[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4916":3,"related-4916":89},{"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":32,"classification":33,"search_phrases":67,"slug":70,"view_count":71,"doi":72,"paper":73,"created_at":88},4916,"Physiological and Biochemical Effects of Insecticides on Catla catla from Freshwater Ecosystems: A Biomarker-Based Monitoring System for Yeldari Reservoir, Maharashtra","https:\u002F\u002Fdoi.org\u002F10.22214\u002Fijraset.2026.85141","Agricultural insecticides reach freshwater reservoirs through runoff, drainage, leaching and accidental discharge, and fish are exposed continuously through gills, skin and diet. Catla catla (Hamilton), an Indian major carp of high economic and ecological value, is a suitable sentinel species for such contamination. This paper reviews the physiological, haematological, biochemical, oxidative and histopathological responses of C. catla to organophosphate, organochlorine, pyrethroid and neonicotinoid insecticides, and identifies the gaps that limit their use in field risk assessment. Building on this evidence, we present a methodology and a proposed six-module system for Yeldari Reservoir, a hydroelectric and irrigation reservoir on the Purna River, that links catchment pesticide-use surveys, seasonal field monitoring, laboratory bioassays, a multi-biomarker panel, integrated data analysis (Integrated Biomarker Response and risk quotient) and decision support. The approach is intended to show whether agricultural insecticides cause measurable physiological stress in the reservoir’s C. catla population, and to convert that evidence into management advice.","农业杀虫剂通过径流、排水、淋溶和意外排放进入淡水水库，鱼类则通过鳃、皮肤和摄食持续暴露。卡特拉鲃（Catla catla (Hamilton)）是一种具有高经济价值和生态价值的印度主要鲤科鱼类，是此类污染的合适指示物种。本文综述了卡特拉鲃对有机磷、有机氯、拟除虫菊酯和新烟碱类杀虫剂在生理、血液学、生化、氧化应激和组织病理学方面的响应，并指出了限制其用于野外风险评估的空白。在此基础上，我们提出了一套方法和一个拟议的六模块系统，应用于耶尔达里水库（Yeldari Reservoir）——位于普尔纳河（Purna River）上的一座水力发电和灌溉水库——该系统将流域农药使用调查、季节性野外监测、实验室生物测定、多生物标志物组合、集成数据分析（综合生物标志物响应和风险商）以及决策支持相衔接。该方法旨在揭示农业杀虫剂是否对水库中卡特拉鲃种群造成可测量的生理胁迫，并将相关证据转化为管理建议。",null,"International Journal for Research in Applied Science and Engineering Technology","2026-10-13T00:00:00Z","论文",10,false,56,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},8,18,15,6,9,1,"以印度鲤鱼为哨兵物种构建水库农药污染六模块监测体系，方法有参考价值但属区域性研究，公共影响有限。",[25],{"name":10,"url":6},[27,28,29,30,31],"农业面源污染","渔业水质监测","生物标志物","农药污染","水库生态",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":37},"needs_review","2026-10-22.2","rules",{"candidates":38,"agricultural_evidence":41,"reason":66},[39,47,54,61],{"code":40,"score":20,"supported":41,"title":42,"abstract":43,"tags":46},"F4",true,[],[44,45],"农药","pesticide",[],{"code":48,"score":20,"supported":41,"title":49,"abstract":50,"tags":53},"H3",[],[51,52],"灌溉","irrigation",[],{"code":55,"score":56,"supported":41,"title":57,"abstract":58,"tags":60},"I2",3,[],[59],"decision support",[],{"code":62,"score":22,"supported":14,"title":63,"abstract":64,"tags":65},"H5",[],[],[27],"多个产业证据相当，需要确认主归属",[68,69],"印度鲤 农药 生物标志物","农业面源污染 渔业水质监测 生物标志物 农药污染","印度鲤农药生物标志物-4916",0,"10.22214\u002Fijraset.2026.85141",{"doi":72,"openalex_id":74,"authors":75,"venue":10,"cited_by_count":71,"oa_url":6,"card":80,"direction":86,"ingested_from":87},"W7221622481",[76,78],{"name":77,"orcid":9},"Ms. Pooja Dinkarappa Tarte",{"name":79,"orcid":9},"Dr. Niwrati Govindrao Popatwar",{"tldr":81,"method":82,"finding":83,"direction":84,"opportunity":85},"综述杀虫剂对印度鲮鱼的生理生化影响，并提出六模块生物标志物监测系统用于水库风险评估。","文献综述结合生物标志物、IBR与风险商，设计Yeldari水库监测方案。","现有研究不足以支撑野外风险评估，需整合多生物标志物与决策支持系统。","农业绿色发展与碳","可开发基于多生物标志物与物联网的农药污染实时预警与决策支持平台。","农业人工智能与决策模型","openalex","2026-10-14T23:30:56.021794Z",{"total":20,"page":22,"page_size":20,"items":90},[91,175,256,334,407,477],{"id":92,"title":93,"url":94,"summary":95,"summary_zh":96,"content":9,"source_name":97,"source_url":94,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":98,"score_detail":99,"sources":104,"tags":106,"primary_topic":111,"secondary_topics":116,"classification":117,"search_phrases":141,"slug":144,"view_count":22,"doi":145,"paper":146,"created_at":174},4915,"Modeling runoff, sediment, and nutrient dynamics in the Ganjiang River Basin, China: A hierarchical SWAT-BiLSTM framework","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.jwpe.2026.111080","Rivers and lakes are vital to regional water security and ecosystem stability, yet the integrated simulation of hydrological, erosion and pollution processes remains constrained by the complex interplay between climate change and human activities. To address systematic biases arising from oversimplified mechanisms and strong non-linearities, this study proposes a hierarchical hybrid framework that sequentially feeds SWAT-simulated hydrological and water-quality processes into a BiLSTM network for residual correction, achieving coordinated, high-precision simulations of runoff, sediment and nutrient fluxes in the Ganjiang River Basin. Validated against multi-source data that hydrological data during 2011–2022 and water quality data during 2021–2022, the SWAT-BiLSTM outperformed standalone SWAT across all metrics, primarily driven by precision gains and residual mitigation rather than computational speedup. Specifically, the average R 2 increased by 6%–9% for runoff, 6%–19% for sediment and significantly by 9%–42% for nutrients, with a maximum P BIAS reduction of 67.4%. The hybrid model further revealed the cascade response mechanisms of the hydrological-erosion-pollution triad, highlighting concentrated rainfall and agricultural cycles as key drivers of seasonal nutrient peaks. These findings confirm the efficacy of deep learning-enhanced mechanistic modeling, offering robust decision support for basin-scale environmental management and pollution control.","河流与湖泊对区域水安全与生态系统稳定至关重要，然而水文、侵蚀与污染过程的集成模拟仍受制于气候变化与人类活动之间复杂的相互作用。为解决机制过度简化与强非线性所导致的系统性偏差，本研究提出了一种分层混合框架，将SWAT模拟的水文与水质过程依次输入BiLSTM网络进行残差校正，从而实现对赣江流域径流、泥沙与营养盐通量的协同高精度模拟。基于多源数据（2011—2022年水文数据及2021—2022年水质数据）的验证表明，SWAT-BiLSTM在所有指标上均优于单一SWAT模型，其优势主要源于精度提升与残差削减，而非计算速度的加快。具体而言，径流平均R²提高了6%—9%，泥沙提高了6%—19%，营养盐显著提高了9%—42%，PBIAS最大降低幅度达67.4%。该混合模型进一步揭示了水文—侵蚀—污染三元体系的级联响应机制，突出表明集中降雨与农业周期是季节性营养盐峰值的关键驱动因素。这些发现证实了深度学习增强机理模型的有效性，为流域尺度环境管理与污染控制提供了有力的决策支持。","Journal of Water Process Engineering",79,{"impact":100,"substance":101,"depth":18,"authority":102,"freshness":21,"relevant":22,"comment":103},16,22,14,"提出SWAT-BiLSTM分层混合框架，显著提升径流、泥沙与营养盐模拟精度，对流域农业面源污染治理有实质参考价值。",[105],{"name":97,"url":94},[107,27,108,109,110],"深度学习","智慧水利","水文模型","赣江流域",{"code":55,"slug":112,"name":113,"path":114,"parent_code":115},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":118,"locked":14,"version":35,"method":36,"evidence":119},"classified",{"candidates":120,"agricultural_evidence":41},[121,126,133,137],{"code":55,"score":13,"supported":41,"title":122,"abstract":123,"tags":125},[],[107,124,59],"deep learning",[107],{"code":127,"score":20,"supported":41,"title":128,"abstract":129,"tags":132},"H7",[],[130,131],"气候变化","climate change",[],{"code":48,"score":22,"supported":14,"title":134,"abstract":135,"tags":136},[],[],[109],{"code":62,"score":22,"supported":14,"title":138,"abstract":139,"tags":140},[],[],[27],[142,143],"赣江流域 SWAT-BiLSTM 径流模拟","赣江 泥沙 营养盐 模拟","赣江流域SWAT-BiLSTM径流模拟-4915","10.1016\u002Fj.jwpe.2026.111080",{"doi":145,"openalex_id":147,"authors":148,"venue":97,"cited_by_count":71,"oa_url":94,"card":169,"direction":86,"ingested_from":87},"W7221543472",[149,151,153,155,157,159,161,163,165,167],{"name":150,"orcid":9},"Xihua Wang",{"name":152,"orcid":9},"Xuming Ji",{"name":154,"orcid":9},"Y. Jun Xu",{"name":156,"orcid":9},"Boyang Mao",{"name":158,"orcid":9},"Shunqing Jia",{"name":160,"orcid":9},"Zejun Liu",{"name":162,"orcid":9},"Qinya Lv",{"name":164,"orcid":9},"Chengming Luo",{"name":166,"orcid":9},"Yan Dai",{"name":168,"orcid":9},"Yanxin Rong",{"tldr":170,"method":171,"finding":172,"direction":84,"opportunity":173},"提出SWAT-BiLSTM分层混合框架，高精度模拟赣江流域径流、泥沙与营养物动态。","SWAT模拟水文水质过程，BiLSTM残差校正，用2011-2022年多源数据验","混合模型精度全面优于SWAT，营养物R²提升9%-42%，PBIAS最大降67.4%。","可探索深度学习残差校正框架在农业面源污染关键源区识别与减排情景模拟中的推广。","2026-10-14T23:30:55.922882Z",{"id":176,"title":177,"url":178,"summary":179,"summary_zh":180,"content":9,"source_name":181,"source_url":178,"published_at":182,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":183,"score_detail":184,"sources":189,"tags":191,"primary_topic":196,"secondary_topics":201,"classification":202,"search_phrases":230,"slug":233,"view_count":22,"doi":234,"paper":235,"created_at":255},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":185,"substance":186,"depth":18,"authority":187,"freshness":21,"relevant":22,"comment":188},12,21,13,"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。",[190],{"name":181,"url":178},[192,27,193,194,195],"农业人工智能","作物识别","遥感监测","秸秆焚烧",{"code":197,"slug":198,"name":199,"path":200,"parent_code":115},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",[],{"status":118,"locked":14,"version":35,"method":36,"evidence":203},{"candidates":204,"agricultural_evidence":41},[205,212,219,225],{"code":197,"score":206,"supported":41,"title":207,"abstract":208,"tags":211},7,[],[209,210],"遥感","remote sensing",[194],{"code":213,"score":20,"supported":41,"title":214,"abstract":215,"tags":218},"A1",[],[216,217],"水稻","paddy",[],{"code":55,"score":220,"supported":41,"title":221,"abstract":222,"tags":224},4,[],[223],"机器学习",[192],{"code":62,"score":226,"supported":14,"title":227,"abstract":228,"tags":229},2,[],[],[27,195],[231,232],"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":234,"openalex_id":236,"authors":237,"venue":181,"cited_by_count":71,"oa_url":178,"card":249,"direction":253,"ingested_from":87},"W7221040421",[238,241,244,247],{"name":239,"orcid":240},"Anil Kumar","https:\u002F\u002Forcid.org\u002F0000-0002-7177-0817",{"name":242,"orcid":243},"Anamika Palavesam Sarathamani","https:\u002F\u002Forcid.org\u002F0009-0007-4223-7443",{"name":245,"orcid":246},"Ishwari Datt","https:\u002F\u002Forcid.org\u002F0000-0001-9936-2367",{"name":248,"orcid":9},"R.P. Singh",{"tldr":250,"method":251,"finding":252,"direction":253,"opportunity":254},"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。","农业遥感与作物表型","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":257,"title":258,"url":259,"summary":260,"summary_zh":261,"content":9,"source_name":262,"source_url":259,"published_at":182,"category":12,"cover_url":9,"hotness":263,"is_selected":14,"score":98,"score_detail":264,"sources":266,"tags":271,"primary_topic":275,"secondary_topics":276,"classification":277,"search_phrases":307,"slug":310,"view_count":22,"doi":311,"paper":312,"created_at":333},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,{"impact":18,"substance":101,"depth":18,"authority":185,"freshness":21,"relevant":22,"comment":265},"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。",[267,268],{"name":262,"url":259},{"name":269,"url":270},"International Journal of River Basin Management","https:\u002F\u002Fdoi.org\u002F10.1080\u002F15715124.2026.2742495",[272,27,194,273,274],"可解释机器学习","地下水硝酸盐","硝酸盐脆弱区",{"code":55,"slug":112,"name":113,"path":114,"parent_code":115},[],{"status":118,"locked":14,"version":35,"method":36,"evidence":278},{"candidates":279,"agricultural_evidence":41},[280,285,292,299,303],{"code":55,"score":19,"supported":41,"title":281,"abstract":283,"tags":284},[282],"machine learning",[223,282],[272],{"code":286,"score":20,"supported":41,"title":287,"abstract":288,"tags":291},"C",[],[289,290],"畜牧","livestock",[],{"code":293,"score":20,"supported":41,"title":294,"abstract":295,"tags":298},"H2",[],[296,297],"土壤","soil",[],{"code":62,"score":22,"supported":14,"title":300,"abstract":301,"tags":302},[],[],[27],{"code":197,"score":22,"supported":14,"title":304,"abstract":305,"tags":306},[],[],[194],[308,309],"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":311,"openalex_id":313,"authors":314,"venue":262,"cited_by_count":71,"oa_url":259,"card":328,"direction":86,"ingested_from":87},"W7220971680",[315,318,320,322,325],{"name":316,"orcid":317},"Manuel Rodríguez del Rosario","https:\u002F\u002Forcid.org\u002F0000-0002-4202-6722",{"name":319,"orcid":9},"Victor Gómez-Escalonilla",{"name":321,"orcid":9},"Héctor Aguilera",{"name":323,"orcid":324},"Pedro Martínez‐Santos","https:\u002F\u002Forcid.org\u002F0000-0003-2014-4063",{"name":326,"orcid":327},"África de la Hera Portillo","https:\u002F\u002Forcid.org\u002F0000-0001-7821-1834",{"tldr":329,"method":330,"finding":331,"direction":84,"opportunity":332},"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。","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。","2026-10-09T23:30:47.673746Z",{"id":335,"title":336,"url":337,"summary":338,"summary_zh":339,"content":9,"source_name":340,"source_url":337,"published_at":182,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":341,"score_detail":342,"sources":344,"tags":346,"primary_topic":349,"secondary_topics":353,"classification":354,"search_phrases":376,"slug":379,"view_count":22,"doi":380,"paper":381,"created_at":406},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)",81,{"impact":18,"substance":101,"depth":18,"authority":187,"freshness":13,"relevant":22,"comment":343},"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。",[345],{"name":340,"url":337},[107,27,209,347,348],"水资源管理","水质监测",{"code":115,"slug":350,"name":351,"path":352,"parent_code":9},"digital-agriculture","数字农业与前沿技术","\u002Ftopic\u002Fdigital-agriculture",[],{"status":355,"locked":14,"version":35,"method":36,"evidence":356},"partial",{"candidates":357,"agricultural_evidence":41,"reason":375},[358,362,366,371],{"code":55,"score":19,"supported":41,"title":359,"abstract":360,"tags":361},[124],[107,124],[107],{"code":197,"score":19,"supported":41,"title":363,"abstract":364,"tags":365},[210],[209,210],[209],{"code":48,"score":220,"supported":41,"title":367,"abstract":368,"tags":370},[],[369],"水资源",[347],{"code":62,"score":22,"supported":14,"title":372,"abstract":373,"tags":374},[],[],[27],"一级领域明确，二级方向需要细分",[377,378],"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":380,"openalex_id":382,"authors":383,"venue":340,"cited_by_count":71,"oa_url":337,"card":401,"direction":253,"ingested_from":87},"W7220943541",[384,387,390,393,395,398],{"name":385,"orcid":386},"Vasiliki Thomopoulou","https:\u002F\u002Forcid.org\u002F0009-0000-8361-6879",{"name":388,"orcid":389},"Panagiotis Kossieris","https:\u002F\u002Forcid.org\u002F0000-0002-5201-3079",{"name":391,"orcid":392},"Georgios Bariamis","https:\u002F\u002Forcid.org\u002F0000-0002-9548-3054",{"name":394,"orcid":9},"Konstantinos Peroulis",{"name":396,"orcid":397},"G. Katsouras","https:\u002F\u002Forcid.org\u002F0000-0003-3249-3113",{"name":399,"orcid":400},"Christos Makropoulos","https:\u002F\u002Forcid.org\u002F0000-0003-0308-4265",{"tldr":402,"method":403,"finding":404,"direction":253,"opportunity":405},"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":408,"title":409,"url":410,"summary":411,"summary_zh":412,"content":9,"source_name":413,"source_url":410,"published_at":414,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":415,"score_detail":416,"sources":419,"tags":421,"primary_topic":424,"secondary_topics":425,"classification":426,"search_phrases":451,"slug":454,"view_count":56,"doi":455,"paper":456,"created_at":476},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":18,"substance":417,"depth":18,"authority":102,"freshness":17,"relevant":22,"comment":418},20,"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。",[420],{"name":413,"url":410},[223,27,194,422,423],"农业可持续发展","水质管理",{"code":115,"slug":350,"name":351,"path":352,"parent_code":9},[],{"status":355,"locked":14,"version":35,"method":36,"evidence":427},{"candidates":428,"agricultural_evidence":41,"reason":375},[429,433,437,441,447],{"code":55,"score":206,"supported":41,"title":430,"abstract":431,"tags":432},[],[223,282],[223],{"code":197,"score":206,"supported":41,"title":434,"abstract":435,"tags":436},[],[209,210],[194],{"code":127,"score":20,"supported":41,"title":438,"abstract":439,"tags":440},[],[130,131],[],{"code":442,"score":220,"supported":41,"title":443,"abstract":444,"tags":446},"H8",[],[445],"可持续农业",[422],{"code":62,"score":22,"supported":14,"title":448,"abstract":449,"tags":450},[],[],[27],[452,453],"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":455,"openalex_id":457,"authors":458,"venue":413,"cited_by_count":71,"oa_url":410,"card":471,"direction":253,"ingested_from":87},"W7214310594",[459,462,465,468],{"name":460,"orcid":461},"Fouad H. Jaber","https:\u002F\u002Forcid.org\u002F0000-0001-8643-8668",{"name":463,"orcid":464},"Latif Kalin","https:\u002F\u002Forcid.org\u002F0000-0001-9562-8834",{"name":466,"orcid":467},"Soni  Mulmi Pradhanang","https:\u002F\u002Forcid.org\u002F0000-0002-1142-9457",{"name":469,"orcid":470},"Aleksey Y. Sheshukov","https:\u002F\u002Forcid.org\u002F0000-0002-4842-908X",{"tldr":472,"method":473,"finding":474,"direction":84,"opportunity":475},"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":478,"title":479,"url":480,"summary":481,"summary_zh":482,"content":9,"source_name":483,"source_url":480,"published_at":484,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":485,"score_detail":486,"sources":488,"tags":490,"primary_topic":492,"secondary_topics":493,"classification":494,"search_phrases":514,"slug":517,"view_count":226,"doi":518,"paper":519,"created_at":553},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":18,"substance":101,"depth":18,"authority":102,"freshness":13,"relevant":22,"comment":487},"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。",[489],{"name":483,"url":480},[223,27,491,194,348],"智慧渔业",{"code":115,"slug":350,"name":351,"path":352,"parent_code":9},[],{"status":355,"locked":14,"version":35,"method":36,"evidence":495},{"candidates":496,"agricultural_evidence":41,"reason":375},[497,501,505,510],{"code":55,"score":19,"supported":41,"title":498,"abstract":499,"tags":500},[282],[223,282],[223],{"code":197,"score":19,"supported":41,"title":502,"abstract":503,"tags":504},[210],[209,210],[194],{"code":48,"score":20,"supported":41,"title":506,"abstract":507,"tags":509},[],[369,508],"water resource",[],{"code":62,"score":22,"supported":14,"title":511,"abstract":512,"tags":513},[],[],[27],[515,516],"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":518,"openalex_id":520,"authors":521,"venue":483,"cited_by_count":71,"oa_url":480,"card":548,"direction":253,"ingested_from":87},"W7213230686",[522,525,527,530,532,535,537,539,541,543,545],{"name":523,"orcid":524},"Lakachew Y. Alemneh","https:\u002F\u002Forcid.org\u002F0009-0004-3471-3778",{"name":526,"orcid":9},"Daganchew Aklog",{"name":528,"orcid":529},"Ann van Griensven","https:\u002F\u002Forcid.org\u002F0000-0002-2105-6287",{"name":531,"orcid":9},"Minychl G. Dersseh",{"name":533,"orcid":534},"Goraw Goshu","https:\u002F\u002Forcid.org\u002F0000-0001-9629-0126",{"name":536,"orcid":9},"Seleshi Yalew",{"name":538,"orcid":9},"Demesew A. Mhiret",{"name":540,"orcid":9},"Sisay B. Asress",{"name":542,"orcid":9},"Tigistu Wassie Agegnehu",{"name":544,"orcid":9},"Shawl Abebe Desta",{"name":546,"orcid":547},"Samuel Berihun Kassa","https:\u002F\u002Forcid.org\u002F0009-0004-5618-9743",{"tldr":549,"method":550,"finding":551,"direction":253,"opportunity":552},"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"]