[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2290":3,"related-2290":94},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":8,"source_name":9,"source_url":6,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":15,"sources":21,"tags":23,"primary_topic":29,"secondary_topics":35,"classification":42,"search_phrases":64,"slug":67,"view_count":68,"doi":69,"paper":70,"created_at":93},2290,"Optimizing biochar application strategies to improve soil properties and crop productivity in salt-affected croplands: Evidence from a global meta-analysis and machine learning approach","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.agsy.2026.104975","Optimizing biochar application strategies to improve soil properties and crop productivity in salt-affected croplands: Evidence from a global meta-analysis and machine learning approach。Agricultural Systems",null,"Agricultural Systems","2026-09-13T00:00:00Z","论文",10,false,82,{"impact":16,"substance":17,"depth":16,"authority":18,"freshness":12,"relevant":19,"comment":20},18,22,14,1,"全球荟萃分析与机器学习结合优化盐碱地生物炭施用策略，方法新颖、结论可靠，对盐碱地改良与产能提升有实质参考价值。",[22],{"name":9,"url":6},[24,25,26,27,28],"粮食安全","机器学习","生物炭","土壤改良","盐碱地治理",{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},"H2","soil","土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",[36],{"code":37,"slug":38,"name":39,"path":40,"parent_code":41},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":43,"locked":13,"version":44,"method":45,"evidence":46},"classified","2026-10-22.2","rules",{"candidates":47,"agricultural_evidence":49},[48,53,59],{"code":30,"score":18,"supported":49,"title":50,"abstract":51,"tags":52},true,[31],[31],[27,26,28],{"code":37,"score":54,"supported":49,"title":55,"abstract":57,"tags":58},12,[56],"machine learning",[56],[25],{"code":60,"score":19,"supported":13,"title":61,"abstract":62,"tags":63},"A8",[],[],[24],[65,66],"盐碱地治理 土壤改良 机器学习 粮食安全","盐碱地治理 土壤改良","盐碱地治理土壤改良机器学习粮食安全-2290",3,"10.1016\u002Fj.agsy.2026.104975",{"doi":69,"openalex_id":71,"authors":72,"venue":9,"cited_by_count":91,"oa_url":6,"card":8,"direction":8,"ingested_from":92},"W7212358957",[73,75,77,79,81,83,86,89],{"name":74,"orcid":8},"Haoliang Deng",{"name":76,"orcid":8},"Xiaofan Pan",{"name":78,"orcid":8},"Guang Li",{"name":80,"orcid":8},"Bin Mu",{"name":82,"orcid":8},"Rang Xiao",{"name":84,"orcid":85},"Zheyuan Xiao","https:\u002F\u002Forcid.org\u002F0000-0003-0776-4508",{"name":87,"orcid":88},"Wei Pan","https:\u002F\u002Forcid.org\u002F0000-0003-4518-2082",{"name":90,"orcid":8},"Qinli Wang",0,"openalex","2026-09-13T23:30:05.101959Z",{"total":95,"page":19,"page_size":95,"items":96},6,[97,171,260,348,399,486],{"id":98,"title":99,"url":100,"summary":101,"summary_zh":8,"content":8,"source_name":102,"source_url":100,"published_at":103,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":104,"score_detail":105,"sources":108,"tags":110,"primary_topic":113,"secondary_topics":114,"classification":116,"search_phrases":146,"slug":149,"view_count":68,"doi":150,"paper":151,"created_at":170},1271,"Application and prospect of artificial intelligence in biochar for acidic soil amelioration","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs42773-026-00652-6","Abstract Effective amelioration of acidic soils with biochar is critical for mitigating soil degradation and promoting sustainable agriculture, yet this requires robust mechanistic understanding and predictive modeling. This review synthesizes the key biogeochemical pathways by which biochar neutralizes soil acidity and enhances soil pH buffering capacity. We identify critical data gaps—notably the overlooked relative contributions of organic and inorganic alkalis—that currently limit the predictive performance of artificial intelligence (AI) models. A statistical literature analysis reveals that ensemble learning algorithms, particularly Random Forest, are predominant across various application scenarios, such as crop yield prediction, due to their robustness against overfitting and their capacity for feature importance ranking. However, no single algorithm is universally optimal. The choice of algorithm depends on several factors, including the amount of available data, the complexity of the problem, and the computational resources. Both multi-source data fusion and multi-model ensembling can enhance the predictive performance of AI models when appropriately configured. Future data fusion should prioritize integrating remote sensing with proximal sensor, multi-modal microbial, and imaging-chemical data to elucidate interactions across the biochar–soil–microbe–plant continuum. In conclusion, the predictive accuracy for biochar’s performance in acidic soil amelioration can be enhanced by: (1) integrating sensing technologies to develop new methods with high resolution and low detection limits; (2) applying AI while ensuring model interpretability and avoiding overclaims of causality; (3) constructing benchmark datasets to expand the usability of biochar data; (4) improving the representation of microbial responses to biochar in AI models; and (5) strengthening interdisciplinary collaboration among soil scientists, model developers, and sensing technology experts. Highlights Ensemble learning, especially Random Forest, dominates AI modeling for predicting biochar efficacy in acidic soils. Decoupling organic and inorganic alkalis is critical for advancing mechanism-based AI predictions. Multi-source data fusion integrates sensing technologies to overcome data limitations and enhance model performance.","Biochar","2026-08-28T00:00:00Z",76,{"impact":16,"substance":17,"depth":16,"authority":18,"freshness":106,"relevant":19,"comment":107},4,"综述探讨AI在酸性土壤生物炭改良中的应用，提出数据融合与模型可解释性等前沿方向，对农业科技研究有参考价值。",[109],{"name":102,"url":100},[111,112,26,27],"智慧农业","农业人工智能",{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},[115],{"code":37,"slug":38,"name":39,"path":40,"parent_code":41},{"status":43,"locked":13,"version":44,"method":45,"evidence":117},{"candidates":118,"agricultural_evidence":49},[119,124,129,135,141],{"code":30,"score":120,"supported":49,"title":121,"abstract":122,"tags":123},13,[31],[31],[27,26],{"code":37,"score":54,"supported":49,"title":125,"abstract":127,"tags":128},[126],"artificial intelligence",[126],[112],{"code":130,"score":68,"supported":49,"title":131,"abstract":132,"tags":134},"H8",[],[133],"sustainable agriculture",[],{"code":136,"score":68,"supported":49,"title":137,"abstract":138,"tags":140},"I3",[],[139],"remote sensing",[],{"code":142,"score":19,"supported":13,"title":143,"abstract":144,"tags":145},"I1",[],[],[111],[147,148],"农业人工智能 土壤改良 智慧农业 生物炭","农业人工智能 土壤改良","农业人工智能土壤改良智慧农业生物炭-1271","10.1007\u002Fs42773-026-00652-6",{"doi":150,"openalex_id":152,"authors":153,"venue":102,"cited_by_count":91,"oa_url":162,"card":163,"direction":169,"ingested_from":92},"W7204498237",[154,156,159],{"name":155,"orcid":8},"Linyu Guo",{"name":157,"orcid":158},"Kewei Li","https:\u002F\u002Forcid.org\u002F0000-0003-3401-4796",{"name":160,"orcid":161},"Ren‐kou Xu","https:\u002F\u002Forcid.org\u002F0000-0002-5541-0205","https:\u002F\u002Flink.springer.com\u002Fcontent\u002Fpdf\u002F10.1007\u002Fs42773-026-00652-6.pdf",{"tldr":164,"method":165,"finding":166,"direction":167,"opportunity":168},"综述AI在生物炭改良酸性土壤中的应用，指出数据缺口并提出改进方向。","文献统计分析，综述生物炭机理与AI模型应用。","集成学习（随机森林）为主，但需解耦有机\u002F无机碱，多源数据融合可提升预测。","农业人工智能与决策模型","构建生物炭基准数据集，融合遥感与近端传感等多模态数据，开发可解释AI模型预测酸性土壤改良效果。","智慧农业 \u002F 农业物联网","2026-09-01T04:03:13.155221Z",{"id":172,"title":173,"url":174,"summary":175,"summary_zh":176,"content":8,"source_name":177,"source_url":174,"published_at":178,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":179,"score_detail":180,"sources":185,"tags":187,"primary_topic":191,"secondary_topics":197,"classification":200,"search_phrases":236,"slug":239,"view_count":91,"doi":240,"paper":241,"created_at":259},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":181,"substance":182,"depth":183,"authority":120,"freshness":12,"relevant":19,"comment":184},16,21,17,"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。",[186],{"name":177,"url":174},[111,25,188,189,190],"遥感监测","土壤墒情","冬小麦",{"code":192,"slug":193,"name":194,"path":195,"parent_code":196},"A2","wheat","小麦","\u002Ftopic\u002Ffield-crops\u002Fwheat","A",[198,199],{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},{"code":37,"slug":38,"name":39,"path":40,"parent_code":41},{"status":43,"locked":13,"version":44,"method":45,"evidence":201},{"candidates":202,"agricultural_evidence":49},[203,209,215,219,225,232],{"code":192,"score":204,"supported":49,"title":205,"abstract":207,"tags":208},26,[206,193],"winter wheat",[194,206,193],[190],{"code":30,"score":210,"supported":49,"title":211,"abstract":212,"tags":214},15,[31],[213,31],"土壤",[189],{"code":37,"score":210,"supported":49,"title":216,"abstract":217,"tags":218},[56],[25,56],[25],{"code":136,"score":12,"supported":49,"title":220,"abstract":221,"tags":224},[],[222,139,223],"遥感","multispectral",[188],{"code":226,"score":95,"supported":49,"title":227,"abstract":228,"tags":231},"H3",[],[229,230],"灌溉","irrigation",[],{"code":142,"score":106,"supported":49,"title":233,"abstract":234,"tags":235},[],[111],[111],[237,238],"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":240,"openalex_id":242,"authors":243,"venue":177,"cited_by_count":91,"oa_url":174,"card":253,"direction":169,"ingested_from":92},"W7223156204",[244,247,249,251],{"name":245,"orcid":246},"Mingliang Jiang","https:\u002F\u002Forcid.org\u002F0000-0002-6486-6087",{"name":248,"orcid":8},"Yi Zhang",{"name":250,"orcid":8},"WEI Lei",{"name":252,"orcid":8},"Chengcai Zhang",{"tldr":254,"method":255,"finding":256,"direction":257,"opportunity":258},"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。","农业遥感与作物表型","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。","2026-10-22T11:20:18.887301Z",{"id":261,"title":262,"url":263,"summary":264,"summary_zh":265,"content":8,"source_name":266,"source_url":263,"published_at":267,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":268,"score_detail":269,"sources":273,"tags":275,"primary_topic":279,"secondary_topics":280,"classification":286,"search_phrases":302,"slug":305,"view_count":91,"doi":306,"paper":307,"created_at":347},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":54,"substance":270,"depth":181,"authority":120,"freshness":271,"relevant":19,"comment":272},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。",[274],{"name":266,"url":263},[25,222,276,277,278],"土壤碳","Landsat","数字土壤制图",{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},[281,282],{"code":37,"slug":38,"name":39,"path":40,"parent_code":41},{"code":136,"slug":283,"name":284,"path":285,"parent_code":41},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":43,"locked":13,"version":44,"method":45,"evidence":287},{"candidates":288,"agricultural_evidence":49},[289,293,298],{"code":30,"score":18,"supported":49,"title":290,"abstract":291,"tags":292},[31],[213,31],[],{"code":37,"score":294,"supported":49,"title":295,"abstract":296,"tags":297},9,[56],[],[25],{"code":136,"score":271,"supported":49,"title":299,"abstract":300,"tags":301},[],[222,139],[277,222],[303,304],"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":306,"openalex_id":308,"authors":309,"venue":266,"cited_by_count":91,"oa_url":8,"card":342,"direction":257,"ingested_from":92},"W7222107492",[310,313,316,319,322,325,328,331,333,336,339],{"name":311,"orcid":312},"P. A. Braulov","https:\u002F\u002Forcid.org\u002F0000-0001-9919-7402",{"name":314,"orcid":315},"Pavel M. Shilov","https:\u002F\u002Forcid.org\u002F0000-0003-4113-6396",{"name":317,"orcid":318},"R. G. Gadzhiumarov","https:\u002F\u002Forcid.org\u002F0000-0002-4220-623X",{"name":320,"orcid":321},"V. K. Dridiger","https:\u002F\u002Forcid.org\u002F0000-0002-0510-2220",{"name":323,"orcid":324},"E. V. Bogdan","https:\u002F\u002Forcid.org\u002F0009-0006-4781-5786",{"name":326,"orcid":327},"V. O. Megmerova","https:\u002F\u002Forcid.org\u002F0000-0001-8655-6437",{"name":329,"orcid":330},"Petr Tsymbarovich","https:\u002F\u002Forcid.org\u002F0000-0001-8591-2612",{"name":332,"orcid":8},"A. E. Shatunov",{"name":334,"orcid":335},"Pavel P. Fil","https:\u002F\u002Forcid.org\u002F0000-0002-9851-5381",{"name":337,"orcid":338},"D. E. Mitichkin","https:\u002F\u002Forcid.org\u002F0009-0006-2397-060X",{"name":340,"orcid":341},"Dmitriy S. Fomin","https:\u002F\u002Forcid.org\u002F0000-0003-3733-0284",{"tldr":343,"method":344,"finding":345,"direction":257,"opportunity":346},"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":349,"title":350,"url":351,"summary":352,"summary_zh":8,"content":8,"source_name":353,"source_url":8,"published_at":354,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":355,"score_detail":356,"sources":358,"tags":360,"primary_topic":362,"secondary_topics":363,"classification":365,"search_phrases":386,"slug":389,"view_count":106,"doi":8,"paper":390,"created_at":398},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":16,"substance":17,"depth":16,"authority":18,"freshness":95,"relevant":19,"comment":357},"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。",[359],{"name":353,"url":351},[111,112,25,222,361],"土壤监测",{"code":37,"slug":38,"name":39,"path":40,"parent_code":41},[364],{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},{"status":43,"locked":13,"version":44,"method":45,"evidence":366},{"candidates":367,"agricultural_evidence":49},[368,373,378,382],{"code":37,"score":181,"supported":49,"title":369,"abstract":370,"tags":372},[126],[371,25],"深度学习",[112,25],{"code":30,"score":374,"supported":49,"title":375,"abstract":376,"tags":377},11,[31],[213],[],{"code":136,"score":106,"supported":49,"title":379,"abstract":380,"tags":381},[],[222],[222],{"code":142,"score":19,"supported":13,"title":383,"abstract":384,"tags":385},[],[],[111],[387,388],"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":8,"openalex_id":8,"authors":391,"venue":8,"cited_by_count":91,"oa_url":8,"card":392,"direction":167,"ingested_from":397},[],{"tldr":393,"method":394,"finding":395,"direction":167,"opportunity":396},"系统综述2018-2026年196项AI用于土壤特性与农业的研究。","PRISMA 2020框架，分析机器学习与深度学习模型及多源数据融合。","研究转向数据驱动，树集成模型在不同土壤特性上表现稳健。","可探索可解释AI与多源数据融合在土壤特性预测中的泛化能力。","agent","2026-10-06T00:05:04.976398Z",{"id":400,"title":401,"url":402,"summary":403,"summary_zh":404,"content":8,"source_name":405,"source_url":402,"published_at":406,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":407,"score_detail":408,"sources":410,"tags":412,"primary_topic":416,"secondary_topics":417,"classification":424,"search_phrases":452,"slug":455,"view_count":456,"doi":457,"paper":458,"created_at":485},4172,"Machine learning reveals distinct drivers of soil organic carbon across the mountain-oasis-desert system of northwest China","https:\u002F\u002Fdoi.org\u002F10.1186\u002Fs13021-026-00522-5","The mountain-oasis-desert system (MODS) is a distinctive landscape pattern shaped by interactions between geomorphological configurations and hydrological processes in arid regions. However, most soil organic carbon (SOC) mapping studies treat arid landscapes as homogeneous units, leaving limited quantitative evidence on how SOC patterns and environmental associations differ among MODS subsystems. As a critical ecosystem highly sensitive to climate change and human activities, understanding these responses is essential for regional soil carbon management and ecological restoration. In this study, we developed an ecosystem-based modeling framework in the Hexi Region (HXR) to construct separate SOC prediction models for different subsystems, aiming to investigate the spatiotemporal dynamics of SOC stocks and identify their key driving factors across MODS. The results show that incorporating remote sensing (RS) variables significantly improved model performance, increasing the mean R 2 from 0.51 to 0.58. Among the tested models, XGBoost achieved the best performance, providing an effective tool for SOC mapping in arid regions. Shapley additive explanations (SHAP) analysis of the best-performing XGBoost models identified distinct leading predictors across the MODS, including surface shortwave radiation (SRAD) in mountain and desert ecosystems and the difference vegetation index (DVI) in oasis ecosystems. Furthermore, the partial least squares path model (PLS-PM) revealed contrasting influences of climate change and human activities across ecological subsystems. Climatic factors exerted the strongest influence in the mountainous subsystem, whereas in the oasis subsystem intensive human management became the dominant driver of soil carbon cycling. From 2001 to 2023, SOC stocks in oasis regions increased significantly at a rate of 0.17 t C ha⁻ 1 year⁻ 1 , potentially associated with land-use change and agricultural management. Approximately 19.3% of the study area experienced significant SOC stocks declines. By resolving subsystem-specific SOC patterns and environmental associations, this study advances ecosystem-aware SOC assessment in arid regions. The resulting framework also provides a basis for differentiated carbon management across MODS.","山地-绿洲-荒漠系统（MODS）是干旱区地貌格局与水文过程相互作用形成的独特景观格局。然而，大多数土壤有机碳（SOC）制图研究将干旱区景观视为均质单元，关于MODS各子系统间SOC格局及其环境关联差异的定量证据仍然有限。作为对气候变化和人类活动高度敏感的关键生态系统，理解这些响应对于区域土壤碳管理和生态恢复至关重要。本研究在河西地区（HXR）构建了基于生态系统的建模框架，针对不同子系统分别建立SOC预测模型，旨在探究MODS中SOC储量的时空动态并识别其关键驱动因子。结果表明，引入遥感（RS）变量显著提升了模型性能，平均R²从0.51提高至0.58。在测试的模型中，XGBoost表现最佳，为干旱区SOC制图提供了有效工具。对最优XGBoost模型的SHAP（Shapley加法解释）分析识别出MODS各子系统的不同主导预测因子，其中山地和荒漠生态系统为地表短波辐射（SRAD），绿洲生态系统为差值植被指数（DVI）。此外，偏最小二乘路径模型（PLS-PM）揭示了气候变化和人类活动在各生态子系统中的差异化影响。气候因子在山地子系统中影响最强，而在绿洲子系统中，集约化人类管理成为土壤碳循环的主导驱动因素。2001年至2023年，绿洲区域SOC储量以0.17 t C ha⁻¹ year⁻¹的速率显著增加，这可能与土地利用变化和农业管理有关。约19.3%的研究区域经历了SOC储量的显著下降。通过解析子系统特定的SOC格局及其环境关联，本研究推进了干旱区生态系统感知型SOC评估，所构建的框架也为MODS差异化碳管理提供了依据。","Carbon Balance and Management","2026-10-03T00:00:00Z",79,{"impact":181,"substance":17,"depth":16,"authority":18,"freshness":294,"relevant":19,"comment":409},"基于XGBoost与SHAP的干旱区SOC分异驱动研究，方法新颖、数据翔实，对区域碳管理与生态修复有参考价值。",[411],{"name":405,"url":402},[25,413,414,188,415],"土壤有机碳","生态修复","干旱区农业",{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},[418,423],{"code":419,"slug":420,"name":421,"path":422,"parent_code":34},"H7","climate","气候适应与防灾减灾","\u002Ftopic\u002Fenvironment\u002Fclimate",{"code":37,"slug":38,"name":39,"path":40,"parent_code":41},{"status":43,"locked":13,"version":44,"method":45,"evidence":425},{"candidates":426,"agricultural_evidence":49},[427,431,438,442,447],{"code":30,"score":210,"supported":49,"title":428,"abstract":429,"tags":430},[31],[213,31],[413],{"code":419,"score":12,"supported":49,"title":432,"abstract":433,"tags":437},[],[434,435,436],"气候变化","干旱","climate change",[415],{"code":37,"score":294,"supported":49,"title":439,"abstract":440,"tags":441},[56],[],[25],{"code":136,"score":443,"supported":49,"title":444,"abstract":445,"tags":446},7,[],[222,139],[188],{"code":448,"score":19,"supported":13,"title":449,"abstract":450,"tags":451},"H6",[],[],[414],[453,454],"河西地区 土壤有机碳 机器学习","山地-绿洲-荒漠 遥感 碳储量","河西地区土壤有机碳机器学习-4172",2,"10.1186\u002Fs13021-026-00522-5",{"doi":457,"openalex_id":459,"authors":460,"venue":405,"cited_by_count":91,"oa_url":402,"card":480,"direction":257,"ingested_from":92},"W7219075005",[461,463,466,468,471,473,476,478],{"name":462,"orcid":8},"Y. Chen",{"name":464,"orcid":465},"Haiyang Xi","https:\u002F\u002Forcid.org\u002F0000-0003-3158-8161",{"name":467,"orcid":8},"Meng Zhu",{"name":469,"orcid":470},"Wenju Cheng","https:\u002F\u002Forcid.org\u002F0000-0002-1822-5668",{"name":472,"orcid":8},"Yulian Hao",{"name":474,"orcid":475},"Linbo Qu","https:\u002F\u002Forcid.org\u002F0009-0007-4669-8407",{"name":477,"orcid":8},"Zhehui Wang",{"name":479,"orcid":8},"Bin Wang",{"tldr":481,"method":482,"finding":483,"direction":257,"opportunity":484},"构建基于生态系统的机器学习框架，预测西北荒漠-绿洲-山地系统土壤有机碳并识别各子系统驱动因子。","XGBoost、SHAP、PLS-PM，结合遥感变量与2001-2023年多源数","遥感变量提升模型R²至0.58；山地和沙漠由辐射主导，绿洲由人类管理主导，绿洲碳储量年增0.17 t","可延伸研究绿洲农业管理措施对土壤碳的长期影响，并开发子系统自适应的碳监测与决策模型。","2026-10-04T23:30:24.631460Z",{"id":487,"title":488,"url":489,"summary":490,"summary_zh":491,"content":8,"source_name":492,"source_url":489,"published_at":493,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":494,"score_detail":495,"sources":497,"tags":499,"primary_topic":502,"secondary_topics":503,"classification":506,"search_phrases":534,"slug":537,"view_count":456,"doi":538,"paper":539,"created_at":557},3916,"Hyperspectral inversion of soil total nitrogen content using spectral and machine learning","https:\u002F\u002Fdoi.org\u002F10.3329\u002Fbjb.v55i3.93850","The Agro-pastoral Transitional Ecotone of Northern Shaanxi is an ecologically fragile region. Soil nitrogen is a critical factor influencing crop productivity and regional ecological balance. Rapid and accurate monitoring of farmland soil total nitrogen (TN) content is therefore essential for implementing precision agriculture and ensuring sustainable land use in this area. This study focused on the cultivated soils of Dingbian County, a representative area within this ecotone. Field-collected soil samples underwent TN content determination and laboratory-based hyper spectral reflectance measurement. The original spectral reflectance (R) was first transformed using mathematical methods, including first-derivative (FDR), second-derivative (SDR), and logarithm of the reciprocal's first-derivative (LRFD) analysis, to enhance spectral information and suppress background noise. Subsequently, the successive projections algorithm (SPA) and correlation analysis (CA) were integrated to identify feature wavelengths highly correlated with soil TN from the transformed spectral data. Partial Least Squares Regression (PLSR), Decision Tree (DT), and Random Forest (RF) were developed to estimate soil TN content. Model performance was evaluated and compared using the coefficient of determination (R²), root mean square error (RMSE), and ratio of performance to deviation (RPD). The results indicated that: (1) Spectral derivative transformations effectively highlighted subtle information, with LRFD showing the greatest sensitivity to TN. Models built using LRFD-derived features consistently outperformed those based on original reflectance. (2) Among the machine learning algorithms, the Random Forest (RF) model demonstrated superior predictive performance on the validation set (R² = 0.85, RMSE = 0.11 g\u002Fkg, RPD = 2.15), indicating the highest stability and generalization capability. The PLSR model performed moderately well, while the DT model was prone to over fitting and yielded the lowest accuracy. (3) This study confirms that the integration of hyper spectral technology and machine learning algorithms enables efficient and precise estimation of soil TN content in farmland within the Northern Shaanxi agro-pastoral ecotone, providing a reliable technical framework for soil fertility assessment and precision nutrient management in the region. Bangladesh J. Bot. 55(3): 605-614, 2026 (September)","陕北农牧交错带是生态脆弱区，土壤氮素是影响作物生产力和区域生态平衡的关键因子。快速、准确地监测农田土壤全氮（TN）含量，对于该区实施精准农业和保障土地可持续利用至关重要。本研究以该交错带典型区域定边县的耕作土壤为研究对象，对野外采集的土壤样品进行TN含量测定和实验室高光谱反射率测量。首先采用数学方法对原始光谱反射率（R）进行变换，包括一阶微分（FDR）、二阶微分（SDR）和倒数对数一阶微分（LRFD）分析，以增强光谱信息并抑制背景噪声。随后，将连续投影算法（SPA）与相关分析（CA）相结合，从变换后的光谱数据中筛选出与土壤TN高度相关的特征波长。构建偏最小二乘回归（PLSR）、决策树（DT）和随机森林（RF）模型估算土壤TN含量。采用决定系数（R²）、均方根误差（RMSE）和相对分析误差（RPD）对模型性能进行评价与比较。结果表明：（1）光谱微分变换有效凸显了细微信息，其中LRFD对TN的敏感性最强，基于LRFD衍生特征构建的模型始终优于基于原始反射率的模型。（2）在机器学习算法中，随机森林（RF）模型在验证集上表现出优越的预测性能（R² = 0.85，RMSE = 0.11 g\u002Fkg，RPD = 2.15），具有最高的稳定性和泛化能力。PLSR模型表现中等，而DT模型易于过拟合，精度最低。（3）本研究证实，高光谱技术与机器学习算法相结合能够高效、精确地估算陕北农牧交错带农田土壤TN含量，为该区域土壤肥力评估和精准养分管理提供了可靠的技术框架。Bangladesh J. Bot. 55(3): 605-614, 2026 (September)","Bangladesh Journal of Botany","2026-09-30T00:00:00Z",70,{"impact":54,"substance":270,"depth":183,"authority":120,"freshness":271,"relevant":19,"comment":496},"高光谱结合机器学习反演土壤全氮，方法对比扎实、结论可靠，对精准农业养分管理有参考价值，但属区域性田间研究，影响范围有限。",[498],{"name":492,"url":489},[111,500,25,222,501],"精准施肥","土壤氮素",{"code":37,"slug":38,"name":39,"path":40,"parent_code":41},[504,505],{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},{"code":136,"slug":283,"name":284,"path":285,"parent_code":41},{"status":43,"locked":13,"version":44,"method":45,"evidence":507},{"candidates":508,"agricultural_evidence":49},[509,513,517,522,528],{"code":37,"score":210,"supported":49,"title":510,"abstract":511,"tags":512},[56],[25,56],[25],{"code":30,"score":18,"supported":49,"title":514,"abstract":515,"tags":516},[31],[213,31],[],{"code":136,"score":294,"supported":49,"title":518,"abstract":520,"tags":521},[519],"hyperspectral",[],[222],{"code":142,"score":443,"supported":49,"title":523,"abstract":524,"tags":527},[],[525,526],"精准农业","precision agriculture",[111],{"code":529,"score":106,"supported":49,"title":530,"abstract":531,"tags":533},"F3",[],[532],"养分管理",[500],[535,536],"定边县 土壤全氮 高光谱","陕北农牧交错带 土壤氮素 反演","定边县土壤全氮高光谱-3916","10.3329\u002Fbjb.v55i3.93850",{"doi":538,"openalex_id":540,"authors":541,"venue":492,"cited_by_count":91,"oa_url":489,"card":552,"direction":167,"ingested_from":92},"W7214885868",[542,545,547,549],{"name":543,"orcid":544},"Zhenyu Dong","https:\u002F\u002Forcid.org\u002F0000-0003-0028-3293",{"name":546,"orcid":8},"Ni Wang",{"name":548,"orcid":8},"Jiancang Xie",{"name":550,"orcid":551},"Jungang Luo","https:\u002F\u002Forcid.org\u002F0009-0009-0285-4839",{"tldr":553,"method":554,"finding":555,"direction":257,"opportunity":556},"用高光谱与机器学习反演陕北农牧交错带农田土壤全氮含量。","野外采样测光谱，经FDR\u002FSDR\u002FLRFD变换，SPA+CA选特征波长，建PLS","LRFD变换最敏感，RF模型验证集R²=0.85、RPD=2.15，精度与泛化最优。","可探索多源遥感与深度学习融合，提升生态脆弱区土壤氮素时空反演与制图能力。","2026-10-01T23:30:53.960449Z"]