[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-5606":3,"related-5606":104},{"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":45,"search_phrases":78,"slug":81,"view_count":82,"doi":83,"paper":84,"created_at":103},5606,"Trends in soil organic carbon prediction research using geospatial technologies and artificial intelligence: an exploratory bibliometric analysis (2005-2025)","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.indic.2026.101585","Soil organic carbon (SOC) is central to soil fertility and climate regulation, and its spatial prediction increasingly relies on geospatial technologies and artificial intelligence (AI). Existing bibliometric studies and reviews have examined remote sensing-based soil organic matter monitoring, agricultural SOC components, or digital soil mapping separately, a bibliometric synthesis of how these strands have converged into GeoAI (geospatial AI: the integration of AI with spatially explicit data) for SOC prediction is lacking. This study presents an exploratory bibliometric analysis of SOC prediction research from 2005 to 2025. Scopus was searched on 25 March 2026 with a field-tagged Boolean query restricted to English-language journal articles, after screening and duplicate removal, 1561 articles were analyzed with Bibliometrix in R (performance analysis, co-authorship, co-citation, keyword co-occurrence). The annual growth rate was 28.68%, output rose sharply after 2018 and exceeded 300 articles in 2024, 40.49% of articles involved international co-authorship, and documents averaged 43.67 citations. China and the United States led in total citations (16,602 and 8,006, respectively), and China led in output. Geoderma, Science of the Total Environment, and Environmental Monitoring and Assessment were the most frequent sources, keyword analysis identified machine learning, remote sensing, and digital soil mapping as the methodological core. Output, citations and collaboration were concentrated in a few countries, with Africa, South Asia, and parts of Latin America underrepresented, which may limit model transferability, causes were not measured. As the analysis is bibliometric, findings describe research trends, not model performance or environmental outcomes.","土壤有机碳（SOC）对土壤肥力和气候调节至关重要，其空间预测日益依赖地理空间技术和人工智能（AI）。已有文献计量研究和综述分别考察了基于遥感的土壤有机质监测、农业SOC组分或数字土壤制图，但尚缺乏对这些研究方向如何汇聚为GeoAI（地理空间人工智能：人工智能与空间显式数据的整合）用于SOC预测的文献计量综合。本研究对2005年至2025年SOC预测研究进行了探索性文献计量分析。于2026年3月25日检索Scopus，采用字段标记的布尔查询并限定为英文期刊论文，经筛选和去重后，使用R语言中的Bibliometrix对1561篇文章进行分析（绩效分析、合著分析、共被引分析、关键词共现分析）。年增长率为28.68%，2018年后产出急剧上升，2024年超过300篇文章，40.49%的文章涉及国际合著，文献平均被引43.67次。中国和美国在总被引次数上领先（分别为16602次和8006次），中国在产出上领先。Geoderma、Science of the Total Environment和Environmental Monitoring and Assessment为发文最多的来源期刊，关键词分析识别出机器学习、遥感和数字土壤制图为方法学核心。产出、被引和合作集中于少数国家，非洲、南亚和拉丁美洲部分地区代表性不足，这可能限制模型的可迁移性，其原因未被测量。由于分析属于文献计量性质，研究结果描述的是研究趋势，而非模型性能或环境结果。",null,"Environmental and Sustainability Indicators","2026-10-21T00:00:00Z","论文",10,false,68,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},12,18,16,13,9,1,"基于1561篇文献的GeoAI土壤有机碳预测计量分析，方法规范、数据规模可观，对农业信息化研究趋势有参考价值，但属综述性论文，公共影响有限。",[25],{"name":10,"url":6},[27,28,29,30,31],"农业人工智能","土壤有机碳","遥感","文献计量","数字土壤制图",{"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",[39],{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},"H2","soil","土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",{"status":46,"locked":14,"version":47,"method":48,"evidence":49},"classified","2026-10-22.2","rules",{"candidates":50,"agricultural_evidence":52},[51,59,65,71],{"code":33,"score":18,"supported":52,"title":53,"abstract":55,"tags":58},true,[54],"artificial intelligence",[56,57,54],"机器学习","machine learning",[27],{"code":40,"score":60,"supported":52,"title":61,"abstract":62,"tags":64},15,[41],[63,41],"土壤",[28],{"code":66,"score":60,"supported":52,"title":67,"abstract":69,"tags":70},"I7",[68],"bibliometric",[30,68],[30],{"code":72,"score":73,"supported":52,"title":74,"abstract":75,"tags":77},"I3",7,[],[29,76],"remote sensing",[29],[79,80],"土壤有机碳 GeoAI 预测","SOC 数字土壤制图","土壤有机碳GeoAI预测-5606",0,"10.1016\u002Fj.indic.2026.101585",{"doi":83,"openalex_id":85,"authors":86,"venue":10,"cited_by_count":82,"oa_url":6,"card":96,"direction":100,"ingested_from":102},"W7223097074",[87,90,93],{"name":88,"orcid":89},"Elhoussaine Khaddi","https:\u002F\u002Forcid.org\u002F0009-0003-7735-6152",{"name":91,"orcid":92},"Hafida Zaher","https:\u002F\u002Forcid.org\u002F0000-0002-6835-2542",{"name":94,"orcid":95},"Hafida Naim","https:\u002F\u002Forcid.org\u002F0000-0001-7150-9179",{"tldr":97,"method":98,"finding":99,"direction":100,"opportunity":101},"用文献计量分析2005-2025年地理空间技术与AI预测土壤有机碳的研究趋势。","Scopus检索1561篇文献，用R的Bibliometrix做绩效、共被引与关","年增28.68%，2018年后激增；机器学习、遥感、数字土壤制图为核心方法。","农业遥感与作物表型","非洲、南亚、拉美研究不足，可探索GeoAI模型跨区域迁移与本地化验证。","openalex","2026-10-22T23:30:39.431690Z",{"total":105,"page":22,"page_size":105,"items":106},6,[107,194,271,325,413,467],{"id":108,"title":109,"url":110,"summary":111,"summary_zh":112,"content":9,"source_name":113,"source_url":110,"published_at":114,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":115,"score_detail":116,"sources":120,"tags":122,"primary_topic":125,"secondary_topics":126,"classification":132,"search_phrases":148,"slug":151,"view_count":82,"doi":152,"paper":153,"created_at":193},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":17,"substance":117,"depth":19,"authority":20,"freshness":118,"relevant":22,"comment":119},20,8,"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。",[121],{"name":113,"url":110},[56,29,123,124,31],"土壤碳","Landsat",{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},[127,128],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"code":72,"slug":129,"name":130,"path":131,"parent_code":37},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":46,"locked":14,"version":47,"method":48,"evidence":133},{"candidates":134,"agricultural_evidence":52},[135,140,144],{"code":40,"score":136,"supported":52,"title":137,"abstract":138,"tags":139},14,[41],[63,41],[],{"code":33,"score":21,"supported":52,"title":141,"abstract":142,"tags":143},[57],[],[56],{"code":72,"score":118,"supported":52,"title":145,"abstract":146,"tags":147},[],[29,76],[124,29],[149,150],"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":152,"openalex_id":154,"authors":155,"venue":113,"cited_by_count":82,"oa_url":9,"card":188,"direction":100,"ingested_from":102},"W7222107492",[156,159,162,165,168,171,174,177,179,182,185],{"name":157,"orcid":158},"P. A. Braulov","https:\u002F\u002Forcid.org\u002F0000-0001-9919-7402",{"name":160,"orcid":161},"Pavel M. Shilov","https:\u002F\u002Forcid.org\u002F0000-0003-4113-6396",{"name":163,"orcid":164},"R. G. Gadzhiumarov","https:\u002F\u002Forcid.org\u002F0000-0002-4220-623X",{"name":166,"orcid":167},"V. K. Dridiger","https:\u002F\u002Forcid.org\u002F0000-0002-0510-2220",{"name":169,"orcid":170},"E. V. Bogdan","https:\u002F\u002Forcid.org\u002F0009-0006-4781-5786",{"name":172,"orcid":173},"V. O. Megmerova","https:\u002F\u002Forcid.org\u002F0000-0001-8655-6437",{"name":175,"orcid":176},"Petr Tsymbarovich","https:\u002F\u002Forcid.org\u002F0000-0001-8591-2612",{"name":178,"orcid":9},"A. E. Shatunov",{"name":180,"orcid":181},"Pavel P. Fil","https:\u002F\u002Forcid.org\u002F0000-0002-9851-5381",{"name":183,"orcid":184},"D. E. Mitichkin","https:\u002F\u002Forcid.org\u002F0009-0006-2397-060X",{"name":186,"orcid":187},"Dmitriy S. Fomin","https:\u002F\u002Forcid.org\u002F0000-0003-3733-0284",{"tldr":189,"method":190,"finding":191,"direction":100,"opportunity":192},"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":195,"title":196,"url":197,"summary":198,"summary_zh":199,"content":9,"source_name":200,"source_url":197,"published_at":201,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":202,"score_detail":203,"sources":207,"tags":209,"primary_topic":213,"secondary_topics":214,"classification":217,"search_phrases":245,"slug":248,"view_count":82,"doi":249,"paper":250,"created_at":270},5006,"Mapping Soil Salinity in Arid Agricultural Regions Using Multi-Source Remote Sensing and a Long-Range Dependency-Enhanced Deep Learning Framework","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fland15101966","Soil salinity estimation across arid agricultural regions is challenging due to pronounced environmental heterogeneity and complex dependencies among multi-source variables. This study proposes a Long-Range Dependency-Enhanced Network (LRD-Net) for regional-scale soil salinity estimation in multiple agricultural oasis regions using multi-source remote sensing and environmental covariates. A dataset comprising 180 field samples from three agricultural oasis regions in Xinjiang, China, was constructed with 25 covariates derived from spectral, topographic, climatic, and soil property data. LRD-Net consists of three stages: a multi-scale feature fusion backbone based on depthwise separable convolutions and cross-scale interaction; a Long-Range Dependency Enhancement Module (LDEM) with an asymmetric dual-branch architecture that captures forward and reverse-aware dependencies through reverse alignment and cross-directional fusion; and multi-scale attention refinement with a regression head for continuous salinity estimation. Under the region-stratified random-split evaluation, LRD-Net achieved an R2 of 0.905, an RMSE of 1.207 g·kg−1, and an MAE of 0.868 g·kg−1. Performance decreased under more spatially independent validation, with an R2 of 0.874 under spatial cross-validation and LORO test R2 values ranging from 0.739 to 0.801, indicating that prediction across spatially and geographically independent samples is more challenging than region-stratified random-split evaluation. The proposed framework effectively integrates multi-source information and captures complementary long-range dependencies, providing a potential approach for regional-scale soil salinity estimation within the studied arid agricultural oasis environments and supporting soil salinization monitoring and sustainable land management in the study region.","干旱农业区域土壤盐分估算面临显著的环境异质性和多源变量间复杂依赖关系的挑战。本研究提出了一种长程依赖增强网络（LRD-Net），利用多源遥感与环境协变量对多个农业绿洲区域进行区域尺度土壤盐分估算。研究构建了包含中国新疆三个农业绿洲区域180个野外样本的数据集，并衍生出25个协变量，涵盖光谱、地形、气候和土壤属性数据。LRD-Net由三个阶段组成：基于深度可分离卷积和跨尺度交互的多尺度特征融合骨干网络；具有非对称双分支架构的长程依赖增强模块（LDEM），通过反向对齐和跨方向融合捕获前向与反向感知依赖关系；以及多尺度注意力细化与回归头，用于连续盐分估算。在区域分层随机划分评估下，LRD-Net取得了R²为0.905、RMSE为1.207 g·kg⁻¹、MAE为0.868 g·kg⁻¹的性能。在空间独立性更强的验证下性能有所下降，空间交叉验证R²为0.874，留一区域测试R²范围为0.739至0.801，表明跨空间和地理独立样本的预测比区域分层随机划分评估更具挑战性。所提出的框架有效整合了多源信息并捕获了互补的长程依赖关系，为研究区干旱农业绿洲环境下的区域尺度土壤盐分估算提供了潜在方法，并支持研究区土壤盐渍化监测与可持续土地管理。","Land","2026-10-14T00:00:00Z",72,{"impact":17,"substance":204,"depth":205,"authority":20,"freshness":21,"relevant":22,"comment":206},21,17,"方法新颖、数据扎实的遥感土壤盐渍化估算研究，对干旱区盐碱地监测与治理有参考价值，但属细分领域学术进展，公共影响有限。",[208],{"name":200,"url":197},[210,27,29,211,212],"智慧农业","土壤盐渍化","新疆农业",{"code":72,"slug":129,"name":130,"path":131,"parent_code":37},[215,216],{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":46,"locked":14,"version":47,"method":48,"evidence":218},{"candidates":219,"agricultural_evidence":52},[220,224,228,233,240],{"code":72,"score":60,"supported":52,"title":221,"abstract":222,"tags":223},[76],[29,76],[29],{"code":40,"score":136,"supported":52,"title":225,"abstract":226,"tags":227},[41],[63,41],[],{"code":33,"score":21,"supported":52,"title":229,"abstract":231,"tags":232},[230],"deep learning",[],[27],{"code":234,"score":235,"supported":52,"title":236,"abstract":237,"tags":239},"H7",3,[],[238],"干旱",[],{"code":241,"score":22,"supported":14,"title":242,"abstract":243,"tags":244},"I1",[],[],[210],[246,247],"新疆 农业绿洲 土壤盐渍化 遥感","LRD-Net 土壤盐分 估算","新疆农业绿洲土壤盐渍化遥感-5006","10.3390\u002Fland15101966",{"doi":249,"openalex_id":251,"authors":252,"venue":200,"cited_by_count":82,"oa_url":197,"card":265,"direction":100,"ingested_from":102},"W7221816183",[253,255,258,260,262],{"name":254,"orcid":9},"Mingjie Qian",{"name":256,"orcid":257},"Liangjun Wang","https:\u002F\u002Forcid.org\u002F0009-0006-8718-8326",{"name":259,"orcid":9},"Peng Wang",{"name":261,"orcid":9},"Hangyuan Liu",{"name":263,"orcid":264},"Weitao Chen","https:\u002F\u002Forcid.org\u002F0000-0002-6272-1618",{"tldr":266,"method":267,"finding":268,"direction":100,"opportunity":269},"提出LRD-Net深度学习框架，融合多源遥感与环境协变量，估算新疆干旱绿洲区土壤盐分。","构建180个样点、25个协变量的数据集，设计含长程依赖增强模块的多尺度网络。","区域分层随机划分下R²达0.905，但空间独立验证R²降至0.739-0.874，跨区域预测更难。","可探索跨区域迁移学习与不确定性量化，提升空间独立场景下盐分制图泛化能力。","2026-10-15T23:30:29.667342Z",{"id":272,"title":273,"url":274,"summary":275,"summary_zh":9,"content":9,"source_name":276,"source_url":9,"published_at":277,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":278,"score_detail":279,"sources":282,"tags":284,"primary_topic":286,"secondary_topics":287,"classification":289,"search_phrases":311,"slug":314,"view_count":303,"doi":9,"paper":315,"created_at":324},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":18,"substance":280,"depth":18,"authority":136,"freshness":105,"relevant":22,"comment":281},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。",[283],{"name":276,"url":274},[210,27,56,29,285],"土壤监测",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[288],{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},{"status":46,"locked":14,"version":47,"method":48,"evidence":290},{"candidates":291,"agricultural_evidence":52},[292,297,302,307],{"code":33,"score":19,"supported":52,"title":293,"abstract":294,"tags":296},[54],[295,56],"深度学习",[27,56],{"code":40,"score":298,"supported":52,"title":299,"abstract":300,"tags":301},11,[41],[63],[],{"code":72,"score":303,"supported":52,"title":304,"abstract":305,"tags":306},4,[],[29],[29],{"code":241,"score":22,"supported":14,"title":308,"abstract":309,"tags":310},[],[],[210],[312,313],"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":316,"venue":9,"cited_by_count":82,"oa_url":9,"card":317,"direction":321,"ingested_from":323},[],{"tldr":318,"method":319,"finding":320,"direction":321,"opportunity":322},"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":326,"title":327,"url":328,"summary":329,"summary_zh":330,"content":9,"source_name":331,"source_url":328,"published_at":332,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":333,"score_detail":334,"sources":336,"tags":338,"primary_topic":341,"secondary_topics":342,"classification":345,"search_phrases":376,"slug":379,"view_count":105,"doi":380,"paper":381,"created_at":412},2947,"AI-enabled UAV-based Soil Organic Carbon Mapping in Arid Environments: A Pilot Study Protocol","https:\u002F\u002Fdoi.org\u002F10.2174\u002F0118743315495282260915110324","Introduction Soil organic carbon (SOC) is an important indicator of soil health, agricultural productivity, and carbon sequestration potential. However, accurate and scalable SOC mapping in arid environments is constrained by high spatial heterogeneity and the limitations of conventional soil sampling. This study aims to develop a standardized UAV-enabled framework for high-resolution SOC mapping in arid agricultural environments. Methods A pilot-study protocol integrating UAV-based hyperspectral remote sensing with artificial intelligence and machine learning was developed. The workflow encompasses study-site selection, ground-reference sampling, UAV hyperspectral data acquisition, radiometric and geometric preprocessing, spectral feature extraction and selection, machine-learning model development, validation, uncertainty assessment, and performance evaluation using R 2 , RMSE, and MAE. The protocol also incorporates assessment of environmental confounders, including soil moisture, surface roughness, and crop residues. Results The resulting framework provides a systematic and reproducible workflow for UAV-based SOC estimation, integrating field observations, hyperspectral features, predictive modelling, and uncertainty assessment. It establishes defined procedures for evaluating model robustness and transferability across varying field conditions. Discussion The framework addresses an important methodological gap in UAV-enabled SOC mapping by integrating remote sensing and AI within a standardized pilot-study design. Its emphasis on environmental confounders and uncertainty assessment can improve the reliability and comparability of SOC mapping studies. However, field validation across diverse arid environments remains necessary. Conclusion The proposed protocol provides a practical foundation for reproducible SOC mapping and subsequent field validation, supporting precision agriculture, sustainable soil management, and carbon monitoring, reporting, and verification (MRV) in arid regions.","引言 土壤有机碳（SOC）是衡量土壤健康、农业生产力及碳固存潜力的重要指标。然而，干旱环境中高空间异质性和传统土壤采样的局限性制约了准确且可扩展的SOC制图。本研究旨在开发一个标准化的无人机（UAV）框架，用于干旱农业环境中的高分辨率SOC制图。方法 开发了一套整合无人机高光谱遥感与人工智能及机器学习的试点研究方案。该工作流程涵盖研究地点选择、地面参考采样、无人机高光谱数据采集、辐射与几何预处理、光谱特征提取与选择、机器学习模型开发、验证、不确定性评估，以及使用R²、RMSE和MAE进行的性能评价。该方案还包括对环境混杂因素的评估，包括土壤水分、地表粗糙度和作物残茬。结果 所构建的框架为基于无人机的SOC估算提供了系统且可重复的工作流程，整合了野外观测、高光谱特征、预测建模和不确定性评估。它建立了明确的程序，用于评估模型在不同田间条件下的稳健性和可迁移性。讨论 该框架通过将遥感与人工智能整合于标准化的试点研究设计中，填补了无人机SOC制图领域的重要方法学空白。其对环境混杂因素和不确定性评估的重视，可提高SOC制图研究的可靠性和可比性。然而，仍需在不同干旱环境中进行田间验证。结论 所提出的方案为可重复的SOC制图及后续田间验证提供了实用基础，支持干旱地区的精准农业、可持续土壤管理以及碳监测、报告与核查（MRV）。","The Open Agriculture Journal","2026-09-18T00:00:00Z",67,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":118,"relevant":22,"comment":335},"提出无人机高光谱结合AI的干旱区土壤有机碳制图标准化方案，方法框架清晰但尚属试点协议、缺乏实地验证，具备一定参考价值。",[337],{"name":331,"url":328},[210,27,339,29,340],"精准农业","土壤碳汇",{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},[343,344],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"code":72,"slug":129,"name":130,"path":131,"parent_code":37},{"status":46,"locked":14,"version":47,"method":48,"evidence":346},{"candidates":347,"agricultural_evidence":52},[348,352,356,361,366,372],{"code":40,"score":136,"supported":52,"title":349,"abstract":350,"tags":351},[41],[63,41],[],{"code":33,"score":13,"supported":52,"title":353,"abstract":354,"tags":355},[],[56,57,54],[27],{"code":72,"score":13,"supported":52,"title":357,"abstract":358,"tags":360},[],[29,76,359],"hyperspectral",[29],{"code":241,"score":118,"supported":52,"title":362,"abstract":363,"tags":365},[],[339,364],"precision agriculture",[210,339],{"code":367,"score":303,"supported":52,"title":368,"abstract":369,"tags":371},"H4",[],[370],"carbon sequestration",[340],{"code":234,"score":235,"supported":52,"title":373,"abstract":374,"tags":375},[],[238],[],[377,378],"无人机 土壤有机碳 制图","AI 高光谱 干旱农业","无人机土壤有机碳制图-2947","10.2174\u002F0118743315495282260915110324",{"doi":380,"openalex_id":382,"authors":383,"venue":331,"cited_by_count":82,"oa_url":328,"card":407,"direction":100,"ingested_from":102},"W7213561504",[384,387,390,393,396,399,401,403,405],{"name":385,"orcid":386},"Moath Awawdeh","https:\u002F\u002Forcid.org\u002F0000-0003-1404-6782",{"name":388,"orcid":389},"Irfan Ahmed","https:\u002F\u002Forcid.org\u002F0000-0002-2172-4177",{"name":391,"orcid":392},"Anees Bashir","https:\u002F\u002Forcid.org\u002F0000-0002-4668-6592",{"name":394,"orcid":395},"Tarig Faisal","https:\u002F\u002Forcid.org\u002F0000-0001-6451-7576",{"name":397,"orcid":398},"Nicky Rahmana Putra","https:\u002F\u002Forcid.org\u002F0000-0003-4886-496X",{"name":400,"orcid":9},"Almaha Jamal",{"name":402,"orcid":9},"Afra Rashed",{"name":404,"orcid":9},"Hamda Yousif",{"name":406,"orcid":9},"Sarah Sadeq",{"tldr":408,"method":409,"finding":410,"direction":100,"opportunity":411},"提出一套无人机高光谱结合AI的干旱区土壤有机碳制图标准化试点方案。","无人机高光谱遥感、地面采样、光谱特征选择与机器学习建模，用R²、RMSE、MAE","构建了可复现的SOC估算流程，并纳入环境混杂因素与不确定性评估。","可在多干旱区开展跨区域验证，探索模型迁移性与不确定性量化方法。","2026-09-19T23:30:33.273156Z",{"id":414,"title":415,"url":416,"summary":417,"summary_zh":418,"content":9,"source_name":419,"source_url":416,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":420,"score_detail":421,"sources":423,"tags":425,"primary_topic":429,"secondary_topics":430,"classification":432,"search_phrases":447,"slug":450,"view_count":82,"doi":451,"paper":452,"created_at":466},5583,"Active-Labeling Evaluation for Computer Agriculture Nematode-Cyst Detection Under Sparse Soil-Sample Ground Truth: An Artificial Intelligence Annotation-Efficiency Bound","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23544145","Active learning promises to reduce the annotation burden of training nematode-cyst detection models for precision agriculture, but the size of that reduction is not known when ground truth comes from sparse soil samples rather than exhaustive visual inspection. the present analysis derives an annotation-efficiency bound for pool-based active learning under sparse soil-sample ground truth. The detection task is formalised as a two-stage process in which a classifier selects candidate cysts from soil imagery and a laboratory assay confirms a small labelled subset. Under a declared variance structure with between-cluster standard deviation 6.0, residual standard deviation 4.5 and intraclass correlation 0.64, the bound is evaluated across a design grid of 8, 16, 24 and 32 clusters and effect sizes of 3, 5 and 8 percentage points, with 2000 replications per cell. The annotation-efficiency gain is bounded by the ratio of label noise to cluster-level variance, and that 52 clusters are required to detect a 5-percentage-point improvement at 80% power. The bound provides a design rule for allocating annotation effort between active selection and confirmatory soil sampling.","主动学习有望减轻精准农业中训练线虫囊检测模型所需的标注负担，但当真实标签来自稀疏土壤样本而非详尽的视觉检查时，这种负担减轻的幅度尚不清楚。本分析推导了在稀疏土壤样本真实标签下基于池的主动学习的标注效率界限。检测任务被形式化为两阶段过程：分类器从土壤图像中筛选候选线虫囊，实验室检测确认一个小的已标注子集。在设定的方差结构下——组间标准差为6.0、残差标准差为4.5、组内相关系数为0.64——该界限在8、16、24和32个簇的设计网格以及3、5和8个百分点的效应量下进行评估，每个单元格重复2000次。标注效率增益受标签噪声与簇级方差之比的约束，并且在80%检验功效下检测5个百分点的改进需要52个簇。该界限为在主动选择与验证性土壤采样之间分配标注工作量提供了设计规则。","Zenodo (CERN European Organization for Nuclear Research)",64,{"impact":118,"substance":117,"depth":205,"authority":21,"freshness":13,"relevant":22,"comment":422},"该研究给出稀疏土壤样本下主动学习标注效率的理论边界与聚类设计规则，方法新颖、结论具体，但属细分方法学研究，产业影响有限，适合作为专业精选而非头条。",[424],{"name":419,"url":416},[210,27,426,427,428],"主动学习","线虫检测","土壤采样",{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},[431],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":46,"locked":14,"version":47,"method":48,"evidence":433},{"candidates":434,"agricultural_evidence":52},[435,439,443],{"code":40,"score":136,"supported":52,"title":436,"abstract":437,"tags":438},[41],[63,41],[],{"code":33,"score":21,"supported":52,"title":440,"abstract":441,"tags":442},[54],[],[27],{"code":241,"score":73,"supported":52,"title":444,"abstract":445,"tags":446},[],[339,364],[210],[448,449],"线虫孢囊 检测 主动学习","稀疏土壤样本 标注效率","线虫孢囊检测主动学习-5583","10.5281\u002Fzenodo.23544145",{"doi":451,"openalex_id":453,"authors":454,"venue":419,"cited_by_count":82,"oa_url":416,"card":461,"direction":321,"ingested_from":102},"W7223082195",[455,457,459],{"name":456,"orcid":9},"Amine Ben Salah",{"name":458,"orcid":9},"Ines Trabelsi",{"name":460,"orcid":9},"Mohamed Aziz Khelifi",{"tldr":462,"method":463,"finding":464,"direction":321,"opportunity":465},"推导稀疏土壤样本真值下主动学习标注效率的理论上界。","基于方差结构与设计网格的统计模拟，2000次重复。","标注效率增益受标签噪声与簇间方差之比限制，检测5个百分点提升需52簇。","可将该上界推广到其他稀疏真值农业检测任务，并探索主动选择与确认采样的最优分配策略。","2026-10-22T11:20:58.901747Z",{"id":468,"title":469,"url":470,"summary":471,"summary_zh":472,"content":9,"source_name":419,"source_url":470,"published_at":473,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":115,"score_detail":474,"sources":476,"tags":478,"primary_topic":482,"secondary_topics":483,"classification":485,"search_phrases":501,"slug":504,"view_count":82,"doi":505,"paper":506,"created_at":519},4498,"SMART CROP SELECTION MODEL USING SOIL PH VALUE, TEMPERATURE, HUMIDITY, AND RAINFALL PREDICTION","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23211381","Crop suitability with soil and climatic conditions plays a vital role in increasing productivity of agriculture. This study proposes a smart crop selection model which recommends the suitable crop based on the machine learning techniques with the input parameters of soil pH, soil temperature, soil humidity and rainfall. The data set consisted of 1000 observations and 8 different crop classes and missing values were handled, crop labels were encoded and numerical features were selected. Five-fold cross validation was used to compare the performance of the three classifiers: Random Forest, XGBoost and Support Vector Machine (SVM). Finally, a Gradient-Boosted classification model was trained and evaluated with test-set accuracy, classification metrics, Multiclass ROC analysis and feature importance. The results of the application were 93.60% of the final test accuracy and the model comparison was used to compare the three classification methods. The contribution of four environmental parameters to the crop classification was analyzed by feature-importance analysis. To facilitate practical accessibility, the entire process was carried out using an interactive dashboard developed with Streamlit, allowing for the upload of datasets, evaluation of models, selection of parameters and the generation of predictions in real time for the crops of interest. The developed system is an example of how machine learning can be integrated with an interactive decision support interface to develop a data-driven, crop selection system, relying on simple soil and weather parameters.","作物适宜性与土壤及气候条件对提高农业生产率至关重要。本研究提出了一种智能作物选择模型，该模型基于机器学习技术，以土壤pH值、土壤温度、土壤湿度和降雨量为输入参数，推荐适宜的作物。数据集包含1000个观测值和8个不同作物类别，对缺失值进行了处理，对作物标签进行了编码，并筛选了数值特征。采用五折交叉验证比较了三种分类器——随机森林（Random Forest）、XGBoost和支持向量机（Support Vector Machine, SVM）的性能。最终，训练了一个梯度提升分类模型，并通过测试集准确率、分类指标、多类ROC分析和特征重要性进行了评估。应用结果为最终测试准确率93.60%，并通过模型比较对三种分类方法进行了对比。通过特征重要性分析，探讨了四个环境参数对作物分类的贡献。为便于实际应用，整个流程通过使用Streamlit开发的交互式仪表板实现，支持数据集上传、模型评估、参数选择以及针对感兴趣作物的实时预测生成。所开发的系统展示了如何将机器学习与交互式决策支持界面相结合，构建一个数据驱动的作物选择系统，且仅依赖于简单的土壤和气象参数。","2026-10-07T00:00:00Z",{"impact":17,"substance":117,"depth":19,"authority":20,"freshness":118,"relevant":22,"comment":475},"基于土壤pH、温湿度与降雨的机器学习选种模型，含93.6%测试精度与Streamlit交互看板，方法完整但属常规应用型研究，产业影响有限。",[477],{"name":419,"url":470},[210,27,479,480,481],"决策支持系统","土壤墒情","作物选择",{"code":40,"slug":41,"name":42,"path":43,"parent_code":44},[484],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":46,"locked":14,"version":47,"method":48,"evidence":486},{"candidates":487,"agricultural_evidence":52},[488,492,497],{"code":40,"score":60,"supported":52,"title":489,"abstract":490,"tags":491},[41],[63,41],[480],{"code":33,"score":298,"supported":52,"title":493,"abstract":494,"tags":496},[],[56,57,495],"decision support",[27,479],{"code":241,"score":22,"supported":14,"title":498,"abstract":499,"tags":500},[],[],[210],[502,503],"土壤pH 降雨量 作物选择模型","机器学习 作物推荐 智慧农业","土壤pH降雨量作物选择模型-4498","10.5281\u002Fzenodo.23211381",{"doi":505,"openalex_id":507,"authors":508,"venue":419,"cited_by_count":82,"oa_url":470,"card":513,"direction":518,"ingested_from":102},"W7220991946",[509,511],{"name":510,"orcid":9},"C. SAI KUMAR",{"name":512,"orcid":9},"Prof. G SREENIVASULU",{"tldr":514,"method":515,"finding":516,"direction":321,"opportunity":517},"基于土壤pH、温湿度和降雨，用机器学习构建智能选种模型并开发交互式仪表板。","1000条8类作物数据，五折交叉验证比较RF、XGBoost、SVM，最终用梯度","梯度提升模型测试准确率达93.60%，特征重要性揭示四参数对选种的贡献。","可引入时序气象与多源土壤数据，提升模型泛化性并适配不同区域作物推荐。","智慧农业 \u002F 农业物联网","2026-10-09T23:30:12.285129Z"]