[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-1901":3,"related-1901":80},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":24,"tags":26,"primary_topic":9,"secondary_topics":30,"classification":31,"search_phrases":51,"slug":54,"view_count":22,"doi":55,"paper":56,"created_at":79},1901,"Temperature and land use influence on spatiotemporal dynamics of particulate composition in Chinese Eastern Plain Lakes: a remote sensing-based study","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffenvs.2026.1903409","The composition of particulate matter in lakes is considered a key indicator of underwater light-field dynamics and the proportion of organic matter. In this study, reflectance from Sentinel-3 OLCI (Ocean and Land Colour Instrument) imagery at 510, 560, and 620 nm was utilized to estimate the organic suspended matter to total suspended matter ratio (OSM\u002FTSM) in lakes, serving as an indicator of particulate composition. The multi-year spatiotemporal characteristics of OSM\u002FTSM in 76 lakes (>10 km 2 ) from 2016 to 2023 were investigated. Generalized linear models were used to explore the relative ranking of meteorological and anthropogenic correlates, while a pooled linear mixed-effects model was used for association analysis. The results revealed that OSM\u002FTSM mainly ranged from 0.2 to 0.6, and 79.96% of the lakes showed an increasing trend in OSM\u002FTSM according to the Mann-Kendall test. Additionally, peak OSM\u002FTSM values were often observed in summer and autumn, while the lowest values occurred in spring and winter. Temperature had the highest normalized relative weight (44.93%) for intra-annual OSM\u002FTSM variation. For inter-annual variation, land-use variables had a combined normalized relative weight of 58.00%. The OSM\u002FTSM estimates provided by this study for large inland lakes can serve as a valuable reference for future lake monitoring and assessment in the Eastern Plain Lakes of China.","湖泊中颗粒物组成被视为水下光场动态及有机物比例的关键指标。本研究利用Sentinel-3 OLCI（海洋与陆地颜色仪）影像在510、560和620纳米波段的反射率，估算湖泊中有机悬浮物与总悬浮物之比（OSM\u002FTSM），以此作为颗粒物组成的指示因子。研究调查了2016年至2023年间76个面积大于10平方公里的湖泊OSM\u002FTSM的多年度时空特征。采用广义线性模型探讨气象与人为因素的相对排序，并使用合并线性混合效应模型进行关联分析。结果表明，OSM\u002FTSM主要介于0.2至0.6之间，根据Mann-Kendall检验，79.96%的湖泊OSM\u002FTSM呈上升趋势。此外，OSM\u002FTSM峰值常出现在夏季和秋季，而最低值则出现在春季和冬季。温度对年内OSM\u002FTSM变化的标准化相对权重最高（44.93%）。就年际变化而言，土地利用变量的综合标准化相对权重为58.00%。本研究为大型内陆湖泊提供的OSM\u002FTSM估算结果，可作为中国东部平原湖区未来湖泊监测与评估的有价值参考。",null,"Frontiers in Environmental Science","2026-09-07T00:00:00Z","论文",10,false,70,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},15,22,18,12,3,1,"该研究利用遥感技术分析中国东部平原湖泊颗粒物组成，对农业面源污染监测具有参考价值，但时效性较低。",[25],{"name":10,"url":6},[27,28,29],"农业面源污染","遥感监测","湖泊水质",[],{"status":32,"locked":14,"version":33,"method":34,"evidence":35},"needs_review","2026-10-22.2","rules",{"candidates":36,"agricultural_evidence":14,"reason":50},[37,45],{"code":38,"score":39,"supported":40,"title":41,"abstract":43,"tags":44},"I3",9,true,[42],"remote sensing",[],[28],{"code":46,"score":22,"supported":14,"title":47,"abstract":48,"tags":49},"H5",[],[],[27],"农业相关性需要复核",[52,53],"农业面源污染 湖泊水质 遥感监测","农业面源污染 湖泊水质","农业面源污染湖泊水质遥感监测-1901","10.3389\u002Ffenvs.2026.1903409",{"doi":55,"openalex_id":57,"authors":58,"venue":10,"cited_by_count":70,"oa_url":71,"card":72,"direction":76,"ingested_from":78},"W7211894276",[59,61,64,66,68],{"name":60,"orcid":9},"Fangfang Chen",{"name":62,"orcid":63},"Honglei Guo","https:\u002F\u002Forcid.org\u002F0000-0001-6518-0143",{"name":65,"orcid":9},"Yan Zhaojiang",{"name":67,"orcid":9},"Shijiao Lu",{"name":69,"orcid":9},"Wenyu Liu",0,"https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fenvironmental-science\u002Farticles\u002F10.3389\u002Ffenvs.2026.1903409\u002Fpdf",{"tldr":73,"method":74,"finding":75,"direction":76,"opportunity":77},"利用Sentinel-3遥感估算中国东部平原湖泊颗粒物组成，分析其时空变化及影响因素。","Sentinel-3 OLCI反射率估算OSM\u002FTSM，结合GLM和线性混合效应","OSM\u002FTSM多呈上升趋势，温度主导年内变化，土地利用主导年际变化。","农业遥感与作物表型","可延伸至农业面源污染对湖泊颗粒物组成的影响，结合流域土地利用优化模型。","openalex","2026-09-08T23:30:18.990567Z",{"total":81,"page":22,"page_size":81,"items":82},6,[83,162,246,326,406,484],{"id":84,"title":85,"url":86,"summary":87,"summary_zh":88,"content":9,"source_name":89,"source_url":86,"published_at":90,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":91,"score_detail":92,"sources":96,"tags":98,"primary_topic":102,"secondary_topics":107,"classification":108,"search_phrases":137,"slug":140,"view_count":22,"doi":141,"paper":142,"created_at":161},4599,"Reducing redundancy in multi-temporal analysis to improve field-scale detection of crop residue burning","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.rsase.2026.102310","Accurate field-scale mapping of paddy stubble burning is essential for reliable emission estimation and effective policy intervention. However, current remote sensing approaches often suffer from significant inaccuracies due to the repeated detection of the same field-scale across multi-temporal observations. This leads to systematic overestimation of field-scale and remains insufficiently addressed in existing studies. This study addresses the challenge using multi-temporal remote sensing data and a fuzzy machine-learning technique using the ‘Individual Sample as Mean (ISM)’ training approach. The study was implemented in the Nanakmatta area of Udham Singh Nagar District, Uttarakhand, India. PlanetScope satellite imagery, covering both harvesting and burnt-stubble conditions, was utilised to reduce redundancy. A Modified Possibilistic c -Means (MPCM) classifier, integrated with the ISM approach, was employed to map stubble burning across 13 observation dates during October-November 2025. Peak burning activity was recorded around 23 October 2025, followed by a gradual decline, with no detectable burning on 16 November 2025. The combination of MPCM and ISM effectively minimises inflated estimates of burning events caused by repeated detections of the same burnt areas. Specifically, the ISM training approach handles variability in burning patterns caused by partial combustion, residue mixing, and delayed field preparation. It accounts for class diversity rather than forcing all instances into a single generalised representation. Accuracy assessment using both Mean Membership Difference (MMD) and conventional classification metrics demonstrated the robustness of the proposed framework. A within-class MMD of 0 and a between-class MMD of 0.66 indicated strong class separability, with precision, recall, and F1-score values of 0.775, 0.688, and 0.729, respectively. The proposed framework provides a more reliable and quantitatively validated approach for addressing temporal redundancy and monitoring residue-burning practices across diverse agricultural environments.","准确的田块尺度水稻秸秆焚烧制图对于可靠的排放估算和有效的政策干预至关重要。然而，当前遥感方法常因在多时相观测中重复检测同一田块尺度而导致显著不准确，造成田块尺度的系统性高估，现有研究对此仍未充分解决。本研究利用多时相遥感数据和模糊机器学习技术，采用“个体样本作为均值”（Individual Sample as Mean, ISM）训练方法应对这一挑战。研究在印度北阿坎德邦乌达姆·辛格·纳加尔县的纳纳克马塔地区实施。利用覆盖收割和焚烧后秸秆状况的PlanetScope卫星影像以减少冗余。采用改进的可能性c均值（Modified Possibilistic c-Means, MPCM）分类器，结合ISM方法，对2025年10月至11月期间的13个观测日期进行秸秆焚烧制图。焚烧活动高峰出现在2025年10月23日前后，随后逐渐下降，至2025年11月16日未检测到焚烧。MPCM与ISM的结合有效减少了因重复检测同一焚烧区域而导致的焚烧事件高估。具体而言，ISM训练方法能够处理由不完全燃烧、残茬混合和田间准备延迟引起的焚烧模式变异性，它考虑了类别多样性，而非将所有实例强制归入单一泛化表示。使用平均隶属度差异（Mean Membership Difference, MMD）和传统分类指标进行精度评估，证明了所提框架的稳健性。类内MMD为0，类间MMD为0.66，表明类别可分性强，精确率、召回率和F1分数分别为0.775、0.688和0.729。所提框架为解决时间冗余和监测多样化农业环境中的残茬焚烧行为提供了一种更可靠且经定量验证的方法。","Remote Sensing Applications Society and Environment","2026-10-08T00:00:00Z",73,{"impact":20,"substance":93,"depth":19,"authority":94,"freshness":39,"relevant":22,"comment":95},21,13,"方法新颖、数据扎实的遥感论文，对秸秆焚烧监测与排放估算有参考价值，但属细分领域技术进展，公共影响有限。",[97],{"name":89,"url":86},[99,27,100,28,101],"农业人工智能","作物识别","秸秆焚烧",{"code":38,"slug":103,"name":104,"path":105,"parent_code":106},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",[],{"status":109,"locked":14,"version":33,"method":34,"evidence":110},"classified",{"candidates":111,"agricultural_evidence":40},[112,118,125,132],{"code":38,"score":113,"supported":40,"title":114,"abstract":115,"tags":117},7,[],[116,42],"遥感",[28],{"code":119,"score":81,"supported":40,"title":120,"abstract":121,"tags":124},"A1",[],[122,123],"水稻","paddy",[],{"code":126,"score":127,"supported":40,"title":128,"abstract":129,"tags":131},"I2",4,[],[130],"机器学习",[99],{"code":46,"score":133,"supported":14,"title":134,"abstract":135,"tags":136},2,[],[],[27,101],[138,139],"PlanetScope 秸秆焚烧 遥感","Uttarakhand 稻田 秸秆焚烧","PlanetScope秸秆焚烧遥感-4599","10.1016\u002Fj.rsase.2026.102310",{"doi":141,"openalex_id":143,"authors":144,"venue":89,"cited_by_count":70,"oa_url":86,"card":156,"direction":76,"ingested_from":78},"W7221040421",[145,148,151,154],{"name":146,"orcid":147},"Anil Kumar","https:\u002F\u002Forcid.org\u002F0000-0002-7177-0817",{"name":149,"orcid":150},"Anamika Palavesam Sarathamani","https:\u002F\u002Forcid.org\u002F0009-0007-4223-7443",{"name":152,"orcid":153},"Ishwari Datt","https:\u002F\u002Forcid.org\u002F0000-0001-9936-2367",{"name":155,"orcid":9},"R.P. Singh",{"tldr":157,"method":158,"finding":159,"direction":76,"opportunity":160},"用多时相遥感与模糊机器学习减少重复检测，提升稻田秸秆焚烧田块尺度制图精度。","PlanetScope多时相影像，MPCM分类器结合ISM训练，13期观测。","MPCM+ISM有效抑制重复检测导致的焚烧面积高估，F1达0.729。","可将去冗余框架迁移至其他作物残茬焚烧监测，并融合Sentinel-2提升时空覆盖。","2026-10-10T23:30:31.208858Z",{"id":163,"title":164,"url":165,"summary":166,"summary_zh":167,"content":9,"source_name":168,"source_url":165,"published_at":90,"category":12,"cover_url":9,"hotness":169,"is_selected":14,"score":170,"score_detail":171,"sources":173,"tags":178,"primary_topic":182,"secondary_topics":186,"classification":187,"search_phrases":217,"slug":220,"view_count":22,"doi":221,"paper":222,"created_at":245},4526,"Explainable machine learning for spatial modelling of groundwater nitrate contamination: a multi-year analysis in the Duero basin","https:\u002F\u002Fdoi.org\u002F10.6084\u002Fm9.figshare.34244894.v1","Groundwater nitrate contamination is a major water-quality concern, with implications for drinking water supplies and groundwater-dependent ecosystems. This study assesses the Duero River basin (Spain), where groundwater nitrate concentrations have increased in recent decades due to intensive agriculture and livestock farming. The probability of elevated groundwater nitrate concentrations was predicted using machine learning, formulated as a binary classification problem with a threshold of 37.5 mg\u002FL. Monitoring data were combined with spatially derived environmental and anthropogenic predictors. Several tree-based algorithms were evaluated, with Random Forest selected for its consistent predictive performance. Model performance was assessed through repeated nested cross-validation and the use of metrics suitable for imbalanced datasets, achieving an AUC of 0.79-0.88 and an F1-score of 0.56-0.70 for the minority class across the three analysed hydrological years. SHAP analysis identified precipitation, diffuse agricultural pressures, distance to surface water bodies, NDVI, and soil properties as the main contributing predictors. Multi-year probability maps showed substantial spatial coherence with officially designated Nitrate Vulnerable Zones (46.9-64.9%), while identifying additional high-probability areas outside them (12.7-23.6%). The integration of explainable machine learning, multi-year spatial modelling, and regulatory comparison provides a framework to support groundwater monitoring, review vulnerable-zone delineation, and prioritise mitigation measures.","地下水硝酸盐污染是一个重要的水质问题，对饮用水供应和依赖地下水的生态系统具有影响。本研究评估了西班牙杜埃罗河流域（Duero River basin），近几十年来，由于集约化农业和畜牧业，该地区地下水硝酸盐浓度有所上升。本研究使用机器学习预测地下水硝酸盐浓度升高的概率，并将其表述为以37.5 mg\u002FL为阈值的二分类问题。监测数据与空间衍生的环境及人为预测因子相结合。研究评估了多种基于树的算法，并因随机森林（Random Forest）具有稳定的预测性能而选用该算法。模型性能通过重复嵌套交叉验证以及适用于不平衡数据集的指标进行评估，在三个分析水文年度中，少数类别的AUC达到0.79-0.88，F1分数达到0.56-0.70。SHAP分析确定降水、面源农业压力、距地表水体距离、NDVI和土壤属性为主要贡献预测因子。多年概率图显示出与官方指定硝酸盐脆弱区（Nitrate Vulnerable Zones）较高的空间一致性（46.9-64.9%），同时在这些区域之外识别出额外的高概率区域（12.7-23.6%）。可解释机器学习、多年空间建模和监管比较的整合提供了一个框架，可支持地下水监测、审查脆弱区划定并优先安排缓解措施。","Figshare",25,79,{"impact":19,"substance":18,"depth":19,"authority":20,"freshness":39,"relevant":22,"comment":172},"可解释机器学习结合多年空间建模识别地下水硝酸盐污染高风险区，方法新颖、结论可靠，对农业面源污染监测与脆弱区划定有参考价值。",[174,175],{"name":168,"url":165},{"name":176,"url":177},"International Journal of River Basin Management","https:\u002F\u002Fdoi.org\u002F10.1080\u002F15715124.2026.2742495",[179,27,28,180,181],"可解释机器学习","地下水硝酸盐","硝酸盐脆弱区",{"code":126,"slug":183,"name":184,"path":185,"parent_code":106},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",[],{"status":109,"locked":14,"version":33,"method":34,"evidence":188},{"candidates":189,"agricultural_evidence":40},[190,195,202,209,213],{"code":126,"score":17,"supported":40,"title":191,"abstract":193,"tags":194},[192],"machine learning",[130,192],[179],{"code":196,"score":81,"supported":40,"title":197,"abstract":198,"tags":201},"C",[],[199,200],"畜牧","livestock",[],{"code":203,"score":81,"supported":40,"title":204,"abstract":205,"tags":208},"H2",[],[206,207],"土壤","soil",[],{"code":46,"score":22,"supported":14,"title":210,"abstract":211,"tags":212},[],[],[27],{"code":38,"score":22,"supported":14,"title":214,"abstract":215,"tags":216},[],[],[28],[218,219],"SHAP 硝酸盐脆弱区","可解释机器学习 农业面源污染 地下水硝酸盐 硝酸盐脆弱区","SHAP硝酸盐脆弱区-4526","10.6084\u002Fm9.figshare.34244894.v1",{"doi":221,"openalex_id":223,"authors":224,"venue":168,"cited_by_count":70,"oa_url":165,"card":238,"direction":244,"ingested_from":78},"W7220971680",[225,228,230,232,235],{"name":226,"orcid":227},"Manuel Rodríguez del Rosario","https:\u002F\u002Forcid.org\u002F0000-0002-4202-6722",{"name":229,"orcid":9},"Victor Gómez-Escalonilla",{"name":231,"orcid":9},"Héctor Aguilera",{"name":233,"orcid":234},"Pedro Martínez‐Santos","https:\u002F\u002Forcid.org\u002F0000-0003-2014-4063",{"name":236,"orcid":237},"África de la Hera Portillo","https:\u002F\u002Forcid.org\u002F0000-0001-7821-1834",{"tldr":239,"method":240,"finding":241,"direction":242,"opportunity":243},"用可解释机器学习预测西班牙杜埃罗盆地地下水硝酸盐超标概率并绘制多年风险图。","随机森林二分类，结合监测数据与空间环境人为预测因子，SHAP解释。","模型AUC达0.79-0.88，识别出硝酸盐脆弱区外12.7-23.6%的高风险区。","农业绿色发展与碳","可迁移至其他农业流域，结合时序遥感与政策情景模拟优化脆弱区动态划定。","农业人工智能与决策模型","2026-10-09T23:30:47.673746Z",{"id":247,"title":248,"url":249,"summary":250,"summary_zh":251,"content":9,"source_name":252,"source_url":249,"published_at":253,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":254,"score_detail":255,"sources":260,"tags":262,"primary_topic":265,"secondary_topics":269,"classification":270,"search_phrases":300,"slug":303,"view_count":21,"doi":304,"paper":305,"created_at":325},3553,"Advances and gaps in mitigation and management practices across critical landscapes and scales","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.jenvman.2026.131013","Environmental systems are increasingly stressed by the interacting effects of climate change, land-use change, agricultural intensification, urbanization, and emerging contaminants. This paper synthesizes contributions to the Journal of Environmental Management special collection, “Advances and gaps in mitigation and management practices across critical landscapes and scales,” which examines current progress and remaining challenges in environmental mitigation and best management practices. The reviewed studies span diverse landscapes, scales, and management contexts, with emphasis on water quality, water quantity, pollutant transport, ecological resilience, and sustainable agricultural systems. Four major themes emerge: the combined pressures of climate and human activity on environmental systems; innovations in modeling, monitoring, remote sensing, and statistical forecasting; evaluation of management interventions and mitigation strategies; and cross-cutting insights related to spatial variability, extreme events, long-term dynamics, and implementation gaps. Collectively, the studies demonstrate that mitigation effectiveness is highly context-dependent and influenced by hydrologic connectivity, land use, climate variability, management history, and social factors. Advances in process-based models, machine learning, geospatial technologies, and monitoring, reporting, and verification frameworks are improving the ability to predict environmental responses and evaluate intervention outcomes. However, persistent gaps remain in long-term monitoring, maintenance of management practices, adaptation to extreme events, and translation of scientific findings into policy and practice. This synthesis highlights the need for integrated, adaptive, and stakeholder-informed approaches to strengthen environmental resilience across critical landscapes.","环境系统日益受到气候变化、土地利用变化、农业集约化、城市化以及新兴污染物相互作用的影响。本文综合了《环境管理杂志》特刊“关键景观与尺度下减缓与管理实践的进展与差距”的贡献，该特刊审视了环境减缓与最佳管理实践的当前进展及剩余挑战。所综述的研究涵盖多样化的景观、尺度和管理情境，重点关注水质、水量、污染物迁移、生态韧性和可持续农业系统。由此浮现出四大主题：气候与人类活动对环境系统的复合压力；建模、监测、遥感与统计预测方面的创新；管理干预与减缓策略的评估；以及关于空间变异性、极端事件、长期动态与实施差距的交叉性见解。总体而言，这些研究表明，减缓效果高度依赖于具体情境，并受水文连通性、土地利用、气候变异性、管理历史和社会因素的影响。基于过程的模型、机器学习、地理空间技术以及监测、报告与核查框架的进步，正在提升预测环境响应和评估干预结果的能力。然而，在长期监测、管理实践的维持、极端事件的适应以及科学发现向政策与实践的转化方面，仍存在持续性的差距。本综述强调，需要采取综合性、适应性且利益相关者知情的方法，以增强关键景观的环境韧性。","Journal of Environmental Management","2026-09-25T00:00:00Z",78,{"impact":19,"substance":256,"depth":19,"authority":257,"freshness":258,"relevant":22,"comment":259},20,14,8,"核心期刊综述，系统梳理环境缓解与管理实践进展与缺口，对农业面源污染与水质管理有参考价值，但非农业信息化直接落地成果。",[261],{"name":252,"url":249},[130,27,28,263,264],"农业可持续发展","水质管理",{"code":106,"slug":266,"name":267,"path":268,"parent_code":9},"digital-agriculture","数字农业与前沿技术","\u002Ftopic\u002Fdigital-agriculture",[],{"status":271,"locked":14,"version":33,"method":34,"evidence":272},"partial",{"candidates":273,"agricultural_evidence":40,"reason":299},[274,278,282,289,295],{"code":126,"score":113,"supported":40,"title":275,"abstract":276,"tags":277},[],[130,192],[130],{"code":38,"score":113,"supported":40,"title":279,"abstract":280,"tags":281},[],[116,42],[28],{"code":283,"score":81,"supported":40,"title":284,"abstract":285,"tags":288},"H7",[],[286,287],"气候变化","climate change",[],{"code":290,"score":127,"supported":40,"title":291,"abstract":292,"tags":294},"H8",[],[293],"可持续农业",[263],{"code":46,"score":22,"supported":14,"title":296,"abstract":297,"tags":298},[],[],[27],"一级领域明确，二级方向需要细分",[301,302],"Journal of Environmental Management 缓解措施 管理实践","农业可持续发展 农业面源污染 机器学习 水质管理","JournalofEnvironmentalManagement缓解措施管理实践-3553","10.1016\u002Fj.jenvman.2026.131013",{"doi":304,"openalex_id":306,"authors":307,"venue":252,"cited_by_count":70,"oa_url":249,"card":320,"direction":76,"ingested_from":78},"W7214310594",[308,311,314,317],{"name":309,"orcid":310},"Fouad H. Jaber","https:\u002F\u002Forcid.org\u002F0000-0001-8643-8668",{"name":312,"orcid":313},"Latif Kalin","https:\u002F\u002Forcid.org\u002F0000-0001-9562-8834",{"name":315,"orcid":316},"Soni  Mulmi Pradhanang","https:\u002F\u002Forcid.org\u002F0000-0002-1142-9457",{"name":318,"orcid":319},"Aleksey Y. Sheshukov","https:\u002F\u002Forcid.org\u002F0000-0002-4842-908X",{"tldr":321,"method":322,"finding":323,"direction":242,"opportunity":324},"综述环境减缓与管理实践进展，指出成效高度依赖情境且存在实施缺口。","综合多景观尺度研究，涵盖过程模型、机器学习、遥感与MRV框架。","减缓效果受水文连通、土地利用、气候与历史管理影响，长期监测与政策转化仍不足。","可研究农业景观中管理实践的长期维持机制与极端事件下的适应性策略。","2026-09-26T23:30:29.702279Z",{"id":327,"title":328,"url":329,"summary":330,"summary_zh":331,"content":9,"source_name":332,"source_url":329,"published_at":333,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":334,"score_detail":335,"sources":337,"tags":339,"primary_topic":342,"secondary_topics":343,"classification":344,"search_phrases":366,"slug":369,"view_count":133,"doi":370,"paper":371,"created_at":405},2657,"Retrieval of Optically Active and Inactive Water Quality Parameters Using Remote Sensing and Machine Learning: Evidence from Water Hyacinth-Infested Lake Tana, Ethiopia","https:\u002F\u002Fdoi.org\u002F10.3390\u002Frs18183185","Monitoring water quality is critical for protecting freshwater ecosystems and supporting sustainable water resource management. Lake Tana, Ethiopia’s largest freshwater lake, faces increasing agricultural and urban pressures, while conventional monitoring remains costly and spatially constrained. This study developed an integrated Sentinel-2 remote sensing and machine learning framework to estimate chlorophyll-a (Chl-a), turbidity (TU), total nitrogen (TN), and total phosphorus (TP) using 858 in situ observations and Google Earth Engine. Random Forest (RF), Extreme Gradient Boosting (XGB), Artificial Neural Networks (ANN), and Support Vector Regression (SVR) were evaluated using spectral bands, band combinations, and indices. RF provided the best predictions for Chl-a (R2 = 0.94 ± 0.01; RMSE = 2.11 ± 0.18 µg L−1; MARE = 5%) and TP (R2 = 0.91 ± 0.01; RMSE = 0.26 ± 0.01 mg L−1; MARE = 8.7%), whereas XGB performed best for TU (R2 = 0.93 ± 0.01; RMSE = 5.17 ± 0.43 NTU; MARE = 7%) and TN (R2 = 0.94 ± 0.02; RMSE = 0.18 ± 0.02 mg L−1; MARE = 9.9%). The strong predictive performance of RF and XGB across both optically active and inactive parameters demonstrates the capability of the framework to capture complex spectral water quality relationships and support spatially continuous assessment. Significant seasonal differences (p \u003C 0.001) showed higher dry season Chl-a (137.1%) and higher wet season TP (21.7%), TU (7.5%), and TN (3.9%). Long-term paired observations further indicated increases in Chl-a (73.7%), TN (30%), and TP (14.3%) from December 2016 to December 2025 (p \u003C 0.001). Spatial hotspot analysis revealed strong clustering of TU, TN, and TP, particularly around tributary mouths and nearshore areas, highlighting priority zones for monitoring and intervention. Overall, integrating field observations, Sentinel-2 imagery, and machine learning provides an accurate, scalable, and cost-effective approach for monitoring diverse water quality parameters. The framework offers a transferable solution for strengthening freshwater monitoring in data-scarce regions and supporting sustainable management of lakes under increasing water quality pressures.","监测水质对于保护淡水生态系统和支撑可持续水资源管理至关重要。埃塞俄比亚最大的淡水湖——塔纳湖（Lake Tana）面临着日益加剧的农业和城市压力，而传统监测手段仍然成本高昂且受空间限制。本研究开发了一套集成Sentinel-2遥感与机器学习的框架，利用858个原位观测数据和Google Earth Engine估算叶绿素a（Chl-a）、浊度（TU）、总氮（TN）和总磷（TP）。采用光谱波段、波段组合和指数，评估了随机森林（RF）、极端梯度提升（XGB）、人工神经网络（ANN）和支持向量回归（SVR）的性能。RF对Chl-a（R2 = 0.94 ± 0.01；RMSE = 2.11 ± 0.18 µg L−1；MARE = 5%）和TP（R2 = 0.91 ± 0.01；RMSE = 0.26 ± 0.01 mg L−1；MARE = 8.7%）的预测效果最佳，而XGB对TU（R2 = 0.93 ± 0.01；RMSE = 5.17 ± 0.43 NTU；MARE = 7%）和TN（R2 = 0.94 ± 0.02；RMSE = 0.18 ± 0.02 mg L−1；MARE = 9.9%）的预测效果最佳。RF和XGB在光学活性和非光学活性参数上均表现出强大的预测性能，表明该框架能够捕捉复杂的光谱水质关系并支持空间连续评估。显著的季节性差异（p \u003C 0.001）显示旱季Chl-a较高（137.1%），雨季TP（21.7%）、TU（7.5%）和TN（3.9%）较高。长期配对观测进一步表明，从2016年12月至2025年12月，Chl-a（73.7%）、TN（30%）和TP（14.3%）均有所增加（p \u003C 0.001）。空间热点分析揭示了TU、TN和TP的强烈聚集性，尤其是在支流河口和近岸区域，凸显了优先监测和干预区域。总体而言，整合实地观测、Sentinel-2影像和机器学习为监测多种水质参数提供了一种准确、可扩展且具有成本效益的方法。该框架为加强数据稀缺地区的淡水监测以及支持在水质压力日益增大背景下湖泊的可持续管理提供了一种可迁移的解决方案。","Remote Sensing","2026-09-16T00:00:00Z",82,{"impact":19,"substance":18,"depth":19,"authority":257,"freshness":13,"relevant":22,"comment":336},"基于Sentinel-2与机器学习实现湖泊多参数水质反演，方法可迁移至国内农业面源污染与渔业水域监测，数据规模与精度均具参考价值。",[338],{"name":332,"url":329},[130,27,340,28,341],"智慧渔业","水质监测",{"code":106,"slug":266,"name":267,"path":268,"parent_code":9},[],{"status":271,"locked":14,"version":33,"method":34,"evidence":345},{"candidates":346,"agricultural_evidence":40,"reason":299},[347,351,355,362],{"code":126,"score":17,"supported":40,"title":348,"abstract":349,"tags":350},[192],[130,192],[130],{"code":38,"score":17,"supported":40,"title":352,"abstract":353,"tags":354},[42],[116,42],[28],{"code":356,"score":81,"supported":40,"title":357,"abstract":358,"tags":361},"H3",[],[359,360],"水资源","water resource",[],{"code":46,"score":22,"supported":14,"title":363,"abstract":364,"tags":365},[],[],[27],[367,368],"农业面源污染 智慧渔业 机器学习 水质监测","农业面源污染 智慧渔业","农业面源污染智慧渔业机器学习水质监测-2657","10.3390\u002Frs18183185",{"doi":370,"openalex_id":372,"authors":373,"venue":332,"cited_by_count":70,"oa_url":329,"card":400,"direction":76,"ingested_from":78},"W7213230686",[374,377,379,382,384,387,389,391,393,395,397],{"name":375,"orcid":376},"Lakachew Y. Alemneh","https:\u002F\u002Forcid.org\u002F0009-0004-3471-3778",{"name":378,"orcid":9},"Daganchew Aklog",{"name":380,"orcid":381},"Ann van Griensven","https:\u002F\u002Forcid.org\u002F0000-0002-2105-6287",{"name":383,"orcid":9},"Minychl G. Dersseh",{"name":385,"orcid":386},"Goraw Goshu","https:\u002F\u002Forcid.org\u002F0000-0001-9629-0126",{"name":388,"orcid":9},"Seleshi Yalew",{"name":390,"orcid":9},"Demesew A. Mhiret",{"name":392,"orcid":9},"Sisay B. Asress",{"name":394,"orcid":9},"Tigistu Wassie Agegnehu",{"name":396,"orcid":9},"Shawl Abebe Desta",{"name":398,"orcid":399},"Samuel Berihun Kassa","https:\u002F\u002Forcid.org\u002F0009-0004-5618-9743",{"tldr":401,"method":402,"finding":403,"direction":76,"opportunity":404},"用Sentinel-2与机器学习反演埃塞俄比亚塔纳湖四类水质参数并分析时空变化。","Sentinel-2影像、Google Earth Engine、858个实测点","RF与XGB精度最高（R²达0.91-0.94），水质参数呈显著季节与年际上升趋势。","可迁移至其他数据稀缺湖泊，探索水葫芦覆盖下水体光谱混合与多源遥感协同反演。","2026-09-16T23:30:28.415573Z",{"id":407,"title":408,"url":409,"summary":410,"summary_zh":411,"content":9,"source_name":412,"source_url":409,"published_at":413,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":254,"score_detail":414,"sources":417,"tags":419,"primary_topic":9,"secondary_topics":424,"classification":425,"search_phrases":454,"slug":457,"view_count":70,"doi":458,"paper":459,"created_at":483},5577,"Assessing Land Use and Land Cover Change in the Jamanxim River Region (Brazilian Amazon) from 2015 to 2025 Using CBERS-4\u002FPAN Imagery","https:\u002F\u002Fdoi.org\u002F10.29150\u002Fjhrs.v16i4.269068","Land use and land cover (LULC) changes in the Amazon are among the main drivers of biodiversity loss, ecosystem degradation, and the intensification of climate change. This study aimed to analyze the multitemporal dynamics of LULC around the Jamanxim River, Pará, Brazilian Amazon, between 2015 and 2025, using high-resolution imagery from the CBERS-4\u002FPAN satellite. The study area covers 492.74 km², including part of the Jamanxim National Forest, a conservation unit under strong pressure from agricultural expansion and logging activities. The methodology included geometric correction of the images, Gram–Schmidt pansharpening, and supervised classification with the Random Forest algorithm, validated with historical imagery from Google Earth Pro. Thematic maps of land use and cover were generated, and performance metrics such as overall accuracy, omission and commission errors, and F1-scores were assessed. The results indicated a significant reduction in forest cover, from 412.28 km² in 2015 to 355.47 km² in 2025 (–13.78%). Non-vegetated areas increased by 132.47%, while agricultural areas expanded by 54.97%. The forest and water body classes showed high accuracy (F1-score > 0.95), while confusion persisted between agricultural and bare soil classes. Overall accuracy remained above 90% across all years, with the highest performance recorded in 2020 (96.31%). These results highlight the potential of CBERS-4\u002FPAN imagery for monitoring multitemporal changes in tropical forest landscapes. At the same time, they reveal the intensification of deforestation and the growing threats to conservation in the Amazon, reinforcing the importance of remote sensing for environmental management and policy support.","亚马逊地区的土地利用与土地覆盖（LULC）变化是生物多样性丧失、生态系统退化以及气候变化加剧的主要驱动因素之一。本研究旨在利用CBERS-4\u002FPAN卫星的高分辨率影像，分析2015年至2025年间巴西亚马孙州雅曼辛河（Jamanxim River）周边土地利用与土地覆盖的多时相动态。研究区面积为492.74 km²，包括雅曼辛国家森林（Jamanxim National Forest）的一部分，该保护区正面临农业扩张和采伐活动的强烈压力。研究方法包括影像几何校正、Gram–Schmidt全色锐化以及基于随机森林（Random Forest）算法的监督分类，并利用Google Earth Pro的历史影像进行验证。研究生成了土地利用与覆盖专题图，并评估了总体精度、漏分误差与错分误差以及F1分数等性能指标。结果表明，森林覆盖显著减少，从2015年的412.28 km²降至2025年的355.47 km²（–13.78%）。无植被区域增加了132.47%，农业区域扩张了54.97%。森林和水体类别表现出较高精度（F1分数 > 0.95），而农业类别与裸土类别之间仍存在混淆。各年份总体精度均保持在90%以上，其中2020年性能最高（96.31%）。这些结果凸显了CBERS-4\u002FPAN影像在监测热带森林景观多时相变化方面的潜力，同时揭示了亚马逊地区森林砍伐的加剧以及保护面临的日益增长的威胁，进一步强调了遥感在环境管理和政策支持中的重要性。","Journal of Hyperspectral Remote Sensing","2026-10-20T00:00:00Z",{"impact":19,"substance":18,"depth":415,"authority":20,"freshness":39,"relevant":22,"comment":416},17,"该研究利用CBERS-4\u002FPAN影像量化亚马逊保护区十年间森林减少13.78%，方法规范、结论可靠，对遥感监测与生态保护有参考价值，但地域性强、与国内三农直接关联有限。",[418],{"name":412,"url":409},[28,420,421,422,423],"土地利用","森林保护","亚马逊","CBERS-4",[],{"status":32,"locked":14,"version":33,"method":34,"evidence":426},{"candidates":427,"agricultural_evidence":40,"reason":453},[428,435,439,443,447],{"code":429,"score":113,"supported":40,"title":430,"abstract":431,"tags":434},"H6",[],[432,433],"生物多样性","biodiversity",[420],{"code":38,"score":113,"supported":40,"title":436,"abstract":437,"tags":438},[],[116,42],[28],{"code":283,"score":81,"supported":40,"title":440,"abstract":441,"tags":442},[],[286,287],[],{"code":203,"score":21,"supported":40,"title":444,"abstract":445,"tags":446},[],[207],[],{"code":448,"score":21,"supported":40,"title":449,"abstract":450,"tags":452},"I7",[],[451],"研究方法",[],"多个产业证据相当，需要确认主归属",[455,456],"CBERS-4 亚马逊 土地利用","Jamanxim 森林覆盖 遥感","CBERS-4亚马逊土地利用-5577","10.29150\u002Fjhrs.v16i4.269068",{"doi":458,"openalex_id":460,"authors":461,"venue":412,"cited_by_count":70,"oa_url":409,"card":478,"direction":76,"ingested_from":78},"W7223141286",[462,465,467,470,473,476],{"name":463,"orcid":464},"Ubiratan Joaquim da Silva","https:\u002F\u002Forcid.org\u002F0000-0001-7995-6416",{"name":466,"orcid":9},"Gabriel Henrique Santos Silva",{"name":468,"orcid":469},"Juarez Antonio da Silva","https:\u002F\u002Forcid.org\u002F0000-0002-2898-0309",{"name":471,"orcid":472},"Anderson Luiz Ribeiro de Paiva","https:\u002F\u002Forcid.org\u002F0000-0003-3475-1454",{"name":474,"orcid":475},"Leidjane Maria Maciel de Oliveira","https:\u002F\u002Forcid.org\u002F0000-0003-1251-6998",{"name":477,"orcid":9},"Sylvana Melo dos Santos",{"tldr":479,"method":480,"finding":481,"direction":76,"opportunity":482},"用CBERS-4\u002FPAN影像分析亚马逊Jamanxim河流域2015-2025年土地利用变化。","几何校正、Gram-Schmidt融合、随机森林监督分类，Google Eart","森林覆盖减少13.78%，农业扩张54.97%，裸地增132.47%，总体精度超90%。","可探索中巴地球资源卫星在热带森林退化监测中的业务化应用与多源数据融合。","2026-10-22T11:20:42.901761Z",{"id":485,"title":486,"url":487,"summary":488,"summary_zh":489,"content":9,"source_name":490,"source_url":487,"published_at":413,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":170,"score_detail":491,"sources":494,"tags":496,"primary_topic":501,"secondary_topics":505,"classification":506,"search_phrases":527,"slug":530,"view_count":70,"doi":531,"paper":532,"created_at":564},5576,"Land cover change and soil salinization in Mozambique: A counterfactual analysis over two decades (2001−2022)","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.catena.2026.110691","Soil salinization is a major issue that constrains the sustainable development of agriculture in arid, semi-arid, and coastal lowland areas. It is of great importance for regional land management and climate adaptation to clarify the influence of land cover change on soil salinization. This study aims to quantitatively assess the contribution of land cover change to soil salinization in Mozambique, where both rapid land cover transformation and salinization issues are evident. Firstly, we integrated soil profile electrical conductivity (EC) data, Landsat time-series remote sensing imagery, TerraClimate meteorological data, and the 30 m resolution land cover data, to construct a remote sensing-based EC inversion model for Mozambique. Secondly, we applied a spatially and environmentally constrained counterfactual matching method to quantitatively identify the contributions of different land cover changes on soil salinization trends. Our results reveal that: (1) the spatial distribution of soil salinization in Mozambique exhibits distinct a clear association with proximity to water bodies, with high EC areas primarily concentrated around Lake Malawi in the north and in the coastal regions of Greater Maputo in the south. (2) 26.98% of Mozambique's territory showed a trend of intensifying soil salinization, while 10.88% exhibited a decreasing trend. Areas with intensifying trends are primarily concentrated in the central alluvial plains, localized agricultural development zones, and coastal lowlands. (3) Urbanization was significantly associated with an increasing salinization trend after false discovery rate correction, suggesting that the expansion of impervious surfaces, changes in drainage patterns, and soil compaction may exacerbate localized salt accumulation. Agricultural expansion showed a negative trend difference, consistent with the potential influence of crop cover, tillage, and wet-season leaching, although this association was not significant after false discovery rate correction. The effects of ecological restoration and other factors were not statistically significant. In addition to elucidating the heterogeneous impacts of land cover changes in Mozambique on soil salinization trends, this study also provides methodological guidance and a scientific basis for monitoring\u002Fmanaging soil salinity risks in other coastal lowlands.","土壤盐渍化是制约干旱、半干旱及沿海低地地区农业可持续发展的主要问题。阐明土地覆盖变化对土壤盐渍化的影响，对区域土地管理和气候适应具有重要意义。本研究旨在定量评估土地覆盖变化对莫桑比克土壤盐渍化的贡献，该国土地覆盖转型迅速且盐渍化问题突出。首先，我们整合了土壤剖面电导率（EC）数据、Landsat时间序列遥感影像、TerraClimate气象数据以及30 m分辨率土地覆盖数据，构建了基于遥感的莫桑比克EC反演模型。其次，我们采用空间与环境约束的反事实匹配方法，定量识别不同土地覆盖变化对土壤盐渍化趋势的贡献。研究结果表明：（1）莫桑比克土壤盐渍化的空间分布与水体邻近性呈现明显的关联，高EC区域主要集中于北部的马拉维湖周边以及南部大马普托沿海地区。（2）莫桑比克26.98%的国土面积呈现土壤盐渍化加剧趋势，而10.88%呈现减轻趋势。加剧趋势区域主要集中于中部冲积平原、局部农业开发区及沿海低地。（3）经错误发现率校正后，城市化与盐渍化加剧趋势显著相关，表明不透水面扩张、排水格局改变及土壤压实可能加剧局部盐分累积。农业扩张呈现负向趋势差异，与作物覆盖、耕作及湿季淋洗的潜在影响一致，但该关联经错误发现率校正后不显著。生态恢复及其他因素的影响在统计上不显著。本研究不仅阐明了莫桑比克土地覆盖变化对土壤盐渍化趋势的异质性影响，还为其他沿海低地土壤盐渍化风险的监测与管理提供了方法学指导和科学依据。","CATENA",{"impact":492,"substance":18,"depth":19,"authority":257,"freshness":39,"relevant":22,"comment":493},16,"该研究基于遥感与反事实匹配方法，定量评估土地覆盖变化对盐渍化的贡献，方法新颖、结论可靠，对沿海低地盐渍化监测具有参考价值，但属境外区域研究，国内政策与产业影响有限。",[495],{"name":490,"url":487},[28,497,498,499,500],"莫桑比克","土壤盐渍化","土地覆盖变化","盐分反演",{"code":203,"slug":207,"name":502,"path":503,"parent_code":504},"土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",[],{"status":109,"locked":14,"version":33,"method":34,"evidence":507},{"candidates":508,"agricultural_evidence":40},[509,513,517,523],{"code":203,"score":257,"supported":40,"title":510,"abstract":511,"tags":512},[207],[206,207],[],{"code":38,"score":113,"supported":40,"title":514,"abstract":515,"tags":516},[],[116,42],[28],{"code":283,"score":81,"supported":40,"title":518,"abstract":519,"tags":522},[],[520,521],"气候适应","干旱",[],{"code":429,"score":22,"supported":14,"title":524,"abstract":525,"tags":526},[],[],[499],[528,529],"莫桑比克 土壤盐渍化 遥感","土地覆盖变化 盐渍化 反事实分析","莫桑比克土壤盐渍化遥感-5576","10.1016\u002Fj.catena.2026.110691",{"doi":531,"openalex_id":533,"authors":534,"venue":490,"cited_by_count":70,"oa_url":487,"card":559,"direction":76,"ingested_from":78},"W7223069171",[535,537,539,541,544,546,549,552,554,556],{"name":536,"orcid":9},"Yue Li",{"name":538,"orcid":9},"Mengfei Shi",{"name":540,"orcid":9},"Fei Zhang",{"name":542,"orcid":543},"Brian Alan Johnson","https:\u002F\u002Forcid.org\u002F0000-0003-1911-3585",{"name":545,"orcid":9},"Gowhar Meraj",{"name":547,"orcid":548},"Jaime Carlos Macuácua","https:\u002F\u002Forcid.org\u002F0000-0002-4822-6098",{"name":550,"orcid":551},"Pankaj Kumar","https:\u002F\u002Forcid.org\u002F0000-0002-5264-3951",{"name":553,"orcid":9},"Yuanfang Chai",{"name":555,"orcid":9},"Hongtao Xu",{"name":557,"orcid":558},"Xu Ma","https:\u002F\u002Forcid.org\u002F0000-0003-0644-7498",{"tldr":560,"method":561,"finding":562,"direction":76,"opportunity":563},"量化莫桑比克2001-2022年土地覆盖变化对土壤盐渍化的贡献。","融合EC剖面、Landsat时序与气候数据反演EC，并用空间环境约束的反事实匹配","26.98%区域盐渍化加剧；城市化显著关联盐渍化上升，农业扩张关联不显著。","可将反事实匹配框架迁移至其他滨海低地，并引入作物类型与灌溉制度细化农业扩张的盐渍化效应。","2026-10-22T11:20:42.713789Z"]