizons. However, forecast accuracy gains were variable among lakes; at eight sites satellite data assimilation either improved or was equivalent to forecasts with no data assimilation, but at two sites satellite data worsened performance. Differences in forecast performance were most strongly correlated with water clarity and local meteorology. This study demonstrates the promise of satellite remote sensing as a key tool to improve scalability of near-term iterative freshwater forecasting.","淡水生态系统正因人类活动而经历快速变化和变异性增加。近期迭代预测已被证明是预测这些生态系统未来变化的有价值工具，并可用于改进水资源管理和生态系统理解。许多淡水预测系统需要高频原位传感器数据作为输入，这将其可扩展性限制在已有传感器监测基础设施的站点。为了将这些预测方法扩展到几乎没有或完全没有原位数据的水体，需要新的工具。在此，我们评估了利用开源“湖泊与水库生态系统预测”（FLARE）系统将卫星数据同化到基于过程的水动力模型中，如何影响美国10个湖泊的预测性能。我们在两年内每周预测各水柱深度的水温，预测时效为1至14天，并利用Landsat-8\u002F9地表温度产品的同化来更新预测模型的初始条件和参数。将有卫星数据同化的预测与无数据同化的预测进行比较，结果表明卫星数据可以在1至14天的预测时效内提高预测性能。然而，预测精度的提升在湖泊之间存在差异；在8个站点，卫星数据同化要么改善了预测，要么与无数据同化的预测相当，但在2个站点，卫星数据使预测性能变差。预测性能的差异与水体透明度和当地气象条件相关性最强。本研究表明，卫星遥感有望成为提高近期迭代淡水预测可扩展性的关键工具。","OpenAlex","2026-09-09T00:00:00Z",77,{"impact":193,"substance":18,"depth":17,"authority":194,"freshness":21,"relevant":22,"comment":195},16,13,"将卫星遥感数据同化进FLARE模型，验证了提升淡水水温预报可扩展性的新方法，对水产养殖与水域生态管理有参考价值。",[197],{"name":189,"url":186},[199,28,200,30,201],"智慧渔业","水质监测","淡水养殖",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":204},{"candidates":205,"agricultural_evidence":14,"reason":76},[206,210,217],{"code":48,"score":140,"supported":42,"title":207,"abstract":208,"tags":209},[],[28,50],[28],{"code":211,"score":212,"supported":42,"title":213,"abstract":214,"tags":216},"H3",3,[],[215],"水资源",[],{"code":72,"score":22,"supported":14,"title":218,"abstract":219,"tags":220},[],[],[30],[222,223],"数据同化 智慧渔业 水质监测 淡水养殖","数据同化 智慧渔业","数据同化智慧渔业水质监测淡水养殖-2173","10.22541\u002Fessoar.15008569\u002Fv1",{"doi":225,"openalex_id":227,"authors":228,"venue":9,"cited_by_count":81,"oa_url":241,"card":242,"direction":96,"ingested_from":99},"W7212081241",[229,232,235,238],{"name":230,"orcid":231},"Molly Stroud","https:\u002F\u002Forcid.org\u002F0000-0001-7389-1586",{"name":233,"orcid":234},"Cayelan C. Carey","https:\u002F\u002Forcid.org\u002F0000-0001-8835-4476",{"name":236,"orcid":237},"George H. Allen","https:\u002F\u002Forcid.org\u002F0000-0001-8301-5301",{"name":239,"orcid":240},"R. Quinn Thomas","https:\u002F\u002Forcid.org\u002F0000-0003-1282-7825","https:\u002F\u002Fessopenarchive.org\u002Fdoi\u002Fpdf\u002F10.22541\u002Fessoar.15008569\u002Fv1",{"tldr":243,"method":244,"finding":245,"direction":96,"opportunity":246},"将卫星数据同化进FLARE模型，提升无传感器湖泊水温预报的可扩展性。","用FLARE系统同化Landsat-8\u002F9地表温度，对10个湖泊做1-14天水温","卫星同化整体提升预报精度，但效果因湖而异，与水体透明度和气象相关。","可探索卫星同化在无监测水体中的适用条件，结合水体光学与气象因子优化预报策略。","2026-09-11T23:30:32.851926Z",{"id":249,"title":250,"url":251,"summary":252,"summary_zh":253,"content":9,"source_name":254,"source_url":251,"published_at":255,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":256,"score_detail":257,"sources":260,"tags":262,"primary_topic":265,"secondary_topics":271,"classification":277,"search_phrases":318,"slug":321,"view_count":22,"doi":322,"paper":323,"created_at":348},1902,"Improving Maize Yield Estimation Accuracy by Integrating Satellite Remote Sensing Data and the WOFOST Model Through Data Assimilation","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fagronomy16171742","Under intensified climate change, improving yield estimation accuracy is essential for food security and precision agricultural management. This research aimed to enhance summer maize yield estimation accuracy. GF-1 imagery was used to derive vegetation indices for leaf area index (LAI) modeling; vegetation index–LAI models used partial least squares regression (PLSR), random forest (RF), extreme gradient boosting (XGBoost), support vector regression (SVR), convolutional neural network (CNN), and categorical feature-enhanced gradient boosting (CatBoost). Retrieved summer maize LAI and measured soil moisture (SM) were assimilated into a calibrated World Food Studies (WOFOST) model using ensemble Kalman filtering (EnKF) and four-dimensional variational assimilation (4D-Var). The influence of ensemble size and assimilation period on the accuracy of yield simulations was analyzed. Results showed that all machine learning models effectively retrieved LAI, with CNN achieving the highest accuracy under the evaluation conditions of this study. Compared with the non-assimilation scenario, data assimilation significantly improved WOFOST-based maize yield estimation; EnKF performed best for yield estimation, whereas 4D-Var yielded slightly lower LAI simulation errors than EnKF under the experimental conditions of this study. Among the ensemble sizes evaluated, an ensemble size of 100 produced the lowest yield prediction error, while assimilation during the tasseling-to-grain-filling period resulted in lower yield prediction errors than continuous whole-growth-period assimilation under the conditions examined. Overall, data assimilation effectively improved WOFOST-based maize yield estimation and supported regional crop monitoring and precision agricultural management.","在气候变化加剧的背景下，提高产量估算精度对于粮食安全和精准农业管理至关重要。本研究旨在提升夏玉米产量估算精度。利用GF-1影像提取植被指数用于叶面积指数（LAI）建模；植被指数-LAI模型采用偏最小二乘回归（PLSR）、随机森林（RF）、极端梯度提升（XGBoost）、支持向量回归（SVR）、卷积神经网络（CNN）和类别特征增强梯度提升（CatBoost）等方法。将反演的夏玉米LAI及实测土壤水分（SM）通过集合卡尔曼滤波（EnKF）和四维变分同化（4D-Var）同化到校准后的世界粮食研究（WOFOST）模型中。分析了集合规模和同化时段对产量模拟精度的影响。结果表明，所有机器学习模型均能有效反演LAI，其中在本研究评价条件下CNN取得了最高精度。与未同化情景相比，数据同化显著提高了基于WOFOST的玉米产量估算精度；EnKF在产量估算中表现最佳，而4D-Var在本研究试验条件下产生的LAI模拟误差略低于EnKF。在评估的集合规模中，集合规模为100时产量预测误差最低，而在本研究所考察条件下，抽雄至灌浆期的同化比全生育期连续同化产生了更低的产量预测误差。总体而言，数据同化有效提高了基于WOFOST的玉米产量估算精度，并支持区域作物监测和精准农业管理。","Agronomy","2026-09-07T00:00:00Z",71,{"impact":17,"substance":258,"depth":17,"authority":20,"freshness":212,"relevant":22,"comment":259},20,"研究结合遥感与WOFOST模型提升玉米产量估测精度，方法新颖且结论可靠，对精准农业有参考价值。",[261],{"name":254,"url":251},[263,59,28,264,30],"智慧农业","产量估测",{"code":266,"slug":267,"name":268,"path":269,"parent_code":270},"A3","maize","玉米","\u002Ftopic\u002Ffield-crops\u002Fmaize","A",[272],{"code":48,"slug":273,"name":274,"path":275,"parent_code":276},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",{"status":130,"locked":14,"version":35,"method":36,"evidence":278},{"candidates":279,"agricultural_evidence":42},[280,284,288,292,299,303,309,314],{"code":266,"score":115,"supported":42,"title":281,"abstract":282,"tags":283},[267],[268,267],[],{"code":48,"score":13,"supported":42,"title":285,"abstract":286,"tags":287},[50],[],[264,28],{"code":55,"score":140,"supported":42,"title":289,"abstract":290,"tags":291},[],[59,60],[59],{"code":293,"score":65,"supported":42,"title":294,"abstract":295,"tags":298},"A8",[],[296,297],"粮食安全","food security",[],{"code":123,"score":65,"supported":42,"title":300,"abstract":301,"tags":302},[],[136,124],[],{"code":139,"score":65,"supported":42,"title":304,"abstract":305,"tags":308},[],[306,307],"气候变化","climate change",[],{"code":40,"score":158,"supported":42,"title":310,"abstract":311,"tags":313},[],[312],"精准农业",[263],{"code":72,"score":22,"supported":14,"title":315,"abstract":316,"tags":317},[],[],[30],[319,320],"产量估测 数据同化 智慧农业 机器学习","产量估测 数据同化","产量估测数据同化智慧农业机器学习-1902","10.3390\u002Fagronomy16171742",{"doi":322,"openalex_id":324,"authors":325,"venue":254,"cited_by_count":81,"oa_url":251,"card":343,"direction":96,"ingested_from":99},"W7211913464",[326,329,332,334,336,338,340],{"name":327,"orcid":328},"Xuqing Li","https:\u002F\u002Forcid.org\u002F0009-0009-4215-6701",{"name":330,"orcid":331},"Zekun Zhang","https:\u002F\u002Forcid.org\u002F0009-0003-8014-0707",{"name":333,"orcid":9},"Zhihe Hu",{"name":335,"orcid":9},"Ligang Cui",{"name":337,"orcid":9},"Long Li",{"name":339,"orcid":9},"Tingxuan Wang",{"name":341,"orcid":342},"Tian Yang","https:\u002F\u002Forcid.org\u002F0000-0001-6935-4147",{"tldr":344,"method":345,"finding":346,"direction":96,"opportunity":347},"通过数据同化整合卫星遥感与WOFOST模型，提高夏玉米产量估算精度。","GF-1影像反演LAI，结合土壤水分，用EnKF和4D-Var同化进WOFOST","CNN反演LAI最准，EnKF同化产量估算最优，集合大小100最佳，抽雄至灌浆期同化效果最好。","可探索不同作物、区域及同化策略的泛化性，或结合多源遥感与深度学习改进LAI反演及同化效率。","2026-09-08T23:30:19.053510Z",{"id":350,"title":351,"url":352,"summary":353,"summary_zh":354,"content":9,"source_name":355,"source_url":352,"published_at":356,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":357,"score_detail":358,"sources":361,"tags":363,"primary_topic":9,"secondary_topics":365,"classification":366,"search_phrases":379,"slug":382,"view_count":359,"doi":383,"paper":384,"created_at":406},1821,"Adaptive feature learning and wavelet preservation for forest canopy mapping from UAV imagery","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112403","Adaptive feature learning and wavelet preservation for forest canopy mapping from UAV imagery。Computers and Electronics in Agriculture","基于无人机影像的森林冠层制图的自适应特征学习与小波保持方法。《计算机与电子在农业中的应用》","Computers and Electronics in Agriculture","2026-09-06T00:00:00Z",54,{"impact":13,"substance":41,"depth":41,"authority":20,"freshness":359,"relevant":22,"comment":360},2,"论文提出自适应特征学习与小波保留方法用于无人机森林冠层制图，方法新颖，但时效性较低，影响范围限于细分领域。",[362],{"name":355,"url":352},[263,364,28,29],"无人机",[],{"status":367,"locked":14,"version":35,"method":36,"evidence":368},"unclassified",{"candidates":369,"agricultural_evidence":42,"reason":378},[370,374],{"code":40,"score":22,"supported":14,"title":371,"abstract":372,"tags":373},[],[],[263],{"code":48,"score":22,"supported":14,"title":375,"abstract":376,"tags":377},[],[],[28],"缺少足够的主题证据",[380,381],"智慧农业 森林监测 无人机 遥感","智慧农业 森林监测","智慧农业森林监测无人机遥感-1821","10.1016\u002Fj.compag.2026.112403",{"doi":383,"openalex_id":385,"authors":386,"venue":355,"cited_by_count":81,"oa_url":9,"card":401,"direction":96,"ingested_from":99},"W7210287474",[387,390,392,395,397,399],{"name":388,"orcid":389},"Shikuan Wang","https:\u002F\u002Forcid.org\u002F0000-0003-2780-9590",{"name":391,"orcid":9},"Jianzhou Gong",{"name":393,"orcid":394},"Mengquan Wu","https:\u002F\u002Forcid.org\u002F0000-0003-1822-5980",{"name":396,"orcid":9},"Longxin Liu",{"name":398,"orcid":9},"Mingbin Guo",{"name":400,"orcid":9},"Haiwei Yuan",{"tldr":402,"method":403,"finding":404,"direction":96,"opportunity":405},"提出自适应特征学习与小波保持方法，用于无人机影像的森林冠层制图。","自适应特征学习结合小波变换，处理无人机影像。","该方法能有效提高森林冠层制图的精度和细节保持。","可探索将小波保持与深度学习结合，用于其他作物或复杂地形的遥感制图。","2026-09-07T23:30:01.926780Z",{"id":408,"title":409,"url":410,"summary":411,"summary_zh":412,"content":9,"source_name":413,"source_url":410,"published_at":414,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":415,"score_detail":416,"sources":418,"tags":420,"primary_topic":423,"secondary_topics":427,"classification":428,"search_phrases":451,"slug":454,"view_count":22,"doi":455,"paper":456,"created_at":465},1624,"AGRITWIN AI: A DIGITAL TWIN AND MULTIMODAL EXPLAINABLE AI FRAMEWORK FOR PRECISION AGRICULTURE USING SATELLITE IMAGERY, IOT SENSORS, WEATHER INTELLIGENCE, LARGE LANGUAGE MODELS, AND RETRIEVAL-AUGMENTED GENERATION","https:\u002F\u002Fdoi.org\u002F10.56726\u002Firjmets102032","Current digital precision agricultural systems suffer from a critical, structural operational data-cognition gap: modern cyber-physical sensing systems (e.g.IoT devices, remote sensing pipelines) operate as opaque numeric computation engines yielding multi-dimensional, high-frequency numeric matrices while agriculture specific Large Language Models (LLMs) remain locked into a non-numeric world that is conceptually divorced from physical realities on the ground.To bridge this data-cognition gap, this paper proposes AgriTwin AI: a holistic, end-to-end framework coupling a spatial-temporal Digital Twin engine to an autonomous, Multimodal Explainable AI (XAI) advisory pipeline.AgriTwin AI ingests heterogeneous input from 1D linear IoT sensor streams, text-based meteorological intelligence, and 2D multi-spectral satellite raster images; an asymmetric, cross-modal late-fusion architecture synchronizes these data types into a coherent, real-time virtual representation of the farm field.When the physics-driven equations of the Digital Twin engine identify an environmental threshold breach or anomaly, AgriTwin AI automatically triggers a bespoke Retrieval-Augmented Generation (RAG) cycle that is governed by an agronomic Domain Knowledge Processing Layer (DKPL).Linking fine-tuned vision-language parameters of Low-Rank Adaptation (LoRA) to text documents from regional agricultural handbooks stored in a local vector database, AgriTwin AI translates complex numerical anomalies into highly specific, traceable, and human-verifiable natural language diagnostic information.Based on preliminary simulation, AgriTwin AI reduces biological hallucinations below 0.4% and achieves a 95.2% safety constraint validation accuracy, establishing a reliable system for data-driven, explainable, and secure agricultural decision making.","当前的数字精准农业系统面临着一个关键的结构性运营数据认知鸿沟：现代网络物理感知系统（如物联网设备、遥感处理管道）作为不透明的数值计算引擎运行，产生多维、高频的数值矩阵，而农业专用的大语言模型（LLMs）仍局限于非数值世界，在概念上与地面物理现实脱节。为弥合这一数据认知鸿沟，本文提出AgriTwin AI：一个将时空数字孪生引擎与自主多模态可解释人工智能（XAI）咨询管道相结合的整体端到端框架。AgriTwin AI接收来自一维线性物联网传感器流、基于文本的气象情报以及二维多光谱卫星栅格图像的异构输入；一种非对称的跨模态后期融合架构将这些数据类型同步为连贯、实时的农田虚拟表示。当数字孪生引擎的物理驱动方程识别出环境阈值突破或异常时，AgriTwin AI自动触发由农学领域知识处理层（DKPL）管理的定制检索增强生成（RAG）循环。通过将低秩适应（LoRA）的微调视觉-语言参数与存储在本地向量数据库中的区域农业手册文本文档相连接，AgriTwin AI将复杂的数值异常转化为高度具体、可追溯且可由人工验证的自然语言诊断信息。基于初步模拟，AgriTwin AI将生物幻觉率降至0.4%以下，并达到95.2%的安全约束验证准确率，为数据驱动、可解释且安全的农业决策建立了可靠系统。","International Research Journal of Modernization in Engineering Technology and Science","2026-09-03T00:00:00Z",73,{"impact":17,"substance":18,"depth":17,"authority":21,"freshness":140,"relevant":22,"comment":417},"提出整合数字孪生与多模态可解释AI的农业框架，方法新颖，但尚处模拟阶段，信源为普通期刊。",[419],{"name":413,"url":410},[263,421,422,27,28],"农业人工智能","大语言模型",{"code":72,"slug":424,"name":425,"path":426,"parent_code":276},"agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",[],{"status":130,"locked":14,"version":35,"method":36,"evidence":429},{"candidates":430,"agricultural_evidence":42},[431,437,443,447],{"code":40,"score":432,"supported":42,"title":433,"abstract":435,"tags":436},27,[434,44],"precision agriculture",[312,27,44],[27,263],{"code":72,"score":115,"supported":42,"title":438,"abstract":440,"tags":442},[439],"IoT",[441,439],"物联网",[],{"code":48,"score":140,"supported":42,"title":444,"abstract":445,"tags":446},[],[28,50],[28],{"code":55,"score":359,"supported":14,"title":448,"abstract":449,"tags":450},[],[],[421,422],[452,453],"农业人工智能 大语言模型 数字孪生 智慧农业","农业人工智能 大语言模型","农业人工智能大语言模型数字孪生智慧农业-1624","10.56726\u002Firjmets102032",{"doi":455,"openalex_id":457,"authors":458,"venue":413,"cited_by_count":81,"oa_url":410,"card":459,"direction":98,"ingested_from":99},"W7207853514",[],{"tldr":460,"method":461,"finding":462,"direction":463,"opportunity":464},"提出 AgriTwin AI 框架，融合数字孪生与多模态可解释 AI，弥合农业数据与认知鸿沟。","结合数字孪生、跨模态融合、LoRA微调视觉语言模型及RAG，利用卫星、IoT和气","将数值异常转为可验证的自然语言诊断，幻觉率低于0.4%，安全验证准确率95.2%。","农业人工智能与决策模型","可探索多模态融合在作物病害早期诊断中的应用，或开发轻量化边缘部署方案以适配田间实时决策。","2026-09-04T23:30:11.566549Z",{"id":467,"title":468,"url":469,"summary":470,"summary_zh":471,"content":9,"source_name":472,"source_url":469,"published_at":473,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":474,"score_detail":475,"sources":477,"tags":479,"primary_topic":481,"secondary_topics":485,"classification":486,"search_phrases":511,"slug":514,"view_count":81,"doi":515,"paper":516,"created_at":526},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。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-21T00:00:00Z",74,{"impact":20,"substance":18,"depth":17,"authority":20,"freshness":13,"relevant":22,"comment":476},"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。",[478],{"name":472,"url":469},[263,421,296,28,480],"气候分析",{"code":55,"slug":482,"name":483,"path":484,"parent_code":276},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",[],{"status":130,"locked":14,"version":35,"method":36,"evidence":487},{"candidates":488,"agricultural_evidence":42},[489,494,499,503,507],{"code":55,"score":56,"supported":42,"title":490,"abstract":492,"tags":493},[491],"artificial intelligence",[],[421],{"code":72,"score":212,"supported":42,"title":495,"abstract":496,"tags":498},[],[497],"农业传感",[],{"code":293,"score":22,"supported":14,"title":500,"abstract":501,"tags":502},[],[],[296],{"code":40,"score":22,"supported":14,"title":504,"abstract":505,"tags":506},[],[],[263],{"code":48,"score":22,"supported":14,"title":508,"abstract":509,"tags":510},[],[],[28],[512,513],"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":515,"openalex_id":517,"authors":518,"venue":472,"cited_by_count":81,"oa_url":469,"card":521,"direction":463,"ingested_from":99},"W7223111766",[519],{"name":520,"orcid":9},"Fatima-Zahra El Khattabi",{"tldr":522,"method":523,"finding":524,"direction":96,"opportunity":525},"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"]