[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4680":3,"related-4680":87},{"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":23,"tags":25,"primary_topic":9,"secondary_topics":31,"classification":32,"search_phrases":60,"slug":63,"view_count":64,"doi":65,"paper":66,"created_at":86},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。",null,"OpenAlex","2026-10-09T00:00:00Z","论文",10,false,69,{"impact":17,"substance":18,"depth":19,"authority":17,"freshness":20,"relevant":21,"comment":22},12,20,18,7,1,"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。",[24],{"name":10,"url":6},[26,27,28,29,30],"农业人工智能","机器学习","遥感","水资源管理","地下水潜力",[],{"status":33,"locked":14,"version":34,"method":35,"evidence":36},"needs_review","2026-10-22.2","rules",{"candidates":37,"agricultural_evidence":14,"reason":59},[38,46,52],{"code":39,"score":40,"supported":41,"title":42,"abstract":43,"tags":45},"I2",8,true,[],[27,44],"machine learning",[26,27],{"code":47,"score":20,"supported":41,"title":48,"abstract":49,"tags":51},"I3",[],[28,50],"remote sensing",[28],{"code":53,"score":54,"supported":41,"title":55,"abstract":56,"tags":58},"H3",5,[],[57],"水资源",[30,29],"农业相关性需要复核",[61,62],"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",0,"10.31223\u002Fx5mv5h",{"doi":65,"openalex_id":67,"authors":68,"venue":9,"cited_by_count":64,"oa_url":78,"card":79,"direction":83,"ingested_from":85},"W7221088011",[69,71,73,75],{"name":70,"orcid":9},"Joseph Osumeje",{"name":72,"orcid":9},"Sachet Utekar",{"name":74,"orcid":9},"Morli Li",{"name":76,"orcid":77},"Daniel C. Jones","https:\u002F\u002Forcid.org\u002F0000-0002-8701-4506","https:\u002F\u002Feartharxiv.org\u002Frepository\u002Fobject\u002F15434\u002Fdownload\u002F26756\u002F",{"tldr":80,"method":81,"finding":82,"direction":83,"opportunity":84},"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。","农业遥感与作物表型","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。","openalex","2026-10-11T23:30:30.328869Z",{"total":88,"page":21,"page_size":88,"items":89},6,[90,171,244,322,378,434],{"id":91,"title":92,"url":93,"summary":94,"summary_zh":95,"content":9,"source_name":96,"source_url":97,"published_at":98,"category":12,"cover_url":9,"hotness":99,"is_selected":14,"score":100,"score_detail":101,"sources":106,"tags":110,"primary_topic":112,"secondary_topics":117,"classification":118,"search_phrases":155,"slug":158,"view_count":64,"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":40,"substance":17,"depth":102,"authority":103,"freshness":104,"relevant":21,"comment":105},14,4,9,"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。",[107,108],{"name":96,"url":97},{"name":96,"url":109},"https:\u002F\u002Fajeee.co.in\u002Findex.php\u002Fajeee\u002Farticle\u002Fdownload\u002F6754\u002F5489",[27,28,29,111],"地下水监测",{"code":39,"slug":113,"name":114,"path":115,"parent_code":116},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":119,"locked":14,"version":34,"method":35,"evidence":120},"classified",{"candidates":121,"agricultural_evidence":41},[122,127,131,138,142,149],{"code":39,"score":123,"supported":41,"title":124,"abstract":125,"tags":126},15,[44],[27,44],[27],{"code":47,"score":20,"supported":41,"title":128,"abstract":129,"tags":130},[],[28,50],[28],{"code":132,"score":88,"supported":41,"title":133,"abstract":134,"tags":137},"H2",[],[135,136],"土壤","soil",[],{"code":53,"score":103,"supported":41,"title":139,"abstract":140,"tags":141},[],[57],[29],{"code":143,"score":144,"supported":41,"title":145,"abstract":146,"tags":148},"I4",3,[],[147],"空间分析",[],{"code":150,"score":144,"supported":41,"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":96,"cited_by_count":64,"oa_url":97,"card":165,"direction":83,"ingested_from":85},"W7222805722",[163],{"name":164,"orcid":9},"Prof. I Pandu Ranga Reddy Dr. Hari Ramavath",{"tldr":166,"method":167,"finding":168,"direction":83,"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":9,"secondary_topics":189,"classification":190,"search_phrases":212,"slug":215,"view_count":216,"doi":217,"paper":218,"created_at":243},4881,"Mapping the knowledge structure and evolution of artificial intelligence for water reuse and sustainable water management","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs44163-026-02389-4","Artificial intelligence (AI) has become a powerful instrument to solve complex problems related to sustainable water resource management because it allows creating advanced, data-driven modelling, prediction, and optimization of water systems. Although the studies in this sphere have increased quickly, the global scientific tendencies have not been thoroughly examined. This research paper presents a bibliometric review of the literature about AI applications in green water management that was published from 2015 to 2025. The Scopus database was searched with a structured search strategy on bibliographic data, and 3,280 peer-reviewed articles were analyzed. VOSviewer was used to perform bibliometric mapping and network visualization to investigate the trends in publications, most active journals, most impactful authors, contributions of institutions, country-level partnerships, and research clusters. The findings indicate that the publishing activity has grown tremendously in the last ten years, which suggests that there is a growing interest in AI-based solutions to water quality monitoring, hydrological prediction, optimization of wastewater treatment, and smart water management system. China, the United States and India became the most productive nations with the University of Chinese Academy of Sciences and Beijing normal university as some of the top contributing institutions. The analysis of the key words co-occurrence (dominant research themes) was based on machine learning, water-quality prediction, hydrological modelling, remote sensing, and decision-support systems. The co-citation analysis has shown the core studies in machine learning algorithms, including random forests, neural networks, and boosting algorithms, which underpin the present studies in this field. Overall, the results depict the growing role of AI technologies to enhance the effectiveness of water resources management and wastewater treatment. This research offers a clear insight into the intellectual framework and the future research perspective of AI-based environmentally sustainable water management which can be of great value to researchers, policymakers, and practitioners who would wish to come up with innovative and data-based water management solutions.","人工智能（AI）已成为解决可持续水资源管理相关复杂问题的有力工具，因为它能够构建先进的数据驱动模型，实现水系统的预测与优化。尽管该领域的研究迅速增加，但全球科学趋势尚未得到充分审视。本文对2015年至2025年间发表的关于人工智能在绿色水资源管理中应用的文献进行了文献计量学综述。采用结构化检索策略对Scopus数据库中的文献数据进行检索，共分析了3，280篇同行评审论文。使用VOSviewer进行文献计量制图和网络可视化，以探究发文趋势、最活跃期刊、最具影响力作者、机构贡献、国家层面合作及研究聚类。研究结果表明，过去十年间发文活动急剧增长，表明基于人工智能的水质监测、水文预测、废水处理优化和智能水管理系统解决方案日益受到关注。中国、美国和印度成为最高产国家，中国科学院和北京师范大学为贡献最多的机构之一。关键词共现分析（主导研究主题）基于机器学习、水质预测、水文建模、遥感和决策支持系统。共被引分析揭示了机器学习算法的核心研究，包括随机森林、神经网络和提升算法，这些构成了该领域当前研究的基础。总体而言，研究结果描绘了人工智能技术在提升水资源管理和废水处理效能方面日益增长的作用。本研究为基于人工智能的环境可持续水资源管理的知识框架和未来研究视角提供了清晰见解，对希望提出创新性和数据驱动型水资源管理方案的研究人员、政策制定者和实践者具有重要价值。","Discover Artificial Intelligence","2026-10-12T00:00:00Z",67,{"impact":17,"substance":19,"depth":181,"authority":182,"freshness":40,"relevant":21,"comment":183},16,13,"基于3280篇文献的AI水资源管理文献计量综述，方法规范、结论有参考价值，但属学术综述类，产业与政策落地性有限。",[185],{"name":177,"url":174},[26,28,187,29,188],"文献计量","智慧水务",[],{"status":33,"locked":14,"version":34,"method":35,"evidence":191},{"candidates":192,"agricultural_evidence":14,"reason":59},[193,198,203,207],{"code":39,"score":19,"supported":41,"title":194,"abstract":196,"tags":197},[195],"artificial intelligence",[27,44,195],[26],{"code":53,"score":20,"supported":41,"title":199,"abstract":200,"tags":202},[],[57,201],"water resource",[29],{"code":47,"score":20,"supported":41,"title":204,"abstract":205,"tags":206},[],[28,50],[28],{"code":150,"score":20,"supported":41,"title":208,"abstract":209,"tags":211},[],[187,210],"bibliometric",[187],[213,214],"AI 水资源管理 文献计量","人工智能 再生水 可持续水管理","AI水资源管理文献计量-4881",2,"10.1007\u002Fs44163-026-02389-4",{"doi":217,"openalex_id":219,"authors":220,"venue":177,"cited_by_count":64,"oa_url":235,"card":236,"direction":242,"ingested_from":85},"W7221506022",[221,224,227,229,231,233],{"name":222,"orcid":223},"Narendra Kumar","https:\u002F\u002Forcid.org\u002F0000-0002-5578-3255",{"name":225,"orcid":226},"Mangey Ram Nagar","https:\u002F\u002Forcid.org\u002F0000-0003-3635-3548",{"name":228,"orcid":9},"Isha Dharsandia",{"name":230,"orcid":9},"Ananya Tiwari",{"name":232,"orcid":9},"Santosh Kumar Mishra",{"name":234,"orcid":9},"Mohit Kumar","https:\u002F\u002Flink.springer.com\u002Fcontent\u002Fpdf\u002F10.1007\u002Fs44163-026-02389-4.pdf",{"tldr":237,"method":238,"finding":239,"direction":240,"opportunity":241},"对2015-2025年AI用于水回用与可持续水管理的3280篇文献做文献计量分析，梳理知识结构与演化","Scopus检索3280篇同行评议文献，用VOSviewer做共现与共被引网络可","发文量十年激增，中国、美国、印度领先；主题聚焦机器学习、水质预测、水文建模、遥感与决策支持。","农业人工智能与决策模型","可将AI水管理方法迁移至农业灌溉与面源污染场景，构建农业水-肥-碳协同的智能决策模型。","智慧农业 \u002F 农业物联网","2026-10-14T23:30:10.246538Z",{"id":245,"title":246,"url":247,"summary":248,"summary_zh":249,"content":9,"source_name":250,"source_url":247,"published_at":251,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":179,"score_detail":252,"sources":255,"tags":257,"primary_topic":260,"secondary_topics":264,"classification":274,"search_phrases":301,"slug":304,"view_count":64,"doi":305,"paper":306,"created_at":321},4753,"Mapping groundwater potential zones using GIS, remote sensing and analytical hierarchy process (AHP) in Pader and Kitgum Districts, Uganda","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs43621-026-04943-7","Groundwater is a crucial source of freshwater in semi-arid regions, particularly in water-stressed areas, such as northern Uganda, where the surface water is scarce and unreliable precipitation patterns changes. This province lacks sufficient clean water for human consumption and only 20% of the water for agriculture extracted from the ground due to inaccessibility and insufficient information regarding the groundwater. With regard to these difficulties in water that are faced by the local communities, it has not been yet studied the distribution of groundwater in Kitgum and Pader districts. Therefore, the result of this research contributes preliminary groundwater investigation for contacting this indispensable source of water. The study employed a geospatial approach integrated with multi-criteria analysis to identify groundwater potential zones in Kitgum and Pader districts of Acholi subregion. The Utilization of Geographic Information Systems (GIS), remote sensing, and the Analytic Hierarchy Process (AHP) and six thematic layers; rainfall, drainage density, slope, soil type, geology, and land use\u002Fland cover were selected based on their hydrogeological influence and the accessibility of the data. After standardizing, and assigning normalized weights,a weighted overlay analysis in ArcGIS Pro version 3.1.0 was used to synthesize these layers into a comprehensive groundwater potential zonation map. The result categorized the study area into five zones; very low, low, medium, high, and very high potential. The analysis revealed that Kitgum District is predominantly characterized by very low to low groundwater potential zones of 67.24% when it is combined both, constrained by factors such as higher drainage density, and steeper slopes. Conversely, Pader District showed favorable conditions, with 85.5% of its area classified as high to very high groundwater potential, attributed to gentle slopes, and higher rainfall, that enhance infiltration capacity. Validation against yield data from 18 existing boreholes demonstrated a 75.0% alignment between the model and actual well performance, confirming the model’s reliability at acceptable result. This study demonstrated the effectiveness of GIS-based and AHP as a cost-effective tool for preliminary groundwater exploration in data-scarce environments. The resulting groundwater potential map provides a vital scientific foundation for sustainable water resource management, enabling targeted borehole siting, informed aquifer development, and resilience-building strategies to enhance water security for communities and livelihoods in the Acholi sub-region.","地下水是半干旱地区重要的淡水来源，尤其是在乌干达北部等水资源紧张地区，那里地表水稀缺且降水模式变化不可靠。该地区缺乏足够的清洁饮用水供人类消费，由于地下水难以获取且信息不足，仅有20%的农业用水来自地下开采。鉴于当地社区面临这些水资源困难，基特古姆和帕德尔地区的地下水分布尚未得到研究。因此，本研究结果为接触这一不可或缺的水源提供了初步的地下水调查。本研究采用地理空间方法与多准则分析相结合，识别阿乔利次区域基特古姆和帕德尔地区的地下水潜力区。利用地理信息系统（GIS）、遥感技术和层次分析法（AHP），基于其水文地质影响和数据可获取性，选取了六个主题图层：降雨量、河网密度、坡度、土壤类型、地质和土地利用\u002F土地覆盖。经过标准化和归一化权重赋值后，使用ArcGIS Pro 3.1.0版本中的加权叠加分析将这些图层综合成一张全面的地下水潜力分区图。结果将研究区划分为五个区域：极低、低、中等、高和极高潜力。分析表明，基特古姆区主要以极低至低地下水潜力区为主，两者合计占67.24%，受较高河网密度和较陡坡度等因素制约。相反，帕德尔区表现出有利条件，其85.5%的面积被归类为高至极高地下水潜力，这归因于平缓的坡度和较高的降雨量，增强了入渗能力。利用18口现有钻孔的出水量数据进行验证，模型与实际井表现之间的一致率达到75.0%，证实了模型在可接受结果范围内的可靠性。本研究证明了基于GIS和AHP的方法作为数据稀缺环境中初步地下水勘探的成本效益工具的有效性。所生成的地下水潜力图为可持续水资源管理提供了重要的科学基础，有助于有针对性地选址钻孔，为知情决策提供依据。","Discover Sustainability","2026-10-10T00:00:00Z",{"impact":40,"substance":18,"depth":253,"authority":182,"freshness":104,"relevant":21,"comment":254},17,"基于GIS、遥感与AHP的乌干达北部地下水潜力制图研究，方法成熟、验证可靠，对缺水地区农业水资源规划有参考价值，但属区域性初步研究，公共影响有限。",[256],{"name":250,"url":247},[28,29,258,30,259],"GIS","乌干达农业",{"code":143,"slug":261,"name":262,"path":263,"parent_code":116},"gis","GIS与空间分析","\u002Ftopic\u002Fdigital-agriculture\u002Fgis",[265,269],{"code":47,"slug":266,"name":267,"path":268,"parent_code":116},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"code":53,"slug":270,"name":271,"path":272,"parent_code":273},"irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation","H",{"status":119,"locked":14,"version":34,"method":35,"evidence":275},{"candidates":276,"agricultural_evidence":41},[277,283,287,291,295],{"code":143,"score":19,"supported":41,"title":278,"abstract":279,"tags":282},[258],[280,258,281],"地理信息","geographic information",[258],{"code":47,"score":123,"supported":41,"title":284,"abstract":285,"tags":286},[50],[28,50],[28],{"code":53,"score":40,"supported":41,"title":288,"abstract":289,"tags":290},[],[57,201],[30,29],{"code":132,"score":88,"supported":41,"title":292,"abstract":293,"tags":294},[],[135,136],[],{"code":296,"score":144,"supported":41,"title":297,"abstract":298,"tags":300},"H7",[],[299],"干旱",[],[302,303],"乌干达 Kitgum Pader 地下水","GIS AHP 地下水潜力","乌干达KitgumPader地下水-4753","10.1007\u002Fs43621-026-04943-7",{"doi":305,"openalex_id":307,"authors":308,"venue":250,"cited_by_count":64,"oa_url":247,"card":316,"direction":83,"ingested_from":85},"W7221339030",[309,312,314],{"name":310,"orcid":311},"Ahmed Abdirizak Dirie","https:\u002F\u002Forcid.org\u002F0009-0002-8109-0724",{"name":313,"orcid":9},"Abdulkadir Ahmed Mohamed",{"name":315,"orcid":9},"Ambiga Kannapiran",{"tldr":317,"method":318,"finding":319,"direction":83,"opportunity":320},"用GIS、遥感和AHP制图评估乌干达两区地下水潜力并验证。","GIS与遥感结合AHP，加权叠加6个主题图层，用18口井数据验证。","Kitgum区67.24%为低潜力，Pader区85.5%为高潜力，模型与井数据吻合75%。","可将该地下水潜力制图方法迁移到其他数据稀缺区，并结合农业灌溉需求优化井位。","2026-10-12T23:30:24.761508Z",{"id":323,"title":324,"url":325,"summary":326,"summary_zh":9,"content":9,"source_name":327,"source_url":9,"published_at":328,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":329,"score_detail":330,"sources":333,"tags":335,"primary_topic":338,"secondary_topics":339,"classification":343,"search_phrases":365,"slug":368,"view_count":103,"doi":9,"paper":369,"created_at":377},4286,"Applications of Artificial Intelligence in Soil Characterization and Agriculture: A Systematic Review","https:\u002F\u002Fm2.mtmt.hu\u002Fapi\u002Fpublication\u002F37386408","Navarro Rubio等系统综述2018-2026年196项AI土壤特性与农业应用研究，遵循PRISMA 2020框架。综述发现研究明显向数据驱动方法转变，机器学习和深度学习模型主导近期研究；随机森林、支持向量机、梯度提升方法、人工神经网络、卷积神经网络、长短期记忆架构最常被报告；主要数据源包括原位传感、实验室测量、遥感影像和环境协变量，常通过多源数据融合框架集成；树集成模型在不同土壤特性上提供稳健性能。","Agronomy 2026 16(13):1241 DOI:10.3390\u002Fagronomy16131241","2026-10-02T00:00:00Z",78,{"impact":19,"substance":331,"depth":19,"authority":102,"freshness":88,"relevant":21,"comment":332},22,"PRISMA框架下196项研究的系统综述，方法学扎实、结论可靠，对农业AI土壤应用具较高参考价值。",[334],{"name":327,"url":325},[336,26,27,28,337],"智慧农业","土壤监测",{"code":39,"slug":113,"name":114,"path":115,"parent_code":116},[340],{"code":132,"slug":136,"name":341,"path":342,"parent_code":273},"土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil",{"status":119,"locked":14,"version":34,"method":35,"evidence":344},{"candidates":345,"agricultural_evidence":41},[346,351,356,360],{"code":39,"score":181,"supported":41,"title":347,"abstract":348,"tags":350},[195],[349,27],"深度学习",[26,27],{"code":132,"score":352,"supported":41,"title":353,"abstract":354,"tags":355},11,[136],[135],[],{"code":47,"score":103,"supported":41,"title":357,"abstract":358,"tags":359},[],[28],[28],{"code":361,"score":21,"supported":14,"title":362,"abstract":363,"tags":364},"I1",[],[],[336],[366,367],"AI 土壤特性 系统综述","机器学习 土壤 遥感","AI土壤特性系统综述-4286",{"doi":9,"openalex_id":9,"authors":370,"venue":9,"cited_by_count":64,"oa_url":9,"card":371,"direction":240,"ingested_from":376},[],{"tldr":372,"method":373,"finding":374,"direction":240,"opportunity":375},"系统综述2018-2026年196项AI用于土壤特性与农业的研究。","PRISMA 2020框架，分析机器学习与深度学习模型及多源数据融合。","研究转向数据驱动，树集成模型在不同土壤特性上表现稳健。","可探索可解释AI与多源数据融合在土壤特性预测中的泛化能力。","agent","2026-10-06T00:05:04.976398Z",{"id":379,"title":380,"url":381,"summary":382,"summary_zh":383,"content":9,"source_name":384,"source_url":381,"published_at":328,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":385,"score_detail":386,"sources":388,"tags":390,"primary_topic":9,"secondary_topics":393,"classification":394,"search_phrases":414,"slug":417,"view_count":21,"doi":418,"paper":419,"created_at":433},4239,"Impervious Surface Classification Using Artificial Intelligence from Remote Sensing Imagery, Part I: Evaluation of Machine Learning Algorithms","https:\u002F\u002Fdoi.org\u002F10.48084\u002Fetasr.19081","Rapid urbanization has significantly expanded impervious surfaces in major cities, reducing natural infiltration and increasing urban flood risk. This study develops a fully automated Python workflow that integrates Geographic Information Systems (GIS), remote sensing, and machine learning to classify pervious and impervious surfaces and monitor urbanization dynamics in the central area of Ho Chi Minh City (about 95,100 hectares). A multi-temporal dataset was compiled from Landsat 5, Landsat 8, and Landsat 9 imagery (30 m) and Sentinel-2 imagery (10 m) for 2009, 2017, and 2024. The reference dataset comprised 1,125 survey points (549 impervious and 582 pervious) and 127 field points for independent validation. The workflow performs image preprocessing, Normalized Difference Built-up Index (NDBI) computation, a 70\u002F30 train-test split, and supervised classification using Random Forest (RF), Support Vector Machine (SVM), and K-Nearest Neighbors (KNN). The main novelty lies in (i) an end-to-end, reproducible Python pipeline that requires no manual GIS post-processing, (ii) the joint use of Landsat and Sentinel-2 data over 15 years for a rapidly urbanizing Southeast Asian city, and (iii) a controlled benchmark of three algorithm families using identical inputs. RF achieved the highest performance (overall accuracy 96.97%, Kappa 0.94), closely followed by SVM (96.77%, 0.94); KNN performed lower (90.91%, 0.82). The temporal accuracies were 92.39%, 93.64%, and 93.98% in 2009, 2017, and 2024. Change analysis revealed a 9.15% increase in impervious surfaces from 2009 to 2024, providing a quantitative basis for urban planning, flood-risk management, and sustainable development. The proposed workflow is applicable to other urbanizing regions to support evidence-based urban management.","快速城市化显著扩大了主要城市的不透水面，减少了自然下渗并增加了城市洪水风险。本研究开发了一套全自动Python工作流，集成地理信息系统（GIS）、遥感和机器学习，对胡志明市中心区域（约95,100公顷）的透水面与不透水面进行分类并监测城市化动态。研究构建了多时相数据集，来源于2009年、2017年和2024年的Landsat 5、Landsat 8和Landsat 9影像（30 m）以及Sentinel-2影像（10 m）。参考数据集包括1,125个调查点（549个不透水面点和582个透水面点）以及127个野外点用于独立验证。该工作流执行影像预处理、归一化建筑指数（NDBI）计算、70\u002F30训练-测试集划分，并采用随机森林（RF）、支持向量机（SVM）和K近邻（KNN）进行监督分类。主要创新点在于：（i）一套端到端、可复现的Python流程，无需人工GIS后处理；（ii）联合使用Landsat和Sentinel-2数据，对一座快速城市化的东南亚城市开展15年监测；（iii）在相同输入条件下对三类算法进行受控基准测试。RF表现最佳（总体精度96.97%，Kappa系数0.94），SVM紧随其后（96.77%，0.94）；KNN表现较低（90.91%，0.82）。2009年、2017年和2024年的时间精度分别为92.39%、93.64%和93.98%。变化分析显示，2009年至2024年不透水面增加了9.15%，为城市规划、洪水风险管理和可持续发展提供了定量依据。所提出的工作流可应用于其他城市化地区，以支持基于证据的城市管理。","Engineering Technology & Applied Science Research",71,{"impact":17,"substance":331,"depth":19,"authority":182,"freshness":88,"relevant":21,"comment":387},"方法新颖、数据扎实的遥感AI分类论文，但研究对象为越南城市不透水面，与国内三农信息化关联偏间接，可作技术参考而非重点精选。",[389],{"name":384,"url":381},[26,27,28,391,392],"城市扩张","洪水风险",[],{"status":33,"locked":14,"version":34,"method":35,"evidence":395},{"candidates":396,"agricultural_evidence":14,"reason":59},[397,402,406,410],{"code":39,"score":398,"supported":41,"title":399,"abstract":400,"tags":401},24,[44,195],[27,44],[26,27],{"code":47,"score":123,"supported":41,"title":403,"abstract":404,"tags":405},[50],[28,50],[28],{"code":143,"score":104,"supported":41,"title":407,"abstract":408,"tags":409},[],[280,258,281],[],{"code":296,"score":21,"supported":14,"title":411,"abstract":412,"tags":413},[],[],[392],[415,416],"胡志明市 不透水面 遥感","Landsat Sentinel-2 机器学习 分类","胡志明市不透水面遥感-4239","10.48084\u002Fetasr.19081",{"doi":418,"openalex_id":420,"authors":421,"venue":384,"cited_by_count":64,"oa_url":427,"card":428,"direction":83,"ingested_from":85},"W7219615601",[422,424],{"name":423,"orcid":9},"Huy Gia Giang Nguyen",{"name":425,"orcid":426},"Nhat Thong Tran","https:\u002F\u002Forcid.org\u002F0000-0002-5548-8272","https:\u002F\u002Fwww.etasr.com\u002Findex.php\u002FETASR\u002Farticle\u002Fdownload\u002F19081\u002F7071",{"tldr":429,"method":430,"finding":431,"direction":83,"opportunity":432},"用Landsat与Sentinel-2影像和三种机器学习算法自动分类胡志明市不透水面并监测15年变化","Landsat 5\u002F8\u002F9与Sentinel-2多时相影像，NDBI指数，RF\u002F","随机森林精度最高（总体精度96.97%，Kappa 0.94），2009-2024年不透水面增加9.","可将该端到端Python流程迁移至农业区，结合多源时序影像监测耕地非农化与设施农业扩张。","2026-10-05T23:30:28.045244Z",{"id":435,"title":436,"url":437,"summary":438,"summary_zh":439,"content":9,"source_name":440,"source_url":437,"published_at":328,"category":12,"cover_url":9,"hotness":99,"is_selected":14,"score":441,"score_detail":442,"sources":444,"tags":448,"primary_topic":450,"secondary_topics":451,"classification":452,"search_phrases":481,"slug":484,"view_count":216,"doi":485,"paper":486,"created_at":496},4238,"Comparative Performance of Machine Learning and Deep Learning Algorithms for Agricultural Land Mapping in Anambra State, Nigeria","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23106955","Abstract - Accurate delineation of agricultural land is fundamental to agricultural planning, food-security assessment, land-resource management, and monitoring of land-use transformation. However, the heterogeneous and fragmented character of agricultural landscapes in southeastern Nigeria presents substantial challenges for satellite-image classification. This study comparatively evaluated Random Forest (RF), Support Vector Machine (SVM), Artificial Neural Network (ANN), and Convolutional Neural Network (CNN) for agricultural land mapping in Anambra State, Nigeria. Remotely sensed imagery was classified into waterbody, dense forest, agricultural land, built-up area, and bare ground using the four algorithms. Model performance was evaluated using 210 validation samples and multiple confusion-matrix metrics, including sensitivity, precision, specificity, negative predictive value, overall accuracy, balanced accuracy, and Matthew’s correlation coefficient. Agricultural land estimates varied from 1,000.26 km² (21.78%) for SVM to 1,099.12 km² (23.93%) for ANN. SVM achieved the strongest overall performance, recording 88.5% sensitivity, 85.2% precision, 75.0% specificity, 83.3% overall accuracy, 81.7% balanced accuracy, and a Matthews correlation coefficient of 0.643. CNN produced the lowest overall accuracy of 74.3%. The findings demonstrate that increased model complexity does not necessarily translate into superior classification performance and establish SVM as an effective approach for regional agricultural land delineation under heterogeneous tropical landscape conditions. Keywords: agricultural land mapping; machine learning; deep learning; Support Vector Machine; Random Forest; artificial neural network; convolutional neural network; remote sensing","摘要——准确划定农业用地是农业规划、粮食安全评估、土地资源管理和土地利用变化监测的基础。然而，尼日利亚东南部农业景观的异质性和破碎化特征给卫星图像分类带来了巨大挑战。本研究比较评估了随机森林（RF）、支持向量机（SVM）、人工神经网络（ANN）和卷积神经网络（CNN）在尼日利亚阿南布拉州农业用地制图中的表现。利用这四种算法将遥感影像分类为水体、密林、农业用地、建成区和裸地。使用210个验证样本和多种混淆矩阵指标评估模型性能，包括灵敏度、精确率、特异度、阴性预测值、总体精度、平衡精度和马修斯相关系数。农业用地估计值从SVM的1,000.26 km²（21.78%）到ANN的1,099.12 km²（23.93%）不等。SVM取得了最强的总体表现，灵敏度为88.5%，精确率为85.2%，特异度为75.0%，总体精度为83.3%，平衡精度为81.7%，马修斯相关系数为0.643。CNN的总体精度最低，为74.3%。研究结果表明，模型复杂度的增加并不必然带来更优的分类性能，并确立了SVM作为异质性热带景观条件下区域农业用地划定的有效方法。关键词：农业用地制图；机器学习；深度学习；支持向量机；随机森林；人工神经网络；卷积神经网络；遥感","International Journal of Emerging Trends in Engineering and Development",61,{"impact":40,"substance":18,"depth":181,"authority":40,"freshness":104,"relevant":21,"comment":443},"尼日利亚区域案例研究，方法对比扎实但影响范围限于学术圈，可作为遥感与农业AI主题的参考素材。",[445,446],{"name":440,"url":437},{"name":440,"url":447},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23106954",[336,26,27,28,449],"农地制图",{"code":39,"slug":113,"name":114,"path":115,"parent_code":116},[],{"status":119,"locked":14,"version":34,"method":35,"evidence":453},{"candidates":454,"agricultural_evidence":41},[455,461,465,471,477],{"code":39,"score":456,"supported":41,"title":457,"abstract":459,"tags":460},27,[44,458],"deep learning",[349,27,44,458],[26,27],{"code":47,"score":20,"supported":41,"title":462,"abstract":463,"tags":464},[],[28,50],[28],{"code":466,"score":144,"supported":41,"title":467,"abstract":468,"tags":470},"A8",[],[469],"粮食安全",[],{"code":472,"score":144,"supported":41,"title":473,"abstract":474,"tags":476},"J1",[],[475],"农业规划",[],{"code":361,"score":21,"supported":14,"title":478,"abstract":479,"tags":480},[],[],[336],[482,483],"农业人工智能 农地制图 智慧农业 机器学习","农业人工智能 农地制图","农业人工智能农地制图智慧农业机器学习-4238","10.5281\u002Fzenodo.23106955",{"doi":485,"openalex_id":487,"authors":488,"venue":440,"cited_by_count":64,"oa_url":437,"card":491,"direction":83,"ingested_from":85},"W7219591984",[489],{"name":490,"orcid":9},"J.I. Igbokwe, C.E Ejikeme, J.O and Obi",{"tldr":492,"method":493,"finding":494,"direction":83,"opportunity":495},"比较RF、SVM、ANN、CNN在尼日利亚农业用地制图中的表现","遥感影像分类，210个验证样本，多种混淆矩阵指标评估","SVM总体精度最高（83.3%），CNN最低（74.3%），模型复杂度不保证性能","在碎片化热带景观中，可探索轻量级集成学习或迁移学习以平衡精度与效率","2026-10-05T23:30:27.987196Z"]