[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3230":3,"related-3230":79},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":8,"published_at":11,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":22,"tags":24,"primary_topic":30,"secondary_topics":36,"classification":37,"search_phrases":74,"slug":77,"view_count":45,"doi":8,"paper":8,"created_at":78},3230,"农业科普进校园 科技种子润心田——黑龙江省农科院\"农业科普进校园\"活动走进萧红中学","https:\u002F\u002Fwww.sohu.com\u002Fa\u002F1079072228_121106822","黑龙江省农科院\"农业科普进校园\"活动走进哈尔滨市萧红中学，七位专家把实验室里的科研成果\"翻译\"成生动有趣的科普课堂，围绕食品安全、现代种业、智慧农业、遥感监测、生物防治、健康养殖、未来食品等方向，用图文展示、实物观察、视频演示和互动问答，把硬核科研变成通俗易懂的知识。作为省农科院2026年全国科普月重点活动之一，本次活动紧扣\"科技改变生活 创新赢得未来\"主题，聚焦现代农业科普和青少年科学素养提升，是落实全国科普月\"科普讲堂话前沿\"\"科学文化进基层\"部署、推动农业科普资源进校园的具体实践。",null,"## 农业科普进校园 科技种子润心田 ——省农科院“农业科普进校园”活动走进萧红中学\n\n2026-09-21 17:29 来源: [大东北生活资讯](https:\u002F\u002Fwww.sohu.com\u002F)\n\n发布于：北京市\n\n当“农药去哪了”“玉米的秘密”“未来餐桌”这些话题出现在中学课堂，农业就不再是课本里遥远的名词，而是一场可以看、可以问、可以触摸的科技之旅。\n\n近日，省农科院“农业科普进校园”活动走进哈尔滨市萧红中学。七位专家把实验室里的科研成果“翻译”成生动有趣的科普课堂，带着同学们零距离感受现代农业的魅力。\n\n活动现场，专家们围绕食品安全、现代种业、智慧农业、遥感监测、生物防治、健康养殖、未来食品等方向，用图文展示、实物观察、视频演示和互动问答，把硬核科研变成通俗易懂的知识。同学们在观察、提问、交流中，慢慢理解了“藏粮于技”的意义，也感受到科技给农业带来的改变。\n\n作为省农科院2026年全国科普月重点活动之一，本次活动紧扣“科技改变生活 创新赢得未来”主题，聚焦现代农业科普和青少年科学素养提升，是落实全国科普月“科普讲堂话前沿”“科学文化进基层”部署、推动农业科普资源进校园的具体实践。以青少年为纽带，科研机构与社会公众之间多了一座沟通的桥；通过“请进来”与“走出去”，省农科院在粮食安全、乡村振兴等领域的创新成果被更多年轻人看见。知农、爱农、兴农的种子，正在校园里悄悄发芽。\n\n接下来，省农科院还将继续深化与学校的合作，让更多青少年在沉浸式体验中走近农业、爱上科学，为龙江农业现代化和乡村振兴积蓄青春力量。\n\n![Image 1](https:\u002F\u002Fq0.itc.cn\u002Fq_70\u002Fimages03\u002F20260921\u002Fccb551427fec4af1a347d1e5b521017a.jpeg)\n\n![Image 2](https:\u002F\u002Fq6.itc.cn\u002Fq_70\u002Fimages03\u002F20260921\u002F9f478e5a65a44654acd668ed043bff16.jpeg)\n\n**黑 龙 江 省 农 业 科 学 院 党 宣**\n\n信 息 来 源：科技推广处张唯一\n\n审核：李佳峰\n\n编辑：王红蕾[返回搜狐，查看更多](https:\u002F\u002Fwww.sohu.com\u002F?strategyid=00001 \"点击进入搜狐首页\")","黑龙江省农业科学院","2026-09-19T00:00:00Z","报道",10,false,39,{"impact":17,"substance":17,"depth":18,"authority":13,"freshness":19,"relevant":20,"comment":21},8,6,7,1,"省级农科院面向中学的科普活动通稿，属全国科普月系列活动，有科普教育价值但信息增量有限，适合作为科普类资讯收录。",[23],{"name":10,"url":6},[25,26,27,28,29],"智慧农业","农业科普","遥感监测","全国科普月","青少年科学素养",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",[],{"status":38,"locked":14,"version":39,"method":40,"evidence":41},"classified","2026-10-22.2","rules",{"candidates":42,"agricultural_evidence":46},[43,50,55,62,68],{"code":44,"score":45,"supported":46,"title":47,"abstract":48,"tags":49},"I1",4,true,[],[25],[25],{"code":31,"score":45,"supported":46,"title":51,"abstract":52,"tags":54},[],[53],"遥感",[27],{"code":56,"score":57,"supported":46,"title":58,"abstract":59,"tags":61},"E4",3,[],[60],"食品安全",[],{"code":63,"score":57,"supported":46,"title":64,"abstract":65,"tags":67},"F1",[],[66],"种业",[],{"code":69,"score":57,"supported":46,"title":70,"abstract":71,"tags":73},"F4",[],[72],"生物防治",[],[75,76],"黑龙江省农科院 农业科普进校园","萧红中学 农业科普","黑龙江省农科院农业科普进校园-3230","2026-09-23T00:04:30.535981Z",{"total":18,"page":20,"page_size":18,"items":80},[81,168,242,323,365,464],{"id":82,"title":83,"url":84,"summary":85,"summary_zh":86,"content":8,"source_name":87,"source_url":84,"published_at":88,"category":89,"cover_url":8,"hotness":13,"is_selected":14,"score":90,"score_detail":91,"sources":97,"tags":99,"primary_topic":103,"secondary_topics":109,"classification":111,"search_phrases":136,"slug":139,"view_count":140,"doi":141,"paper":142,"created_at":167},5367,"Integration of multi-source UAV remote sensing features and derived features for winter wheat aboveground biomass estimation","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.atech.2026.102656","Accurate estimation of winter wheat ( Triticum aestivum L.) aboveground biomass (AGB) is important for crop growth monitoring and field management. However, unmanned aerial vehicle (UAV)-based AGB estimation remains challenging due to variations in canopy conditions across growth stages, and different remote sensing features can capture complementary characteristics related to AGB estimation. This study integrated multi-source UAV-derived features, including vegetation indices (VIs), texture features (TFs), light detection and ranging (LiDAR)-derived features, and derived features (DFs) generated from the original feature sets, with four machine learning algorithms for winter wheat AGB estimation. Results showed that TFs provided better prediction performance than other single-source feature sets. Compared with single-source feature sets, the integration of VIs, TFs, LiDAR-derived features, and DFs further improved AGB estimation, and the random forest (RF) model achieved the best performance among the evaluated models (R² = 0.923, RMSE = 1.731 Mg ha⁻¹). Incremental R² analysis based on a stage-only baseline model showed that the RF model explained additional variation in AGB beyond growth-stage information, with an incremental R² of 0.479. Stage-specific evaluation indicated that model performance varied among growth stages, with the highest accuracy observed at the booting stage (R² = 0.632, RMSE = 1.425 Mg ha⁻¹). Feature contribution analysis based on the full-feature fusion model using all growth-stage data identified canopy coverage and several DFs as important predictors, while stage-specific analyses showed differences in dominant predictors across growth stages. The integration of multi-source UAV-derived features and DFs with machine learning provides an effective approach for winter wheat AGB estimation, while model performance remains strongly dependent on growth stage.","准确估算冬小麦（Triticum aestivum L.）地上生物量（aboveground biomass, AGB）对作物生长监测和田间管理具有重要意义。然而，由于不同生育期冠层条件存在差异，且不同遥感特征能够捕捉与AGB估算相关的互补信息，基于无人机（unmanned aerial vehicle, UAV）的AGB估算仍面临挑战。本研究将多源无人机衍生特征，包括植被指数（vegetation indices, VIs）、纹理特征（texture features, TFs）、激光雷达（light detection and ranging, LiDAR）衍生特征以及由原始特征集生成的衍生特征（derived features, DFs），与四种机器学习算法相结合，用于冬小麦AGB估算。结果表明，TFs的预测性能优于其他单一来源特征集。与单一来源特征集相比，融合VIs、TFs、LiDAR衍生特征和DFs进一步提高了AGB估算精度，其中随机森林（random forest, RF）模型在所评估的模型中表现最佳（R² = 0.923，RMSE = 1.731 Mg ha⁻¹）。基于仅含生育期信息的基线模型进行的增量R²分析表明，RF模型在生育期信息之外解释了AGB的额外变异，增量R²为0.479。分生育期评估表明，模型性能在不同生育期之间存在差异，其中在孕穗期观察到最高精度（R² = 0.632，RMSE = 1.425 Mg ha⁻¹）。基于使用全部生育期数据的全特征融合模型进行的特征贡献分析识别出冠层覆盖度和若干DFs为重要预测因子，而分生育期分析则表明不同生育期的主导预测因子存在差异。将多源无人机衍生特征和DFs与机器学习相结合，为冬小麦AGB估算提供了一种有效方法，但模型性能仍强烈依赖于生育期。","Smart Agricultural Technology","2026-10-17T00:00:00Z","论文",77,{"impact":92,"substance":93,"depth":94,"authority":95,"freshness":17,"relevant":20,"comment":96},16,22,18,13,"该研究融合无人机多源遥感特征与衍生特征，用随机森林估算冬小麦地上生物量，方法新颖、结论可靠，对作物长势监测有参考价值。",[98],{"name":87,"url":84},[25,100,27,101,102],"无人机","冬小麦","生物量估算",{"code":104,"slug":105,"name":106,"path":107,"parent_code":108},"A2","wheat","小麦","\u002Ftopic\u002Ffield-crops\u002Fwheat","A",[110],{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"status":38,"locked":14,"version":39,"method":40,"evidence":112},{"candidates":113,"agricultural_evidence":46},[114,120,125,132],{"code":104,"score":115,"supported":46,"title":116,"abstract":118,"tags":119},26,[117,105],"winter wheat",[106,117,105],[101],{"code":31,"score":92,"supported":46,"title":121,"abstract":123,"tags":124},[122],"remote sensing",[53,122],[102,27],{"code":126,"score":18,"supported":46,"title":127,"abstract":128,"tags":131},"I2",[],[129,130],"机器学习","machine learning",[],{"code":44,"score":20,"supported":14,"title":133,"abstract":134,"tags":135},[],[],[25],[137,138],"无人机 多源遥感 冬小麦 生物量","冬小麦 地上生物量 随机森林","无人机多源遥感冬小麦生物量-5367",0,"10.1016\u002Fj.atech.2026.102656",{"doi":141,"openalex_id":143,"authors":144,"venue":87,"cited_by_count":140,"oa_url":84,"card":160,"direction":164,"ingested_from":166},"W7222806066",[145,147,149,151,154,156,158],{"name":146,"orcid":8},"Guangtao Wang",{"name":148,"orcid":8},"Sumei Yao",{"name":150,"orcid":8},"Yanzheng Xie",{"name":152,"orcid":153},"Anzhen Qin","https:\u002F\u002Forcid.org\u002F0000-0002-2550-0015",{"name":155,"orcid":8},"Xiangdong Chen",{"name":157,"orcid":8},"Yuhao Zhang",{"name":159,"orcid":8},"Lina Jiang",{"tldr":161,"method":162,"finding":163,"direction":164,"opportunity":165},"融合无人机多源遥感特征与衍生特征，用机器学习估算冬小麦地上生物量。","无人机植被指数、纹理、LiDAR特征及衍生特征结合四种机器学习算法建模。","多源特征融合优于单一特征，随机森林最优（R²=0.923），精度随生育期变化。","农业遥感与作物表型","可探索生育期自适应建模与特征选择，提升跨期生物量估算的稳健性与可迁移性。","openalex","2026-10-20T23:30:03.106267Z",{"id":169,"title":170,"url":171,"summary":172,"summary_zh":173,"content":8,"source_name":174,"source_url":171,"published_at":175,"category":89,"cover_url":8,"hotness":13,"is_selected":14,"score":176,"score_detail":177,"sources":182,"tags":184,"primary_topic":187,"secondary_topics":188,"classification":189,"search_phrases":211,"slug":214,"view_count":20,"doi":215,"paper":216,"created_at":241},5162,"Detection of Eulecanium giganteum Infestation in Jujube Orchards Based on UAV Multispectral Remote Sensing","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fhorticulturae12101286","The application of remote sensing technology to monitor agricultural pests and diseases provides an effective approach for rapid and non-destructive assessment of crop health. This study evaluated a UAV multispectral remote sensing framework integrating vegetation indices and SPAD information for assessing Eulecanium giganteum infestation in jujube orchards. Initially, 24 vegetation indices were extracted from canopy multispectral imagery, and Pearson correlation analysis was used for feature screening, resulting in a refined subset of 19 vegetation indices. Seven machine learning algorithms were evaluated during model development, with Grid Search combined with tree-level grouped 7-fold cross-validation for hyperparameter selection. Vegetation indices were used as predictor variables, while SPAD value and infestation severity were treated as response variables in the regression and classification tasks, respectively. During internal model development, the CatBoost-19opt model achieved an R2 of 0.81 and an RMSE of 1.84 for SPAD estimation. On the independent test set consisting of 58 jujube trees, the previously selected model achieved an R2 of 0.84 and an RMSE of 1.56. During internal model development, incorporating measured SPAD values improved pest classification performance, with XGBoost-19sopt achieving an OA of 0.89 and a Kappa coefficient of 0.84. On the independent test set, the measured-SPAD configuration achieved an OA of 0.88, whereas both the VI-only and VI combined with predicted-SPAD configurations achieved an OA of 0.71. Thus, incorporating predicted SPAD did not improve overall classification accuracy relative to using vegetation indices alone. Further model optimization and additional validation across different orchards, growing seasons, and phenological stages are required before the approach can be considered for operational large-scale monitoring.","遥感技术在农业病虫害监测中的应用，为作物健康的快速、无损评估提供了有效途径。本研究评估了一种集成植被指数与SPAD信息的无人机多光谱遥感框架，用于评估枣园中枣球蜡蚧（Eulecanium giganteum）的危害情况。首先，从冠层多光谱影像中提取了24个植被指数，并采用Pearson相关分析进行特征筛选，最终得到包含19个植被指数的精简子集。在模型开发过程中评估了7种机器学习算法，采用网格搜索结合树级分组7折交叉验证进行超参数选择。以植被指数作为预测变量，分别将SPAD值和危害程度作为回归任务和分类任务的响应变量。在内部模型开发中，CatBoost-19opt模型在SPAD估算中取得了R²为0.81、RMSE为1.84的结果。在由58株枣树构成的独立测试集上，先前选定的模型取得了R²为0.84、RMSE为1.56的结果。在内部模型开发中，引入实测SPAD值提升了病虫害分类性能，XGBoost-19sopt取得了OA为0.89、Kappa系数为0.84的结果。在独立测试集上，实测SPAD配置取得了OA为0.88的结果，而仅使用植被指数以及植被指数结合预测SPAD的配置均取得了OA为0.71的结果。因此，相对于仅使用植被指数，引入预测SPAD并未提升整体分类精度。在该方法可被视为适用于业务化大规模监测之前，仍需进一步的模型优化，并在不同枣园、生长季和物候期开展额外验证。","Horticulturae","2026-10-16T00:00:00Z",73,{"impact":178,"substance":93,"depth":179,"authority":95,"freshness":180,"relevant":20,"comment":181},12,17,9,"方法扎实、数据完整的单果园研究，但作者自述尚未达到大规模业务化监测水平，属细分领域进展，可入精选但非重大突破。",[183],{"name":174,"url":171},[25,100,27,185,186],"病虫害防治","枣树",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":14,"version":39,"method":40,"evidence":190},{"candidates":191,"agricultural_evidence":46},[192,198,202,207],{"code":31,"score":115,"supported":46,"title":193,"abstract":195,"tags":197},[122,194],"multispectral",[53,196,122,194],"无人机多光谱",[27],{"code":126,"score":18,"supported":46,"title":199,"abstract":200,"tags":201},[],[129,130],[],{"code":203,"score":57,"supported":46,"title":204,"abstract":205,"tags":206},"B2",[],[186],[],{"code":44,"score":20,"supported":14,"title":208,"abstract":209,"tags":210},[],[],[25],[212,213],"无人机 多光谱 枣园 虫害","Eulecanium giganteum 遥感 监测","无人机多光谱枣园虫害-5162","10.3390\u002Fhorticulturae12101286",{"doi":215,"openalex_id":217,"authors":218,"venue":174,"cited_by_count":140,"oa_url":171,"card":236,"direction":164,"ingested_from":166},"W7222575708",[219,221,223,226,229,231,233],{"name":220,"orcid":8},"Yueteng Chao",{"name":222,"orcid":8},"Yulong Wang",{"name":224,"orcid":225},"Zhuoyang Xu","https:\u002F\u002Forcid.org\u002F0000-0003-0344-3424",{"name":227,"orcid":228},"Ruohong He","https:\u002F\u002Forcid.org\u002F0009-0000-7404-9112",{"name":230,"orcid":8},"Rina Yangdao",{"name":232,"orcid":8},"Hongqiang Dong",{"name":234,"orcid":235},"Ping Li","https:\u002F\u002Forcid.org\u002F0009-0007-4465-1023",{"tldr":237,"method":238,"finding":239,"direction":164,"opportunity":240},"用无人机多光谱植被指数与SPAD估算枣园大球蚧发生程度。","24个植被指数筛选19个，7种机器学习+网格搜索与分组交叉验证。","CatBoost估SPAD R²达0.84；实测SPAD提升分类，预测SPAD无增益。","可探索预测SPAD失效原因及跨果园、物候期泛化与多源数据融合监测。","2026-10-17T23:30:28.025984Z",{"id":243,"title":244,"url":245,"summary":246,"summary_zh":247,"content":8,"source_name":248,"source_url":245,"published_at":249,"category":89,"cover_url":8,"hotness":13,"is_selected":14,"score":90,"score_detail":250,"sources":253,"tags":255,"primary_topic":258,"secondary_topics":263,"classification":269,"search_phrases":296,"slug":299,"view_count":20,"doi":300,"paper":301,"created_at":322},4808,"Early Detection of Apple Scab in Orchards and Mildew in Vineyards Using A Novel Deep Learning Model and Multispectral Imagery","https:\u002F\u002Fdoi.org\u002F10.15832\u002Fankutbd.1898342","Agricultural diseases are a significant problem for growers as they cause substantial damage to fruits and leaves, leading to yield losses. Therefore, developing systems for early detection of plant diseases is a crucial issue. In this study, a new deep learning-based hybrid model is presented for the detection and segmentation of plant diseases, specifically apple scab disease in apple orchards and mildew disease in vineyards. Multispectral imagery data collected in agricultural areas of Tekirdag province in Turkey via drones between May 2023 and December 2024 were used in developing the early disease detection system. The datasets contain 3625 images of apple orchards and 5625 images of vineyards. DJI Phantom 4 Multispectral drone, equipped with five spectral bands (Blue, Green, Red, Red Edge, and Near Infrared), was utilized to capture both spectral richness and temporal progression. This study introduces a novel deep learning architecture developed specifically for time series-based disease detection and segmentation using multispectral drone imagery. Changes in plants over time provide important information about the occurrence of plant diseases. For this reason, time series were used in this study to extract features from the changes in plants over time. The proposed model architecture was specifically designed to leverage time series information, enabling robust tracking of crop health changes over time. The model trained with the dataset collected for apple diseases achieved an average Intersection Over Unit (IoU) value of 82.05%, while the model trained with the dataset collected for vineyard diseases reached an IoU value of 79.67%. The findings highlight the effectiveness of integrating drone-acquired multispectral time-series data with advanced deep learning models for scalable, accurate, and timely plant disease detection in precision agriculture.","农业病害是种植者面临的重大问题，会对果实和叶片造成严重损害，导致产量损失。因此，开发植物病害早期检测系统是一个至关重要的问题。本研究提出了一种基于深度学习的新型混合模型，用于植物病害的检测与分割，具体针对苹果园中的苹果黑星病和葡萄园中的霜霉病。该早期病害检测系统的开发使用了2023年5月至2024年12月期间通过无人机在土耳其泰基尔达省农业区域采集的多光谱影像数据。数据集包含3625幅苹果园图像和5625幅葡萄园图像。所用DJI Phantom 4多光谱无人机配备五个光谱波段（蓝、绿、红、红边和近红外），用于捕捉光谱丰富度和时间变化过程。本研究提出了一种专门开发的深度学习架构，用于基于时间序列的多光谱无人机影像病害检测与分割。植物随时间的变化提供了关于植物病害发生的重要信息。因此，本研究使用时间序列从植物随时间的变化中提取特征。所提出的模型架构专门设计以利用时间序列信息，从而能够稳健地跟踪作物健康状况随时间的变化。使用苹果病害数据集训练的模型达到了82.05%的平均交并比（IoU）值，而使用葡萄园病害数据集训练的模型达到了79.67%的IoU值。研究结果凸显了将无人机获取的多光谱时间序列数据与先进深度学习模型相结合，在精准农业中实现可扩展、准确且及时的植物病害检测方面的有效性。","Tarım Bilimleri Dergisi","2026-10-12T00:00:00Z",{"impact":92,"substance":251,"depth":94,"authority":95,"freshness":180,"relevant":20,"comment":252},21,"该研究提出基于多光谱时序影像的新型深度学习模型，实现果园与葡萄园病害早期检测，数据规模大、方法新颖，对精准农业病害预警具有参考价值。",[254],{"name":248,"url":245},[25,100,256,27,257],"农业人工智能","病害预警",{"code":203,"slug":259,"name":260,"path":261,"parent_code":262},"fruit","果树","\u002Ftopic\u002Fhorticulture\u002Ffruit","B",[264,268],{"code":126,"slug":265,"name":266,"path":267,"parent_code":35},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"status":38,"locked":14,"version":39,"method":40,"evidence":270},{"candidates":271,"agricultural_evidence":46},[272,279,286,290],{"code":203,"score":179,"supported":46,"title":273,"abstract":275,"tags":278},[274],"apple",[276,277,274],"苹果","葡萄",[],{"code":126,"score":280,"supported":46,"title":281,"abstract":283,"tags":285},15,[282],"deep learning",[284,282],"深度学习",[256],{"code":31,"score":178,"supported":46,"title":287,"abstract":288,"tags":289},[194],[194],[27],{"code":44,"score":19,"supported":46,"title":291,"abstract":292,"tags":295},[],[293,294],"精准农业","precision agriculture",[25],[297,298],"苹果黑星病 无人机 多光谱","葡萄园 霜霉病 深度学习","苹果黑星病无人机多光谱-4808","10.15832\u002Fankutbd.1898342",{"doi":300,"openalex_id":302,"authors":303,"venue":248,"cited_by_count":140,"oa_url":315,"card":316,"direction":321,"ingested_from":166},"W7221558726",[304,307,310,312],{"name":305,"orcid":306},"Batuhan Aşıroğlu","https:\u002F\u002Forcid.org\u002F0000-0003-0767-6348",{"name":308,"orcid":309},"Aydın Kağan Turkoglu","https:\u002F\u002Forcid.org\u002F0009-0001-8383-8807",{"name":311,"orcid":8},"Fatih Sinan Bir",{"name":313,"orcid":314},"Sibel Senan","https:\u002F\u002Forcid.org\u002F0000-0001-6773-0428","https:\u002F\u002Fdergipark.org.tr\u002Fen\u002Fdownload\u002Farticle-file\u002F5761152",{"tldr":317,"method":318,"finding":319,"direction":164,"opportunity":320},"提出一种基于无人机多光谱时序影像的深度学习混合模型，实现苹果黑星病和葡萄霉病的早期检测与分割。","DJI Phantom 4多光谱无人机采集时序影像，构建时序深度学习分割模型。","苹果病IoU达82.05%，葡萄病达79.67%，验证多光谱时序数据有效性。","可探索多作物、多病害的时序多光谱通用模型，并融合气象与地面数据提升早期预警能力。","智慧农业 \u002F 农业物联网","2026-10-13T23:30:10.242467Z",{"id":324,"title":325,"url":326,"summary":327,"summary_zh":8,"content":328,"source_name":329,"source_url":8,"published_at":330,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":331,"score_detail":332,"sources":335,"tags":337,"primary_topic":341,"secondary_topics":342,"classification":343,"search_phrases":360,"slug":363,"view_count":57,"doi":8,"paper":8,"created_at":364},4612,"国家级改革试验任务,为何选中了苏州高新区的作物云?","http:\u002F\u002Fwww.snd.gov.cn\u002Fhqqrmzf\u002Fzwxw\u002F202610\u002F89525c03b91346fc86441fa304fcf2d4.shtml","农业农村部、国家发展改革委等10部委批复2026年全国农村改革试验区拓展试验任务,苏州市申报的探索应用作物云数智管理技术精准服务粮食生产成功入选。该平台用1部手机、2张照片、3类信息,围绕适期播栽、适情管理、适熟估产、适时收获四个环节提供精准调度;2025年稻麦季面向苏州8个涉农县区累计发布农情简报96期,服务指导农户4.1万户次。核查准确度接近100%,惠农补贴发放、农技指导环节实现升级。","陆洲介绍，在惠农补贴发放环节，系统能够精准识别作物种类并核查面积，核查准确度接近100%，有效防范虚报造假。在农技指导环节，“作物云”平台依托“AI+遥感+气象数据”，开展稻麦全生命周期观测与预测，为农户提供“一田一策”个性化种植方案。此外，平台联合农业保险机构，实现作物“精准承保、精准理赔”，从源头构建可信、可溯的数据底座，使每一亩地都有清晰的身份画像；构建“天空地”一体化查勘定损体系，实现灾害应对的快速响应、精准核损。","苏州高新区管委会 2026-10-09","2026-10-09T00:00:00Z",75,{"impact":93,"substance":333,"depth":92,"authority":180,"freshness":17,"relevant":20,"comment":334},20,"国家级农村改革试验区落地案例，作物云在补贴核查、农技指导与保险理赔上给出可量化成效，具备行业示范价值。",[336],{"name":329,"url":326},[25,338,27,339,340],"农业保险","农村改革试验区","作物云",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":14,"version":39,"method":40,"evidence":344},{"candidates":345,"agricultural_evidence":46},[346,351,356],{"code":31,"score":45,"supported":46,"title":347,"abstract":348,"tags":350},[],[349],"估产",[27],{"code":352,"score":20,"supported":14,"title":353,"abstract":354,"tags":355},"G3",[],[],[338],{"code":44,"score":20,"supported":14,"title":357,"abstract":358,"tags":359},[],[],[25],[361,362],"苏州高新区 作物云","作物云 精准承保 遥感","苏州高新区作物云-4612","2026-10-11T00:09:35.550412Z",{"id":366,"title":367,"url":368,"summary":369,"summary_zh":370,"content":8,"source_name":371,"source_url":368,"published_at":372,"category":89,"cover_url":8,"hotness":13,"is_selected":14,"score":373,"score_detail":374,"sources":378,"tags":380,"primary_topic":383,"secondary_topics":384,"classification":392,"search_phrases":439,"slug":442,"view_count":443,"doi":444,"paper":445,"created_at":463},4575,"A review of remote sensing for agricultural drought: technologies, indices, modelling advances and future prospects","https:\u002F\u002Fdoi.org\u002F10.1080\u002F15481603.2026.2738981","Agricultural drought is a complex hazard that jeopardises food security and progress toward the Sustainable Development Goals. We systematically reviewed peer-reviewed English-language literature published between 2015 and 2025, focusing on Remote Sensing (RS)-driven agricultural drought monitoring and prediction. Eligible studies were identified from the Web of Science and Scopus databases (last searched in August 2025); review articles, duplicates, and irrelevant studies were excluded, resulting in 181 articles. This review critically examined the evolution of sensors, drought indices, modelling approaches, and emerging technologies used to assess agricultural drought across diverse agro-ecological regions. Specifically, we (1) systematically evaluated the use of optical, thermal, and microwave RS platforms, along with satellite-based, model-based, and reanalysis products for agricultural drought monitoring; (2) reviewed widely used RS-based drought indices, including single indices grouped into nine categories, as well as composite indices; (3) reviewed software or programming languages applied; (4) assessed the progression of modelling approaches from traditional statistical and time-series methods to machine learning (ML) and deep learning (DL) frameworks; and (5) examined validation strategies applied to agricultural drought assessment. The analysis reveals a growing research interest in this topic, with a strong geographic concentration in Asia, particularly China. Optical and thermal platforms (e.g. MODIS and Landsat) dominate the literature (~54%) due to their accessibility, followed by satellite-derived precipitation products (17%), while microwave soil-moisture missions remain underutilized (~7%). Regarding RS-based indices, most studies employed more than one index: 44% analysed multiple individual indices, 51% used composite indices (either alone or in combination with individual indices), and only 5% relied on a single index. Vegetation indices, such as NDVI, remain workhorses; however, their sensitivity to soil background effects and canopy saturation has driven increased adoption of thermal composites (e.g. VHI), as well as adaptive weighting schemes and principal component analysis-based approaches. Moreover, computational tools used in drought research can be broadly grouped into geospatial and RS platforms for large-scale data processing and analysis (e.g. QGIS, GEE), and general-purpose programming languages (e.g. R, Python) for model development and advanced analytics. Regarding the methodology, statistical and time-series approaches account for 64% of the reviewed studies, followed by ML models (20%) and DL methods (15%), while explainable artificial intelligence (XAI) remains nascent. Techniques, such as random forests, support vector machines, and CNN and LSTM architectures, generally outperform traditional models but require large training datasets and raise concerns related to interpretability and ethics. In terms of validation, hydro-climatic indices such as SPI and SPEI are most commonly used (32%), followed by crop yield and yield anomaly data (19%). This review further identifies key research gaps across sensors, indices, and modelling approaches and proposes a roadmap for developing equitable, interpretable, and resilient agricultural drought monitoring systems. Emerging opportunities include context-aware and interpretable AI, multi-sensor and multi-scale data fusion across optical, thermal, and microwave domains, integration of physiologically meaningful indicators such as sun-induced chlorophyll fluorescence (SIF), robust uncertainty quantification, and the development of hybrid and physics-informed modelling frameworks.","农业干旱是一种复杂的灾害，威胁粮食安全和可持续发展目标的实现。我们系统综述了2015年至2025年间发表的同行评议英文文献，聚焦于遥感（RS）驱动的农业干旱监测与预测。符合条件的研究通过Web of Science和Scopus数据库检索确定（最后检索时间为2025年8月）；综述文章、重复文献及不相关研究被排除，最终纳入181篇文献。本综述批判性地审视了用于评估不同农业生态区农业干旱的传感器、干旱指数、建模方法及新兴技术的演变。具体而言，我们（1）系统评估了光学、热红外和微波遥感平台，以及基于卫星、基于模型和再分析产品在农业干旱监测中的应用；（2）综述了广泛使用的基于遥感的干旱指数，包括归为九类的单一指数以及复合指数；（3）综述了所应用的软件或编程语言；（4）评估了建模方法从传统统计和时间序列方法向机器学习（ML）和深度学习（DL）框架的演进；（5）考察了应用于农业干旱评估的验证策略。分析显示，该主题的研究兴趣日益增长，地理上高度集中于亚洲，尤其是中国。光学和热红外平台（如MODIS和Landsat）因其可获取性在文献中占主导地位（约54%），其次是卫星降水产品（17%），而微波土壤水分任务仍未得到充分利用（约7%）。在基于遥感的指数方面，大多数研究采用了不止一种指数：44%分析了多个单一指数，51%使用了复合指数（单独使用或与单一指数结合使用），仅5%依赖单一指数。植被指数（如NDVI）仍是主力工具；然而，其对土壤背景效应和冠层饱和的敏感性推动了热红外复合指数（如VHI）以及自适应权重方案和基于主成分分析的方法得到更多采用。此外，干旱研究中使用的计算工具可大致分为用于大规模数据处理和分析的地理空间与遥感平台（如QGIS、GEE），以及用于模型开发的通用编程语言（如R、Python）。","GIScience & Remote Sensing","2026-10-08T00:00:00Z",81,{"impact":94,"substance":93,"depth":375,"authority":376,"freshness":17,"relevant":20,"comment":377},19,14,"系统综述181篇文献，梳理遥感干旱监测的传感器、指数与建模进展，方法学价值高，但属学术综述，产业落地影响有限。",[379],{"name":371,"url":368},[25,381,129,27,382],"粮食安全","农业干旱",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[385,391],{"code":386,"slug":387,"name":388,"path":389,"parent_code":390},"H7","climate","气候适应与防灾减灾","\u002Ftopic\u002Fenvironment\u002Fclimate","H",{"code":126,"slug":265,"name":266,"path":267,"parent_code":35},{"status":38,"locked":14,"version":39,"method":40,"evidence":393},{"candidates":394,"agricultural_evidence":46},[395,399,405,410,416,423,429,435],{"code":31,"score":280,"supported":46,"title":396,"abstract":397,"tags":398},[122],[53,122],[27],{"code":386,"score":376,"supported":46,"title":400,"abstract":402,"tags":404},[401],"drought",[403,401],"干旱",[],{"code":126,"score":13,"supported":46,"title":406,"abstract":407,"tags":409},[],[284,129,130,282,408],"artificial intelligence",[129],{"code":411,"score":19,"supported":46,"title":412,"abstract":413,"tags":415},"A8",[],[381,414],"food security",[381],{"code":417,"score":18,"supported":46,"title":418,"abstract":419,"tags":422},"H2",[],[420,421],"土壤","soil",[],{"code":424,"score":57,"supported":46,"title":425,"abstract":426,"tags":428},"D",[],[427],"水产",[],{"code":430,"score":57,"supported":46,"title":431,"abstract":432,"tags":434},"H6",[],[433],"农业生态",[],{"code":44,"score":20,"supported":14,"title":436,"abstract":437,"tags":438},[],[],[25],[440,441],"遥感 农业干旱 监测","GIScience Remote Sensing 干旱指数","遥感农业干旱监测-4575",2,"10.1080\u002F15481603.2026.2738981",{"doi":444,"openalex_id":446,"authors":447,"venue":371,"cited_by_count":140,"oa_url":457,"card":458,"direction":321,"ingested_from":166},"W7221081979",[448,451,454],{"name":449,"orcid":450},"Fatemeh Saba","https:\u002F\u002Forcid.org\u002F0000-0001-6171-155X",{"name":452,"orcid":453},"Nima Ahmadian","https:\u002F\u002Forcid.org\u002F0000-0003-3676-1840",{"name":455,"orcid":456},"Olena Dubovyk","https:\u002F\u002Forcid.org\u002F0000-0002-7338-3167","https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Fpdf\u002F10.1080\u002F15481603.2026.2738981?needAccess=true",{"tldr":459,"method":460,"finding":461,"direction":164,"opportunity":462},"系统综述2015-2025年遥感农业干旱监测与预测的传感器、指数、建模及验证进展。","基于Web of Science与Scopus的181篇文献系统综述，涵盖光学\u002F","光学热红外平台占主导，微波土壤水分利用不足；复合指数与机器学习建模成为趋势。","微波土壤水分数据融合与深度学习干旱预测模型在数据稀缺区验证是潜在研究空白。","2026-10-10T23:30:14.933078Z",{"id":465,"title":466,"url":467,"summary":468,"summary_zh":469,"content":8,"source_name":470,"source_url":467,"published_at":471,"category":89,"cover_url":8,"hotness":13,"is_selected":14,"score":472,"score_detail":473,"sources":475,"tags":477,"primary_topic":481,"secondary_topics":482,"classification":486,"search_phrases":501,"slug":504,"view_count":443,"doi":505,"paper":506,"created_at":520},4365,"An Index-Based Algorithm for Detecting Water Soil Erosion Indicators from Sentinel-2 Multispectral Data and Its Verification on Field Data of Rostov Oblast and Krasnodar Krai","https:\u002F\u002Fdoi.org\u002F10.23947\u002F2587-8999-2026-10-3-49-57","Introduction . The paper presents the development and testing of an index-based algorithm for detecting indicators of soil erosion by water from Sentinel-2 remote sensing data, considered as the first practical stage in constructing a hybrid physics-based mass-transport model with neural-network parameter identification. Materials and Methods . The algorithm relies on joint analysis of time series of the Normalized Difference Vegetation Index (NDVI) and the Bare Soil Index (BSI), followed by spatial change detection (ΔBSI) with threshold filtering at the 90th percentile. The algorithm was first validated on synthetic data and then applied to real Sentinel-2 imagery for two test sites – the Kamensky District of Rostov Oblast and the vicinity of Moldovanskoye village, Krymsky District, Krasnodar Krai – covering 10 dates within 2024. Results. The algorithm is shown to consistently identify spatially localised zones of increasing bare-soil exposure. Discussion . A key limitation – the inability to distinguish erosion-related exposure from ordinary agrotechnical bare soil — is discussed, along with directions for resolving it (digital elevation model overlay, multi-year analysis). Conclusion . An index-based algorithm for detecting indicators of water-induced soil erosion from Sentinel-2 multispectral time series was developed and validated. Verification on synthetic data and application to two real test areas in southern Russia confirmed its operability while demonstrating the need to separate erosion-related changes from agricultural soil exposure in subsequent model development.","引言。本文介绍了一种基于指数的算法开发与测试，该算法用于从Sentinel-2遥感数据中检测水蚀土壤侵蚀指标，被视为构建基于物理的质量输运混合模型并结合神经网络参数辨识的第一个实践阶段。材料与方法。该算法依赖于对归一化植被指数（NDVI）和裸土指数（BSI）时间序列的联合分析，随后进行空间变化检测（ΔBSI），并在第90百分位数处进行阈值滤波。该算法首先在合成数据上进行了验证，然后应用于两个测试点的真实Sentinel-2影像——罗斯托夫州卡缅斯基区和克拉斯诺达尔边疆区克里姆斯克区摩尔多瓦诺夫斯科耶村附近——覆盖2024年内的10个日期。结果。结果表明，该算法能够一致地识别出裸土暴露增加的空间局部区域。讨论。讨论了关键局限性——无法区分与侵蚀相关的裸土暴露和普通农技作业造成的裸土——以及解决该问题的方向（叠加数字高程模型、多年分析）。结论。开发并验证了一种基于指数的算法，用于从Sentinel-2多光谱时间序列中检测水蚀土壤侵蚀指标。在合成数据上的验证以及在俄罗斯南部两个真实测试区域的应用证实了其可操作性，同时表明在后续模型开发中有必要将与侵蚀相关的变化与农业裸土暴露区分开来。","COMPUTATIONAL MATHEMATICS AND INFORMATION TECHNOLOGIES","2026-10-05T00:00:00Z",70,{"impact":178,"substance":333,"depth":179,"authority":95,"freshness":17,"relevant":20,"comment":474},"提出基于NDVI与BSI时序的土壤水蚀指标遥感识别算法，并在俄罗斯南部两个试验区验证，方法有新意但属区域尺度研究，对国内农业遥感监测有参考价值。",[476],{"name":470,"url":467},[25,478,479,27,480],"Sentinel-2","NDVI","土壤侵蚀",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[483],{"code":417,"slug":421,"name":484,"path":485,"parent_code":390},"土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil",{"status":38,"locked":14,"version":39,"method":40,"evidence":487},{"candidates":488,"agricultural_evidence":46},[489,493,497],{"code":31,"score":333,"supported":46,"title":490,"abstract":491,"tags":492},[194],[53,122,194],[479,478,27],{"code":417,"score":376,"supported":46,"title":494,"abstract":495,"tags":496},[421],[420,421],[],{"code":44,"score":20,"supported":14,"title":498,"abstract":499,"tags":500},[],[],[25],[502,503],"Sentinel-2 土壤侵蚀 遥感","罗斯托夫州 克拉斯诺达尔 土壤侵蚀","Sentinel-2土壤侵蚀遥感-4365","10.23947\u002F2587-8999-2026-10-3-49-57",{"doi":505,"openalex_id":507,"authors":508,"venue":470,"cited_by_count":140,"oa_url":467,"card":515,"direction":164,"ingested_from":166},"W7220651513",[509,512],{"name":510,"orcid":511},"V. A. Blagin","https:\u002F\u002Forcid.org\u002F0009-0003-3239-6150",{"name":513,"orcid":514},"V. A. Beraia","https:\u002F\u002Forcid.org\u002F0009-0006-2270-5011",{"tldr":516,"method":517,"finding":518,"direction":164,"opportunity":519},"开发基于Sentinel-2时序NDVI与BSI指数的水土流失指标检测算法，并在俄罗斯南部实地验证。","联合NDVI与BSI时序，用ΔBSI阈值（90百分位）检测裸土变化，合成与真实数","算法能稳定识别裸土暴露增加区域，但无法区分侵蚀与农事裸土，需DEM和多年度分析。","可融合DEM与多年度时序，构建区分侵蚀与农事裸土的分类模型，并接入神经网络参数识别。","2026-10-07T23:30:29.080156Z"]