[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-5574":3,"related-5574":63},{"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":18,"tags":20,"primary_topic":9,"secondary_topics":24,"classification":25,"search_phrases":40,"slug":43,"view_count":15,"doi":44,"paper":45,"created_at":62},5574,"Aggregation of results of automatic classification of remote sensing data of natural objects","https:\u002F\u002Fdoi.org\u002F10.31772\u002F2712-8970-2026-27-3-390-399","Methods for aggregating the results of automatic classification of multidimensional spectral remote sensing data are proposed. This task is accomplished using a modified «Forel» algorithm and a procedure for testing the hypothesis of the homogeneity of the distribution laws of random variables characterizing the detected classes. When automatic classification algorithms are designed to detect sets of random variable values corresponding to unimodal fragments of their probability density, it is reasonable to regroup classes within the space of their mean random variable values. This is implemented using a modification of the “Forel” algorithm, the parameters of which are determined based on the results of a computational experiment. If additional information about the properties of a natural object is available, it can be used to aggregate the results of automatic classification in the spectral feature space. Under these conditions, class aggregation is based on testing the hypothesis of the homogeneity of the distribution laws of the random variables that characterize the additional information. To solve this problem, a nonparametric pattern recognition algorithm that follows the maximum likelihood criterion is used. The optimal blur coefficients of the classification algorithm's kernel functions are selected based on the requirement to minimize the pattern recognition error estimate in the “sliding exam” mode. The obtained results are summarized in the construction of an information graph, the nodes of which correspond to classes. An edge is formed between two graph nodes if the pattern recognition error for a given pair of classes does not differ significantly from 0,5. A modification of the Kolmogorov–Smirnov test is used to test the hypotheses. A macroclass is formed by classes corresponding to a complete subgraph that do not reliably differ in the distribution patterns of features in the additional information. The sequential procedure for forming macroclasses begins with finding the complete subgraph with the maximum number of classes. The results obtained form the basis for developing a decision rule for assessing the membership of spectral feature values in the resulting macroclasses. The proposed method for aggregating the results of automatic classification is relevant for the system analysis of remote sensing data.","针对多维光谱遥感数据自动分类结果的聚合方法被提出。该任务通过改进的“Forel”算法以及用于检验表征所检测类别的随机变量分布律同质性假设的程序来完成。当自动分类算法旨在检测对应于其概率密度单峰片段的随机变量值集合时，在其均值随机变量值空间内重新分组类别是合理的。这通过“Forel”算法的改进版本实现，其参数基于计算实验结果确定。如果存在关于自然对象属性的附加信息，则可将其用于聚合光谱特征空间中的自动分类结果。在这些条件下，类别聚合基于检验表征附加信息的随机变量分布律同质性假设。为解决该问题，采用遵循最大似然准则的非参数模式识别算法。分类算法核函数的最优模糊系数基于在“滑动检验”模式下最小化模式识别误差估计的要求进行选择。所得结果汇总于信息图的构建中，其节点对应于类别。如果给定类别对的模式识别误差与0.5无显著差异，则在两个图节点之间形成边。使用Kolmogorov–Smirnov检验的改进版本来检验假设。宏类由对应于完全子图的类别形成，这些类别在附加信息中的特征分布模式上没有可靠差异。形成宏类的顺序过程从寻找具有最大类别数的完全子图开始。所得结果构成了开发决策规则的基础，该规则用于评估光谱特征值在所得宏类中的隶属关系。所提出的用于聚合自动分类结果的方法对于遥感数据的系统分析具有相关性。",null,"Siberian Aerospace Journal","2026-10-20T00:00:00Z","论文",10,false,0,{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":17},"该文为遥感数据自动分类结果聚合的算法论文，属通用遥感方法研究，与三农、农业信息化、智慧农业无直接关联，不建议进入每日精选。",[19],{"name":10,"url":6},[21,22,23],"遥感","光谱数据","自动分类",[],{"status":26,"locked":14,"version":27,"method":28,"evidence":29},"needs_review","2026-10-22.2","rules",{"candidates":30,"agricultural_evidence":14,"reason":39},[31],{"code":32,"score":33,"supported":34,"title":35,"abstract":37,"tags":38},"I3",15,true,[36],"remote sensing",[21,36],[21],"农业相关性需要复核",[41,42],"光谱数据 自动分类 遥感","光谱数据 自动分类","光谱数据自动分类遥感-5574","10.31772\u002F2712-8970-2026-27-3-390-399",{"doi":44,"openalex_id":46,"authors":47,"venue":10,"cited_by_count":15,"oa_url":54,"card":55,"direction":59,"ingested_from":61},"W7223058937",[48,51],{"name":49,"orcid":50},"Aleksandr V. Lapko","https:\u002F\u002Forcid.org\u002F0000-0002-0664-3870",{"name":52,"orcid":53},"Vasiliy A. Lapko","https:\u002F\u002Forcid.org\u002F0000-0001-6938-9323","https:\u002F\u002Fjournals.eco-vector.com\u002F2712-8970\u002Farticle\u002Fdownload\u002F719886\u002F228882",{"tldr":56,"method":57,"finding":58,"direction":59,"opportunity":60},"提出聚合多维光谱遥感自动分类结果的方法，合并相似类别为宏类。","改进Forel算法、非参数模式识别、Kolmogorov-Smirnov检验与信","基于分布同质性检验可有效聚合自动分类类别，形成稳定宏类。","农业遥感与作物表型","可将该聚合框架用于作物遥感分类后处理，提升类别一致性与可解释性。","openalex","2026-10-22T11:20:42.307504Z",{"total":64,"page":65,"page_size":64,"items":66},6,1,[67,143,199,276,340,390],{"id":68,"title":69,"url":70,"summary":71,"summary_zh":72,"content":9,"source_name":73,"source_url":70,"published_at":74,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":75,"score_detail":76,"sources":81,"tags":83,"primary_topic":88,"secondary_topics":94,"classification":95,"search_phrases":126,"slug":129,"view_count":15,"doi":130,"paper":131,"created_at":142},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":77,"substance":78,"depth":79,"authority":77,"freshness":13,"relevant":65,"comment":80},12,22,18,"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。",[82],{"name":73,"url":70},[84,85,86,21,87],"智慧农业","农业人工智能","粮食安全","气候分析",{"code":89,"slug":90,"name":91,"path":92,"parent_code":93},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":96,"locked":14,"version":27,"method":28,"evidence":97},"classified",{"candidates":98,"agricultural_evidence":34},[99,105,112,117,122],{"code":89,"score":100,"supported":34,"title":101,"abstract":103,"tags":104},9,[102],"artificial intelligence",[],[85],{"code":106,"score":107,"supported":34,"title":108,"abstract":109,"tags":111},"I5",3,[],[110],"农业传感",[],{"code":113,"score":65,"supported":14,"title":114,"abstract":115,"tags":116},"A8",[],[],[86],{"code":118,"score":65,"supported":14,"title":119,"abstract":120,"tags":121},"I1",[],[],[84],{"code":32,"score":65,"supported":14,"title":123,"abstract":124,"tags":125},[],[],[21],[127,128],"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":130,"openalex_id":132,"authors":133,"venue":73,"cited_by_count":15,"oa_url":70,"card":136,"direction":141,"ingested_from":61},"W7223111766",[134],{"name":135,"orcid":9},"Fatima-Zahra El Khattabi",{"tldr":137,"method":138,"finding":139,"direction":59,"opportunity":140},"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。","农业人工智能与决策模型","2026-10-22T11:21:02.682497Z",{"id":144,"title":145,"url":146,"summary":147,"summary_zh":9,"content":9,"source_name":148,"source_url":146,"published_at":74,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":149,"score_detail":150,"sources":153,"tags":155,"primary_topic":159,"secondary_topics":163,"classification":164,"search_phrases":177,"slug":180,"view_count":15,"doi":181,"paper":182,"created_at":198},5579,"A Composite Field-Evaluation Framework for Digital Agriculture Maps","https:\u002F\u002Fdoi.org\u002F10.21203\u002Frs.3.rs-11283264\u002Fv1","A Composite Field-Evaluation Framework for Digital Agriculture Maps。Research Square","Research Square",38,{"impact":151,"substance":64,"depth":151,"authority":64,"freshness":13,"relevant":65,"comment":152},8,"预印本提出数字农业地图的田间复合评估框架，方法有一定新意，但摘要信息极少、未经同行评审，公共影响有限，暂不宜进入每日精选。",[154],{"name":148,"url":146},[156,157,21,158],"数字农业","农业信息化","地图评估",{"code":118,"slug":160,"name":161,"path":162,"parent_code":93},"smart-agriculture","智慧农业总论","\u002Ftopic\u002Fdigital-agriculture\u002Fsmart-agriculture",[],{"status":96,"locked":14,"version":27,"method":28,"evidence":165},{"candidates":166,"agricultural_evidence":34},[167,173],{"code":118,"score":168,"supported":34,"title":169,"abstract":171,"tags":172},13,[170],"digital agriculture",[170],[157,156],{"code":32,"score":65,"supported":14,"title":174,"abstract":175,"tags":176},[],[],[21],[178,179],"Research Square 数字农业","农业信息化 地图评估 数字农业 遥感","ResearchSquare数字农业-5579","10.21203\u002Frs.3.rs-11283264\u002Fv1",{"doi":181,"openalex_id":183,"authors":184,"venue":148,"cited_by_count":15,"oa_url":146,"card":9,"direction":197,"ingested_from":61},"W7223099987",[185,188,191,194],{"name":186,"orcid":187},"Phillip Lanza","https:\u002F\u002Forcid.org\u002F0000-0002-5545-1744",{"name":189,"orcid":190},"David G. Rossiter","https:\u002F\u002Forcid.org\u002F0000-0003-4558-1286",{"name":192,"orcid":193},"Diana Stuart Sinton","https:\u002F\u002Forcid.org\u002F0000-0001-5828-9001",{"name":195,"orcid":196},"Louis Longchamps","https:\u002F\u002Forcid.org\u002F0000-0002-4761-6094","数字乡村与农业信息化","2026-10-22T11:20:47.463814Z",{"id":200,"title":201,"url":202,"summary":203,"summary_zh":204,"content":9,"source_name":205,"source_url":202,"published_at":74,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":206,"score_detail":207,"sources":210,"tags":212,"primary_topic":217,"secondary_topics":222,"classification":223,"search_phrases":256,"slug":259,"view_count":15,"doi":260,"paper":261,"created_at":275},5572,"Potential erosion risk assessment of Kanak stream basin (Sivas, Sarkisla) with the ICONA model","https:\u002F\u002Fdoi.org\u002F10.51753\u002Fflsrt.1828829","The rapid development of technology following the Industrial Revolution has increased human domination over nature. Erosion, which plays a critical role in the process of natural shaping of the earth, can accelerate over time because of improper utilization of the natural environment by humans. The main objective of this study is to determine the erosion susceptibility of the Kanak Creek Basin, one of the sub-basins in the upper reaches of the Kizilirmak River, using the ICONA model, whose main parameters are slope, lithology, land use and vegetation cover, and Geographic Information Systems (GIS) and Remote Sensing techniques, and to list the measures that can be taken against erosion. According to the results of the ICONA model potential erosion level map, 48% of the study area has low erosion susceptibility. These areas largely correspond to the vicinity of Sama Mountain, which has volcanic rocks resistant to erosion, and the base of Sarkisla Plain where the slope is very low. The plain floor is largely covered with agricultural lands. The expansion of irrigated agriculture in this region is one of the main measures that can be taken against erosion. Erosion susceptibility increases around Turna Mountain on the northern border of the basin and Cal Mountain in the south due to both the increase in slope and the lack of resistance of the rocks in the region to erosion, and corresponds to 30% of the study area. In 22% of the basin, susceptibility to erosion is at a medium level. Most of these areas consist of natural meadows and pastures. It is essential to take measures against overgrazing in these areas to prevent the complete loss of the already sparse vegetation cover. Planning land use in the basin in a sustainable manner, arranging fields and layers perpendicular to the slope, expanding irrigated agriculture, and preventing overgrazing are of vital importance in terms of combating soil erosion.","工业革命以来技术的迅猛发展增强了人类对自然的支配能力。侵蚀在地球自然塑造过程中起着关键作用，而人类对自然环境的不当利用会加速侵蚀进程。本研究的主要目标是利用ICONA模型（其主要参数为坡度、岩性、土地利用和植被覆盖）以及地理信息系统（GIS）和遥感技术，确定克孜勒河上游子流域之一卡纳克溪流域的侵蚀敏感性，并列出可采取的侵蚀防治措施。根据ICONA模型潜在侵蚀等级图的结果，研究区48%的区域侵蚀敏感性较低。这些区域主要对应于具有抗侵蚀火山岩的萨马山附近以及坡度极低的萨尔基什拉平原底部。平原底部大部分为农业用地覆盖。在该地区扩大灌溉农业是防治侵蚀的主要措施之一。在流域北部边界的图尔纳山和南部的恰尔山周围，由于坡度增大以及该地区岩石抗侵蚀能力不足，侵蚀敏感性增加，占研究区面积的30%。流域22%的区域侵蚀敏感性为中等水平。这些区域大部分为天然草甸和牧场。在这些地区采取措施防止过度放牧至关重要，以避免本已稀疏的植被覆盖完全丧失。以可持续方式规划流域土地利用、沿垂直于坡向布置田块和土层、扩大灌溉农业以及防止过度放牧，对防治土壤侵蚀具有至关重要的意义。","Frontiers in Life Sciences and Related Technologies",61,{"impact":151,"substance":79,"depth":208,"authority":77,"freshness":100,"relevant":65,"comment":209},14,"该研究以ICONA模型结合GIS与遥感评估土耳其小流域侵蚀风险，方法规范、结论具体，但属区域性案例，公共影响有限，可作为专业参考而非每日精选。",[211],{"name":205,"url":202},[21,213,214,215,216],"土地利用","土壤侵蚀","GIS","水土保持",{"code":218,"slug":219,"name":220,"path":221,"parent_code":93},"I4","gis","GIS与空间分析","\u002Ftopic\u002Fdigital-agriculture\u002Fgis",[],{"status":96,"locked":14,"version":27,"method":28,"evidence":224},{"candidates":225,"agricultural_evidence":34},[226,232,237,244,250],{"code":218,"score":13,"supported":34,"title":227,"abstract":228,"tags":231},[],[229,215,230],"地理信息","geographic information",[215],{"code":32,"score":233,"supported":34,"title":234,"abstract":235,"tags":236},7,[],[21,36],[21],{"code":238,"score":64,"supported":34,"title":239,"abstract":240,"tags":243},"H2",[],[241,242],"土壤","soil",[],{"code":245,"score":107,"supported":34,"title":246,"abstract":247,"tags":249},"H3",[],[248],"灌溉",[],{"code":251,"score":252,"supported":14,"title":253,"abstract":254,"tags":255},"H6",2,[],[],[213,216],[257,258],"ICONA 模型 侵蚀风险","Kanak 流域 侵蚀","ICONA模型侵蚀风险-5572","10.51753\u002Fflsrt.1828829",{"doi":260,"openalex_id":262,"authors":263,"venue":205,"cited_by_count":15,"oa_url":9,"card":269,"direction":59,"ingested_from":61},"W7223117733",[264,266],{"name":265,"orcid":9},"MERİÇ KURT",{"name":267,"orcid":268},"Celal ŞENOL","https:\u002F\u002Forcid.org\u002F0000-0003-0857-866X",{"tldr":270,"method":271,"finding":272,"direction":273,"opportunity":274},"用ICONA模型评估土耳其Kanak流域潜在侵蚀风险并列出防治措施。","ICONA模型结合GIS与遥感，输入坡度、岩性、土地利用与植被覆盖。","48%区域低侵蚀风险，30%高敏感，22%中等，主因坡度与岩性。","农业绿色发展与碳","可将ICONA与遥感时序数据结合，动态监测流域侵蚀并评估农业管理措施效果。","2026-10-22T11:20:39.475037Z",{"id":277,"title":278,"url":279,"summary":280,"summary_zh":281,"content":9,"source_name":282,"source_url":279,"published_at":74,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":283,"score_detail":284,"sources":288,"tags":290,"primary_topic":293,"secondary_topics":297,"classification":298,"search_phrases":315,"slug":318,"view_count":15,"doi":319,"paper":320,"created_at":339},5571,"Temporal Multi-Scale Spatio-Temporal Network (TMST): Polarization–Temporal Feature Selection and Multi-Scale Spatiotemporal Fusion for Crop Mapping","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fagronomy16202068","Accurate and timely crop mapping supports agricultural resource management, yield prediction, and food security decision-making. In this study, we propose the Temporal Multi-scale Spatio-Temporal Network (TMST), a crop mapping method that integrates multi-source remote sensing time series through polarization–temporal feature selection and multi-scale spatiotemporal fusion. TMST combines Sentinel-1 dual-polarization synthetic aperture radar (SAR), Sentinel-2 multispectral data, and vegetation indices. Its Temporal Feature Importance Explainer (TFIExplainer) selects informative polarization–time features, the Multi-Scale Attention Aggregation (MSAA) module enhances spatial representations, and the Spatio-Temporal Feature Encoder (STFE) models long-range spatial dependencies and phenological dynamics; a composite loss improves minority-class and difficult-pixel recognition. On the Xinxiang dataset, TMST achieved an overall accuracy (OA) of 0.8625 and a mean F1-score (mF1) of 0.8329. Module and data-source ablations suggested benefits of the combined modules and multi-source fusion, while a cropland mask reduced non-cropland misclassification. In direct cross-dataset evaluation, models trained on a self-constructed Austrian dataset and tested on the radar-extended Panoptic Agricultural Satellite Time Series (PASTIS-R) dataset showed that TMST outperformed the evaluated baselines under the specified source–target setting. Annual mapping of Xinxiang for 2019–2023, using year-specific samples and independently trained models, provided map-based estimates of regional cropping structures and spatial patterns. Under the evaluated settings, TMST provides an effective approach to crop classification and annually updated crop mapping.","准确的作物制图有助于农业资源管理、产量预测和粮食安全决策。本研究提出了一种时间多尺度时空网络（Temporal Multi-scale Spatio-Temporal Network，TMST），这是一种通过极化—时间特征选择和多尺度时空融合来整合多源遥感时间序列的作物制图方法。TMST结合了Sentinel-1双极化合成孔径雷达（SAR）、Sentinel-2多光谱数据和植被指数。其时间特征重要性解释器（Temporal Feature Importance Explainer，TFIExplainer）用于选择信息量丰富的极化—时间特征，多尺度注意力聚合（Multi-Scale Attention Aggregation，MSAA）模块增强空间表征，时空特征编码器（Spatio-Temporal Feature Encoder，STFE）建模长程空间依赖关系和物候动态；复合损失函数改善了少数类和困难像元的识别。在新乡数据集上，TMST取得了0.8625的总体精度（OA）和0.8329的平均F1分数（mF1）。模块和数据源消融实验表明，组合模块和多源融合具有优势，而耕地掩膜减少了非耕地误分类。在直接的跨数据集评估中，在自行构建的奥地利数据集上训练并在雷达扩展的Panoptic农业卫星时间序列（PASTIS-R）数据集上测试的模型表明，在指定的源—目标设置下，TMST优于所评估的基线方法。使用逐年样本和独立训练的模型对新乡2019—2023年进行年度制图，提供了基于制图的区域种植结构和空间格局估计。在所评估的设置下，TMST为作物分类和年度更新的作物制图提供了一种有效方法。","Agronomy",73,{"impact":77,"substance":285,"depth":286,"authority":208,"freshness":13,"relevant":65,"comment":287},20,17,"提出多源遥感融合的作物制图新方法，方法新颖、实验充分，但属细分技术进展，公共影响有限。",[289],{"name":282,"url":279},[84,291,21,292],"作物制图","SAR",{"code":32,"slug":294,"name":295,"path":296,"parent_code":93},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",[],{"status":96,"locked":14,"version":27,"method":28,"evidence":299},{"candidates":300,"agricultural_evidence":34},[301,306,311],{"code":32,"score":13,"supported":34,"title":302,"abstract":303,"tags":305},[],[21,36,304],"multispectral",[21],{"code":113,"score":64,"supported":34,"title":307,"abstract":308,"tags":310},[],[86,309],"food security",[],{"code":118,"score":65,"supported":14,"title":312,"abstract":313,"tags":314},[],[],[84],[316,317],"Sentinel-1 Sentinel-2 作物分类","TMST 多尺度时空网络","Sentinel-1Sentinel-2作物分类-5571","10.3390\u002Fagronomy16202068",{"doi":319,"openalex_id":321,"authors":322,"venue":282,"cited_by_count":15,"oa_url":279,"card":334,"direction":59,"ingested_from":61},"W7223117203",[323,326,328,331],{"name":324,"orcid":325},"Xi Kan","https:\u002F\u002Forcid.org\u002F0000-0002-4629-9357",{"name":327,"orcid":9},"Wentao Lv",{"name":329,"orcid":330},"Lei Gong","https:\u002F\u002Forcid.org\u002F0000-0001-6429-267X",{"name":332,"orcid":333},"Linglong Zhu","https:\u002F\u002Forcid.org\u002F0000-0002-8863-9911",{"tldr":335,"method":336,"finding":337,"direction":59,"opportunity":338},"提出TMST网络，融合SAR与多光谱时序数据实现作物制图。","Sentinel-1\u002F2时序、极化-时序特征选择、多尺度注意力与时空编码器。","新乡OA达0.8625，多源融合与模块组合有效，跨数据集优于基线。","可探索极化-时序特征选择在跨区域迁移与少样本作物制图中的泛化能力。","2026-10-22T11:20:39.359881Z",{"id":341,"title":342,"url":343,"summary":344,"summary_zh":345,"content":9,"source_name":73,"source_url":343,"published_at":74,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":346,"score_detail":347,"sources":349,"tags":351,"primary_topic":354,"secondary_topics":355,"classification":357,"search_phrases":374,"slug":377,"view_count":15,"doi":378,"paper":379,"created_at":389},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。",67,{"impact":151,"substance":285,"depth":286,"authority":77,"freshness":13,"relevant":65,"comment":348},"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。",[350],{"name":73,"url":343},[84,85,352,21,353],"产量预测","可解释性",{"code":89,"slug":90,"name":91,"path":92,"parent_code":93},[356],{"code":32,"slug":294,"name":295,"path":296,"parent_code":93},{"status":96,"locked":14,"version":27,"method":28,"evidence":358},{"candidates":359,"agricultural_evidence":34},[360,366,370],{"code":89,"score":77,"supported":34,"title":361,"abstract":363,"tags":365},[362],"computer vision",[364],"计算机视觉",[85],{"code":32,"score":151,"supported":34,"title":367,"abstract":368,"tags":369},[],[21,36],[352,21],{"code":118,"score":65,"supported":14,"title":371,"abstract":372,"tags":373},[],[],[84],[375,376],"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":378,"openalex_id":380,"authors":381,"venue":73,"cited_by_count":15,"oa_url":343,"card":384,"direction":59,"ingested_from":61},"W7223114002",[382],{"name":383,"orcid":9},"Kadiatou Barry",{"tldr":385,"method":386,"finding":387,"direction":59,"opportunity":388},"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":391,"title":392,"url":393,"summary":394,"summary_zh":395,"content":9,"source_name":396,"source_url":393,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":397,"score_detail":398,"sources":400,"tags":402,"primary_topic":406,"secondary_topics":412,"classification":414,"search_phrases":439,"slug":442,"view_count":15,"doi":443,"paper":444,"created_at":486},5567,"Capturing Spatial Heterogeneity Using UAV-Derived Multispectral Phenotypes and Random Regression Models Improves Genetic Evaluation in Alfalfa Breeding Trials","https:\u002F\u002Fdoi.org\u002F10.64898\u002F2026.10.14.759249","Spatial heterogeneity is a major source of environmental noise in field trials, reducing genetic evaluation accuracy. Conventional spatial correction methods use field layout and plot proximity but often fail to capture in-season dynamics or leverage temporal data from high-throughput phenotyping. We hypothesized that longitudinal UAV-derived multispectral measurements could characterize field-scale environmental heterogeneity and improve genetic evaluation in breeding trials. Multispectral imagery was collected throughout the growing season across eight alfalfa trials in New York and New Mexico (20222023). Vegetation indices were evaluated for heritability and association with biomass yield using univariate and multi-trait models. Longitudinal measurements were modeled with random regression (RR) to estimate plot-specific permanent environmental effects (PEE), incorporated into genomic mixed models within a two-stage framework. Model performance was compared with conventional autoregressive (AR) and baseline (no correction) models using metrics of consistency and accuracy of estimated genetic effects across replicates. Vegetation indices showed moderate to high heritability, with GNDVI consistently outperforming NDVI and NDRE. Both univariate and multi-trait analyses revealed substantial spatial variability, particularly in New Mexico trials. RR-derived PEE captured field-scale spatial patterns and improved genetic signal recovery relative to baseline and AR models, with the largest gains under strong spatial heterogeneity and comparable performance where variability was limited. The RR framework improved reproducibility of genetic effect estimates across independent field subsets without compromising agreement with full-trial evaluations. These findings show that integrating UAV data via random regression enhances genetic signal recovery and selection accuracy, with broader potential for precision agriculture and biosensor-driven crop management.","空间异质性是田间试验中环境噪声的主要来源，会降低遗传评估的准确性。传统空间校正方法利用田间布局和小区邻近性，但往往无法捕捉生育期内的动态变化，也未能充分利用高通量表型分析产生的时间序列数据。我们假设，基于无人机（UAV）的纵向多光谱测量能够表征田块尺度的环境异质性，并改善育种试验中的遗传评估。在2022—2023年纽约州和新墨西哥州的8个紫花苜蓿试验中，于整个生长季收集了多光谱影像。采用单性状和多性状模型评估了植被指数的遗传力及其与生物量产量的关联。纵向测量数据采用随机回归（RR）建模，以估计小区特异性永久环境效应（PEE），并在两阶段框架中将其纳入基因组混合模型。利用重复间估计遗传效应的一致性和准确性指标，将模型性能与传统的自回归（AR）模型和基线（无校正）模型进行比较。植被指数表现出中到高的遗传力，其中GNDVI始终优于NDVI和NDRE。单性状和多性状分析均揭示了显著的空间变异，尤其在新墨西哥州的试验中更为明显。RR衍生的PEE捕捉到了田块尺度的空间格局，相对于基线模型和AR模型改善了遗传信号的恢复，在强空间异质性条件下增益最大，而在变异有限时性能相当。RR框架提高了遗传效应估计在独立田间子集间的可重复性，同时未损害与全试验评估的一致性。这些结果表明，通过随机回归整合UAV数据可增强遗传信号恢复和选择准确性，在精准农业和生物传感器驱动的作物管理方面具有更广泛的潜力。","bioRxiv (Cold Spring Harbor Laboratory)",79,{"impact":79,"substance":78,"depth":79,"authority":77,"freshness":100,"relevant":65,"comment":399},"该研究利用无人机多光谱表型与随机回归模型校正田间空间异质性，显著提升苜蓿育种遗传评估精度，方法新颖、数据覆盖两州八组试验，对智慧育种有实质参考价值。",[401],{"name":396,"url":393},[84,403,404,21,405],"无人机","育种","紫花苜蓿",{"code":407,"slug":408,"name":409,"path":410,"parent_code":411},"A7","forage-cropping","饲草与耕作制度","\u002Ftopic\u002Ffield-crops\u002Fforage-cropping","A",[413],{"code":32,"slug":294,"name":295,"path":296,"parent_code":93},{"status":96,"locked":14,"version":27,"method":28,"evidence":415},{"candidates":416,"agricultural_evidence":34},[417,423,427,433],{"code":407,"score":33,"supported":34,"title":418,"abstract":420,"tags":422},[419],"alfalfa",[421,419],"苜蓿",[405],{"code":32,"score":77,"supported":34,"title":424,"abstract":425,"tags":426},[304],[304],[21],{"code":118,"score":233,"supported":34,"title":428,"abstract":429,"tags":432},[],[430,431],"精准农业","precision agriculture",[84],{"code":434,"score":435,"supported":34,"title":436,"abstract":437,"tags":438},"C4",4,[],[421],[405],[440,441],"无人机 多光谱 苜蓿 育种","随机回归 空间异质性 遗传评估","无人机多光谱苜蓿育种-5567","10.64898\u002F2026.10.14.759249",{"doi":443,"openalex_id":445,"authors":446,"venue":396,"cited_by_count":15,"oa_url":393,"card":481,"direction":59,"ingested_from":61},"W7223083966",[447,450,453,456,459,461,463,466,469,472,475,478],{"name":448,"orcid":449},"Dinesh Ghimire","https:\u002F\u002Forcid.org\u002F0009-0008-2281-1396",{"name":451,"orcid":452},"Ranjita Thapa","https:\u002F\u002Forcid.org\u002F0000-0001-6116-7611",{"name":454,"orcid":455},"Karl H. Kunze","https:\u002F\u002Forcid.org\u002F0000-0003-4548-1808",{"name":457,"orcid":458},"Felipe Sabadin","https:\u002F\u002Forcid.org\u002F0000-0003-2937-1465",{"name":460,"orcid":9},"Julie Hansen",{"name":462,"orcid":9},"Christopher Pierce",{"name":464,"orcid":465},"Liam Wickes-Do","https:\u002F\u002Forcid.org\u002F0009-0003-2927-4590",{"name":467,"orcid":468},"Nicholas Santantonio","https:\u002F\u002Forcid.org\u002F0000-0002-4351-4023",{"name":470,"orcid":471},"Ian M. Ray","https:\u002F\u002Forcid.org\u002F0000-0003-2056-536X",{"name":473,"orcid":474},"Michael A. Gore","https:\u002F\u002Forcid.org\u002F0000-0001-6896-8024",{"name":476,"orcid":477},"Virginia Mae Moore","https:\u002F\u002Forcid.org\u002F0000-0001-7888-3366",{"name":479,"orcid":480},"Kelly R. Robbins","https:\u002F\u002Forcid.org\u002F0000-0001-9522-9585",{"tldr":482,"method":483,"finding":484,"direction":59,"opportunity":485},"用无人机多光谱时序表型和随机回归模型校正田间空间异质性，提升苜蓿育种遗传评估精度。","八项苜蓿试验的无人机多光谱植被指数，随机回归估计小区永久环境效应并嵌入基因组混合","随机回归提取的环境效应能捕捉田块尺度空间格局，在强异质性下显著提升遗传信号恢复与选择准确性。","可将无人机时序表型与随机回归框架推广到其他作物育种试验，并探索多源遥感与基因组选择的联合建模。","2026-10-22T11:20:32.655394Z"]