[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2309":3,"related-2309":83},{"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":22,"tags":24,"primary_topic":8,"secondary_topics":30,"classification":31,"search_phrases":62,"slug":65,"view_count":66,"doi":67,"paper":68,"created_at":82},2309,"Modeling Water Quality Parameters in Laga Dadi Reservoir, Ethiopia: An Integrated Remote Sensing and Machine Learning Approach","https:\u002F\u002Fdoi.org\u002F10.21203\u002Frs.3.rs-10838920\u002Fv1","Modeling Water Quality Parameters in Laga Dadi Reservoir, Ethiopia: An Integrated Remote Sensing and Machine Learning Approach。Research Square",null,"Research Square","2026-09-10T00:00:00Z","论文",10,false,55,{"impact":16,"substance":17,"depth":18,"authority":19,"freshness":16,"relevant":20,"comment":21},8,18,15,6,1,"埃塞俄比亚水库水质遥感与机器学习建模研究，方法有参考价值但属区域性案例，公共影响有限。",[23],{"name":9,"url":6},[25,26,27,28,29],"智慧农业","机器学习","遥感","水资源管理","水质监测",[],{"status":32,"locked":13,"version":33,"method":34,"evidence":35},"needs_review","2026-10-22.2","rules",{"candidates":36,"agricultural_evidence":13,"reason":61},[37,45,51,56],{"code":38,"score":39,"supported":40,"title":41,"abstract":43,"tags":44},"I2",12,true,[42],"machine learning",[42],[26],{"code":46,"score":39,"supported":40,"title":47,"abstract":49,"tags":50},"I3",[48],"remote sensing",[48],[27],{"code":52,"score":20,"supported":13,"title":53,"abstract":54,"tags":55},"H3",[],[],[28],{"code":57,"score":20,"supported":13,"title":58,"abstract":59,"tags":60},"I1",[],[],[25],"农业相关性需要复核",[63,64],"水资源管理 智慧农业 机器学习 水质监测","水资源管理 智慧农业","水资源管理智慧农业机器学习水质监测-2309",9,"10.21203\u002Frs.3.rs-10838920\u002Fv1",{"doi":67,"openalex_id":69,"authors":70,"venue":9,"cited_by_count":78,"oa_url":79,"card":8,"direction":80,"ingested_from":81},"W7212151964",[71,73,76],{"name":72,"orcid":8},"Sadirak Tasissa",{"name":74,"orcid":75},"Kenatu Angassa","https:\u002F\u002Forcid.org\u002F0000-0002-1449-2451",{"name":77,"orcid":8},"Workineh Tesfaye",0,"https:\u002F\u002Fwww.researchsquare.com\u002Farticle\u002Frs-10838920\u002Flatest.pdf","智慧农业 \u002F 农业物联网","openalex","2026-09-13T23:30:12.531084Z",{"total":19,"page":20,"page_size":19,"items":84},[85,167,250,307,383,441],{"id":86,"title":87,"url":88,"summary":89,"summary_zh":90,"content":8,"source_name":91,"source_url":92,"published_at":93,"category":11,"cover_url":8,"hotness":94,"is_selected":13,"score":95,"score_detail":96,"sources":100,"tags":104,"primary_topic":106,"secondary_topics":111,"classification":112,"search_phrases":150,"slug":153,"view_count":78,"doi":154,"paper":155,"created_at":166},5322,"MACHINE LEARNING BASED PREDICTION OF HYDROGEOLOGICAL PARAMETERS AND GROUNDWATER POTENTIAL INDEX USING GEOSPATIAL AND BOREHOLE DATA","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23434956","Abstract: Groundwater is a critical natural resource for domestic consumption, agricultural production, industrial development, and ecological sustainability. Accurate prediction of hydrogeological parameters and groundwater potential is essential for sustainable groundwater management, particularly in regions experiencing irregular rainfall, increasing water demand, and declining groundwater levels. This research paper presents a machine learning-based framework for predicting hydrogeological parameters and developing a Groundwater Potential Index (GWPI) by integrating geospatial datasets with borehole records. The proposed approach combines terrain characteristics, geological formations, soil properties, land use and land cover, drainage density, rainfall, slope, and remotely sensed indices with borehole-derived information, including water-table depth, aquifer thickness, lithology, and well yield. Machine learning algorithms such as Random Forest, Support Vector Regression, Gradient Boosting, and Artificial Neural Networks can be employed to estimate hydrogeological variables and identify areas with different groundwater potential levels. The predicted parameters are integrated within a geospatial framework to generate a spatially distributed groundwater potential index. Model performance can be assessed using the coefficient of determination (\\(R^2\\)), root mean square error (RMSE), and mean absolute error (MAE). The proposed framework offers a reproducible and scalable approach for groundwater exploration, borehole siting, and regional water-resource planning. Since no study-area dataset or model outputs have been provided, the paper presents a methodological framework rather than claiming experimentally validated results. Keywords: Machine Learning, Groundwater Potential Index, Hydrogeological Parameters, Geospatial Analysis, Borehole Data, Random Forest, Remote Sensing, Groundwater Management.","摘要：地下水是生活用水、农业生产、工业发展和生态可持续性的关键自然资源。准确预测水文地质参数和地下水潜力对于可持续地下水管理至关重要，尤其是在降雨不规律、用水需求不断增加和地下水位持续下降的地区。本文提出了一种基于机器学习的框架，通过将地理空间数据集与钻孔记录相结合，预测水文地质参数并构建地下水潜力指数（GWPI）。所提方法综合了地形特征、地质构造、土壤性质、土地利用与土地覆盖、河网密度、降雨、坡度以及遥感指数，并结合钻孔衍生信息，包括水位埋深、含水层厚度、岩性和井出水量。可采用随机森林、支持向量回归、梯度提升和人工神经网络等机器学习算法估算水文地质变量，并识别具有不同地下水潜力水平的区域。预测参数在地理空间框架内进行集成，以生成空间分布的地下水潜力指数。模型性能可通过决定系数（\\(R^2\\)）、均方根误差（RMSE）和平均绝对误差（MAE）进行评估。所提框架为地下水勘探、钻孔选址和区域水资源规划提供了一种可重复且可扩展的方法。由于未提供研究区数据集或模型输出，本文呈现的是方法学框架，而非声称经过实验验证的结果。关键词：机器学习，地下水潜力指数，水文地质参数，地理空间分析，钻孔数据，随机森林，遥感，地下水管理。","ACCENT JOURNAL OF  ECONOMICS ECOLOGY  & ENGINEERING","https:\u002F\u002Fajeee.co.in\u002Findex.php\u002Fajeee\u002Farticle\u002Fview\u002F6754","2026-10-17T00:00:00Z",25,47,{"impact":16,"substance":39,"depth":97,"authority":98,"freshness":66,"relevant":20,"comment":99},14,4,"方法框架类论文，无实测数据与验证结果，主题与农业水资源相关但公共价值有限，不宜进入每日精选。",[101,102],{"name":91,"url":92},{"name":91,"url":103},"https:\u002F\u002Fajeee.co.in\u002Findex.php\u002Fajeee\u002Farticle\u002Fdownload\u002F6754\u002F5489",[26,27,28,105],"地下水监测",{"code":38,"slug":107,"name":108,"path":109,"parent_code":110},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":113,"locked":13,"version":33,"method":34,"evidence":114},"classified",{"candidates":115,"agricultural_evidence":40},[116,120,125,132,137,144],{"code":38,"score":18,"supported":40,"title":117,"abstract":118,"tags":119},[42],[26,42],[26],{"code":46,"score":121,"supported":40,"title":122,"abstract":123,"tags":124},7,[],[27,48],[27],{"code":126,"score":19,"supported":40,"title":127,"abstract":128,"tags":131},"H2",[],[129,130],"土壤","soil",[],{"code":52,"score":98,"supported":40,"title":133,"abstract":134,"tags":136},[],[135],"水资源",[28],{"code":138,"score":139,"supported":40,"title":140,"abstract":141,"tags":143},"I4",3,[],[142],"空间分析",[],{"code":145,"score":139,"supported":40,"title":146,"abstract":147,"tags":149},"I7",[],[148],"methodological framework",[],[151,152],"机器学习 地下水潜力指数","钻孔数据 水文地质参数","机器学习地下水潜力指数-5322","10.5281\u002Fzenodo.23434956",{"doi":154,"openalex_id":156,"authors":157,"venue":91,"cited_by_count":78,"oa_url":92,"card":160,"direction":164,"ingested_from":81},"W7222805722",[158],{"name":159,"orcid":8},"Prof. I Pandu Ranga Reddy Dr. Hari Ramavath",{"tldr":161,"method":162,"finding":163,"direction":164,"opportunity":165},"提出融合地理空间与钻孔数据的机器学习框架，预测水文地质参数与地下水潜力指数。","随机森林、SVR、梯度提升、神经网络结合遥感与钻孔数据建模。","构建了可复现的地下水潜力评估方法框架，尚未经实测数据验证。","农业遥感与作物表型","可将该框架落地到具体农业区，用实测钻孔数据验证并耦合灌溉需水预测。","2026-10-19T23:30:22.978385Z",{"id":168,"title":169,"url":170,"summary":171,"summary_zh":172,"content":8,"source_name":173,"source_url":170,"published_at":174,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":175,"score_detail":176,"sources":181,"tags":183,"primary_topic":186,"secondary_topics":191,"classification":192,"search_phrases":228,"slug":231,"view_count":78,"doi":8,"paper":232,"created_at":249},4890,"ระบบพยากรณและเฝาระวงคณภาพนำอจฉรยะตามดชนคณภาพนำ ดวยเทคนคการเรยนรของเครองและอนเทอรเนตของสรรพสง","https:\u002F\u002Fso04.tci-thaijo.org\u002Findex.php\u002FJSSE\u002Farticle\u002Fview\u002F289948","This research utilizes Internet of Things (IoT) technology and Machine Learning (ML) to develop a prototype for a smart water quality forecasting and monitoring system. The study focuses on analyzing the Reduced Water Quality Index (rWQI) based on water temperature, pH, and Total Dissolved Solids (TDS). To forecast water quality 1 to 6 hours in advance, the performance of four predictive models was evaluated and compared: Extremely Randomized Trees (ET), Random Forest (RF), Simple Linear Regression (LR), and Multiple Linear Regression (MLR). The efficiency of these algorithms was validated using four key evaluation metrics: Coefficient of Determination (R2), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and Symmetric Mean Absolute Percentage Error (sMAPE). The experimental results indicated that the predictive performance of the models varied significantly depending on the forecasting horizon. In the short-term horizon (1–3 hours ahead), the RF model achieved the highest performance, with an R² of 0.566 and an MAE of 5.215 in the first hour. Conversely, for long-term forecasting (4–6 hours ahead), all models exhibited a significant drop in performance (R² \u003C 0), yielding higher prediction errors than the Mean Baseline. This long-term limitation stems from high water quality volatility in real-world environments combined with error accumulation in multi-step ahead forecasting. In conclusion, these findings emphasize that aligning model selection with the specific forecasting horizon is critical for enhancing system efficiency and stability. The developed model demonstrates high accuracy and suitability for short-term early warnings within 3 hours. This knowledge enables operators to plan water quality management with precision and speed, thereby reducing operational costs and the risk of aquatic livestock loss. Furthermore, this system serves as a technological prototype in digital agriculture, elevating conventional water quality monitoring into proactive management through intelligent technology.","本研究利用物联网（IoT）技术与机器学习（ML），开发了一套智能水质预测与监测系统原型。研究聚焦于基于水温、pH值和总溶解固体（TDS）的简化水质指数（rWQI）分析。为提前1至6小时预测水质，本研究评估并比较了四种预测模型的性能：极端随机树（ET）、随机森林（RF）、简单线性回归（LR）和多元线性回归（MLR）。采用四项关键评价指标验证了这些算法的有效性：决定系数（R²）、平均绝对误差（MAE）、平均绝对百分比误差（MAPE）和对称平均绝对百分比误差（sMAPE）。实验结果表明，各模型的预测性能因预测时间跨度不同而存在显著差异。在短期预测（提前1至3小时）中，RF模型表现最佳，第一小时的R²为0.566，MAE为5.215。相反，在长期预测（提前4至6小时）中，所有模型性能均显著下降（R² \u003C 0），预测误差高于均值基线。这一长期局限性源于真实环境中水质的高波动性以及多步超前预测中的误差累积。综上所述，这些发现强调，将模型选择与特定预测时间跨度相匹配对于提升系统效率与稳定性至关重要。所开发的模型具有较高精度，适用于3小时内的短期预警。这一认识使操作人员能够精准、快速地规划水质管理，从而降低运营成本和水产养殖损失风险。此外，该系统可作为数字农业中的技术原型，通过智能技术将传统水质监测提升为主动管理。","Journal of Science and Science Education (JSSE)","2026-10-12T00:00:00Z",70,{"impact":39,"substance":177,"depth":178,"authority":179,"freshness":16,"relevant":20,"comment":180},20,17,13,"论文将物联网与机器学习结合用于水产养殖水质短期预警，方法对比扎实、结论明确，但属细分技术原型，影响范围有限。",[182],{"name":173,"url":170},[25,26,184,185,29],"物联网","水产养殖",{"code":187,"slug":188,"name":189,"path":190,"parent_code":110},"I5","agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",[],{"status":113,"locked":13,"version":33,"method":34,"evidence":193},{"candidates":194,"agricultural_evidence":40},[195,201,207,211,217,223],{"code":187,"score":12,"supported":40,"title":196,"abstract":197,"tags":200},[],[184,198,199],"internet of things","IoT",[184],{"code":57,"score":121,"supported":40,"title":202,"abstract":203,"tags":206},[],[204,205],"数字农业","digital agriculture",[25],{"code":38,"score":121,"supported":40,"title":208,"abstract":209,"tags":210},[],[26,42],[26],{"code":212,"score":98,"supported":40,"title":213,"abstract":214,"tags":216},"D",[],[215],"水产",[185],{"code":218,"score":139,"supported":40,"title":219,"abstract":220,"tags":222},"C",[],[221],"livestock",[],{"code":224,"score":20,"supported":13,"title":225,"abstract":226,"tags":227},"D4",[],[],[29],[229,230],"物联网 机器学习 水质预测","rWQI 水质监测 水产养殖","物联网机器学习水质预测-4890",{"doi":8,"openalex_id":233,"authors":234,"venue":173,"cited_by_count":78,"oa_url":170,"card":244,"direction":80,"ingested_from":81},"W7221732805",[235,237,239,241],{"name":236,"orcid":8},"Wanarase Sinhashthita",{"name":238,"orcid":8},"Tossaporn Alherbe",{"name":240,"orcid":8},"Kamol Chareonsri",{"name":242,"orcid":243},"Chayaporn Kaensar","https:\u002F\u002Forcid.org\u002F0009-0005-3330-8532",{"tldr":245,"method":246,"finding":247,"direction":80,"opportunity":248},"利用物联网与机器学习构建水质预测监测系统，提前1-6小时预测rWQI。","基于水温、pH、TDS数据，比较ET、RF、LR、MLR四种模型预测性能。","短期（1-3小时）RF最优，长期（4-6小时）所有模型性能显著下降。","可探索融合时序深度学习与误差校正，提升长期水质预测精度与鲁棒性。","2026-10-14T23:30:13.314647Z",{"id":251,"title":252,"url":253,"summary":254,"summary_zh":255,"content":8,"source_name":256,"source_url":253,"published_at":257,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":258,"score_detail":259,"sources":261,"tags":263,"primary_topic":8,"secondary_topics":266,"classification":267,"search_phrases":283,"slug":286,"view_count":78,"doi":287,"paper":288,"created_at":306},4680,"Groundwater Potential Mapping in Northwestern Nigeria: A Comparison of the Analytic Hierarchy Process and Galileo-Enhanced CAT-XGB","https:\u002F\u002Fdoi.org\u002F10.31223\u002Fx5mv5h","Global water scarcity intensifies the need for high-resolution groundwater assessment tools, yet traditional approaches struggle to reconcile qualitative expert weights with the extensive spatial coverage offered by remote sensing data. This study presents a comparative framework evaluating expert-driven Multi-Criteria Decision Analysis (a ten-layer Analytic Hierarchy Process (AHP)) against data-driven ensemble machine learning for groundwater potential mapping in the geologically complex terrain of Northwestern Nigeria. Standard thematic layers were integrated with embeddings from a pretrained remote sensing foundation model to train ensemble classifiers, with groundwater potential validated against Vertical Electrical Sounding (VES) data. The foundation-model-enhanced CAT-XGB ensemble achieved notable predictive performance, consistently outperforming standalone tree-based classifiers and traditional AHP. Spatial difference mapping revealed that the enhanced ensemble captured critical, localized hydrogeological anomalies smoothed over by expert-driven weighting. Bridging heuristic decision-making with foundation-model-enhanced machine learning significantly improves spatial precision and reliability, potentially providing a field-validated tool for optimizing borehole siting and sustainable aquifer management in data-scarce, geologically complex regions.","全球水资源短缺加剧了对高分辨率地下水评估工具的需求，然而传统方法难以在定性专家权重与遥感数据所提供的广泛空间覆盖之间取得协调。本研究提出一个比较框架，在尼日利亚西北部地质复杂地形区，评估专家驱动的多准则决策分析（十层层次分析法（AHP））与数据驱动的集成机器学习在地下水潜力制图中的表现。研究将标准主题图层与预训练遥感基础模型的嵌入特征相结合以训练集成分类器，并利用垂直电测深（VES）数据对地下水潜力进行验证。经基础模型增强的CAT-XGB集成模型取得了显著的预测性能，持续优于独立的树基分类器和传统AHP。空间差异制图揭示，增强集成模型捕捉到了被专家驱动权重所平滑化的关键局部水文地质异常。将启发式决策与基础模型增强的机器学习相衔接，显著提升了空间精度与可靠性，有望为数据稀缺、地质复杂区域优化钻孔选址和可持续含水层管理提供一种经野外验证的工具。","OpenAlex","2026-10-09T00:00:00Z",69,{"impact":39,"substance":177,"depth":17,"authority":39,"freshness":121,"relevant":20,"comment":260},"将遥感基础模型与集成机器学习用于尼日利亚西北部地下水潜力制图，方法新颖、有实地验证，对缺水地区灌溉与水资源管理有参考价值，但属区域案例研究，公共影响有限。",[262],{"name":256,"url":253},[264,26,27,28,265],"农业人工智能","地下水潜力",[],{"status":32,"locked":13,"version":33,"method":34,"evidence":268},{"candidates":269,"agricultural_evidence":13,"reason":61},[270,274,278],{"code":38,"score":16,"supported":40,"title":271,"abstract":272,"tags":273},[],[26,42],[264,26],{"code":46,"score":121,"supported":40,"title":275,"abstract":276,"tags":277},[],[27,48],[27],{"code":52,"score":279,"supported":40,"title":280,"abstract":281,"tags":282},5,[],[135],[265,28],[284,285],"尼日利亚 地下水潜力 遥感","CAT-XGB 地下水 制图","尼日利亚地下水潜力遥感-4680","10.31223\u002Fx5mv5h",{"doi":287,"openalex_id":289,"authors":290,"venue":8,"cited_by_count":78,"oa_url":300,"card":301,"direction":164,"ingested_from":81},"W7221088011",[291,293,295,297],{"name":292,"orcid":8},"Joseph Osumeje",{"name":294,"orcid":8},"Sachet Utekar",{"name":296,"orcid":8},"Morli Li",{"name":298,"orcid":299},"Daniel C. Jones","https:\u002F\u002Forcid.org\u002F0000-0002-8701-4506","https:\u002F\u002Feartharxiv.org\u002Frepository\u002Fobject\u002F15434\u002Fdownload\u002F26756\u002F",{"tldr":302,"method":303,"finding":304,"direction":164,"opportunity":305},"对比专家驱动AHP与遥感基础模型增强的CAT-XGB集成，用于尼日利亚西北部地下水潜力制图。","十层AHP与预训练遥感基础模型嵌入训练CAT-XGB集成，用垂直电测深数据验证。","基础模型增强的CAT-XGB集成预测性能优于传统AHP和独立树模型，能捕捉局部水文地质异常。","可探索遥感基础模型嵌入与专家知识融合，提升数据稀缺复杂区地下水等农业水资源评估精度。","2026-10-11T23:30:30.328869Z",{"id":308,"title":309,"url":310,"summary":311,"summary_zh":312,"content":8,"source_name":313,"source_url":310,"published_at":314,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":315,"score_detail":316,"sources":319,"tags":321,"primary_topic":324,"secondary_topics":328,"classification":329,"search_phrases":352,"slug":355,"view_count":20,"doi":356,"paper":357,"created_at":382},4503,"FUSING DEEP LEARNING AND REMOTE SENSING DATA TO ESTIMATE NON-OPTICALLY ACTIVE WATER QUALITY VARIABLES","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23243307","The efficient monitoring of inland water bodies such as rivers and lakes is crucial not only for ensuring human health and ecosystem balance, but also for the effective management of water resources. Two water quality variables of high importance and interest are Dissolved Oxygen (DO) and pH. The former variable is an ecosystem health index as it is connected to hypoxia events, while the latter one is linked to biochemical processes and the acidity of water. Currently, conventional water quality monitoring methods (e.g., via in-situ point sampling) are accurate for the particular point, but costly and time-consuming. On the other hand, satellite remote sensing provides a remedy, as it offers high spatial and temporal coverage. Most of the water quality applications of remote sensing data have focused on optically active parameters like Chlorophyll-a and Colored Dissolved Organic Matter (CDOM), but the estimation of non-optically active variables such as pH and DO poses a significant challenge. This study introduces a novel approach, that fuses Earth Observation (EO) and in-situ data, in a deep learning context, to provide estimations of non-optically active variables, characterized by high accuracy, high spatial coverage and low latency. The approach also considers the data imbalance challenge, which is common in environmental datasets. The approach is applied to Lake Yliki in central Greece. The Boeotikos Kifissos river basin, which lies upstream of Lake Yliki, is dominated by intense agricultural activity. The lake is also part of Athens’ water distribution system, making its efficient monitoring even more important.","对河流、湖泊等内陆水体的高效监测，不仅对保障人类健康和生态系统平衡至关重要，也对水资源的有效管理不可或缺。溶解氧（Dissolved Oxygen, DO）和pH值是两项备受关注且极为重要的水质变量。前者作为生态系统健康指标，与缺氧事件密切相关；后者则与生物化学过程及水体酸度相关。目前，传统的水质监测方法（如原位定点采样）对特定点位而言较为准确，但成本高昂且耗时费力。相比之下，卫星遥感提供了一种解决方案，因其具备较高的时空覆盖能力。遥感数据在水质方面的应用大多集中于光学活性参数，如叶绿素a和有色溶解有机物（Colored Dissolved Organic Matter, CDOM），而对pH值和溶解氧等非光学活性变量的估算则构成重大挑战。本研究提出了一种新方法，在深度学习框架下融合地球观测（Earth Observation, EO）数据与原位数据，以实现对非光学活性变量的高精度、高空间覆盖度和低延迟估算。该方法还考虑了环境数据集中常见的数据不平衡问题。该方法已应用于希腊中部的伊利基湖（Lake Yliki）。位于伊利基湖上游的维奥蒂亚基菲索斯河流域（Boeotikos Kifissos river basin）以密集的农业活动为主。该湖也是雅典供水系统的组成部分，因此对其开展高效监测尤为重要。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-08T00:00:00Z",81,{"impact":17,"substance":317,"depth":17,"authority":179,"freshness":12,"relevant":20,"comment":318},22,"将深度学习与遥感、地面实测数据融合估算内陆水体非光学活性水质参数，方法新颖且面向农业流域与饮用水源监测，具备较高专业参考价值。",[320],{"name":313,"url":310},[322,323,27,28,29],"深度学习","农业面源污染",{"code":110,"slug":325,"name":326,"path":327,"parent_code":8},"digital-agriculture","数字农业与前沿技术","\u002Ftopic\u002Fdigital-agriculture",[],{"status":330,"locked":13,"version":33,"method":34,"evidence":331},"partial",{"candidates":332,"agricultural_evidence":40,"reason":351},[333,338,342,346],{"code":38,"score":18,"supported":40,"title":334,"abstract":336,"tags":337},[335],"deep learning",[322,335],[322],{"code":46,"score":18,"supported":40,"title":339,"abstract":340,"tags":341},[48],[27,48],[27],{"code":52,"score":98,"supported":40,"title":343,"abstract":344,"tags":345},[],[135],[28],{"code":347,"score":20,"supported":13,"title":348,"abstract":349,"tags":350},"H5",[],[],[323],"一级领域明确，二级方向需要细分",[353,354],"Yliki湖 水质 遥感","溶解氧 pH 遥感 估算","Yliki湖水质遥感-4503","10.5281\u002Fzenodo.23243307",{"doi":356,"openalex_id":358,"authors":359,"venue":313,"cited_by_count":78,"oa_url":310,"card":377,"direction":164,"ingested_from":81},"W7220943541",[360,363,366,369,371,374],{"name":361,"orcid":362},"Vasiliki Thomopoulou","https:\u002F\u002Forcid.org\u002F0009-0000-8361-6879",{"name":364,"orcid":365},"Panagiotis Kossieris","https:\u002F\u002Forcid.org\u002F0000-0002-5201-3079",{"name":367,"orcid":368},"Georgios Bariamis","https:\u002F\u002Forcid.org\u002F0000-0002-9548-3054",{"name":370,"orcid":8},"Konstantinos Peroulis",{"name":372,"orcid":373},"G. Katsouras","https:\u002F\u002Forcid.org\u002F0000-0003-3249-3113",{"name":375,"orcid":376},"Christos Makropoulos","https:\u002F\u002Forcid.org\u002F0000-0003-0308-4265",{"tldr":378,"method":379,"finding":380,"direction":164,"opportunity":381},"融合深度学习与遥感及实地数据，估算湖泊非光学活性水质变量（溶解氧和pH）。","深度学习融合地球观测与实地数据，处理数据不平衡，应用于希腊Yliki湖。","该方法能高精度、高覆盖、低延迟地估算非光学活性水质变量。","可探索将此类方法迁移至农业流域水质监测，结合农业活动数据提升预警能力。","2026-10-09T23:30:25.773729Z",{"id":384,"title":385,"url":386,"summary":387,"summary_zh":8,"content":8,"source_name":388,"source_url":8,"published_at":8,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":389,"score_detail":390,"sources":392,"tags":394,"primary_topic":398,"secondary_topics":403,"classification":404,"search_phrases":427,"slug":430,"view_count":431,"doi":8,"paper":432,"created_at":440},4477,"玉米生产精准农业系统综述：技术、应用与产量优化（2020—2026）","https:\u002F\u002Fm2.mtmt.hu\u002Fapi\u002Fpublication\u002F37500368","依据PRISMA 2020指南，系统检索Scopus与Web of Science共464篇文献，最终纳入129项研究；样本构成为田间试验（28.6%）、遥感与精准农业整合研究（25.5%）、机器学习应用（19.4%）、气候知情精准农业策略（23.4%）和土壤退化研究（3.1%）；研究表明精准农业技术通过定点管理和数据驱动决策支持，提升了玉米生产力、养分利用效率、水利用效率和产量预测准确性；指出采用精准农业仍受制于实施成本高、技术复杂、数据有限等因素。","Precision Agriculture in Maize Production Systematic Review 2026",74,{"impact":17,"substance":317,"depth":17,"authority":179,"freshness":139,"relevant":20,"comment":391},"基于PRISMA 2020的系统综述，纳入129项研究，数据规模与方法规范性强，对玉米精准农业技术路径与瓶颈有实质参考价值，但发布日期不明、时效性偏弱。",[393],{"name":388,"url":386},[25,395,26,396,397,27],"产量预测","玉米","精准农业",{"code":399,"slug":400,"name":396,"path":401,"parent_code":402},"A3","maize","\u002Ftopic\u002Ffield-crops\u002Fmaize","A",[],{"status":113,"locked":13,"version":33,"method":34,"evidence":405},{"candidates":406,"agricultural_evidence":40},[407,411,415,419,423],{"code":57,"score":179,"supported":40,"title":408,"abstract":409,"tags":410},[397],[397],[25,397],{"code":399,"score":39,"supported":40,"title":412,"abstract":413,"tags":414},[396],[396],[396],{"code":46,"score":279,"supported":40,"title":416,"abstract":417,"tags":418},[],[27],[395,27],{"code":38,"score":98,"supported":40,"title":420,"abstract":421,"tags":422},[],[26],[26],{"code":126,"score":139,"supported":40,"title":424,"abstract":425,"tags":426},[],[129],[],[428,429],"玉米 精准农业 系统综述","玉米 遥感 机器学习 产量","玉米精准农业系统综述-4477",2,{"doi":8,"openalex_id":8,"authors":433,"venue":8,"cited_by_count":78,"oa_url":8,"card":434,"direction":80,"ingested_from":439},[],{"tldr":435,"method":436,"finding":437,"direction":80,"opportunity":438},"系统综述2020—2026年玉米精准农业技术、应用与产量优化研究。","按PRISMA 2020检索Scopus与WoS，纳入129项研究做分类分析。","精准农业通过定点管理与数据决策提升玉米产量、养分和水利用效率。","成本高、技术复杂与数据不足制约推广，低成本轻量化方案与本地化数据共享是研究空白。","agent","2026-10-09T00:05:02.451957Z",{"id":442,"title":443,"url":444,"summary":445,"summary_zh":446,"content":8,"source_name":447,"source_url":444,"published_at":448,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":449,"score_detail":450,"sources":454,"tags":456,"primary_topic":8,"secondary_topics":458,"classification":459,"search_phrases":491,"slug":494,"view_count":78,"doi":495,"paper":496,"created_at":517},4311,"Cross-Regional Digital Soil Mapping of OpenLandMap-Derived USDA Soil Texture Classes Using Remote Sensing and Machine Learning","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fagriculture16192147","Soil is a fundamental environmental resource that supports food production and sustainable agricultural systems. Soil’s texture is a key soil property that affects its capacity to hold water, infiltration rate, fertility, erosion risk, and crop productivity. Traditionally, it is determined using hydrometer or pipette analysis. These laboratory procedures are costly and time-consuming, typically requiring approximately two working days, which limits their practicality for large-scale assessments. This paper proposes a cross-regional digital soil texture classification system based on remote sensing data and machine learning in Malaysia and Pakistan. The two countries were chosen because they represent contrasting environmental conditions: Malaysia has humid tropical conditions, and Pakistan has arid and semi-arid conditions. The OpenLandMap United States Department of Agriculture (USDA) soil texture classes served as the reference labels, and the spectral bands from Landsat, together with spectral indices and Shuttle Radar Topography Mission (SRTM) elevation, were used as predictor variables. The three ensemble models, including Random Forest (RF), XGBoost, and CatBoost, were evaluated for multi-class classification of USDA soil texture. The main Landsat-based Malaysia–Pakistan dataset produced the best results, with RF achieving the highest accuracy of 71.45%, XGBoost 71.31%, and CatBoost 67.33%. Additional experiments using 2025 Landsat 8\u002F9 and Sentinel-2 imagery achieved lower accuracies of 63.00% and 56.10%, respectively, while five-fold spatial block cross-validation produced a mean accuracy of 59.27 ± 1.84%. To strengthen dataset reliability, representative OpenLandMap-derived soil texture classes were externally validated using PCRWR sand–silt–clay fractions plotted on the USDA soil texture triangle and independent Malaysian soil resource references. The results of the feature importance analysis showed that elevation, Bare Soil Index (BSI), Normalized Difference Water Index (NDWI), and Normalized Difference Vegetation Index (NDVI) were important predictors for classifying OpenLandMap-derived USDA soil texture classes. These show that the Landsat-based spectral and terrain features, when used in conjunction with ensemble learning, could assist cross-regional soil texture classification for the USDA. However, class imbalance, spectral overlap between soil texture classes, temporal variability, and resolution mismatch between satellite predictors and soil labels remain important challenges. The findings of this study provide a useful foundation for large-scale soil texture mapping and future spatial validation across different environmental regions.","土壤是支撑粮食生产和可持续农业系统的基础环境资源。土壤质地是影响土壤持水能力、入渗速率、肥力、侵蚀风险和作物生产力的关键土壤属性。传统上，土壤质地采用比重计法或吸管法测定。这些实验室方法成本高、耗时长，通常需要约两个工作日，限制了其在大规模评估中的实用性。本文提出了一种基于遥感数据和机器学习的跨区域数字土壤质地分类系统，研究区域为马来西亚和巴基斯坦。选择这两个国家是因为它们代表了截然不同的环境条件：马来西亚属于湿润热带条件，巴基斯坦属于干旱和半干旱条件。以OpenLandMap提供的美国农业部（USDA）土壤质地类别作为参考标签，以Landsat光谱波段、光谱指数和航天飞机雷达地形测绘任务（SRTM）高程数据作为预测变量。评估了三种集成模型，包括随机森林（RF）、XGBoost和CatBoost，用于USDA土壤质地的多类分类。基于Landsat的马来西亚—巴基斯坦主数据集取得了最佳结果，RF达到最高精度71.45%，XGBoost为71.31%，CatBoost为67.33%。使用2025年Landsat 8\u002F9和Sentinel-2影像的额外实验分别取得了较低的精度，为63.00%和56.10%，而五折空间块交叉验证产生的平均精度为59.27 ± 1.84%。为增强数据集可靠性，使用PCRWR砂—粉—黏粒比例绘制在USDA土壤质地三角图上，并结合独立的马来西亚土壤资源参考资料，对具有代表性的OpenLandMap衍生土壤质地类别进行了外部验证。特征重要性分析结果表明，高程、裸土指数（BSI）、归一化差异水体指数（NDWI）和归一化差异植被指数（NDVI）是分类OpenLandMap衍生USDA土壤质地类别的重要预测因子。这些结果表明，基于Landsat的光谱和地形特征与集成学习结合使用时，可辅助USDA的跨区域土壤质地分类。然而，类别不平衡、土壤质地类别之间的光谱重叠、时间变异性以及卫星预测因子与s之间的分辨率不匹配","Agriculture","2026-10-05T00:00:00Z",77,{"impact":451,"substance":452,"depth":17,"authority":179,"freshness":66,"relevant":20,"comment":453},16,21,"跨区域遥感与集成学习土壤质地分类研究，方法扎实、结论有参考价值，但精度有限，属细分领域进展。",[455],{"name":447,"url":444},[204,25,26,27,457],"土壤制图",[],{"status":32,"locked":13,"version":33,"method":34,"evidence":460},{"candidates":461,"agricultural_evidence":40,"reason":490},[462,466,470,474,480,486],{"code":126,"score":18,"supported":40,"title":463,"abstract":464,"tags":465},[130],[129,130],[457],{"code":38,"score":18,"supported":40,"title":467,"abstract":468,"tags":469},[42],[26,42],[26],{"code":46,"score":18,"supported":40,"title":471,"abstract":472,"tags":473},[48],[27,48],[27],{"code":475,"score":139,"supported":40,"title":476,"abstract":477,"tags":479},"H7",[],[478],"干旱",[],{"code":481,"score":139,"supported":40,"title":482,"abstract":483,"tags":485},"H8",[],[484],"可持续农业",[],{"code":57,"score":431,"supported":13,"title":487,"abstract":488,"tags":489},[],[],[204,25],"多个产业证据相当，需要确认主归属",[492,493],"OpenLandMap USDA 土壤质地","Landsat 土壤质地 机器学习","OpenLandMapUSDA土壤质地-4311","10.3390\u002Fagriculture16192147",{"doi":495,"openalex_id":497,"authors":498,"venue":447,"cited_by_count":78,"oa_url":444,"card":512,"direction":164,"ingested_from":81},"W7220411242",[499,501,503,506,509],{"name":500,"orcid":8},"Umair Maqsood",{"name":502,"orcid":8},"Fatima Iftikhar",{"name":504,"orcid":505},"Kashif Sattar","https:\u002F\u002Forcid.org\u002F0000-0001-8620-9419",{"name":507,"orcid":508},"Iftikhar A. Ahmad","https:\u002F\u002Forcid.org\u002F0000-0003-3719-2387",{"name":510,"orcid":511},"Madini Obad Alassafi","https:\u002F\u002Forcid.org\u002F0000-0001-9919-8368",{"tldr":513,"method":514,"finding":515,"direction":164,"opportunity":516},"用Landsat光谱与地形特征结合集成学习，实现马来西亚与巴基斯坦跨区域USDA土壤质地分类。","Landsat光谱波段、光谱指数与SRTM高程，RF\u002FXGBoost\u002FCatBo","RF精度最高71.45%，高程、BSI、NDWI、NDVI为关键预测因子，跨区域可行但精度受限。","可探索多源遥感融合与类别不平衡校正，提升跨气候区土壤质地制图精度与迁移能力。","2026-10-06T23:30:20.282911Z"]