[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3178":3,"related-3178":109},{"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":31,"secondary_topics":37,"classification":38,"search_phrases":71,"slug":74,"view_count":21,"doi":75,"paper":76,"created_at":108},3178,"Geostatistics and Spatial Modelling in Soil Science: A Critical Appraisal of Methods, Advantages, Inconveniences and Applications","https:\u002F\u002Fdoi.org\u002F10.9734\u002Fajoger\u002F2026\u002Fv9i3302","Soil properties vary continuously across space and time, making spatial prediction at unsampled locations fundamental to soil science. Geostatistics has provided a coherent framework for quantifying, mapping and communicating this variation for several decades. However, its role is increasingly challenged by machine learning, extensive environmental covariates from remote and proximal sensing, and growing demands for national and global soil information with reliable uncertainty estimates. This review critically evaluates the methodological foundations, strengths, limitations and applications of geostatistical and hybrid spatial modelling in soil science. Relevant literature was identified through structured searches of scholarly databases and citation tracking and assessed for methodological adequacy, validation quality, transparency and relevance. Five major issues emerge. First, key assumptions underlying kriging, particularly stationarity of the mean and covariance structure, are frequently violated in soil datasets, while the implications are often inadequately reported. Second, variogram estimation remains central to geostatistics, but limited sample sizes in many studies reduce its reliability and weaken interpretations of spatial dependence. Third, comparisons among kriging methods, regression-kriging and machine learning show inconsistent performance, largely because of differences in sampling design, covariate quality, extrapolation requirements and validation procedures. Fourth, although uncertainty quantification has improved conceptually, its practical validation remains inadequate, raising concerns about reported model accuracy. Fifth, applications in precision agriculture, contamination assessment, salinity management and soil carbon accounting differ substantially in evidential maturity, with soil carbon monitoring showing notable gaps between mapped precision and decision-grade reliability. Overall, geostatistics remains important for representing spatial dependence, designing sampling strategies and quantifying uncertainty. Future advances are likely to be strongest when geostatistical methods and machine learning are integrated rather than treated as competing alternatives.","土壤属性在空间和时间上连续变化，因此对未采样位置进行空间预测是土壤科学的基础。几十年来，地统计学为量化、制图与传达这种变异提供了一个连贯的框架。然而，其作用正日益受到机器学习的挑战，后者依托遥感和近地传感获取的大量环境协变量，并且对具有可靠不确定性估计的国家和全球土壤信息的需求不断增长。本文综述批判性地评估了地统计学与混合空间建模在土壤科学中的方法学基础、优势、局限与应用。相关文献通过结构化检索学术数据库和引文追踪识别，并对其方法学充分性、验证质量、透明度和相关性进行了评估。由此浮现出五个主要问题。第一，克里金法的关键假设，特别是均值与协方差结构的平稳性，在土壤数据集中常被违背，而其影响往往未得到充分报告。第二，变异函数估计仍然是地统计学的核心，但许多研究中有限的样本量降低了其可靠性，并削弱了对空间依赖性的解释。第三，克里金方法、回归克里金与机器学习之间的比较显示出不一致的表现，这主要是由于采样设计、协变量质量、外推需求和验证程序方面的差异。第四，尽管不确定性量化在概念上有所改进，但其实际验证仍然不足，引发了对所报告模型精度的担忧。第五，在精准农业、污染评估、盐渍化管理与土壤碳核算中的应用，其证据成熟度差异显著，其中土壤碳监测在地图精度与决策级可靠性之间显示出明显差距。总体而言，地统计学对于表征空间依赖性、设计采样策略和量化不确定性仍然重要。未来的进展很可能在地统计方法与机器学习实现整合而非被视为相互竞争的替代方案时最为显著。",null,"OpenAlex","2026-09-21T00:00:00Z","论文",10,false,79,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":20,"relevant":21,"comment":22},18,22,13,8,1,"系统评述地统计学与机器学习融合的土壤空间建模方法，对精准农业与土壤碳核算有实质参考价值。",[24],{"name":10,"url":6},[26,27,28,29,30],"机器学习","精准农业","空间建模","土壤科学","地统计学",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},"H2","soil","土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",[],{"status":39,"locked":14,"version":40,"method":41,"evidence":42},"classified","2026-10-22.2","rules",{"candidates":43,"agricultural_evidence":46},[44,51,58,64],{"code":32,"score":45,"supported":46,"title":47,"abstract":48,"tags":50},14,true,[33],[49,33],"土壤",[],{"code":52,"score":53,"supported":46,"title":54,"abstract":55,"tags":57},"I1",7,[],[27,56],"precision agriculture",[27],{"code":59,"score":53,"supported":46,"title":60,"abstract":61,"tags":63},"I2",[],[26,62],"machine learning",[26],{"code":65,"score":66,"supported":46,"title":67,"abstract":68,"tags":70},"I3",3,[],[69],"遥感",[],[72,73],"地统计学 土壤空间预测","土壤碳监测 不确定性评估","地统计学土壤空间预测-3178","10.9734\u002Fajoger\u002F2026\u002Fv9i3302",{"doi":75,"openalex_id":77,"authors":78,"venue":9,"cited_by_count":100,"oa_url":6,"card":101,"direction":105,"ingested_from":107},"W7213933504",[79,81,83,85,87,89,92,94,96,98],{"name":80,"orcid":9},"Primus Azinwi Tamfuh",{"name":82,"orcid":9},"Bertrand Kenzong",{"name":84,"orcid":9},"Hassan Yap Mfouapon",{"name":86,"orcid":9},"Colete Nyuongo Nayah",{"name":88,"orcid":9},"Chantal Kuh Ful",{"name":90,"orcid":91},"Evariste Moundjeu","https:\u002F\u002Forcid.org\u002F0009-0008-5475-1017",{"name":93,"orcid":9},"Georges Simplice Kouedeu Kameni",{"name":95,"orcid":9},"Achille Ibrahim",{"name":97,"orcid":9},"Joseph Zetekouang Guepi Vounang",{"name":99,"orcid":9},"Dieudonné Bitom",0,{"tldr":102,"method":103,"finding":104,"direction":105,"opportunity":106},"综述地统计学与混合空间建模在土壤科学中的方法、优势、局限及应用，指出其与机器学习融合是未来方向。","结构化文献检索与引文追踪，批判性评估克里金、回归克里金及机器学习等方法。","地统计学仍关键，但假设违背、变异函数可靠性、方法比较不一致及不确定性验证不足等问题突出。","农业遥感与作物表型","可探索地统计学与机器学习融合框架，并针对土壤碳监测等应用提升不确定性验证与决策级可靠性。","openalex","2026-09-22T23:30:23.641691Z",{"total":110,"page":21,"page_size":110,"items":111},6,[112,167,257,343,429,511],{"id":113,"title":114,"url":115,"summary":116,"summary_zh":9,"content":9,"source_name":117,"source_url":9,"published_at":118,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":119,"score_detail":120,"sources":125,"tags":127,"primary_topic":131,"secondary_topics":132,"classification":133,"search_phrases":153,"slug":156,"view_count":100,"doi":9,"paper":157,"created_at":166},5462,"Architecture diverse TabNet ensemble for crop type classification using harmonized multisource soil data（基于多源土壤数据融合的架构多样性TabNet集成作物类型分类）","https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41598-026-75366-7","对18,237条多源土壤记录、7类作物构建TabNet集成框架。TPE优化使对数损失由0.3325降至0.2566，集成后准确率0.9053、宏F1 0.9025，优于XGBoost的0.8724。作者称尚未做外部验证。","Scientific Reports 2026-10-18","2026-10-18T00:00:00Z",70,{"impact":121,"substance":122,"depth":123,"authority":19,"freshness":20,"relevant":21,"comment":124},12,20,17,"方法新颖、数据规模可观且指标有实质提升，但缺乏外部验证、属细分方法研究，公共影响有限，可作候选而非必选。",[126],{"name":117,"url":115},[128,26,27,129,130],"农业人工智能","土壤数据","作物分类",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":14,"version":40,"method":41,"evidence":134},{"candidates":135,"agricultural_evidence":46},[136,140,145,149],{"code":32,"score":122,"supported":46,"title":137,"abstract":138,"tags":139},[49,33],[49],[129],{"code":59,"score":141,"supported":14,"title":142,"abstract":143,"tags":144},2,[],[],[128,26],{"code":52,"score":21,"supported":14,"title":146,"abstract":147,"tags":148},[],[],[27],{"code":65,"score":21,"supported":14,"title":150,"abstract":151,"tags":152},[],[],[130],[154,155],"TabNet 作物类型分类","多源土壤数据 作物分类","TabNet作物类型分类-5462",{"doi":9,"openalex_id":9,"authors":158,"venue":9,"cited_by_count":100,"oa_url":9,"card":159,"direction":163,"ingested_from":165},[],{"tldr":160,"method":161,"finding":162,"direction":163,"opportunity":164},"构建架构多样性TabNet集成，用多源土壤数据分类7类作物。","18,237条多源土壤记录，TPE调参的TabNet集成，对比XGBoost。","集成后准确率0.9053、宏F1 0.9025，优于XGBoost的0.8724。","农业人工智能与决策模型","尚未外部验证，可跨区域迁移验证并融合遥感时序特征提升泛化。","agent","2026-10-21T00:10:08.428584Z",{"id":168,"title":169,"url":170,"summary":171,"summary_zh":172,"content":9,"source_name":173,"source_url":170,"published_at":174,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":175,"sources":177,"tags":179,"primary_topic":183,"secondary_topics":184,"classification":190,"search_phrases":227,"slug":230,"view_count":231,"doi":232,"paper":233,"created_at":256},3516,"Approaches to forecast soil nutrient dynamics for precision agriculture and sustainable fertiliser management: A review","https:\u002F\u002Fdoi.org\u002F10.14719\u002Fpst.16160","Predictive modelling of soil nutrient dynamics is an essential tool for promoting sustainable agricultural practices and environmentally responsible farming methods. The statistical and machine learning techniques used to forecast the availability and dynamics of soil nutrients are summarised in this review. The core frameworks for measuring spatio-temporal nutritional variability are established by traditional statistical approaches such as time-series models autoregressive integrated moving average (ARIMA), seasonal autoregressive integrated moving average (SARIMA), multivariate techniques (Principal component analysis (PCA) and factor analysis) and geostatistical tools (kriging). By capturing intricate nonlinear interactions within heterogeneous agroecosystems, machine learning techniques like random forest, support vector machines and ensemble approaches (XGBoost, LightGBM and AdaBoost) provide higher prediction accuracy. Forecasting capabilities are further enhanced by hybrid frameworks [Autoregressive integrated moving average with exogenous variables–artificial neural network. (ARIMAX-ANN)] and deep learning architectures (Convolutional neural network (CNN), long short-term memory (LSTM), ANN). With R2 values above 0.93 and notable decreases in prediction errors, ensemble approaches routinely perform better than traditional linear models. Nevertheless, persistent challenges include data quality limitations, spatial sampling constraints, insufficient environmental covariates and reduced model transferability across diverse pedoclimatic regions. Integrating high-resolution soil properties, climatic variables, terrain attributes and spectral information with advanced modelling architectures remains crucial for enhancing predictive reliability, ultimately supporting precision nutrient management, improved fertiliser efficiency and environmentally responsible agricultural systems.","土壤养分动态的预测建模是推动可持续农业实践和环境友好型耕作方法的重要工具。本综述总结了用于预测土壤养分有效性及其动态变化的统计与机器学习技术。传统统计方法，如时间序列模型自回归积分滑动平均模型（ARIMA）、季节性自回归积分滑动平均模型（SARIMA）、多变量技术（主成分分析（PCA）和因子分析）以及地统计工具（克里金法），为量化养分的时空变异性奠定了核心框架。通过捕捉异质性农业生态系统中复杂的非线性相互作用，随机森林、支持向量机和集成方法（XGBoost、LightGBM和AdaBoost）等机器学习技术可实现更高的预测精度。混合框架[含外生变量的自回归积分滑动平均模型–人工神经网络（ARIMAX-ANN）]和深度学习架构（卷积神经网络（CNN）、长短期记忆网络（LSTM）、人工神经网络（ANN））进一步增强了预测能力。集成方法的R²值超过0.93，且预测误差显著降低，其表现通常优于传统线性模型。然而，持续存在的挑战包括数据质量限制、空间采样约束、环境协变量不足以及模型在不同土壤气候区域间可迁移性降低等问题。将高分辨率土壤属性、气候变量、地形属性和光谱信息与先进建模架构相结合，对于提高预测可靠性仍然至关重要，最终可为精准养分管理、提高肥料利用效率以及环境友好型农业系统提供支撑。","Plant Science Today","2026-09-24T00:00:00Z",{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":20,"relevant":21,"comment":176},"系统综述土壤养分动态预测的统计与机器学习方法，方法体系完整、结论有量化支撑，对精准施肥与农业信息化有参考价值，但属综述类论文，产业级影响有限。",[178],{"name":173,"url":170},[180,181,26,27,182],"智慧农业","变量施肥","土壤养分",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[185],{"code":59,"slug":186,"name":187,"path":188,"parent_code":189},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":39,"locked":14,"version":40,"method":41,"evidence":191},{"candidates":192,"agricultural_evidence":46},[193,198,202,208,215,221],{"code":32,"score":194,"supported":46,"title":195,"abstract":196,"tags":197},15,[33],[49,33],[182],{"code":52,"score":13,"supported":46,"title":199,"abstract":200,"tags":201},[56],[],[180,27],{"code":59,"score":13,"supported":46,"title":203,"abstract":204,"tags":207},[],[205,26,62,206],"深度学习","deep learning",[26],{"code":209,"score":53,"supported":46,"title":210,"abstract":211,"tags":214},"F3",[],[212,213],"肥料","养分管理",[181],{"code":216,"score":66,"supported":46,"title":217,"abstract":218,"tags":220},"H6",[],[219],"农业生态",[],{"code":222,"score":66,"supported":46,"title":223,"abstract":224,"tags":226},"H8",[],[225],"可持续农业",[],[228,229],"土壤养分 预测模型 精准农业","机器学习 施肥管理 可持续农业","土壤养分预测模型精准农业-3516",4,"10.14719\u002Fpst.16160",{"doi":232,"openalex_id":234,"authors":235,"venue":173,"cited_by_count":100,"oa_url":170,"card":251,"direction":163,"ingested_from":107},"W7214167059",[236,239,242,245,248],{"name":237,"orcid":238},"R Rathna","https:\u002F\u002Forcid.org\u002F0009-0004-7797-2673",{"name":240,"orcid":241},"B Sivasankari","https:\u002F\u002Forcid.org\u002F0000-0001-9921-8170",{"name":243,"orcid":244},"R. Gangai Selvi","https:\u002F\u002Forcid.org\u002F0000-0002-4475-2293",{"name":246,"orcid":247},"J Prabhakaran","https:\u002F\u002Forcid.org\u002F0000-0001-7339-175X",{"name":249,"orcid":250},"K. G. Sabarinathan","https:\u002F\u002Forcid.org\u002F0000-0002-8659-6479",{"tldr":252,"method":253,"finding":254,"direction":163,"opportunity":255},"综述土壤养分动态预测的统计与机器学习方法，比较精度与局限。","综述ARIMA、地统计、随机森林、XGBoost、CNN\u002FLSTM及混合模型。","集成与深度学习模型精度更高（R²>0.93），但数据质量与跨区迁移性仍是瓶颈。","可研究多源遥感与气候数据融合的迁移学习模型，提升跨区域养分预测泛化能力。","2026-09-25T23:30:54.950445Z",{"id":258,"title":259,"url":260,"summary":261,"summary_zh":262,"content":9,"source_name":263,"source_url":260,"published_at":264,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":265,"score_detail":266,"sources":270,"tags":272,"primary_topic":276,"secondary_topics":282,"classification":285,"search_phrases":319,"slug":322,"view_count":100,"doi":323,"paper":324,"created_at":342},5558,"Estimation of Soil Water Content in Winter Wheat Field at Jointing Stage Using Multi-Source Features and Machine Learning","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fagronomy16202071","Accurate and timely monitoring of soil water content (SWC) plays an essential supporting role in crop irrigation management and smart agricultural practice. Remote sensing technology provides rapid and convenient approaches to large-scale farmland SWC estimation or inversion. However, existing mechanistic modeling methods are limited by parameter localization and land surface heterogeneity, while machine learning data-driven methods lack quite good physical interpretability. To address deficiencies in single data-driven methods and single vegetation microwave scattering models, and explore the estimation effect of different feature variables in machine learning. This study proposes an innovative estimation model that integrates machine learning strategies and multi-source features, including spectral indices and features derived from the classic water cloud model (WCM). The novelty of the proposed model lies in balancing physical interpretability and data-driven accuracy, namely extracting relevant soil backscattering parameters through WCM, which are then used as input features in the machine learning. A combination of field-measured data and unmanned aerial vehicle (UAV) multi-source remote sensing data, including multispectral and synthetic aperture radar (SAR) data, was acquired synchronously at the jointing stage of winter wheat. Through extracting variables such as the SAR microwave backscattering coefficient and the optical vegetation index, and conducting feature screening and parameter sensitivity analysis, we optimized the input variable sets of models based on back-propagation (BP) neural network, support vector regression (SVR) and random forest (RF) algorithms. The study results showed that the established estimation model had excellent estimation performance, especially for the RF algorithm, with the highest R2 of 0.855, lowest MAE of 0.0212 cm3\u002Fcm3, and lowest RMSE of 0.0253 cm3\u002Fcm3. It was also shown that different feature input schemes have obvious effects on SWC estimation performance. On the whole, RF had the best estimation accuracy, followed by SVR and then BPNN. This study demonstrated that models integrating multi-source remote sensing data and machine learning could enhance SWC estimation ability for winter wheat fields, and could also serve as a promising approach for SWC monitoring in winter wheat fields in the North China Plain.","准确、及时地监测土壤含水量（SWC）对作物灌溉管理和智慧农业实践具有重要的支撑作用。遥感技术为大规模农田土壤含水量估算或反演提供了快速便捷的手段。然而，现有机理建模方法受参数本地化和地表异质性限制，机器学习数据驱动方法则缺乏良好的物理解释性。针对单一数据驱动方法和单一植被微波散射模型的不足，并探究不同特征变量在机器学习中的估算效果，本研究提出了一种融合机器学习策略与多源特征的创新估算模型，所采用特征包括光谱指数和经典水云模型（WCM）衍生的特征。该模型的新颖性在于平衡物理解释性与数据驱动精度，即通过WCM提取相关土壤后向散射参数，再将其作为机器学习的输入特征。研究在冬小麦拔节期同步获取了田间实测数据与无人机（UAV）多源遥感数据，包括多光谱和合成孔径雷达（SAR）数据。通过提取SAR微波后向散射系数和光学植被指数等变量，并进行特征筛选和参数敏感性分析，优化了基于反向传播（BP）神经网络、支持向量回归（SVR）和随机森林（RF）算法的模型输入变量集。研究结果表明，所建立的估算模型具有优良的估算性能，尤其是RF算法，最高R²为0.855，最低MAE为0.0212 cm³\u002Fcm³，最低RMSE为0.0253 cm³\u002Fcm³。研究还表明，不同特征输入方案对土壤含水量估算性能有明显影响。总体而言，RF估算精度最佳，SVR次之，BPNN再次之。本研究证明，融合多源遥感数据与机器学习的模型能够提升冬小麦田土壤含水量估算能力，也可为华北平原冬小麦田土壤含水量监测提供一种有前景的方法。","Agronomy","2026-10-21T00:00:00Z",77,{"impact":267,"substance":268,"depth":123,"authority":19,"freshness":13,"relevant":21,"comment":269},16,21,"该研究融合多源遥感与机器学习估算冬小麦拔节期土壤含水量，方法有创新、结论可靠，对智慧灌溉有参考价值，但属细分领域论文，影响范围有限。",[271],{"name":263,"url":260},[180,26,273,274,275],"遥感监测","土壤墒情","冬小麦",{"code":277,"slug":278,"name":279,"path":280,"parent_code":281},"A2","wheat","小麦","\u002Ftopic\u002Ffield-crops\u002Fwheat","A",[283,284],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"code":59,"slug":186,"name":187,"path":188,"parent_code":189},{"status":39,"locked":14,"version":40,"method":41,"evidence":286},{"candidates":287,"agricultural_evidence":46},[288,294,298,302,308,315],{"code":277,"score":289,"supported":46,"title":290,"abstract":292,"tags":293},26,[291,278],"winter wheat",[279,291,278],[275],{"code":32,"score":194,"supported":46,"title":295,"abstract":296,"tags":297},[33],[49,33],[274],{"code":59,"score":194,"supported":46,"title":299,"abstract":300,"tags":301},[62],[26,62],[26],{"code":65,"score":13,"supported":46,"title":303,"abstract":304,"tags":307},[],[69,305,306],"remote sensing","multispectral",[273],{"code":309,"score":110,"supported":46,"title":310,"abstract":311,"tags":314},"H3",[],[312,313],"灌溉","irrigation",[],{"code":52,"score":231,"supported":46,"title":316,"abstract":317,"tags":318},[],[180],[180],[320,321],"冬小麦 土壤含水量 遥感","多源遥感 机器学习 墒情","冬小麦土壤含水量遥感-5558","10.3390\u002Fagronomy16202071",{"doi":323,"openalex_id":325,"authors":326,"venue":263,"cited_by_count":100,"oa_url":260,"card":336,"direction":341,"ingested_from":107},"W7223156204",[327,330,332,334],{"name":328,"orcid":329},"Mingliang Jiang","https:\u002F\u002Forcid.org\u002F0000-0002-6486-6087",{"name":331,"orcid":9},"Yi Zhang",{"name":333,"orcid":9},"WEI Lei",{"name":335,"orcid":9},"Chengcai Zhang",{"tldr":337,"method":338,"finding":339,"direction":105,"opportunity":340},"融合WCM物理特征与多源遥感，用机器学习估算冬小麦拔节期土壤含水量。","无人机多光谱与SAR数据，WCM参数+光谱指数，BP\u002FSVR\u002FRF建模。","RF最优，R²达0.855，RMSE为0.0253 cm³\u002Fcm³，特征方案影响显著。","可探索物理约束与深度学习耦合，并迁移至多生育期、多作物及不同土壤质地验证。","智慧农业 \u002F 农业物联网","2026-10-22T11:20:18.887301Z",{"id":344,"title":345,"url":346,"summary":347,"summary_zh":348,"content":9,"source_name":349,"source_url":346,"published_at":350,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":351,"score_detail":352,"sources":354,"tags":356,"primary_topic":360,"secondary_topics":361,"classification":367,"search_phrases":383,"slug":386,"view_count":100,"doi":387,"paper":388,"created_at":428},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":121,"substance":122,"depth":267,"authority":19,"freshness":20,"relevant":21,"comment":353},"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。",[355],{"name":349,"url":346},[26,69,357,358,359],"土壤碳","Landsat","数字土壤制图",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[362,363],{"code":59,"slug":186,"name":187,"path":188,"parent_code":189},{"code":65,"slug":364,"name":365,"path":366,"parent_code":189},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":39,"locked":14,"version":40,"method":41,"evidence":368},{"candidates":369,"agricultural_evidence":46},[370,374,379],{"code":32,"score":45,"supported":46,"title":371,"abstract":372,"tags":373},[33],[49,33],[],{"code":59,"score":375,"supported":46,"title":376,"abstract":377,"tags":378},9,[62],[],[26],{"code":65,"score":20,"supported":46,"title":380,"abstract":381,"tags":382},[],[69,305],[358,69],[384,385],"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":387,"openalex_id":389,"authors":390,"venue":349,"cited_by_count":100,"oa_url":9,"card":423,"direction":105,"ingested_from":107},"W7222107492",[391,394,397,400,403,406,409,412,414,417,420],{"name":392,"orcid":393},"P. A. Braulov","https:\u002F\u002Forcid.org\u002F0000-0001-9919-7402",{"name":395,"orcid":396},"Pavel M. Shilov","https:\u002F\u002Forcid.org\u002F0000-0003-4113-6396",{"name":398,"orcid":399},"R. G. Gadzhiumarov","https:\u002F\u002Forcid.org\u002F0000-0002-4220-623X",{"name":401,"orcid":402},"V. K. Dridiger","https:\u002F\u002Forcid.org\u002F0000-0002-0510-2220",{"name":404,"orcid":405},"E. V. Bogdan","https:\u002F\u002Forcid.org\u002F0009-0006-4781-5786",{"name":407,"orcid":408},"V. O. Megmerova","https:\u002F\u002Forcid.org\u002F0000-0001-8655-6437",{"name":410,"orcid":411},"Petr Tsymbarovich","https:\u002F\u002Forcid.org\u002F0000-0001-8591-2612",{"name":413,"orcid":9},"A. E. Shatunov",{"name":415,"orcid":416},"Pavel P. Fil","https:\u002F\u002Forcid.org\u002F0000-0002-9851-5381",{"name":418,"orcid":419},"D. E. Mitichkin","https:\u002F\u002Forcid.org\u002F0009-0006-2397-060X",{"name":421,"orcid":422},"Dmitriy S. Fomin","https:\u002F\u002Forcid.org\u002F0000-0003-3733-0284",{"tldr":424,"method":425,"finding":426,"direction":105,"opportunity":427},"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":430,"title":431,"url":432,"summary":433,"summary_zh":434,"content":9,"source_name":435,"source_url":432,"published_at":436,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":437,"score_detail":438,"sources":440,"tags":442,"primary_topic":445,"secondary_topics":446,"classification":453,"search_phrases":496,"slug":499,"view_count":141,"doi":9,"paper":500,"created_at":510},5013,"REMOTE SENSING AND GIS-BASED ASSESSMENT OF SOIL SALINITY IN IRRIGATED LANDS: METHODS, CHALLENGES AND PROSPECTS FOR PRECISION AGRICULTURE","http:\u002F\u002Fwww.arabianjournalofscience.com\u002Findex.php\u002Findex\u002Farticle\u002Fview\u002F1223","Soil salinization is a major land degradation process affecting the sustainability of irrigated agriculture, particularly in arid and semi-arid regions. Conventional soil sampling provides essential information about salinity levels but may be insufficient for continuous monitoring of large agricultural territories because of spatial variability, sampling costs, and temporal limitations. Remote sensing (RS) and geographic information systems (GIS) offer complementary approaches for identifying spatial patterns of salinity, monitoring land conditions, and supporting agricultural management. This article examines the scientific and methodological foundations of integrating multispectral satellite imagery, spectral indices, geospatial analysis, and machine learning for soil salinity assessment in irrigated lands. Particular attention is given to Landsat and Sentinel-2 imagery, the interpretation of vegetation and soil reflectance indicators, the role of electrical conductivity measurements in model calibration, and the limitations associated with vegetation cover, soil moisture, and seasonal variability. The analysis indicates that reliable salinity assessment requires the integration of satellite observations with field measurements and environmental variables rather than the isolated application of spectral indices. The article proposes a methodological framework for developing spatially explicit salinity assessment systems applicable to irrigated agricultural landscapes, including those of Central Asia. The framework provides a basis for improving monitoring strategies and supporting evidence-based land management without assuming unverified local measurement results.","土壤盐渍化是影响灌溉农业可持续性的主要土地退化过程，在干旱和半干旱地区尤为突出。传统土壤采样可提供盐分水平的基本信息，但由于空间变异性、采样成本和时间限制，可能不足以对大面积农业区域进行持续监测。遥感（RS）和地理信息系统（GIS）为识别盐渍化空间格局、监测土地状况和支持农业管理提供了互补性方法。本文探讨了整合多光谱卫星影像、光谱指数、地理空间分析和机器学习进行灌溉土地土壤盐渍化评估的科学与方法学基础。文章特别关注Landsat和Sentinel-2影像、植被与土壤反射率指标的解译、电导率测量在模型校准中的作用，以及与植被覆盖、土壤湿度和季节变异性相关的局限性。分析表明，可靠的盐渍化评估需要将卫星观测与野外测量和环境变量相结合，而非孤立地应用光谱指数。本文提出了一个方法学框架，用于开发适用于灌溉农业景观（包括中亚地区）的空间显式盐渍化评估系统。该框架为改进监测策略和支持基于证据的土地管理提供了基础，且不以未经核实的当地测量结果为假设前提。","Arabian journal of science.","2026-10-13T00:00:00Z",74,{"impact":267,"substance":122,"depth":123,"authority":19,"freshness":20,"relevant":21,"comment":439},"系统综述遥感与GIS在灌溉农田盐渍化评估中的方法框架与挑战，对盐碱地治理和精准农业有参考价值，但属综述性论文，非突破性成果。",[441],{"name":435,"url":432},[180,27,69,443,444],"盐碱地治理","土壤监测",{"code":65,"slug":364,"name":365,"path":366,"parent_code":189},[447,452],{"code":448,"slug":449,"name":450,"path":451,"parent_code":189},"I4","gis","GIS与空间分析","\u002Ftopic\u002Fdigital-agriculture\u002Fgis",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":39,"locked":14,"version":40,"method":41,"evidence":454},{"candidates":455,"agricultural_evidence":46},[456,460,468,472,476,480,484,490],{"code":65,"score":17,"supported":46,"title":457,"abstract":458,"tags":459},[305],[69,305,306],[69],{"code":448,"score":123,"supported":46,"title":461,"abstract":463,"tags":467},[462],"GIS",[464,465,462,466],"地理信息","空间分析","geographic information",[],{"code":32,"score":194,"supported":46,"title":469,"abstract":470,"tags":471},[33],[49,33],[443],{"code":52,"score":13,"supported":46,"title":473,"abstract":474,"tags":475},[56],[],[180,27],{"code":59,"score":110,"supported":46,"title":477,"abstract":478,"tags":479},[],[26,62],[],{"code":309,"score":66,"supported":46,"title":481,"abstract":482,"tags":483},[],[312],[],{"code":485,"score":66,"supported":46,"title":486,"abstract":487,"tags":489},"H7",[],[488],"干旱",[],{"code":491,"score":66,"supported":46,"title":492,"abstract":493,"tags":495},"I7",[],[494],"methodological framework",[],[497,498],"遥感 GIS 土壤盐渍化","Landsat Sentinel-2 盐分监测","遥感GIS土壤盐渍化-5013",{"doi":9,"openalex_id":501,"authors":502,"venue":435,"cited_by_count":100,"oa_url":432,"card":505,"direction":105,"ingested_from":107},"W7221843179",[503],{"name":504,"orcid":9},"Sadullayev Sardor Zokirjon o'g'li",{"tldr":506,"method":507,"finding":508,"direction":105,"opportunity":509},"综述遥感与GIS评估灌溉地土壤盐渍化的方法、挑战与前景，并提出空间显式评估框架。","整合多光谱卫星影像、光谱指数、GIS空间分析与机器学习，结合电导率校准。","可靠盐渍化评估需卫星观测与实地测量及环境变量融合，而非孤立使用光谱指数。","可探索多源遥感与机器学习融合的盐渍化动态监测，并验证于中亚等干旱灌区。","2026-10-15T23:30:32.401626Z",{"id":512,"title":513,"url":514,"summary":515,"summary_zh":516,"content":9,"source_name":517,"source_url":514,"published_at":436,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":518,"score_detail":519,"sources":521,"tags":523,"primary_topic":527,"secondary_topics":528,"classification":529,"search_phrases":550,"slug":553,"view_count":100,"doi":554,"paper":555,"created_at":573},5000,"Soil phenotyping: Integrating phenosoils and proximal soil sensing for spatiotemporal characterisation of managed soil variability","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.still.2026.107530","The characterisation of soil variability has challenged soil science since the early recognition that soils exhibit complex, structured spatial patterns across landscapes. As agriculture intensifies and soils are expected to deliver more—storing carbon, supporting biodiversity, and sustaining other key functions—there is an urgent need for scalable, quantitative methods to monitor and manage soil variability across space and time. Here we synthesise and advance a framework for soil phenotyping, defined as the quantitative assessment of soil structural, chemical, physical, and biological properties and their spatiotemporal patterns using proximal sensing—explicitly grounded in the distinction between genosoils (baseline soils under minimal human influence) and phenosoils (persistent management-modified soil expressions). Drawing parallels with field plant phenotyping, we argue that soils exhibit phenotypic responses arising from interactions among inherent soil capacity, environmental, and management drivers, and that these responses can be measured efficiently using high-throughput sensing. We review proximal soil sensing technologies, including electromagnetic induction and vis–NIR spectroscopy, and discuss their integration within multi-sensor platforms, digital soil mapping, and machine-learning workflows for data fusion, prediction, and uncertainty quantification. We position soil phenotyping as a practical pipeline from in situ sensing to spatially explicit indicators of soil condition and function, supporting precision agriculture, soil health assessment, and soil security planning. Finally, we identify key challenges for operational deployment, including calibration transferability, sensor harmonisation, spatiotemporal sampling design, and open, interoperable data frameworks, and outline research priorities to accelerate adoption in managed landscapes","土壤变异性的表征一直是土壤科学面临的挑战，早在人们认识到土壤在景观尺度上呈现复杂、结构化的空间格局之时便已如此。随着农业集约化程度提高，以及人们对土壤寄予更多期望——固碳、支撑生物多样性并维持其他关键功能——迫切需要可扩展的定量方法来监测和管理土壤在时空上的变异性。本文综合并推进了一个土壤表型分析框架，将其定义为利用近端传感对土壤结构、化学、物理和生物特性及其时空格局进行定量评估，并明确以基因土壤（genosoils，即在人类影响最小条件下的基线土壤）与表型土壤（phenosoils，即持续受到管理改造的土壤表现）之间的区分为基础。通过与田间植物表型分析的类比，我们认为土壤表现出由固有土壤能力、环境和管理驱动因素之间相互作用所产生的表型响应，并且这些响应可以通过高通量传感高效测量。我们综述了近端土壤传感技术，包括电磁感应和可见光—近红外光谱（vis–NIR spectroscopy），并讨论了它们在多传感器平台、数字土壤制图以及用于数据融合、预测和不确定性量化的机器学习工作流程中的整合。我们将土壤表型分析定位为一条从原位传感走向土壤状况与功能的时空显式指标的实用路径，支撑精准农业、土壤健康评估和土壤安全规划。最后，我们指出了业务化部署面临的关键挑战，包括校准可迁移性、传感器协调统一、时空采样设计以及开放可互操作的数据框架，并概述了加速其在管理景观中应用的研究优先方向。","Soil and Tillage Research",81,{"impact":17,"substance":18,"depth":17,"authority":45,"freshness":375,"relevant":21,"comment":520},"提出土壤表型学框架并整合近地传感与机器学习，方法新颖、对精准农业与土壤健康管理有实质参考价值，但属学术综述、产业落地尚远。",[522],{"name":517,"url":514},[27,524,359,525,526],"土壤健康","土壤表型","近地传感",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":14,"version":40,"method":41,"evidence":530},{"candidates":531,"agricultural_evidence":46},[532,536,540,546],{"code":32,"score":194,"supported":46,"title":533,"abstract":534,"tags":535},[33],[49,33],[524],{"code":52,"score":53,"supported":46,"title":537,"abstract":538,"tags":539},[],[27,56],[27],{"code":216,"score":110,"supported":46,"title":541,"abstract":542,"tags":545},[],[543,544],"生物多样性","biodiversity",[],{"code":59,"score":66,"supported":46,"title":547,"abstract":548,"tags":549},[],[26],[],[551,552],"土壤表型 近地传感 土壤健康","phenosoils 数字土壤制图","土壤表型近地传感土壤健康-5000","10.1016\u002Fj.still.2026.107530",{"doi":554,"openalex_id":556,"authors":557,"venue":517,"cited_by_count":100,"oa_url":514,"card":568,"direction":105,"ingested_from":107},"W7221718473",[558,561,563,565],{"name":559,"orcid":560},"Damien J. Field","https:\u002F\u002Forcid.org\u002F0000-0002-6877-8332",{"name":562,"orcid":9},"Alex McBratney",{"name":564,"orcid":9},"Budiman Minasny",{"name":566,"orcid":567},"John Triantafilis","https:\u002F\u002Forcid.org\u002F0000-0003-1561-0242",{"tldr":569,"method":570,"finding":571,"direction":105,"opportunity":572},"提出土壤表型组框架，用近端传感量化管理导致的土壤时空变异。","整合电磁感应与可见-近红外光谱，结合多传感器平台、数字土壤制图和机器学习。","区分本原土与表型土，可高效监测土壤功能并支撑精准农业与土壤健康评估。","开发跨传感器校准迁移与时空采样优化方法，构建开放互操作的土壤表型数据框架。","2026-10-15T23:30:26.546545Z"]