[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-1650":3,"related-1650":82},{"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":52,"slug":55,"view_count":47,"doi":56,"paper":57,"created_at":81},1650,"Integrating remote sensing and machine learning for forest fire susceptibility mapping in Peninsular Malaysia: the spatio-temporal sampling tree (STS-T)","https:\u002F\u002Fdoi.org\u002F10.1080\u002F10106049.2026.2724458","The field of forest fire susceptibility mapping has long been constrained by a persistent trade-off between accuracy and interpretability: black-box ensemble algorithms deliver high accuracy but operate as opaque processes, while transparent decision tree models offer strong interpretability but fail to achieve sufficient accuracy. To fill this gap, this study builds on the forest fire dataset of Peninsular Malaysia spanning 2001–2023. Using recursive feature elimination, we extracted 49 key environmental features from 7349 original attributes and proposed a novel spatiotemporal sampling tree algorithm, STS-T, which has node-level adaptive temporal selection capability and incorporates historical meteorological lag terms into its decision-making process. Validated through stratified 10-fold cross-validation and a hold-out spatial test set from Johor, the pruned STS-T model fitted with a 1-year time window reached an accuracy of 98.48% and an ROC-AUC of 0.988.","森林火灾易发性制图领域长期以来一直受制于精度与可解释性之间的持续权衡：黑箱集成算法虽能提供高精度，但其运行过程不透明；而透明的决策树模型虽具备较强的可解释性，却难以达到足够的精度。为填补这一空白，本研究基于马来西亚半岛2001—2023年的森林火灾数据集，采用递归特征消除法，从7349个原始属性中提取出49个关键环境特征，并提出了一种新颖的时空采样树算法STS-T。该算法具备节点级自适应时间选择能力，并将历史气象滞后项纳入其决策过程。通过分层10折交叉验证以及来自柔佛州的留出空间测试集验证，采用1年时间窗口拟合的剪枝STS-T模型达到了98.48%的准确率和0.988的ROC-AUC值。",null,"Geocarto International","2026-09-02T00:00:00Z","论文",10,false,0,{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":17},"主题为森林火灾制图，不涉及农业信息化或智慧农业，故不入选。",[19],{"name":10,"url":6},[21,22,23],"机器学习","遥感","森林火灾",[],{"status":26,"locked":14,"version":27,"method":28,"evidence":29},"needs_review","2026-10-22.2","rules",{"candidates":30,"agricultural_evidence":14,"reason":51},[31,39,45],{"code":32,"score":33,"supported":34,"title":35,"abstract":37,"tags":38},"I2",9,true,[36],"machine learning",[],[21],{"code":40,"score":33,"supported":34,"title":41,"abstract":43,"tags":44},"I3",[42],"remote sensing",[],[22],{"code":46,"score":47,"supported":14,"title":48,"abstract":49,"tags":50},"H7",1,[],[],[23],"农业相关性需要复核",[53,54],"机器学习 森林火灾 遥感","机器学习 森林火灾","机器学习森林火灾遥感-1650","10.1080\u002F10106049.2026.2724458",{"doi":56,"openalex_id":58,"authors":59,"venue":10,"cited_by_count":15,"oa_url":73,"card":74,"direction":78,"ingested_from":80},"W7205709513",[60,63,66,68,71],{"name":61,"orcid":62},"Zheng You Lim","https:\u002F\u002Forcid.org\u002F0000-0003-3326-8276",{"name":64,"orcid":65},"Yee Jian Chew","https:\u002F\u002Forcid.org\u002F0000-0002-2952-986X",{"name":67,"orcid":9},"Shih Yin Ooi",{"name":69,"orcid":70},"Ying Han Pang","https:\u002F\u002Forcid.org\u002F0000-0002-3781-6623",{"name":72,"orcid":9},"Pa Pa Min","https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Fpdf\u002F10.1080\u002F10106049.2026.2724458?needAccess=true",{"tldr":75,"method":76,"finding":77,"direction":78,"opportunity":79},"提出时空采样树算法STS-T，用于马来西亚半岛森林火灾易发性制图，兼顾精度与可解释性。","递归特征选择提取49个环境特征，提出STS-T算法，含节点级时间选择和气象滞后项","STS-T模型精度98.48%，AUC 0.988，优于黑盒模型且保持可解释性。","农业遥感与作物表型","STS-T可扩展至农业火灾或作物病害预测，结合遥感与气象数据，实现高精度可解释的时空建模。","openalex","2026-09-04T23:30:34.949298Z",{"total":83,"page":47,"page_size":83,"items":84},6,[85,171,245,336,391,441],{"id":86,"title":87,"url":88,"summary":89,"summary_zh":90,"content":9,"source_name":91,"source_url":92,"published_at":93,"category":12,"cover_url":9,"hotness":94,"is_selected":14,"score":95,"score_detail":96,"sources":102,"tags":106,"primary_topic":109,"secondary_topics":114,"classification":115,"search_phrases":155,"slug":158,"view_count":15,"doi":159,"paper":160,"created_at":170},5322,"MACHINE LEARNING BASED PREDICTION OF HYDROGEOLOGICAL PARAMETERS AND GROUNDWATER POTENTIAL INDEX USING GEOSPATIAL AND BOREHOLE DATA","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23434956","Abstract: Groundwater is a critical natural resource for domestic consumption, agricultural production, industrial development, and ecological sustainability. Accurate prediction of hydrogeological parameters and groundwater potential is essential for sustainable groundwater management, particularly in regions experiencing irregular rainfall, increasing water demand, and declining groundwater levels. This research paper presents a machine learning-based framework for predicting hydrogeological parameters and developing a Groundwater Potential Index (GWPI) by integrating geospatial datasets with borehole records. The proposed approach combines terrain characteristics, geological formations, soil properties, land use and land cover, drainage density, rainfall, slope, and remotely sensed indices with borehole-derived information, including water-table depth, aquifer thickness, lithology, and well yield. Machine learning algorithms such as Random Forest, Support Vector Regression, Gradient Boosting, and Artificial Neural Networks can be employed to estimate hydrogeological variables and identify areas with different groundwater potential levels. The predicted parameters are integrated within a geospatial framework to generate a spatially distributed groundwater potential index. Model performance can be assessed using the coefficient of determination (\\(R^2\\)), root mean square error (RMSE), and mean absolute error (MAE). The proposed framework offers a reproducible and scalable approach for groundwater exploration, borehole siting, and regional water-resource planning. Since no study-area dataset or model outputs have been provided, the paper presents a methodological framework rather than claiming experimentally validated results. Keywords: Machine Learning, Groundwater Potential Index, Hydrogeological Parameters, Geospatial Analysis, Borehole Data, Random Forest, Remote Sensing, Groundwater Management.","摘要：地下水是生活用水、农业生产、工业发展和生态可持续性的关键自然资源。准确预测水文地质参数和地下水潜力对于可持续地下水管理至关重要，尤其是在降雨不规律、用水需求不断增加和地下水位持续下降的地区。本文提出了一种基于机器学习的框架，通过将地理空间数据集与钻孔记录相结合，预测水文地质参数并构建地下水潜力指数（GWPI）。所提方法综合了地形特征、地质构造、土壤性质、土地利用与土地覆盖、河网密度、降雨、坡度以及遥感指数，并结合钻孔衍生信息，包括水位埋深、含水层厚度、岩性和井出水量。可采用随机森林、支持向量回归、梯度提升和人工神经网络等机器学习算法估算水文地质变量，并识别具有不同地下水潜力水平的区域。预测参数在地理空间框架内进行集成，以生成空间分布的地下水潜力指数。模型性能可通过决定系数（\\(R^2\\)）、均方根误差（RMSE）和平均绝对误差（MAE）进行评估。所提框架为地下水勘探、钻孔选址和区域水资源规划提供了一种可重复且可扩展的方法。由于未提供研究区数据集或模型输出，本文呈现的是方法学框架，而非声称经过实验验证的结果。关键词：机器学习，地下水潜力指数，水文地质参数，地理空间分析，钻孔数据，随机森林，遥感，地下水管理。","ACCENT JOURNAL OF  ECONOMICS ECOLOGY  & ENGINEERING","https:\u002F\u002Fajeee.co.in\u002Findex.php\u002Fajeee\u002Farticle\u002Fview\u002F6754","2026-10-17T00:00:00Z",25,47,{"impact":97,"substance":98,"depth":99,"authority":100,"freshness":33,"relevant":47,"comment":101},8,12,14,4,"方法框架类论文，无实测数据与验证结果，主题与农业水资源相关但公共价值有限，不宜进入每日精选。",[103,104],{"name":91,"url":92},{"name":91,"url":105},"https:\u002F\u002Fajeee.co.in\u002Findex.php\u002Fajeee\u002Farticle\u002Fdownload\u002F6754\u002F5489",[21,22,107,108],"水资源管理","地下水监测",{"code":32,"slug":110,"name":111,"path":112,"parent_code":113},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":116,"locked":14,"version":27,"method":28,"evidence":117},"classified",{"candidates":118,"agricultural_evidence":34},[119,124,129,136,142,149],{"code":32,"score":120,"supported":34,"title":121,"abstract":122,"tags":123},15,[36],[21,36],[21],{"code":40,"score":125,"supported":34,"title":126,"abstract":127,"tags":128},7,[],[22,42],[22],{"code":130,"score":83,"supported":34,"title":131,"abstract":132,"tags":135},"H2",[],[133,134],"土壤","soil",[],{"code":137,"score":100,"supported":34,"title":138,"abstract":139,"tags":141},"H3",[],[140],"水资源",[107],{"code":143,"score":144,"supported":34,"title":145,"abstract":146,"tags":148},"I4",3,[],[147],"空间分析",[],{"code":150,"score":144,"supported":34,"title":151,"abstract":152,"tags":154},"I7",[],[153],"methodological framework",[],[156,157],"机器学习 地下水潜力指数","钻孔数据 水文地质参数","机器学习地下水潜力指数-5322","10.5281\u002Fzenodo.23434956",{"doi":159,"openalex_id":161,"authors":162,"venue":91,"cited_by_count":15,"oa_url":92,"card":165,"direction":78,"ingested_from":80},"W7222805722",[163],{"name":164,"orcid":9},"Prof. I Pandu Ranga Reddy Dr. Hari Ramavath",{"tldr":166,"method":167,"finding":168,"direction":78,"opportunity":169},"提出融合地理空间与钻孔数据的机器学习框架，预测水文地质参数与地下水潜力指数。","随机森林、SVR、梯度提升、神经网络结合遥感与钻孔数据建模。","构建了可复现的地下水潜力评估方法框架，尚未经实测数据验证。","可将该框架落地到具体农业区，用实测钻孔数据验证并耦合灌溉需水预测。","2026-10-19T23:30:22.978385Z",{"id":172,"title":173,"url":174,"summary":175,"summary_zh":176,"content":9,"source_name":177,"source_url":174,"published_at":178,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":179,"score_detail":180,"sources":184,"tags":186,"primary_topic":190,"secondary_topics":195,"classification":196,"search_phrases":218,"slug":221,"view_count":15,"doi":222,"paper":223,"created_at":244},5319,"Synergistic Use of Multitemporal SAR and Optical Data with Random Forest Approach for Rice Mapping in Bangladesh","https:\u002F\u002Fdoi.org\u002F10.31223\u002Fx5f22w","Accurate in-season crop mapping is vital for national food security, yet traditional ground-based estimation methods in Bangladesh often lack precision. This study develops a robust machine-learning framework to map Boro rice in the Manikganj district by integrating Sentinel-1 Synthetic Aperture Radar (SAR) and Sentinel-2 optical imagery. To overcome the challenge of seasonal cloud cover, Sentinel-1 VH polarization was utilized to identify unique backscatter reductions during the transplantation phase (late February to early March) caused by specular reflection from flooded fields. By combining these SAR signatures with high-resolution spectral indices (NDVI, EVI, and BSI) from Sentinel-2 during peak growth stages, the research captures the distinct phenological signatures of paddy rice. A pixel-based Random Forest algorithm was applied within the Google Earth Engine (GEE) platform, utilizing about 200 field-verified reference points per sub-district (1,385 in total) for training and validation. The results demonstrated high classification performance, with overall accuracies ranging from 88.1% to 94.9% across the seven sub-districts. Furthermore, a comparison with official government statistics revealed a minimal total area difference of only 2.34%, underscoring the reliability of this integrated satellite approach for operational crop monitoring.","准确的当季作物制图对国家粮食安全至关重要，然而孟加拉国传统的基于地面估计的方法往往缺乏精度。本研究开发了一个稳健的机器学习框架，通过整合Sentinel-1合成孔径雷达（SAR）和Sentinel-2光学影像，对马尼格甘杰县的Boro水稻进行制图。为克服季节性云覆盖的挑战，研究利用Sentinel-1 VH极化识别插秧期（2月下旬至3月上旬）由淹水田块镜面反射所引起的独特后向散射降低特征。通过将这些SAR特征与Sentinel-2在生长旺盛期的高分辨率光谱指数（NDVI、EVI和BSI）相结合，研究捕捉到了水稻独特的物候特征。在Google Earth Engine（GEE）平台上应用了基于像元的随机森林算法，利用每个乡约200个实地验证参考点（共计1，385个）进行训练和验证。结果表明分类性能较高，七个乡的总体精度在88.1%至94.9%之间。此外，与政府官方统计数据相比，总面积差异仅为2.34%，凸显了这种综合卫星方法在业务化作物监测中的可靠性。","OpenAlex","2026-10-18T00:00:00Z",79,{"impact":181,"substance":182,"depth":181,"authority":98,"freshness":33,"relevant":47,"comment":183},18,22,"方法扎实、精度可靠的水稻遥感制图研究，对农业遥感业务化监测有参考价值，但属区域性案例，影响层级有限。",[185],{"name":177,"url":174},[187,188,21,189,22],"水稻","粮食安全","作物制图",{"code":191,"slug":192,"name":187,"path":193,"parent_code":194},"A1","rice","\u002Ftopic\u002Ffield-crops\u002Frice","A",[],{"status":116,"locked":14,"version":27,"method":28,"evidence":197},{"candidates":198,"agricultural_evidence":34},[199,204,210,214],{"code":191,"score":181,"supported":34,"title":200,"abstract":201,"tags":203},[192],[187,192,202],"paddy",[187],{"code":205,"score":125,"supported":34,"title":206,"abstract":207,"tags":209},"A8",[],[188,208],"food security",[188],{"code":32,"score":100,"supported":34,"title":211,"abstract":212,"tags":213},[],[21],[21],{"code":40,"score":47,"supported":14,"title":215,"abstract":216,"tags":217},[],[],[22],[219,220],"Sentinel-1 Sentinel-2 水稻制图","孟加拉国 Boro 水稻 遥感","Sentinel-1Sentinel-2水稻制图-5319","10.31223\u002Fx5f22w",{"doi":222,"openalex_id":224,"authors":225,"venue":9,"cited_by_count":15,"oa_url":238,"card":239,"direction":78,"ingested_from":80},"W7222810209",[226,228,231,234,236],{"name":227,"orcid":9},"Mst. Farida Perveen",{"name":229,"orcid":230},"Sravan Shrestha","https:\u002F\u002Forcid.org\u002F0000-0001-6979-1726",{"name":232,"orcid":233},"Abdullah Al Mehadi","https:\u002F\u002Forcid.org\u002F0000-0002-9002-633X",{"name":235,"orcid":9},"Saima Kazmina",{"name":237,"orcid":9},"Amio Al Saem","https:\u002F\u002Feartharxiv.org\u002Frepository\u002Fobject\u002F15552\u002Fdownload\u002F26951\u002F",{"tldr":240,"method":241,"finding":242,"direction":78,"opportunity":243},"融合Sentinel-1 SAR与Sentinel-2光学影像，用随机森林在GEE上绘制孟加拉国Bo","Sentinel-1 VH后向散射与Sentinel-2 NDVI\u002FEVI\u002FBS","七个分县总体精度88.1%–94.9%，与官方统计面积仅差2.34%。","可将该SAR-光学协同框架迁移至其他多云雨稻区，并探索多时相特征优选与跨季泛化。","2026-10-19T23:30:22.772950Z",{"id":246,"title":247,"url":248,"summary":249,"summary_zh":250,"content":9,"source_name":251,"source_url":248,"published_at":252,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":253,"score_detail":254,"sources":259,"tags":261,"primary_topic":265,"secondary_topics":269,"classification":275,"search_phrases":290,"slug":293,"view_count":15,"doi":294,"paper":295,"created_at":335},5178,"Spatial Modeling of Topsoil Total Carbon and Texture from Spectral Characteristics of Bare Soil Surface Images of Landsat 5\u002F8 Using Machine Learning","https:\u002F\u002Fdoi.org\u002F10.1134\u002Fs1064229326601228","— This study examines the possibility for detecting bare soil surface (BSS), using remote sensing data and for applying this approach to model texture and total soil carbon in the topsoil. The study area comprises agricultural fields within the North Caucasus Federal Agricultural Research Center in the northeastern spurs of the Stavropol Upland. Landsat 5\u002F8 imagery and spectral indices (NDVI, NBR2, and BSI) were used to classify BSS. Optimal discrimination of BSS from green and non-photosynthetic vegetation was achieved, using a BSI threshold of >0.18 (F1-score = 0.98). Spatial modeling of topsoil properties was conducted by comparing five regression models (Linear Regression, K-Nearest Neighbors, Random Forest, Extreme Gradient Boosting, and Cubist). A linear regression model demonstrated the highest performance; key predictors included the mean and standard deviation of SWIR2. The model exhibits strong predictive capability for sand, silt, clay, and total carbon (adjusted R 2 = 0.82, 0.75, 0.78, and 0.74, respectively). The topsoil is characterized by the range of clay content from 5 to 30%, of silt content from 15 to 60%, of sand content from 20 to 80%, and of total carbon from 0.5 to 3%. Predictive maps of texture and total carbon derived from BSS reveal considerable local heterogeneity, with soils consisting of Chernozems and Phaeozems, influenced by parent rock variability. The modeling results highlight the high predictive power of the BSS spectral characteristics, even when used as a single predictor for digital soil mapping.","本研究探讨了利用遥感数据检测裸露土壤表面（BSS）的可能性，并将该方法应用于表层土壤质地和总碳的建模。研究区包括位于斯塔夫罗波尔高地东北支脉的北高加索联邦农业研究中心内的农田。利用Landsat 5\u002F8影像和光谱指数（NDVI、NBR2和BSI）对BSS进行分类。当BSI阈值>0.18时，实现了BSS与绿色植被及非光合植被的最优区分（F1分数=0.98）。通过比较五种回归模型（线性回归、K近邻、随机森林、极端梯度提升和Cubist）对表层土壤属性进行了空间建模。线性回归模型表现出最高的性能；关键预测变量包括SWIR2的均值和标准差。该模型对砂粒、粉粒、黏粒和总碳表现出较强的预测能力（调整R²分别为0.82、0.75、0.78和0.74）。表层土壤的黏粒含量范围为5%至30%，粉粒含量为15%至60%，砂粒含量为20%至80%，总碳含量为0.5%至3%。基于BSS生成的质地和总碳预测图揭示了显著的局部异质性，土壤由黑钙土和暗色始成土组成，受母岩变异性的影响。建模结果凸显了BSS光谱特征的高预测能力，即使仅作为数字土壤制图的单一预测变量使用亦然。","Eurasian Soil Science","2026-10-15T00:00:00Z",69,{"impact":98,"substance":255,"depth":256,"authority":257,"freshness":97,"relevant":47,"comment":258},20,16,13,"方法新颖、结论可靠，但属区域尺度研究，公共影响有限，适合作为技术类精选。",[260],{"name":251,"url":248},[21,22,262,263,264],"土壤碳","Landsat","数字土壤制图",{"code":130,"slug":134,"name":266,"path":267,"parent_code":268},"土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",[270,271],{"code":32,"slug":110,"name":111,"path":112,"parent_code":113},{"code":40,"slug":272,"name":273,"path":274,"parent_code":113},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":116,"locked":14,"version":27,"method":28,"evidence":276},{"candidates":277,"agricultural_evidence":34},[278,282,286],{"code":130,"score":99,"supported":34,"title":279,"abstract":280,"tags":281},[134],[133,134],[],{"code":32,"score":33,"supported":34,"title":283,"abstract":284,"tags":285},[36],[],[21],{"code":40,"score":97,"supported":34,"title":287,"abstract":288,"tags":289},[],[22,42],[263,22],[291,292],"Landsat 裸土 土壤碳","北高加索 土壤质地 遥感","Landsat裸土土壤碳-5178","10.1134\u002Fs1064229326601228",{"doi":294,"openalex_id":296,"authors":297,"venue":251,"cited_by_count":15,"oa_url":9,"card":330,"direction":78,"ingested_from":80},"W7222107492",[298,301,304,307,310,313,316,319,321,324,327],{"name":299,"orcid":300},"P. A. Braulov","https:\u002F\u002Forcid.org\u002F0000-0001-9919-7402",{"name":302,"orcid":303},"Pavel M. Shilov","https:\u002F\u002Forcid.org\u002F0000-0003-4113-6396",{"name":305,"orcid":306},"R. G. Gadzhiumarov","https:\u002F\u002Forcid.org\u002F0000-0002-4220-623X",{"name":308,"orcid":309},"V. K. Dridiger","https:\u002F\u002Forcid.org\u002F0000-0002-0510-2220",{"name":311,"orcid":312},"E. V. Bogdan","https:\u002F\u002Forcid.org\u002F0009-0006-4781-5786",{"name":314,"orcid":315},"V. O. Megmerova","https:\u002F\u002Forcid.org\u002F0000-0001-8655-6437",{"name":317,"orcid":318},"Petr Tsymbarovich","https:\u002F\u002Forcid.org\u002F0000-0001-8591-2612",{"name":320,"orcid":9},"A. E. Shatunov",{"name":322,"orcid":323},"Pavel P. Fil","https:\u002F\u002Forcid.org\u002F0000-0002-9851-5381",{"name":325,"orcid":326},"D. E. Mitichkin","https:\u002F\u002Forcid.org\u002F0009-0006-2397-060X",{"name":328,"orcid":329},"Dmitriy S. Fomin","https:\u002F\u002Forcid.org\u002F0000-0003-3733-0284",{"tldr":331,"method":332,"finding":333,"direction":78,"opportunity":334},"用Landsat 5\u002F8裸土光谱指数识别裸土并机器学习建模表层土壤质地与全碳。","Landsat 5\u002F8影像、NDVI\u002FNBR2\u002FBSI指数、五种回归模型对比。","BSI阈值0.18识别裸土F1达0.98，线性回归最优，SWIR2均值与标准差为关键预测因子。","可探索多时相裸土合成与深度学习模型，提升数字土壤制图精度与跨区域迁移能力。","2026-10-17T23:30:31.485949Z",{"id":337,"title":338,"url":339,"summary":340,"summary_zh":341,"content":9,"source_name":177,"source_url":339,"published_at":342,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":253,"score_detail":343,"sources":345,"tags":347,"primary_topic":9,"secondary_topics":350,"classification":351,"search_phrases":367,"slug":370,"view_count":15,"doi":371,"paper":372,"created_at":390},4680,"Groundwater Potential Mapping in Northwestern Nigeria: A Comparison of the Analytic Hierarchy Process and Galileo-Enhanced CAT-XGB","https:\u002F\u002Fdoi.org\u002F10.31223\u002Fx5mv5h","Global water scarcity intensifies the need for high-resolution groundwater assessment tools, yet traditional approaches struggle to reconcile qualitative expert weights with the extensive spatial coverage offered by remote sensing data. This study presents a comparative framework evaluating expert-driven Multi-Criteria Decision Analysis (a ten-layer Analytic Hierarchy Process (AHP)) against data-driven ensemble machine learning for groundwater potential mapping in the geologically complex terrain of Northwestern Nigeria. Standard thematic layers were integrated with embeddings from a pretrained remote sensing foundation model to train ensemble classifiers, with groundwater potential validated against Vertical Electrical Sounding (VES) data. The foundation-model-enhanced CAT-XGB ensemble achieved notable predictive performance, consistently outperforming standalone tree-based classifiers and traditional AHP. Spatial difference mapping revealed that the enhanced ensemble captured critical, localized hydrogeological anomalies smoothed over by expert-driven weighting. Bridging heuristic decision-making with foundation-model-enhanced machine learning significantly improves spatial precision and reliability, potentially providing a field-validated tool for optimizing borehole siting and sustainable aquifer management in data-scarce, geologically complex regions.","全球水资源短缺加剧了对高分辨率地下水评估工具的需求，然而传统方法难以在定性专家权重与遥感数据所提供的广泛空间覆盖之间取得协调。本研究提出一个比较框架，在尼日利亚西北部地质复杂地形区，评估专家驱动的多准则决策分析（十层层次分析法（AHP））与数据驱动的集成机器学习在地下水潜力制图中的表现。研究将标准主题图层与预训练遥感基础模型的嵌入特征相结合以训练集成分类器，并利用垂直电测深（VES）数据对地下水潜力进行验证。经基础模型增强的CAT-XGB集成模型取得了显著的预测性能，持续优于独立的树基分类器和传统AHP。空间差异制图揭示，增强集成模型捕捉到了被专家驱动权重所平滑化的关键局部水文地质异常。将启发式决策与基础模型增强的机器学习相衔接，显著提升了空间精度与可靠性，有望为数据稀缺、地质复杂区域优化钻孔选址和可持续含水层管理提供一种经野外验证的工具。","2026-10-09T00:00:00Z",{"impact":98,"substance":255,"depth":181,"authority":98,"freshness":125,"relevant":47,"comment":344},"将遥感基础模型与集成机器学习用于尼日利亚西北部地下水潜力制图，方法新颖、有实地验证，对缺水地区灌溉与水资源管理有参考价值，但属区域案例研究，公共影响有限。",[346],{"name":177,"url":339},[348,21,22,107,349],"农业人工智能","地下水潜力",[],{"status":26,"locked":14,"version":27,"method":28,"evidence":352},{"candidates":353,"agricultural_evidence":14,"reason":51},[354,358,362],{"code":32,"score":97,"supported":34,"title":355,"abstract":356,"tags":357},[],[21,36],[348,21],{"code":40,"score":125,"supported":34,"title":359,"abstract":360,"tags":361},[],[22,42],[22],{"code":137,"score":363,"supported":34,"title":364,"abstract":365,"tags":366},5,[],[140],[349,107],[368,369],"尼日利亚 地下水潜力 遥感","CAT-XGB 地下水 制图","尼日利亚地下水潜力遥感-4680","10.31223\u002Fx5mv5h",{"doi":371,"openalex_id":373,"authors":374,"venue":9,"cited_by_count":15,"oa_url":384,"card":385,"direction":78,"ingested_from":80},"W7221088011",[375,377,379,381],{"name":376,"orcid":9},"Joseph Osumeje",{"name":378,"orcid":9},"Sachet Utekar",{"name":380,"orcid":9},"Morli Li",{"name":382,"orcid":383},"Daniel C. Jones","https:\u002F\u002Forcid.org\u002F0000-0002-8701-4506","https:\u002F\u002Feartharxiv.org\u002Frepository\u002Fobject\u002F15434\u002Fdownload\u002F26756\u002F",{"tldr":386,"method":387,"finding":388,"direction":78,"opportunity":389},"对比专家驱动AHP与遥感基础模型增强的CAT-XGB集成，用于尼日利亚西北部地下水潜力制图。","十层AHP与预训练遥感基础模型嵌入训练CAT-XGB集成，用垂直电测深数据验证。","基础模型增强的CAT-XGB集成预测性能优于传统AHP和独立树模型，能捕捉局部水文地质异常。","可探索遥感基础模型嵌入与专家知识融合，提升数据稀缺复杂区地下水等农业水资源评估精度。","2026-10-11T23:30:30.328869Z",{"id":392,"title":393,"url":394,"summary":395,"summary_zh":396,"content":9,"source_name":397,"source_url":394,"published_at":398,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":399,"score_detail":400,"sources":402,"tags":404,"primary_topic":9,"secondary_topics":408,"classification":409,"search_phrases":420,"slug":423,"view_count":47,"doi":424,"paper":425,"created_at":440},4591,"Uydu görüntüleri ile yanan orman alanının değerlendirilmesi: Çandır orman yangını örneği","https:\u002F\u002Fdoi.org\u002F10.18182\u002Ftjf.1721381","Bu çalışmada, 2021 yılında Çandır Orman İşletme Şefliğinde meydana gelen orman yangınında zarar gören orman alanlarının uzaktan algılama veri ve yöntemleriyle belirlenmesi ve değerlendirilmesi amaçlanmıştır. Bu kapsamda, yangın öncesi ve yangın sonrası Landsat-8 ve Sentinel-2 uydu görüntülerinden Normalleştirilmiş Fark Vejetasyon İndeksi (NDVI) ve Normalleştirilmiş Yanma Oranı (NBR) spektral indeksleri üretilmiştir. Yangının etkisini nicel olarak ortaya koymak amacıyla yangın öncesi ve sonrası indeks görüntüleri arasındaki fark alınarak dNDVI ve dNBR görüntüleri elde edilmiştir. Bu fark görüntülerine eşikleme yöntemi uygulanarak yanan orman alanları belirlenmiştir. Ayrıca Landsat-8 ve Sentinel-2 görüntüleri üzerinde kontrollü sınıflandırma yöntemi uygulanmış ve Maximum Likelihood algoritmasıyla tematik haritalar üretilmiştir. Elde edilen sonuçlara göre en yüksek sınıflandırma doğrulukları Sentinel-2 verilerinden üretilen dNBR ve dNDVI görüntülerinde elde edilmiş olup, genel doğruluk değerleri sırasıyla 0.92 ve 0.88, kappa değerleri ise 0.83 ve 0.77 olarak hesaplanmıştır. Landsat-8 verilerinden üretilen dNBR ve dNDVI görüntülerinde ise genel doğruluk değerleri sırasıyla 0.87 ve 0.85, kappa değerleri ise 0.73 ve 0.7 olarak belirlenmiştir. Kontrollü sınıflandırma sonucunda üretilen tematik haritalarda Sentinel-2 ve Landsat-8 için genel doğruluk değerleri sırasıyla 0.88 ve 0.85, kappa değerleri ise 0.85 ve 0.82 olarak bulunmuştur. Farklı yöntemlerden elde edilen sonuçların ortalamasına göre yanan orman alanının büyüklüğü 760 hektar hesaplanmıştır. Sonuç olarak, Sentinel-2 ve Landsat-8 uydu verilerinden elde edilen dNDVI ve dNBR görüntülerinin, yanan orman alanlarının belirlenmesi ve yangın etkisinin değerlendirilmesinde verimli, güvenilir ve uygulanabilir sonuçlar üretme potansiyeline sahip olduğu ortaya konulmuştur.","本研究旨在利用遥感数据和方法，确定并评估2021年昌德尔森林经营管理局辖区内发生的森林火灾中受损的森林面积。在此范围内，利用火灾前后的Landsat-8和Sentinel-2卫星影像生成了归一化差异植被指数（NDVI）和归一化燃烧比率（NBR）光谱指数。为了定量揭示火灾的影响，通过计算火灾前后指数影像之间的差值，获得了dNDVI和dNBR影像。对这些差值影像应用阈值法，确定了过火森林区域。此外，对Landsat-8和Sentinel-2影像应用了监督分类方法，并利用最大似然法（Maximum Likelihood）生成了专题地图。根据所得结果，最高的分类精度来自Sentinel-2数据生成的dNBR和dNDVI影像，其总体精度分别为0.92和0.88，Kappa系数分别为0.83和0.77。在Landsat-8数据生成的dNBR和dNDVI影像中，总体精度分别为0.87和0.85，Kappa系数分别为0.73和0.7。在监督分类生成的专题地图中，Sentinel-2和Landsat-8的总体精度分别为0.88和0.85，Kappa系数分别为0.85和0.82。根据不同方法所得结果的平均值，过火森林面积计算为760公顷。综上所述，由Sentinel-2和Landsat-8卫星数据获得的dNDVI和dNBR影像在确定过火森林区域和评估火灾影响方面具有产生高效、可靠且可应用结果的潜力。","Turkish Journal of Forestry | Türkiye Ormancılık Dergisi","2026-10-08T00:00:00Z",73,{"impact":98,"substance":182,"depth":181,"authority":257,"freshness":97,"relevant":47,"comment":401},"该论文利用Landsat-8与Sentinel-2遥感数据评估土耳其Çandır森林火灾过火面积，方法可靠、结论具体，对农业信息化中的遥感监测有参考价值，但属区域性案例研究，影响范围有限。",[403],{"name":397,"url":394},[405,22,23,406,407],"Sentinel-2","植被指数","Landsat-8",[],{"status":26,"locked":14,"version":27,"method":28,"evidence":410},{"candidates":411,"agricultural_evidence":14,"reason":51},[412,416],{"code":40,"score":83,"supported":34,"title":413,"abstract":414,"tags":415},[],[22],[405,406,22],{"code":46,"score":47,"supported":14,"title":417,"abstract":418,"tags":419},[],[],[23],[421,422],"Çandır orman yangını","森林火灾 植被指数 遥感 Sentinel-2","Çandırormanyangını-4591","10.18182\u002Ftjf.1721381",{"doi":424,"openalex_id":426,"authors":427,"venue":397,"cited_by_count":15,"oa_url":434,"card":435,"direction":78,"ingested_from":80},"W7220904781",[428,431],{"name":429,"orcid":430},"Abdurrahman Cankut Göz","https:\u002F\u002Forcid.org\u002F0000-0003-1786-7658",{"name":432,"orcid":433},"HÜSEYİN OĞUZ ÇOBAN","https:\u002F\u002Forcid.org\u002F0000-0002-4037-4811","https:\u002F\u002Fdergipark.org.tr\u002Ftr\u002Fdownload\u002Farticle-file\u002F4966779",{"tldr":436,"method":437,"finding":438,"direction":78,"opportunity":439},"利用Landsat-8和Sentinel-2影像评估2021年Çandır森林火灾过火面积。","计算火灾前后NDVI、NBR及dNDVI、dNBR，结合阈值法和最大似然监督分类","Sentinel-2的dNBR精度最高（总体精度0.92，Kappa 0.83），过火面积约760公","可探索多源卫星时序数据融合与深度学习，提升火烧区制图精度并拓展至植被恢复监测。","2026-10-10T23:30:29.424999Z",{"id":442,"title":443,"url":444,"summary":445,"summary_zh":9,"content":9,"source_name":446,"source_url":9,"published_at":9,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":447,"score_detail":448,"sources":450,"tags":452,"primary_topic":457,"secondary_topics":461,"classification":462,"search_phrases":486,"slug":489,"view_count":490,"doi":9,"paper":491,"created_at":500},4477,"玉米生产精准农业系统综述：技术、应用与产量优化（2020—2026）","https:\u002F\u002Fm2.mtmt.hu\u002Fapi\u002Fpublication\u002F37500368","依据PRISMA 2020指南，系统检索Scopus与Web of Science共464篇文献，最终纳入129项研究；样本构成为田间试验（28.6%）、遥感与精准农业整合研究（25.5%）、机器学习应用（19.4%）、气候知情精准农业策略（23.4%）和土壤退化研究（3.1%）；研究表明精准农业技术通过定点管理和数据驱动决策支持，提升了玉米生产力、养分利用效率、水利用效率和产量预测准确性；指出采用精准农业仍受制于实施成本高、技术复杂、数据有限等因素。","Precision Agriculture in Maize Production Systematic Review 2026",74,{"impact":181,"substance":182,"depth":181,"authority":257,"freshness":144,"relevant":47,"comment":449},"基于PRISMA 2020的系统综述，纳入129项研究，数据规模与方法规范性强，对玉米精准农业技术路径与瓶颈有实质参考价值，但发布日期不明、时效性偏弱。",[451],{"name":446,"url":444},[453,454,21,455,456,22],"智慧农业","产量预测","玉米","精准农业",{"code":458,"slug":459,"name":455,"path":460,"parent_code":194},"A3","maize","\u002Ftopic\u002Ffield-crops\u002Fmaize",[],{"status":116,"locked":14,"version":27,"method":28,"evidence":463},{"candidates":464,"agricultural_evidence":34},[465,470,474,478,482],{"code":466,"score":257,"supported":34,"title":467,"abstract":468,"tags":469},"I1",[456],[456],[453,456],{"code":458,"score":98,"supported":34,"title":471,"abstract":472,"tags":473},[455],[455],[455],{"code":40,"score":363,"supported":34,"title":475,"abstract":476,"tags":477},[],[22],[454,22],{"code":32,"score":100,"supported":34,"title":479,"abstract":480,"tags":481},[],[21],[21],{"code":130,"score":144,"supported":34,"title":483,"abstract":484,"tags":485},[],[133],[],[487,488],"玉米 精准农业 系统综述","玉米 遥感 机器学习 产量","玉米精准农业系统综述-4477",2,{"doi":9,"openalex_id":9,"authors":492,"venue":9,"cited_by_count":15,"oa_url":9,"card":493,"direction":497,"ingested_from":499},[],{"tldr":494,"method":495,"finding":496,"direction":497,"opportunity":498},"系统综述2020—2026年玉米精准农业技术、应用与产量优化研究。","按PRISMA 2020检索Scopus与WoS，纳入129项研究做分类分析。","精准农业通过定点管理与数据决策提升玉米产量、养分和水利用效率。","智慧农业 \u002F 农业物联网","成本高、技术复杂与数据不足制约推广，低成本轻量化方案与本地化数据共享是研究空白。","agent","2026-10-09T00:05:02.451957Z"]