[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2329":3,"related-2329":105},{"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":24,"tags":26,"primary_topic":32,"secondary_topics":38,"classification":39,"search_phrases":73,"slug":76,"view_count":77,"doi":78,"paper":79,"created_at":104},2329,"Spatio-temporal characteristics and driving factor identification of precipitation use efficiency: Based on machine learning and SHAP analysis","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.agwat.2026.110763","Precipitation use efficiency (PUE) is a key indicator of the \"carbon-water\" coupling in ecosystems; research on its spatiotemporal distribution and the identification of its driving factors is of great significance for regional ecohydrological processes and resource management. This study focuses on the cold region of Northeast China, an important agricultural and natural ecological zone. Based on multi-source remote sensing data from 2001 to 2024, it employs the Theil-Sen trend estimation and Mann–Kendall significance tests to identify trends in PUE, and combined the Hurst index and coefficient of variation to analyze its future evolution. Furthermore, by integrating the SHAP explainable machine learning model framework, this study quantifies the multiscale driving contributions of climate, vegetation, and topographic factors to PUE and identifies the ecological thresholds of key factors. The results show that: (1) The spatial distribution of PUE exhibits a gradient pattern characterized by higher values in the northwest and lower values in the southeast. Interannual variations follow a three-phase pattern of “gradual increase, significant decline, and fluctuation at high levels,” with values ranging from 0.67 to 0.96 gC·m⁻²·mm⁻¹ . (2) Spatially, PUE is not only regulated by multiple individual factors, but the interactions among these factors further reinforce its patterns; temporally, PUE is jointly regulated by dynamic meteorological and vegetation factors, and key influencing factors exhibit significant nonlinear threshold responses. (3) The dominant driving mechanisms in regions with different PUE values exhibit significant heterogeneity: regions with low PUE values are primarily constrained by high evapotranspiration and weak water-holding capacity, whereas regions with high PUE values rely on efficient water conversion and utilization strategies under low-precipitation conditions. This study reveals the multiscale factors driving PUE in the cold regions of Northeast China and identifies key regulatory thresholds, providing quantitative evidence for regional “carbon-water” integrated management, precision-based vegetation restoration, and climate change adaptation strategies.","降水利用效率（PUE）是生态系统“碳水”耦合的关键指标，研究其时空分布及驱动因素识别对区域生态水文过程与资源管理具有重要意义。本研究以我国东北寒区这一重要农业与自然生态区为对象，基于2001—2024年多源遥感数据，采用Theil-Sen趋势估计与Mann-Kendall显著性检验识别PUE变化趋势，并结合Hurst指数与变异系数分析其未来演变；进一步集成SHAP可解释机器学习模型框架，量化气候、植被与地形因素对PUE的多尺度驱动贡献，并识别关键因子的生态阈值。结果表明：（1）PUE空间分布呈西北高、东南低的梯度格局，年际变化呈“缓慢上升—显著下降—高位波动”的三阶段特征，数值范围为0.67~0.96 gC·m⁻²·mm⁻¹。（2）空间上，PUE不仅受多个单因子调控，因子间交互作用进一步强化其格局；时间上，PUE受气象与植被动态因子共同调控，关键影响因子表现出显著的非线性阈值响应。（3）不同PUE值区域的主导驱动机制存在显著异质性：低PUE值区域主要受高蒸散与弱持水能力制约，而高PUE值区域则依赖低降水条件下高效的水分转化利用策略。本研究揭示了东北寒区PUE的多尺度驱动因素并识别了关键调控阈值，为区域“碳水”一体化管理、精准植被恢复及气候变化适应策略提供了定量依据。",null,"Agricultural Water Management","2026-09-10T00:00:00Z","论文",10,false,78,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},16,22,18,14,8,1,"基于2001—2024年多源遥感与SHAP可解释机器学习量化东北寒区降水利用效率驱动机制与生态阈值，方法新颖、数据规模大，对区域水土资源精准管理有参考价值，但属细分领域研究，公共影响有限。",[25],{"name":10,"url":6},[27,28,29,30,31],"机器学习","农业水资源","遥感","气候变化适应","东北黑土区",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":40,"locked":14,"version":41,"method":42,"evidence":43},"classified","2026-10-22.2","rules",{"candidates":44,"agricultural_evidence":47},[45,52,60,66],{"code":33,"score":46,"supported":47,"title":48,"abstract":50,"tags":51},15,true,[49],"machine learning",[27,49],[27],{"code":53,"score":54,"supported":47,"title":55,"abstract":56,"tags":59},"H7",7,[],[57,58],"气候变化","climate change",[30],{"code":61,"score":54,"supported":47,"title":62,"abstract":63,"tags":65},"I3",[],[29,64],"remote sensing",[29],{"code":67,"score":68,"supported":47,"title":69,"abstract":70,"tags":72},"H3",4,[],[71],"evapotranspiration",[28],[74,75],"气候变化适应 东北黑土区 农业水资源 机器学习","气候变化适应 东北黑土区","气候变化适应东北黑土区农业水资源机器学习-2329",2,"10.1016\u002Fj.agwat.2026.110763",{"doi":78,"openalex_id":80,"authors":81,"venue":10,"cited_by_count":96,"oa_url":6,"card":97,"direction":101,"ingested_from":103},"W7212162650",[82,84,87,90,92,94],{"name":83,"orcid":9},"Shuai Zou",{"name":85,"orcid":86},"Fanxiang Meng","https:\u002F\u002Forcid.org\u002F0009-0000-5015-1120",{"name":88,"orcid":89},"Ennan Zheng","https:\u002F\u002Forcid.org\u002F0000-0002-8186-8738",{"name":91,"orcid":9},"Tianxiao Li",{"name":93,"orcid":9},"Gang Li",{"name":95,"orcid":9},"Mo Li",0,{"tldr":98,"method":99,"finding":100,"direction":101,"opportunity":102},"基于多源遥感与可解释机器学习，揭示东北寒区降水利用效率时空特征及驱动因子。","2001-2024多源遥感数据，Theil-Sen、Mann-Kendall、H","PUE呈西北高东南低格局，驱动因子具非线性阈值与区域异质性。","农业遥感与作物表型","可结合碳通量数据，探究PUE与碳汇耦合机制及阈值调控的生态管理策略。","openalex","2026-09-13T23:30:25.912065Z",{"total":106,"page":22,"page_size":106,"items":107},6,[108,184,274,329,384,447],{"id":109,"title":110,"url":111,"summary":112,"summary_zh":113,"content":9,"source_name":114,"source_url":115,"published_at":116,"category":12,"cover_url":9,"hotness":117,"is_selected":14,"score":118,"score_detail":119,"sources":123,"tags":127,"primary_topic":130,"secondary_topics":131,"classification":132,"search_phrases":168,"slug":171,"view_count":96,"doi":172,"paper":173,"created_at":183},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":21,"substance":120,"depth":20,"authority":68,"freshness":121,"relevant":22,"comment":122},12,9,"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。",[124,125],{"name":114,"url":115},{"name":114,"url":126},"https:\u002F\u002Fajeee.co.in\u002Findex.php\u002Fajeee\u002Farticle\u002Fdownload\u002F6754\u002F5489",[27,29,128,129],"水资源管理","地下水监测",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":133},{"candidates":134,"agricultural_evidence":47},[135,139,143,150,155,162],{"code":33,"score":46,"supported":47,"title":136,"abstract":137,"tags":138},[49],[27,49],[27],{"code":61,"score":54,"supported":47,"title":140,"abstract":141,"tags":142},[],[29,64],[29],{"code":144,"score":106,"supported":47,"title":145,"abstract":146,"tags":149},"H2",[],[147,148],"土壤","soil",[],{"code":67,"score":68,"supported":47,"title":151,"abstract":152,"tags":154},[],[153],"水资源",[128],{"code":156,"score":157,"supported":47,"title":158,"abstract":159,"tags":161},"I4",3,[],[160],"空间分析",[],{"code":163,"score":157,"supported":47,"title":164,"abstract":165,"tags":167},"I7",[],[166],"methodological framework",[],[169,170],"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":172,"openalex_id":174,"authors":175,"venue":114,"cited_by_count":96,"oa_url":115,"card":178,"direction":101,"ingested_from":103},"W7222805722",[176],{"name":177,"orcid":9},"Prof. I Pandu Ranga Reddy Dr. Hari Ramavath",{"tldr":179,"method":180,"finding":181,"direction":101,"opportunity":182},"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":185,"title":186,"url":187,"summary":188,"summary_zh":189,"content":9,"source_name":190,"source_url":187,"published_at":191,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":192,"score_detail":193,"sources":197,"tags":199,"primary_topic":203,"secondary_topics":207,"classification":213,"search_phrases":228,"slug":231,"view_count":96,"doi":232,"paper":233,"created_at":273},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":120,"substance":194,"depth":17,"authority":195,"freshness":21,"relevant":22,"comment":196},20,13,"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。",[198],{"name":190,"url":187},[27,29,200,201,202],"土壤碳","Landsat","数字土壤制图",{"code":144,"slug":148,"name":204,"path":205,"parent_code":206},"土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",[208,209],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"code":61,"slug":210,"name":211,"path":212,"parent_code":37},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":40,"locked":14,"version":41,"method":42,"evidence":214},{"candidates":215,"agricultural_evidence":47},[216,220,224],{"code":144,"score":20,"supported":47,"title":217,"abstract":218,"tags":219},[148],[147,148],[],{"code":33,"score":121,"supported":47,"title":221,"abstract":222,"tags":223},[49],[],[27],{"code":61,"score":21,"supported":47,"title":225,"abstract":226,"tags":227},[],[29,64],[201,29],[229,230],"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":232,"openalex_id":234,"authors":235,"venue":190,"cited_by_count":96,"oa_url":9,"card":268,"direction":101,"ingested_from":103},"W7222107492",[236,239,242,245,248,251,254,257,259,262,265],{"name":237,"orcid":238},"P. A. Braulov","https:\u002F\u002Forcid.org\u002F0000-0001-9919-7402",{"name":240,"orcid":241},"Pavel M. Shilov","https:\u002F\u002Forcid.org\u002F0000-0003-4113-6396",{"name":243,"orcid":244},"R. G. Gadzhiumarov","https:\u002F\u002Forcid.org\u002F0000-0002-4220-623X",{"name":246,"orcid":247},"V. K. Dridiger","https:\u002F\u002Forcid.org\u002F0000-0002-0510-2220",{"name":249,"orcid":250},"E. V. Bogdan","https:\u002F\u002Forcid.org\u002F0009-0006-4781-5786",{"name":252,"orcid":253},"V. O. Megmerova","https:\u002F\u002Forcid.org\u002F0000-0001-8655-6437",{"name":255,"orcid":256},"Petr Tsymbarovich","https:\u002F\u002Forcid.org\u002F0000-0001-8591-2612",{"name":258,"orcid":9},"A. E. Shatunov",{"name":260,"orcid":261},"Pavel P. Fil","https:\u002F\u002Forcid.org\u002F0000-0002-9851-5381",{"name":263,"orcid":264},"D. E. Mitichkin","https:\u002F\u002Forcid.org\u002F0009-0006-2397-060X",{"name":266,"orcid":267},"Dmitriy S. Fomin","https:\u002F\u002Forcid.org\u002F0000-0003-3733-0284",{"tldr":269,"method":270,"finding":271,"direction":101,"opportunity":272},"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":275,"title":276,"url":277,"summary":278,"summary_zh":279,"content":9,"source_name":280,"source_url":277,"published_at":281,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":96,"score_detail":282,"sources":284,"tags":286,"primary_topic":289,"secondary_topics":290,"classification":291,"search_phrases":302,"slug":305,"view_count":96,"doi":306,"paper":307,"created_at":328},4317,"Machine-learning modelling of regional landslide susceptibility in eThekwini, South Africa","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-73316-x","The occurrence of landslides, particularly within urban landscapes, has gained significant research interest because of their devastating impacts on infrastructure, resulting in casualties, displacement, and economic losses. This study aimed to examine the probability of landslide events and landslide-prone areas within the eThekwini Metropolitan Municipality in KwaZulu-Natal Province, South Africa. To achieve this, robust machine learning models, including Random Forest (RF) and Support Vector Machines (SVM), combined with geospatial tools and key landslide-triggering factors, were considered in the analysis and characterised based on susceptibility indexes ranging from very low to very high based on various carefully chosen thresholds. The results indicate that land use, elevation, NDVI, and lithology are important landslide-influencing factors. In contrast, land use parameters, such as cultivated land and built-up areas, were associated with high susceptibility zones. Furthermore, RF yielded slightly higher overall accuracy scores than SVM, with accuracy scores of 99.45% and 98.63%, respectively. The SVM susceptibility output was further analysed based on the spatial distribution of formal and informal housing types. The results confirmed that only a small percentage of each housing type fell within the high-susceptibility zones, calculated as 1.33% and 2.41% for formal and informal housing, respectively. Although SVM is one of the strongest models, RF shows higher accuracy in landslide susceptibility modelling. Furthermore, its slightly higher recall score compared to its precision score is deemed most applicable for identifying landslide-prone areas. The study suggested that human-engineered land-use activities, such as road and property development, contribute significantly to increased landslide susceptibility within the eThekwini area.","滑坡的发生，尤其是在城市景观中，因其对基础设施的破坏性影响，导致人员伤亡、流离失所和经济损失，已引起广泛的研究关注。本研究旨在考察南非夸祖鲁-纳塔尔省eThekwini大都市自治市范围内滑坡事件的发生概率及滑坡易发区域。为实现这一目标，本研究在分析中采用了稳健的机器学习模型，包括随机森林（Random Forest, RF）和支持向量机（Support Vector Machines, SVM），并结合地理空间工具和关键滑坡触发因子，基于多种精心选取的阈值，按照从极低到极高的易发性指数进行了表征。结果表明，土地利用、海拔、归一化植被指数（NDVI）和岩性是重要的滑坡影响因素。相比之下，耕地和建成区等土地利用参数与高易发性区域相关。此外，RF的总体精度得分略高于SVM，分别为99.45%和98.63%。研究进一步基于正式住房和非正式住房类型的空间分布对SVM易发性输出进行了分析。结果证实，每种住房类型仅有一小部分位于高易发性区域内，正式住房和非正式住房分别为1.33%和2.41%。尽管SVM是最强的模型之一，但RF在滑坡易发性建模中表现出更高的精度。此外，其召回率得分略高于精确率得分，被认为最适合用于识别滑坡易发区域。研究提示，人为工程土地利用活动，如道路和房地产开发，对eThekwini地区滑坡易发性的增加具有显著贡献。","Scientific Reports","2026-10-04T00:00:00Z",{"impact":96,"substance":96,"depth":96,"authority":96,"freshness":96,"relevant":96,"comment":283},"南非城市滑坡易发性机器学习研究，属地质遥感领域，与三农、农业信息化、智慧农业无直接关联，不建议进入每日精选。",[285],{"name":280,"url":277},[27,29,287,288],"滑坡易发性","城市地质",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":292},{"candidates":293,"agricultural_evidence":47},[294,298],{"code":33,"score":54,"supported":47,"title":295,"abstract":296,"tags":297},[],[27,49],[27],{"code":61,"score":22,"supported":14,"title":299,"abstract":300,"tags":301},[],[],[29],[303,304],"eThekwini 滑坡 易发性","Random Forest 滑坡 建模","eThekwini滑坡易发性-4317","10.1038\u002Fs41598-026-73316-x",{"doi":306,"openalex_id":308,"authors":309,"venue":280,"cited_by_count":96,"oa_url":322,"card":323,"direction":101,"ingested_from":103},"W7219918606",[310,313,316,319],{"name":311,"orcid":312},"Cher Petersen","https:\u002F\u002Forcid.org\u002F0000-0002-0434-6928",{"name":314,"orcid":315},"Paidamwoyo Mhangara","https:\u002F\u002Forcid.org\u002F0000-0002-0594-6626",{"name":317,"orcid":318},"Laven Naidoo","https:\u002F\u002Forcid.org\u002F0000-0002-7091-0566",{"name":320,"orcid":321},"Eskinder Gidey","https:\u002F\u002Forcid.org\u002F0000-0001-6953-5562","https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-026-73316-x_reference.pdf",{"tldr":324,"method":325,"finding":326,"direction":101,"opportunity":327},"用随机森林与支持向量机评估南非eThekwini地区滑坡易发性并分析住房风险。","随机森林、支持向量机结合地理空间工具与NDVI、岩性等触发因子。","土地利用、高程、NDVI和岩性最关键；RF精度99.45%略高于SVM，非正式住房更易受灾。","可探索将滑坡易发性模型与农业土地利用规划结合，评估农田与乡村道路的灾害风险。","2026-10-06T23:30:21.860018Z",{"id":330,"title":331,"url":332,"summary":333,"summary_zh":9,"content":9,"source_name":334,"source_url":9,"published_at":335,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":336,"sources":338,"tags":340,"primary_topic":344,"secondary_topics":345,"classification":347,"search_phrases":370,"slug":373,"view_count":68,"doi":9,"paper":374,"created_at":383},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",{"impact":19,"substance":18,"depth":19,"authority":20,"freshness":106,"relevant":22,"comment":337},"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。",[339],{"name":334,"url":332},[341,342,27,29,343],"智慧农业","农业人工智能","土壤监测",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[346],{"code":144,"slug":148,"name":204,"path":205,"parent_code":206},{"status":40,"locked":14,"version":41,"method":42,"evidence":348},{"candidates":349,"agricultural_evidence":47},[350,356,361,365],{"code":33,"score":17,"supported":47,"title":351,"abstract":353,"tags":355},[352],"artificial intelligence",[354,27],"深度学习",[342,27],{"code":144,"score":357,"supported":47,"title":358,"abstract":359,"tags":360},11,[148],[147],[],{"code":61,"score":68,"supported":47,"title":362,"abstract":363,"tags":364},[],[29],[29],{"code":366,"score":22,"supported":14,"title":367,"abstract":368,"tags":369},"I1",[],[],[341],[371,372],"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":375,"venue":9,"cited_by_count":96,"oa_url":9,"card":376,"direction":380,"ingested_from":382},[],{"tldr":377,"method":378,"finding":379,"direction":380,"opportunity":381},"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。","农业人工智能与决策模型","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":385,"title":386,"url":387,"summary":388,"summary_zh":389,"content":9,"source_name":390,"source_url":387,"published_at":335,"category":12,"cover_url":9,"hotness":117,"is_selected":14,"score":391,"score_detail":392,"sources":394,"tags":398,"primary_topic":400,"secondary_topics":401,"classification":402,"search_phrases":431,"slug":434,"view_count":77,"doi":435,"paper":436,"created_at":446},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":21,"substance":194,"depth":17,"authority":21,"freshness":121,"relevant":22,"comment":393},"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。",[395,396],{"name":390,"url":387},{"name":390,"url":397},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23106954",[341,342,27,29,399],"农地制图",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":403},{"candidates":404,"agricultural_evidence":47},[405,411,415,421,427],{"code":33,"score":406,"supported":47,"title":407,"abstract":409,"tags":410},27,[49,408],"deep learning",[354,27,49,408],[342,27],{"code":61,"score":54,"supported":47,"title":412,"abstract":413,"tags":414},[],[29,64],[29],{"code":416,"score":157,"supported":47,"title":417,"abstract":418,"tags":420},"A8",[],[419],"粮食安全",[],{"code":422,"score":157,"supported":47,"title":423,"abstract":424,"tags":426},"J1",[],[425],"农业规划",[],{"code":366,"score":22,"supported":14,"title":428,"abstract":429,"tags":430},[],[],[341],[432,433],"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":435,"openalex_id":437,"authors":438,"venue":390,"cited_by_count":96,"oa_url":387,"card":441,"direction":101,"ingested_from":103},"W7219591984",[439],{"name":440,"orcid":9},"J.I. Igbokwe, C.E Ejikeme, J.O and Obi",{"tldr":442,"method":443,"finding":444,"direction":101,"opportunity":445},"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",{"id":448,"title":449,"url":450,"summary":451,"summary_zh":452,"content":9,"source_name":280,"source_url":450,"published_at":453,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":454,"score_detail":455,"sources":457,"tags":459,"primary_topic":462,"secondary_topics":463,"classification":464,"search_phrases":489,"slug":492,"view_count":54,"doi":493,"paper":494,"created_at":521},4171,"A machine learning framework for predicting potential urban cool island locations using Landsat 9 data: a case study of Oued Zenati, Algeria","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-72875-3","Abstract Urban heat stress is increasing in semi-arid Mediterranean towns, making the identification of Urban Cool Island (UCI) patterns essential for climate-resilient urban planning. This study developed an integrated remote sensing, GIS, and explainable machine-learning framework to map potential UCI locations in Oued Zenati, northeastern Algeria, using Landsat 9 imagery and geospatial environmental variables processed in Google Earth Engine. ArcGIS Desktop 10.8 was used for the final cartographic layout and map generation. Predictor variables included land surface temperature, albedo, elevation, slope, distance to roads, distance to rivers, and population density. Because field observations of UCIs were unavailable, proxy reference samples were generated from vegetation, moisture, and built-up indicators. Under the prevailing semi-arid conditions, NDWI values remained below − 0.06 across the study area, and all cool-zone reference samples were therefore derived from the vegetation criterion (NDVI ≥ 0.20). Four machine-learning algorithms (Random Forest, Gradient Tree Boosting, CART, and MaxEnt) were evaluated using a 70\u002F30 training-testing split and independent validation. Gradient Tree Boosting achieved the highest discrimination ability (ROC-AUC = 0.916), whereas Random Forest provided the best threshold-dependent performance, with an accuracy of 0.900, Kappa of 0.800, Precision of 0.929, and F1-score of 0.897. Susceptibility maps showed that cooling potential is concentrated in vegetated and agricultural areas, while built-up and bare surfaces exhibit low cooling potential. SHAP analysis identified elevation as the most influential predictor, followed by slope, albedo, and land surface temperature, whereas distance to roads, distance to rivers, and population density exerted comparatively weaker effects. The proposed framework provides a robust, interpretable, and transferable approach for Urban Cool Island susceptibility mapping, supporting climate adaptation, green infrastructure planning, and sustainable urban development in semi-arid cities.","摘要 在半干旱地中海城镇，城市热胁迫日益加剧，因此识别城市冷岛（Urban Cool Island, UCI）格局对于气候适应性城市规划至关重要。本研究开发了一个集成遥感、GIS和可解释机器学习的框架，利用Landsat 9影像和在Google Earth Engine中处理的地理空间环境变量，绘制了阿尔及利亚东北部Oued Zenati潜在UCI位置图。使用ArcGIS Desktop 10.8进行最终制图布局和地图生成。预测变量包括地表温度、反照率、高程、坡度、距道路距离、距河流距离和人口密度。由于缺乏UCI的实地观测数据，研究从植被、湿度和建成区指标生成了代理参考样本。在半干旱条件下，研究区NDWI值均低于−0.06，因此所有冷区参考样本均基于植被标准（NDVI ≥ 0.20）提取。采用70\u002F30的训练-测试划分和独立验证，评估了四种机器学习算法（随机森林、梯度树提升、CART和MaxEnt）。梯度树提升取得了最高的判别能力（ROC-AUC = 0.916），而随机森林在阈值依赖性能方面表现最佳，准确率为0.900，Kappa为0.800，精确率为0.929，F1分数为0.897。敏感性图显示，降温潜力集中在植被和农业区域，而建成区和裸地表面的降温潜力较低。SHAP分析表明，高程是最具影响力的预测变量，其次是坡度、反照率和地表温度，而距道路距离、距河流距离和人口密度的影响相对较弱。所提出的框架为城市冷岛敏感性制图提供了一种稳健、可解释且可迁移的方法，可支持半干旱城市的气候适应、绿色基础设施规划和可持续城市发展。","2026-10-03T00:00:00Z",66,{"impact":21,"substance":194,"depth":17,"authority":195,"freshness":121,"relevant":22,"comment":456},"方法新颖、结论可靠的城市冷岛遥感预测研究，对农业信息化与气候适应型规划有参考价值，但属区域案例、影响范围有限。",[458],{"name":280,"url":450},[341,27,29,460,461],"气候适应","城市热岛",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":465},{"candidates":466,"agricultural_evidence":47},[467,471,476,480,485],{"code":33,"score":120,"supported":47,"title":468,"abstract":469,"tags":470},[49],[27],[27],{"code":53,"score":54,"supported":47,"title":472,"abstract":473,"tags":475},[],[460,474],"干旱",[460],{"code":61,"score":54,"supported":47,"title":477,"abstract":478,"tags":479},[],[29,64],[29],{"code":156,"score":157,"supported":47,"title":481,"abstract":482,"tags":484},[],[483],"GIS",[],{"code":366,"score":22,"supported":14,"title":486,"abstract":487,"tags":488},[],[],[341],[490,491],"Landsat 9 城市冷岛 阿尔及利亚","Oued Zenati 城市冷岛 遥感","Landsat9城市冷岛阿尔及利亚-4171","10.1038\u002Fs41598-026-72875-3",{"doi":493,"openalex_id":495,"authors":496,"venue":280,"cited_by_count":96,"oa_url":450,"card":516,"direction":101,"ingested_from":103},"W7218855599",[497,499,501,504,507,510,513],{"name":498,"orcid":9},"Amina Naidja",{"name":500,"orcid":9},"Dalal FARID",{"name":502,"orcid":503},"Djamal Bengusmia","https:\u002F\u002Forcid.org\u002F0000-0003-4480-8637",{"name":505,"orcid":506},"Haythem Dinar","https:\u002F\u002Forcid.org\u002F0000-0002-4504-2963",{"name":508,"orcid":509},"Nouh Rebouh","https:\u002F\u002Forcid.org\u002F0000-0001-6214-2942",{"name":511,"orcid":512},"Imtiyaz Akbar Najar","https:\u002F\u002Forcid.org\u002F0000-0002-7338-6771",{"name":514,"orcid":515},"Nadeem Ahmad Khan","https:\u002F\u002Forcid.org\u002F0000-0003-4366-9639",{"tldr":517,"method":518,"finding":519,"direction":101,"opportunity":520},"用遥感与可解释机器学习预测阿尔及利亚半干旱城市潜在城市冷岛位置。","Landsat 9、Google Earth Engine、GIS与四种机器学习","梯度提升树判别最优（AUC=0.916），冷岛潜力集中于植被与农业区，海拔为最关键预测因子。","可迁移至其他半干旱城市，并引入时序遥感与实地冷岛观测验证，提升模型泛化性。","2026-10-04T23:30:24.545092Z"]