[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-713":3,"related-713":51},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":8,"source_name":9,"source_url":8,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":15,"sources":22,"tags":24,"primary_topic":8,"secondary_topics":30,"classification":31,"search_phrases":45,"slug":48,"view_count":49,"doi":8,"paper":8,"created_at":50},713,"防灾减灾救灾,离不开正确政绩观(农民日报评论员文章)","https:\u002F\u002Fszb.farmer.com.cn\u002Fnmrb\u002Fhtml\u002F2026\u002F20260820\u002F20260820_1\u002Fnmrb_20260820_13382_1_2090185812226445331.html","农民日报8月20日要闻1版评论员文章解读《求是》杂志8月19日发表的习近平总书记重要文章《提高防灾减灾救灾能力》:做好防灾减灾救灾工作需要树立和践行正确政绩观。当前汛期未结束、防汛形势依然严峻,极端天气频发易发对'三农'工作提出持久战要求。文章呼吁十防九空的'白工'恰是检验干部政绩观最直观标尺,强调清淤疏浚田间沟渠、检修排灌设施、普及避险常识等基础工作必须常抓不懈。",null,"农民日报全媒体评论员 2026-08-20","2026-08-20T00:00:00Z","报道",10,true,88,{"impact":16,"substance":17,"depth":18,"authority":19,"freshness":12,"relevant":20,"comment":21},25,20,18,15,1,"央媒评论员文章，结合总书记重要论述，对防灾减灾与政绩观关系进行深度剖析，对三农工作有指导意义。",[23],{"name":9,"url":6},[25,26,27,28,29],"防灾减灾","正确政绩观","求是","习近平总书记","农民日报评论员",[],{"status":32,"locked":33,"version":34,"method":35,"evidence":36},"needs_review",false,"2026-10-22.2","rules",{"candidates":37,"agricultural_evidence":33,"reason":44},[38],{"code":39,"score":40,"supported":13,"title":41,"abstract":42,"tags":43},"H7",12,[25],[25],[25],"农业相关性需要复核",[46,47],"农民日报评论员 习近平总书记 正确政绩观 防灾减灾","农民日报评论员 习近平总书记","农民日报评论员习近平总书记正确政绩观防灾减灾-713",7,"2026-08-19T23:57:26.144331Z",{"total":52,"page":20,"page_size":52,"items":53},6,[54,133,195,284,350,403],{"id":55,"title":56,"url":57,"summary":58,"summary_zh":59,"content":8,"source_name":60,"source_url":57,"published_at":61,"category":62,"cover_url":8,"hotness":12,"is_selected":33,"score":63,"score_detail":64,"sources":66,"tags":68,"primary_topic":72,"secondary_topics":78,"classification":89,"search_phrases":113,"slug":116,"view_count":63,"doi":117,"paper":118,"created_at":132},5326,"Flood Hazard and Vulnerability Assessment of Chitrakoot District, Uttar Pradesh: An Integrated Geographical, GIS and Remote Sensing Approach","https:\u002F\u002Fdoi.org\u002F10.36948\u002Fijfmr.2026.v08i05.89708","Flood is one of the most important hydro-meteorological hazards affecting human settlements, agriculture, infrastructure and regional economies. Chitrakoot district of Uttar Pradesh presents a distinctive case of hydro-climatic vulnerability because it belongs to the drought-prone Bundelkhand region but simultaneously experiences recurrent riverine and flash-flood conditions during intense monsoon rainfall. The present study assesses the spatial characteristics and determinants of flood hazard and vulnerability in Chitrakoot district using an integrated geographical, GIS and remote sensing approach. The analysis incorporates the Digital Elevation Model (DEM), drainage network, physiography, river proximity, historical flood information, satellite-based flood observations and socio-economic exposure. The district's DEM indicates a marked elevation gradient, approximately from 66 m to 451 m, with relatively higher terrain in the southern part and lower terrain towards the northern Yamuna valley. This topographic configuration facilitates rapid surface runoff from elevated southern terrain towards comparatively low-lying riverine areas. The drainage system is dominated by the Yamuna and Mandakini\u002FPaisuni systems along with Baghain, Gunta, Bardaha and smaller tributaries. The Uttar Pradesh Flood Hazard Atlas identifies 5,114 ha of flood-hazard area in Chitrakoot for 1998–2020, of which 4,129 ha (81%) falls in the very-low hazard category and 985 ha (19%) in the low-hazard category. However, the historical classification does not fully represent the potential consequences of extreme rainfall events. The August 2026 flood provides compelling evidence: the Mandakini at Chitrakoot reached a reported new high flood level of 145.60 m on 29 August 2026, approximately 2.95 m above the previous reported high level, while the water level rose by about 7.5 m within six hours. The study concludes that flood risk in Chitrakoot is spatially concentrated around river corridors, low-elevation areas, floodplains, agricultural land, settlements and tourism infrastructure. A shift from conventional relief-oriented flood management towards integrated floodplain regulation, watershed management, GIS-based risk zonation, real-time monitoring and community-based preparedness is therefore essential.","洪水是影响人类住区、农业、基础设施和区域经济的最重要的水文气象灾害之一。北方邦吉德古德（Chitrakoot）县在水文气候脆弱性方面呈现出独特案例，因为它属于易受干旱影响的本德尔坎德（Bundelkhand）地区，但同时在强季风降雨期间反复遭遇河流洪水和山洪状况。本研究采用地理学、地理信息系统（GIS）和遥感相结合的综合方法，评估吉德古德县洪水灾害与脆弱性的空间特征及其决定因素。分析纳入了数字高程模型（DEM）、河网、地貌、距河流远近、历史洪水信息、基于卫星的洪水观测以及社会经济暴露度。该县的DEM显示出明显的高程梯度，大约从66米到451米，南部地形相对较高，向北部的亚穆纳（Yamuna）河谷地势降低。这种地形格局促使地表径流从较高的南部地形快速流向相对低洼的河流区域。排水系统以亚穆纳河和曼达基尼\u002F派苏尼（Mandakini\u002FPaisuni）水系为主，另有巴盖恩（Baghain）、贡塔（Gunta）、巴尔达哈（Bardaha）及较小支流。北方邦洪水灾害图集确认，1998—2020年吉德古德县洪水灾害面积为5，114公顷，其中4，129公顷（81%）属于极低灾害类别，985公顷（19%）属于低灾害类别。然而，历史分类并不能充分反映极端降雨事件的潜在后果。2026年8月的洪水提供了有力证据：据报道，2026年8月29日吉德古德的曼达基尼河达到145.60米的新高洪水位，比此前报告的高水位高出约2.95米，而水位在六小时内上升了约7.5米。研究得出结论，吉德古德的洪水风险在空间上集中于河流廊道、低海拔地区、洪泛平原、农业用地、住区和旅游基础设施周围。因此，必须从传统的以救济为导向的洪水管理转向洪泛平原综合调控、流域管理、基于GIS的风险区划、实时监测和社区为基础的备灾。","International Journal For Multidisciplinary Research","2026-10-17T00:00:00Z","论文",0,{"impact":63,"substance":63,"depth":63,"authority":63,"freshness":63,"relevant":63,"comment":65},"该研究聚焦印度北方邦的洪水灾害评估，虽涉及GIS与遥感方法，但与三农、农业信息化、智慧农业等主题无直接关联，不建议进入每日精选。",[67],{"name":60,"url":57},[25,69,70,71],"遥感监测","洪水风险评估","GIS应用",{"code":73,"slug":74,"name":75,"path":76,"parent_code":77},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",[79,84],{"code":80,"slug":81,"name":82,"path":83,"parent_code":77},"I4","gis","GIS与空间分析","\u002Ftopic\u002Fdigital-agriculture\u002Fgis",{"code":39,"slug":85,"name":86,"path":87,"parent_code":88},"climate","气候适应与防灾减灾","\u002Ftopic\u002Fenvironment\u002Fclimate","H",{"status":90,"locked":33,"version":34,"method":35,"evidence":91},"classified",{"candidates":92,"agricultural_evidence":13},[93,99,106],{"code":73,"score":19,"supported":13,"title":94,"abstract":96,"tags":98},[95],"remote sensing",[97,95],"遥感",[69],{"code":80,"score":100,"supported":13,"title":101,"abstract":103,"tags":105},14,[102],"GIS",[104,102],"地理信息",[],{"code":39,"score":107,"supported":13,"title":108,"abstract":109,"tags":112},8,[],[110,111],"干旱","drought",[70,25],[114,115],"Chitrakoot 洪水风险 GIS","Yamuna 洪水脆弱性 遥感","Chitrakoot洪水风险GIS-5326","10.36948\u002Fijfmr.2026.v08i05.89708",{"doi":117,"openalex_id":119,"authors":120,"venue":60,"cited_by_count":63,"oa_url":124,"card":125,"direction":129,"ingested_from":131},"W7222885988",[121],{"name":122,"orcid":123},"Birendra Yadav","https:\u002F\u002Forcid.org\u002F0009-0007-0864-474X","https:\u002F\u002Fwww.ijfmr.com\u002Fpapers\u002F2026\u002F5\u002F89708.pdf",{"tldr":126,"method":127,"finding":128,"direction":129,"opportunity":130},"用GIS与遥感综合评估Chitrakoot区洪水灾害与脆弱性空间分布。","DEM、河网、历史洪水与卫星观测及社会经济数据叠加分析。","洪水风险集中于河谷低地、农田与居民点，历史分级低估极端降雨风险。","农业遥感与作物表型","可结合时序遥感与水文模型，构建极端降雨情景下的农田洪涝风险动态制图与预警。","openalex","2026-10-19T23:30:24.356743Z",{"id":134,"title":135,"url":136,"summary":137,"summary_zh":8,"content":138,"source_name":139,"source_url":8,"published_at":140,"category":141,"cover_url":8,"hotness":12,"is_selected":13,"score":142,"score_detail":143,"sources":149,"tags":151,"primary_topic":156,"secondary_topics":157,"classification":158,"search_phrases":190,"slug":193,"view_count":20,"doi":8,"paper":8,"created_at":194},5250,"全国秋粮收获过七成 农业农村部部署应对最强厄尔尼诺","https:\u002F\u002Fwww.toutiao.com\u002Farticle\u002F7697848015725298214","据农业农村部10月17日农情调度,全国秋粮收获过七成(东北过六成、黄淮海和西南过八成、西北近八成、长江中下游过六成、华南过三成),冬小麦播种过一成、冬油菜过三成;针对赤道中东太平洋已发生的超强东部型厄尔尼诺,部印发防范预案部署\"秋防秋汛防旺长、冬防冻害和雨雪冰冻、春抗倒春寒干旱低温春涝、夏防干热风烂场雨洪涝台风高温\"四季防灾重点。","## 全国秋粮收获过七成 农业相关部门部署应对超强厄尔尼诺保障来年粮食生产\n\n2026-10-18 11:42·[央广网](https:\u002F\u002Fwww.toutiao.com\u002Fc\u002Fuser\u002Ftoken\u002FMS4wLjABAAAAiR6RuL6xARCa1a88UYsGDkFIn-3CItRPyJJaR4Ym4C8\u002F?source=tuwen_detail)\n\n央广网北京10月18日消息（记者朱敏 孙鲁晋）据中央广播电视总台中国之声《新闻和报纸摘要》报道，农业农村部最新农情调度显示，全国秋粮收获已过七成，冬小麦播种超一成，冬油菜播种过三成。农业农村部近日制定印发防范应对超强厄尔尼诺夺取粮食和农业丰收相关预案，各地部署应对超强厄尔尼诺有关措施，保障来年粮食生产。\n\n根据国家气候中心的监测，目前，赤道中东太平洋已经发生了一次超强的东部型厄尔尼诺事件。预计未来3个月，赤道中东太平洋海表温度将继续升高，在秋末冬初达到峰值，此次厄尔尼诺事件将成为有系统性监测以来最强厄尔尼诺事件，可能对农业生产带来风险挑战。\n\n中国农业科学院农业环境与可持续发展研究所研究员刘恩科：需重点警惕北方阶段性干旱、南方洪涝、冬春冷暖交替以及台风等多重风险叠加，相关风险可能从今年秋种持续传导至明年春耕和夏季生产。\n\n据农业农村部最新农情调度，当前秋粮收获东北过六成、黄淮海、西南过八成；西北近八成；长江中下游过六成；华南过三成。\n\n面对本轮超强厄尔尼诺，农业农村部明确今年秋季重点是防秋汛、防旺长，冬季防冻害和雨雪冰冻；明年春季抗“倒春寒”、抗干旱、抗低温春涝，夏季防“干热风”、“烂场雨”、洪涝、台风、高温等灾害。\n\n刘恩科：我国农业气象监测预警和防灾减灾体系不断完善，并且我国已建成10亿亩以上的高标准农田，国家长期的夏粮一喷三防、秋粮抗逆防灾政策，为我国农业生产争取了防灾减灾的主动权。\n\n**更多精彩资讯请在应用市场下载“央广网”客户端。欢迎提供新闻线索，24小时报料热线400-800-0088；消费者也可通过央广网“啄木鸟消费者投诉平台”线上投诉。版权声明：本文章版权归属央广网所有，未经授权不得转载。转载请联系：cnrbanquan@cnr.cn，不尊重原创的行为我们将追究责任。**","央广网(2026-10-18)","2026-10-18T00:00:00Z","政策",91,{"impact":144,"substance":145,"depth":146,"authority":19,"freshness":147,"relevant":20,"comment":148},28,22,17,9,"全国性农情数据与部委防灾预案同步发布，信息增量足、权威性强，值得进入每日精选。",[150],{"name":139,"url":136},[152,25,153,154,155],"粮食安全","厄尔尼诺","秋冬种","秋粮收获",{"code":39,"slug":85,"name":86,"path":87,"parent_code":88},[],{"status":90,"locked":33,"version":34,"method":35,"evidence":159},{"candidates":160,"agricultural_evidence":13},[161,166,173,179,185],{"code":39,"score":49,"supported":13,"title":162,"abstract":163,"tags":165},[],[110,164],"洪涝",[25],{"code":167,"score":168,"supported":13,"title":169,"abstract":170,"tags":172},"A2",3,[],[171],"小麦",[],{"code":174,"score":168,"supported":13,"title":175,"abstract":176,"tags":178},"A4",[],[177],"油菜",[],{"code":180,"score":181,"supported":33,"title":182,"abstract":183,"tags":184},"J4",2,[],[],[154,155],{"code":186,"score":20,"supported":33,"title":187,"abstract":188,"tags":189},"A8",[],[],[152],[191,192],"农业农村部 超强厄尔尼诺 预案","秋粮收获 冬小麦播种 农情调度","农业农村部超强厄尔尼诺预案-5250","2026-10-19T00:07:31.036094Z",{"id":196,"title":197,"url":198,"summary":199,"summary_zh":200,"content":8,"source_name":201,"source_url":198,"published_at":202,"category":62,"cover_url":8,"hotness":12,"is_selected":33,"score":203,"score_detail":204,"sources":207,"tags":209,"primary_topic":214,"secondary_topics":219,"classification":220,"search_phrases":257,"slug":260,"view_count":63,"doi":261,"paper":262,"created_at":283},4985,"Hybrid deep ensemble learning for crop disease prediction and climate-resilient disaster management in smart agriculture","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs10791-026-10579-y","Abstract Accurate crop disease prediction and climate-resilient disaster management are essential for improving agricultural productivity and ensuring food security under increasingly dynamic environmental conditions. Existing deep learning approaches typically perform crop disease detection and climate forecasting independently and often rely on deterministic CNN–LSTM architectures without effective multimodal feature fusion, predictive uncertainty estimation, or comprehensive statistical validation. Consequently, their ability to provide reliable decision support under changing climatic conditions remains limited. To address these challenges, this paper proposes a novel hybrid deep ensemble learning framework for integrated crop disease prediction and climate-resilient disaster management in smart agriculture. The proposed framework combines convolutional neural networks (CNNs) for spatial crop image feature extraction with long short-term memory (LSTM) networks for temporal climate forecasting. An attention-based multimodal feature fusion mechanism is employed to integrate heterogeneous crop and climate information, while Bayesian uncertainty estimation and deep ensemble learning are incorporated to improve prediction reliability, robustness, and confidence-aware decision support. Experimental evaluation is performed using multimodal datasets comprising crop images and climate observations collected from the PlantVillage, NOAA, and NASA EOS datasets. The dataset is divided into training, validation, and testing subsets using a 70:15:15 ratio. The proposed framework is evaluated using classification and regression metrics, including Accuracy, Precision, Recall, F1-score, RMSE, MAE, MAPE, and AUC-ROC. To ensure reproducibility, all experiments are repeated five times using different random seeds, and the results are reported with mean $$\\pm$$ standard deviation, 95% confidence intervals, and paired Student’s $$t$$ -tests. Experimental results demonstrate that the proposed framework consistently outperforms conventional CNN, LSTM, and CNN–LSTM hybrid models by achieving higher classification accuracy, lower climate forecasting error, improved robustness under varying climate conditions, and statistically significant performance improvements. The proposed framework provides a reliable, scalable, and uncertainty-aware solution for intelligent climate-resilient smart agriculture and early agricultural disaster management.","摘要：准确的作物病害预测和气候适应性灾害管理对于在日益动态的环境条件下提高农业生产力和保障粮食安全至关重要。现有深度学习方法通常独立执行作物病害检测和气候预测，且往往依赖确定性CNN–LSTM架构，缺乏有效的多模态特征融合、预测不确定性估计或全面的统计验证。因此，其在气候变化条件下提供可靠决策支持的能力仍然有限。为应对这些挑战，本文提出了一种新颖的混合深度集成学习框架，用于智慧农业中的作物病害预测与气候适应性灾害管理一体化。该框架将用于空间作物图像特征提取的卷积神经网络（CNN）与用于时间气候预测的长短期记忆（LSTM）网络相结合。采用基于注意力的多模态特征融合机制整合异构的作物与气候信息，同时引入贝叶斯不确定性估计和深度集成学习，以提高预测可靠性、鲁棒性和置信感知决策支持能力。实验评估使用包含作物图像和气候观测数据的多模态数据集，数据来源于PlantVillage、NOAA和NASA EOS数据集。数据集按70：15：15的比例划分为训练集、验证集和测试集。采用分类和回归指标对所提框架进行评估，包括准确率、精确率、召回率、F1分数、RMSE、MAE、MAPE和AUC-ROC。为确保可复现性，所有实验使用不同随机种子重复五次，结果以均值$$\\pm$$标准差、95%置信区间和配对Student's $$t$$检验报告。实验结果表明，所提框架在分类准确率、气候预测误差、不同气候条件下的鲁棒性以及统计显著性性能提升方面均持续优于传统CNN、LSTM和CNN–LSTM混合模型。该框架为智能气候适应性智慧农业和早期农业灾害管理提供了一种可靠、可扩展且具有不确定性感知能力的解决方案。","Discover Computing","2026-10-14T00:00:00Z",71,{"impact":40,"substance":17,"depth":146,"authority":205,"freshness":147,"relevant":20,"comment":206},13,"提出CNN-LSTM注意力融合与贝叶斯不确定性估计的混合深度集成框架，多源数据与统计验证扎实，但属方法类论文，产业落地影响有限。",[208],{"name":201,"url":198},[210,211,212,25,213],"智慧农业","农业人工智能","农业遥感","作物病害预测",{"code":215,"slug":216,"name":217,"path":218,"parent_code":77},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",[],{"status":90,"locked":33,"version":34,"method":35,"evidence":221},{"candidates":222,"agricultural_evidence":13},[223,229,236,242,247,253],{"code":224,"score":19,"supported":13,"title":225,"abstract":227,"tags":228},"I1",[226],"smart agriculture",[210,226],[210],{"code":215,"score":12,"supported":13,"title":230,"abstract":231,"tags":235},[],[232,233,234],"深度学习","deep learning","decision support",[211],{"code":39,"score":49,"supported":13,"title":237,"abstract":238,"tags":241},[],[239,240],"气候变化","气候适应",[25],{"code":186,"score":52,"supported":13,"title":243,"abstract":244,"tags":246},[],[152,245],"food security",[],{"code":248,"score":168,"supported":13,"title":249,"abstract":250,"tags":252},"A7",[],[251],"间作",[],{"code":73,"score":20,"supported":33,"title":254,"abstract":255,"tags":256},[],[],[212],[258,259],"PlantVillage NOAA NASA 作物病害预测","CNN LSTM 气候韧性 智慧农业","PlantVillageNOAANASA作物病害预测-4985","10.1007\u002Fs10791-026-10579-y",{"doi":261,"openalex_id":263,"authors":264,"venue":201,"cited_by_count":63,"oa_url":198,"card":276,"direction":282,"ingested_from":131},"W7221778141",[265,268,271,273],{"name":266,"orcid":267},"Deepak Motwani","https:\u002F\u002Forcid.org\u002F0000-0002-0217-7155",{"name":269,"orcid":270},"Sellappan Palaniappan","https:\u002F\u002Forcid.org\u002F0009-0009-1168-2864",{"name":272,"orcid":8},"A. Daniel",{"name":274,"orcid":275},"Azween B. Abdullah","https:\u002F\u002Forcid.org\u002F0000-0003-4425-8604",{"tldr":277,"method":278,"finding":279,"direction":280,"opportunity":281},"提出混合深度集成框架，融合CNN与LSTM并引入注意力机制，实现作物病害预测与气候韧性灾害管理。","CNN提取图像特征、LSTM预测气候，注意力多模态融合，贝叶斯不确定性估计与深度","框架在分类精度与气候预测误差上均优于CNN、LSTM及CNN-LSTM基线，且性能提升具统计显著性。","农业人工智能与决策模型","可探索轻量化边缘部署与多作物跨区域迁移，结合实时物联网数据提升不确定性感知的灾害预警时效。","智慧农业 \u002F 农业物联网","2026-10-15T23:30:08.408875Z",{"id":285,"title":286,"url":287,"summary":288,"summary_zh":289,"content":8,"source_name":290,"source_url":287,"published_at":291,"category":62,"cover_url":8,"hotness":12,"is_selected":33,"score":203,"score_detail":292,"sources":294,"tags":296,"primary_topic":8,"secondary_topics":299,"classification":300,"search_phrases":322,"slug":325,"view_count":63,"doi":326,"paper":327,"created_at":349},4880,"Development of an Explainable GeoAI Wildfire Risk Analysis Model Using Multi-Source Geospatial Data","https:\u002F\u002Fdoi.org\u002F10.5194\u002Fisprs-archives-xlviii-m-13-2026-17-2026","Accounting for approximately 31% of the global land surface, forests play a critical and indispensable role in sustaining ecological balance. Among the various pressures affecting forests, forest fires constitute a major environmental problem, posing significant threats to natural ecosystems while disrupting forestry activities and leading to substantial economic losses. In Türkiye, forest fires are predominantly observed in the Aegean, Mediterranean, and Marmara regions. This study presents a proactive, explainable GeoAI framework for wildfire risk analysis by integrating multi-source geospatial data. The methodology calculates a physical hazard index by evaluating advanced ensemble machine learning algorithm, specifically extreme gradient boosting (XGBoost) with the latter demonstrating superior predictive performance. The model is driven by topographic, meteorological, biotic and anthropogenic parameters. In parallel, a comprehensive vulnerability matrix encompassing physical, social, economic and environmental dimensions is constructed utilizing the Best-Worst Method (BWM). These two main components are spatially synthesized in a Geographic Information Systems (GIS) environment. The model's interpretability is enhanced focusing on feature importance to identify the primary drivers of fire ignition and spread. Results demonstrate that anthropogenic pressures and Wildland-Urban Interface (WUI) dynamics are the most significant risk determinants. The resulting high-resolution maps provide a robust Spatial Decision Support System (SDSS) for local authorities, enabling targeted mitigation strategies and contributing to the development of sustainable, smart and resilient cities.","森林约占全球陆地表面的31%，在维持生态平衡方面发挥着不可或缺的关键作用。在影响森林的诸多压力中，森林火灾构成重大环境问题，对自然生态系统造成严重威胁，同时干扰林业活动并导致重大经济损失。在土耳其，森林火灾主要发生于爱琴海、地中海和马尔马拉地区。本研究通过整合多源地理空间数据，提出了一种具有前瞻性和可解释性的地理人工智能（GeoAI）框架，用于野火风险分析。该方法通过评估先进的集成机器学习算法计算物理危险性指数，其中极端梯度提升（XGBoost）表现出更优的预测性能。模型由地形、气象、生物和人为参数驱动。与此同时，利用最优最劣法（BWM）构建了涵盖物理、社会、经济和环境维度的综合脆弱性矩阵。这两个主要组成部分在地理信息系统（GIS）环境中进行空间综合。通过聚焦特征重要性以识别火灾点燃和蔓延的主要驱动因素，增强了模型的可解释性。结果表明，人为压力和野地-城市交界区（WUI）动态是最重要的风险决定因素。所生成的高分辨率地图为地方当局提供了稳健的空间决策支持系统（SDSS），有助于制定有针对性的减缓策略，并促进可持续、智慧和韧性城市的发展。","˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences\u002FInternational archives of the photogrammetry, remote sensing and spatial information sciences","2026-10-12T00:00:00Z",{"impact":40,"substance":17,"depth":146,"authority":205,"freshness":147,"relevant":20,"comment":293},"将可解释GeoAI与多源地理空间数据结合用于野火风险分析，方法新颖、结论明确，对农业与乡村防灾减灾有参考价值。",[295],{"name":290,"url":287},[211,25,97,297,298],"森林防火","地理信息系统",[],{"status":32,"locked":33,"version":34,"method":35,"evidence":301},{"candidates":302,"agricultural_evidence":33,"reason":44},[303,309,314,318],{"code":215,"score":12,"supported":13,"title":304,"abstract":305,"tags":308},[],[306,307,234],"机器学习","machine learning",[211],{"code":80,"score":12,"supported":13,"title":310,"abstract":311,"tags":313},[],[104,102,312],"geographic information",[298],{"code":39,"score":181,"supported":33,"title":315,"abstract":316,"tags":317},[],[],[297,25],{"code":73,"score":20,"supported":33,"title":319,"abstract":320,"tags":321},[],[],[97],[323,324],"GeoAI 野火风险 XGBoost","土耳其 森林火灾 遥感","GeoAI野火风险XGBoost-4880","10.5194\u002Fisprs-archives-xlviii-m-13-2026-17-2026",{"doi":326,"openalex_id":328,"authors":329,"venue":290,"cited_by_count":63,"oa_url":343,"card":344,"direction":282,"ingested_from":131},"W7221503678",[330,333,336,338,340],{"name":331,"orcid":332},"Esra Günaydın","https:\u002F\u002Forcid.org\u002F0000-0003-1868-0887",{"name":334,"orcid":335},"Muhammed Oğuzhan Mete","https:\u002F\u002Forcid.org\u002F0000-0002-9312-1965",{"name":337,"orcid":8},"Furkan Ali Kucuk",{"name":339,"orcid":8},"Ayça Hafızoğlu",{"name":341,"orcid":342},"Mahmut Oğuz Selbesoğlu","https:\u002F\u002Forcid.org\u002F0000-0002-1132-3978","https:\u002F\u002Fisprs-archives.copernicus.org\u002Farticles\u002FXLVIII-M-13-2026\u002F17\u002F2026\u002Fisprs-archives-XLVIII-M-13-2026-17-2026.pdf",{"tldr":345,"method":346,"finding":347,"direction":129,"opportunity":348},"构建可解释GeoAI框架，融合多源地理数据评估土耳其野火风险并制图。","XGBoost算危险指数，BWM建脆弱性矩阵，GIS空间合成。","人为压力与野火城市交界带动态是最显著的风险决定因素。","可将该可解释GeoAI框架迁移至农业火险与秸秆焚烧风险，结合时序遥感做动态预警。","2026-10-14T23:30:10.102337Z",{"id":351,"title":352,"url":353,"summary":354,"summary_zh":355,"content":8,"source_name":356,"source_url":353,"published_at":357,"category":62,"cover_url":8,"hotness":12,"is_selected":33,"score":63,"score_detail":358,"sources":360,"tags":362,"primary_topic":8,"secondary_topics":365,"classification":366,"search_phrases":383,"slug":386,"view_count":20,"doi":387,"paper":388,"created_at":402},4751,"A DISASTER RISK PREPAREDNESS MANAGEMENT PLAN FOR MARKETS IN MUBI TOWN, ADAMAWA STATE, NIGERIA","https:\u002F\u002Fdoi.org\u002F10.70382\u002Fhijiras.v013i2.088","The study evaluates disaster risk preparedness in major commercial markets within Mubi Town, Adamawa State, Nigeria, with a view to identifying hazard hotspots, structural deficiencies, and formulating a proactive, GIS-based disaster risk management plan. Major markets in developing urban centres face recurrent catastrophes, notably destructive fire outbreaks, exacerbated by high stall densities, combustible building materials, infrastructural deficits, and reactive emergency administration. Data for the study were obtained through both primary and secondary sources, comprising Global Positioning System (GPS) field coordinates of market boundaries, stall footprints, water sources, transformers, and hazardous activity points, paired with high-resolution georeferenced satellite imagery, physical lane width measurements, structured questionnaires administered to 384 market stakeholders, and document review of historical fire records. The data collected were subjected to descriptive statistical analysis and advanced spatial analysis within an ArcGIS Pro environment, utilizing Buffer Analysis, Network Analysis, and Multi-Criteria Decision Analysis (MCDA) via Weighted Overlay. The empirical findings indicate that 74.2% of market stalls are constructed from highly combustible temporary materials (timber, thatch, and corrugated iron sheets), while 68.5% of internal circulation lanes measure less than 2.0 metres in width, severely impeding fire appliance navigability. Critical firefighting infrastructure is virtually non-existent; the entire metropolitan area lacks functional municipal fire hydrants and relies on a severely under-resourced fire station with only one functional water tender. Spatial buffer analysis revealed that 63.8% of commercial stalls are situated within high-hazard impact zones (\u003C20 m) of unregulated fuel and liquefied petroleum gas (LPG) vendors. Furthermore, composite multi-criteria risk mapping established that 58.4% of the aggregate market acreage falls within the \"High\" and \"Extreme\" vulnerability classes. Stakeholder evaluation of institutional coordination yielded a grand mean score of 1.74 on a 4-point scale, demonstrating severe institutional fragmentation among local government authorities, emergency agencies, and market associations. The study recommends the official integration of market management committees into municipal disaster risk governance, the immediate installation of dedicated pressurized fire hydrants, statutory enforcement of a minimum 3.5-metre emergency lane clearance, strict spatial zoning of hazardous commodity vendors, and the institutionalization of a GIS-based spatial decision support tool for proactive disaster mitigation.","本研究评估了尼日利亚阿达马瓦州穆比镇主要商业市场的灾害风险防范情况，旨在识别灾害热点、结构性缺陷，并制定基于地理信息系统（GIS）的前瞻性灾害风险管理方案。发展中城市中心的主要市场面临反复发生的灾难，尤其是破坏性火灾，其加剧因素包括摊位密度高、建筑材料可燃、基础设施不足以及应急管理被动。研究数据通过一手和二手来源获取，包括市场边界、摊位占地、水源、变压器和危险活动点的全球定位系统（GPS）实地坐标，并结合高分辨率地理参照卫星影像、物理通道宽度测量、对384名市场利益相关者进行的结构化问卷调查，以及历史火灾记录的文件审查。所收集数据在ArcGIS Pro环境中进行了描述性统计分析和高级空间分析，运用了缓冲区分析、网络分析和通过加权叠加实现的多准则决策分析（MCDA）。实证结果表明，74.2%的市场摊位由高度可燃的临时材料（木材、茅草和波纹铁皮）建造，而68.5%的内部流通通道宽度不足2.0米，严重阻碍了消防车辆通行。关键消防基础设施几乎不存在；整个都市区缺乏功能正常的市政消防栓，仅依赖一个资源严重不足、只有一辆可用水罐车的消防站。空间缓冲区分析显示，63.8%的商业摊位位于无监管燃料和液化石油气（LPG）销售商的高危影响区（\u003C20米）内。此外，综合多准则风险制图确定，市场总面积的58.4%属于“高”和“极高”脆弱性等级。利益相关者对机构协调的评价在4分制量表上总平均得分为1.74，表明地方政府当局、应急机构和市场协会之间存在严重的机构碎片化。研究建议将市场管理委员会正式纳入市政灾害风险治理体系，立即安装专用加压消防栓，并依法强制执行","International Journal of Innovation Research and Advanced Studies","2026-10-10T00:00:00Z",{"impact":63,"substance":63,"depth":63,"authority":63,"freshness":63,"relevant":63,"comment":359},"研究尼日利亚市场火灾风险与GIS防灾规划，属城市应急管理范畴，与三农、农业信息化主题无关，不建议进入每日精选。",[361],{"name":356,"url":353},[25,363,102,364],"应急管理","市场安全",[],{"status":32,"locked":33,"version":34,"method":35,"evidence":367},{"candidates":368,"agricultural_evidence":33,"reason":44},[369,375,379],{"code":80,"score":12,"supported":13,"title":370,"abstract":371,"tags":374},[],[104,372,102,373],"空间分析","spatial analysis",[102],{"code":215,"score":168,"supported":13,"title":376,"abstract":377,"tags":378},[],[234],[],{"code":39,"score":20,"supported":33,"title":380,"abstract":381,"tags":382},[],[],[25],[384,385],"Mubi 市场 火灾风险","尼日利亚 市场 GIS 防灾","Mubi市场火灾风险-4751","10.70382\u002Fhijiras.v013i2.088",{"doi":387,"openalex_id":389,"authors":390,"venue":356,"cited_by_count":63,"oa_url":395,"card":396,"direction":129,"ingested_from":131},"W7221329767",[391,393],{"name":392,"orcid":8},"Yakubu Usman Mohammed",{"name":394,"orcid":8},"NUWARI ATI BATHON","https:\u002F\u002Fharvardpublications.com\u002Fhijiras\u002Farticle\u002Fdownload\u002F777\u002F716",{"tldr":397,"method":398,"finding":399,"direction":400,"opportunity":401},"评估尼日利亚穆比镇市场火灾风险，用GIS制定防灾准备管理规划。","GPS测绘、卫星影像、384份问卷与ArcGIS空间分析（缓冲、网络、加权叠加M","74.2%摊位为易燃材料，68.5%通道不足2米，58.4%市场面积属高至极高脆弱等级。","数字乡村与农业信息化","可将该GIS-MCDA框架移植到农产品批发市场与乡村集市，结合物联网传感实现火灾实时预警。","2026-10-12T23:30:24.642855Z",{"id":404,"title":405,"url":406,"summary":407,"summary_zh":408,"content":8,"source_name":409,"source_url":406,"published_at":410,"category":62,"cover_url":8,"hotness":12,"is_selected":33,"score":411,"score_detail":412,"sources":415,"tags":417,"primary_topic":420,"secondary_topics":421,"classification":423,"search_phrases":442,"slug":445,"view_count":63,"doi":446,"paper":447,"created_at":460},4747,"Spatiotemporal mapping of agricultural drought using geospatial approach in the East Bale Zone, Ethiopia","https:\u002F\u002Fdoi.org\u002F10.1002\u002Fagg2.70475","Abstract Agricultural drought significantly threatens food security, livelihoods, and ecosystem stability, especially in regions prone to drought, such as the East Bale zone. This study investigates the spatial and temporal patterns of agricultural drought over 30 years (1993–2024) by combining meteorological station data with satellite‐derived vegetation and thermal indices. To assess meteorological drought, the standardized precipitation index (SPI) was calculated at 3‐, 6‐, and 12‐month intervals. For agricultural and thermal stress analysis, remote sensing‐based indices including the vegetation condition index (VCI), temperature condition index, and vegetation health index (VHI) were utilized. The results indicate that the years 2003, 2008, and 2018 experienced the most severe droughts, as shown consistently across all indices. Spatial analysis revealed that the central, southern, and eastern lowland areas faced the highest frequency and severity of drought, while the northwestern highlands remained comparatively resilient. Cross‐index correlation revealed strong agreement between SPI and VCI ( R 2 = 0.77), and between VHI and VCI ( R 2 = 0.83), supporting the effectiveness of integrated drought monitoring approaches. This research advances the field of drought assessment by enhancing spatial and temporal resolution and validating cross‐index relationships at the subregional level. The results provide critical insights for localized drought early warning systems, climate adaptation strategies, and future research to improve agricultural resilience under changing climatic conditions. Hence, agricultural drought risk mapping serves as a valuable tool for guiding decision‐making in drought monitoring and for mitigating its impacts on agricultural productivity.","摘要 农业干旱严重威胁粮食安全、生计和生态系统稳定性，尤其是在东巴莱区等易旱地区。本研究结合气象站数据与卫星反演的植被和热力指数，探讨了30年（1993—2024年）间农业干旱的时空格局。为评估气象干旱，计算了3个月、6个月和12个月尺度的标准化降水指数（SPI）。在农业与热胁迫分析方面，采用了基于遥感的植被状态指数（VCI）、温度状态指数和植被健康指数（VHI）。结果表明，2003年、2008年和2018年经历了最严重的干旱，各指数均一致反映了这一情况。空间分析显示，中部、南部和东部低地地区干旱发生频率最高、程度最严重，而西北部高地则相对具有较强恢复力。跨指数相关性分析表明，SPI与VCI之间（R²=0.77）以及VHI与VCI之间（R²=0.83）具有高度一致性，支持了综合干旱监测方法的有效性。本研究通过提高时空分辨率并在次区域尺度上验证跨指数关系，推进了干旱评估领域的发展。研究结果为地方性干旱预警系统、气候适应策略以及未来研究提供了重要见解，有助于在气候变化条件下提升农业韧性。因此，农业干旱风险制图为干旱监测决策及其对农业生产影响的减缓提供了有价值的工具。","Agrosystems Geosciences & Environment","2026-10-11T00:00:00Z",68,{"impact":107,"substance":413,"depth":146,"authority":205,"freshness":147,"relevant":20,"comment":414},21,"基于30年气象与遥感指数交叉验证的农业干旱时空制图研究，方法扎实、结论可靠，但属区域性案例，对国内三农信息化仅有方法借鉴价值。",[416],{"name":409,"url":406},[152,25,69,418,419],"植被指数","农业干旱",{"code":39,"slug":85,"name":86,"path":87,"parent_code":88},[422],{"code":73,"slug":74,"name":75,"path":76,"parent_code":77},{"status":90,"locked":33,"version":34,"method":35,"evidence":424},{"candidates":425,"agricultural_evidence":13},[426,430,434,438],{"code":39,"score":18,"supported":13,"title":427,"abstract":428,"tags":429},[111],[239,240,110,111],[25],{"code":73,"score":107,"supported":13,"title":431,"abstract":432,"tags":433},[],[97,95],[418,69],{"code":186,"score":49,"supported":13,"title":435,"abstract":436,"tags":437},[],[152,245],[152],{"code":80,"score":52,"supported":13,"title":439,"abstract":440,"tags":441},[],[372,373],[],[443,444],"埃塞俄比亚 East Bale 农业干旱","SPI VCI 干旱监测","埃塞俄比亚EastBale农业干旱-4747","10.1002\u002Fagg2.70475",{"doi":446,"openalex_id":448,"authors":449,"venue":409,"cited_by_count":63,"oa_url":406,"card":455,"direction":129,"ingested_from":131},"W7221455809",[450,452],{"name":451,"orcid":8},"Murad Hedo Haji",{"name":453,"orcid":454},"Karuturi Venkata Suryabhagavan","https:\u002F\u002Forcid.org\u002F0000-0003-2528-9106",{"tldr":456,"method":457,"finding":458,"direction":129,"opportunity":459},"结合气象站与卫星植被热指数，绘制埃塞俄比亚East Bale区30年农业干旱时空图。","用SPI（3\u002F6\u002F12月）与遥感VCI、TCI、VHI指数做交叉相关分析。","2003、2008、2018年干旱最重，中南部和东部低地最脆弱，SPI与VCI相关性R²=0.77。","可在小区域尺度融合多源指数构建干旱预警模型，并验证指数在不同作物区的适用性。","2026-10-12T23:30:24.342375Z"]