[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4239":3,"related-4239":93},{"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":70,"slug":73,"view_count":22,"doi":74,"paper":75,"created_at":92},4239,"Impervious Surface Classification Using Artificial Intelligence from Remote Sensing Imagery, Part I: Evaluation of Machine Learning Algorithms","https:\u002F\u002Fdoi.org\u002F10.48084\u002Fetasr.19081","Rapid urbanization has significantly expanded impervious surfaces in major cities, reducing natural infiltration and increasing urban flood risk. This study develops a fully automated Python workflow that integrates Geographic Information Systems (GIS), remote sensing, and machine learning to classify pervious and impervious surfaces and monitor urbanization dynamics in the central area of Ho Chi Minh City (about 95,100 hectares). A multi-temporal dataset was compiled from Landsat 5, Landsat 8, and Landsat 9 imagery (30 m) and Sentinel-2 imagery (10 m) for 2009, 2017, and 2024. The reference dataset comprised 1,125 survey points (549 impervious and 582 pervious) and 127 field points for independent validation. The workflow performs image preprocessing, Normalized Difference Built-up Index (NDBI) computation, a 70\u002F30 train-test split, and supervised classification using Random Forest (RF), Support Vector Machine (SVM), and K-Nearest Neighbors (KNN). The main novelty lies in (i) an end-to-end, reproducible Python pipeline that requires no manual GIS post-processing, (ii) the joint use of Landsat and Sentinel-2 data over 15 years for a rapidly urbanizing Southeast Asian city, and (iii) a controlled benchmark of three algorithm families using identical inputs. RF achieved the highest performance (overall accuracy 96.97%, Kappa 0.94), closely followed by SVM (96.77%, 0.94); KNN performed lower (90.91%, 0.82). The temporal accuracies were 92.39%, 93.64%, and 93.98% in 2009, 2017, and 2024. Change analysis revealed a 9.15% increase in impervious surfaces from 2009 to 2024, providing a quantitative basis for urban planning, flood-risk management, and sustainable development. The proposed workflow is applicable to other urbanizing regions to support evidence-based urban management.","快速城市化显著扩大了主要城市的不透水面，减少了自然下渗并增加了城市洪水风险。本研究开发了一套全自动Python工作流，集成地理信息系统（GIS）、遥感和机器学习，对胡志明市中心区域（约95,100公顷）的透水面与不透水面进行分类并监测城市化动态。研究构建了多时相数据集，来源于2009年、2017年和2024年的Landsat 5、Landsat 8和Landsat 9影像（30 m）以及Sentinel-2影像（10 m）。参考数据集包括1,125个调查点（549个不透水面点和582个透水面点）以及127个野外点用于独立验证。该工作流执行影像预处理、归一化建筑指数（NDBI）计算、70\u002F30训练-测试集划分，并采用随机森林（RF）、支持向量机（SVM）和K近邻（KNN）进行监督分类。主要创新点在于：（i）一套端到端、可复现的Python流程，无需人工GIS后处理；（ii）联合使用Landsat和Sentinel-2数据，对一座快速城市化的东南亚城市开展15年监测；（iii）在相同输入条件下对三类算法进行受控基准测试。RF表现最佳（总体精度96.97%，Kappa系数0.94），SVM紧随其后（96.77%，0.94）；KNN表现较低（90.91%，0.82）。2009年、2017年和2024年的时间精度分别为92.39%、93.64%和93.98%。变化分析显示，2009年至2024年不透水面增加了9.15%，为城市规划、洪水风险管理和可持续发展提供了定量依据。所提出的工作流可应用于其他城市化地区，以支持基于证据的城市管理。",null,"Engineering Technology & Applied Science Research","2026-10-02T00:00:00Z","论文",10,false,71,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},12,22,18,13,6,1,"方法新颖、数据扎实的遥感AI分类论文，但研究对象为越南城市不透水面，与国内三农信息化关联偏间接，可作技术参考而非重点精选。",[25],{"name":10,"url":6},[27,28,29,30,31],"农业人工智能","机器学习","遥感","城市扩张","洪水风险",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":37},"needs_review","2026-10-22.2","rules",{"candidates":38,"agricultural_evidence":14,"reason":69},[39,48,55,64],{"code":40,"score":41,"supported":42,"title":43,"abstract":46,"tags":47},"I2",24,true,[44,45],"machine learning","artificial intelligence",[28,44],[27,28],{"code":49,"score":50,"supported":42,"title":51,"abstract":53,"tags":54},"I3",15,[52],"remote sensing",[29,52],[29],{"code":56,"score":57,"supported":42,"title":58,"abstract":59,"tags":63},"I4",9,[],[60,61,62],"地理信息","GIS","geographic information",[],{"code":65,"score":22,"supported":14,"title":66,"abstract":67,"tags":68},"H7",[],[],[31],"农业相关性需要复核",[71,72],"胡志明市 不透水面 遥感","Landsat Sentinel-2 机器学习 分类","胡志明市不透水面遥感-4239","10.48084\u002Fetasr.19081",{"doi":74,"openalex_id":76,"authors":77,"venue":10,"cited_by_count":83,"oa_url":84,"card":85,"direction":89,"ingested_from":91},"W7219615601",[78,80],{"name":79,"orcid":9},"Huy Gia Giang Nguyen",{"name":81,"orcid":82},"Nhat Thong Tran","https:\u002F\u002Forcid.org\u002F0000-0002-5548-8272",0,"https:\u002F\u002Fwww.etasr.com\u002Findex.php\u002FETASR\u002Farticle\u002Fdownload\u002F19081\u002F7071",{"tldr":86,"method":87,"finding":88,"direction":89,"opportunity":90},"用Landsat与Sentinel-2影像和三种机器学习算法自动分类胡志明市不透水面并监测15年变化","Landsat 5\u002F8\u002F9与Sentinel-2多时相影像，NDBI指数，RF\u002F","随机森林精度最高（总体精度96.97%，Kappa 0.94），2009-2024年不透水面增加9.","农业遥感与作物表型","可将该端到端Python流程迁移至农业区，结合多源时序影像监测耕地非农化与设施农业扩张。","openalex","2026-10-05T23:30:28.045244Z",{"total":21,"page":22,"page_size":21,"items":94},[95,157,224,290,351,442],{"id":96,"title":97,"url":98,"summary":99,"summary_zh":100,"content":9,"source_name":101,"source_url":98,"published_at":102,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":103,"score_detail":104,"sources":108,"tags":110,"primary_topic":9,"secondary_topics":113,"classification":114,"search_phrases":133,"slug":136,"view_count":83,"doi":137,"paper":138,"created_at":156},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":17,"substance":105,"depth":19,"authority":17,"freshness":106,"relevant":22,"comment":107},20,7,"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。",[109],{"name":101,"url":98},[27,28,29,111,112],"水资源管理","地下水潜力",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":115},{"candidates":116,"agricultural_evidence":14,"reason":69},[117,122,126],{"code":40,"score":118,"supported":42,"title":119,"abstract":120,"tags":121},8,[],[28,44],[27,28],{"code":49,"score":106,"supported":42,"title":123,"abstract":124,"tags":125},[],[29,52],[29],{"code":127,"score":128,"supported":42,"title":129,"abstract":130,"tags":132},"H3",5,[],[131],"水资源",[112,111],[134,135],"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":137,"openalex_id":139,"authors":140,"venue":9,"cited_by_count":83,"oa_url":150,"card":151,"direction":89,"ingested_from":91},"W7221088011",[141,143,145,147],{"name":142,"orcid":9},"Joseph Osumeje",{"name":144,"orcid":9},"Sachet Utekar",{"name":146,"orcid":9},"Morli Li",{"name":148,"orcid":149},"Daniel C. Jones","https:\u002F\u002Forcid.org\u002F0000-0002-8701-4506","https:\u002F\u002Feartharxiv.org\u002Frepository\u002Fobject\u002F15434\u002Fdownload\u002F26756\u002F",{"tldr":152,"method":153,"finding":154,"direction":89,"opportunity":155},"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":158,"title":159,"url":160,"summary":161,"summary_zh":9,"content":9,"source_name":162,"source_url":9,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":163,"score_detail":164,"sources":167,"tags":169,"primary_topic":172,"secondary_topics":177,"classification":184,"search_phrases":210,"slug":213,"view_count":201,"doi":9,"paper":214,"created_at":223},4286,"Applications of Artificial Intelligence in Soil Characterization and Agriculture: A Systematic Review","https:\u002F\u002Fm2.mtmt.hu\u002Fapi\u002Fpublication\u002F37386408","Navarro Rubio等系统综述2018-2026年196项AI土壤特性与农业应用研究，遵循PRISMA 2020框架。综述发现研究明显向数据驱动方法转变，机器学习和深度学习模型主导近期研究；随机森林、支持向量机、梯度提升方法、人工神经网络、卷积神经网络、长短期记忆架构最常被报告；主要数据源包括原位传感、实验室测量、遥感影像和环境协变量，常通过多源数据融合框架集成；树集成模型在不同土壤特性上提供稳健性能。","Agronomy 2026 16(13):1241 DOI:10.3390\u002Fagronomy16131241",78,{"impact":19,"substance":18,"depth":19,"authority":165,"freshness":21,"relevant":22,"comment":166},14,"PRISMA框架下196项研究的系统综述，方法学扎实、结论可靠，对农业AI土壤应用具较高参考价值。",[168],{"name":162,"url":160},[170,27,28,29,171],"智慧农业","土壤监测",{"code":40,"slug":173,"name":174,"path":175,"parent_code":176},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[178],{"code":179,"slug":180,"name":181,"path":182,"parent_code":183},"H2","soil","土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",{"status":185,"locked":14,"version":35,"method":36,"evidence":186},"classified",{"candidates":187,"agricultural_evidence":42},[188,194,200,205],{"code":40,"score":189,"supported":42,"title":190,"abstract":191,"tags":193},16,[45],[192,28],"深度学习",[27,28],{"code":179,"score":195,"supported":42,"title":196,"abstract":197,"tags":199},11,[180],[198],"土壤",[],{"code":49,"score":201,"supported":42,"title":202,"abstract":203,"tags":204},4,[],[29],[29],{"code":206,"score":22,"supported":14,"title":207,"abstract":208,"tags":209},"I1",[],[],[170],[211,212],"AI 土壤特性 系统综述","机器学习 土壤 遥感","AI土壤特性系统综述-4286",{"doi":9,"openalex_id":9,"authors":215,"venue":9,"cited_by_count":83,"oa_url":9,"card":216,"direction":220,"ingested_from":222},[],{"tldr":217,"method":218,"finding":219,"direction":220,"opportunity":221},"系统综述2018-2026年196项AI用于土壤特性与农业的研究。","PRISMA 2020框架，分析机器学习与深度学习模型及多源数据融合。","研究转向数据驱动，树集成模型在不同土壤特性上表现稳健。","农业人工智能与决策模型","可探索可解释AI与多源数据融合在土壤特性预测中的泛化能力。","agent","2026-10-06T00:05:04.976398Z",{"id":225,"title":226,"url":227,"summary":228,"summary_zh":229,"content":9,"source_name":230,"source_url":227,"published_at":11,"category":12,"cover_url":9,"hotness":231,"is_selected":14,"score":232,"score_detail":233,"sources":235,"tags":239,"primary_topic":241,"secondary_topics":242,"classification":243,"search_phrases":273,"slug":276,"view_count":277,"doi":278,"paper":279,"created_at":289},4238,"Comparative Performance of Machine Learning and Deep Learning Algorithms for Agricultural Land Mapping in Anambra State, Nigeria","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23106955","Abstract - Accurate delineation of agricultural land is fundamental to agricultural planning, food-security assessment, land-resource management, and monitoring of land-use transformation. However, the heterogeneous and fragmented character of agricultural landscapes in southeastern Nigeria presents substantial challenges for satellite-image classification. This study comparatively evaluated Random Forest (RF), Support Vector Machine (SVM), Artificial Neural Network (ANN), and Convolutional Neural Network (CNN) for agricultural land mapping in Anambra State, Nigeria. Remotely sensed imagery was classified into waterbody, dense forest, agricultural land, built-up area, and bare ground using the four algorithms. Model performance was evaluated using 210 validation samples and multiple confusion-matrix metrics, including sensitivity, precision, specificity, negative predictive value, overall accuracy, balanced accuracy, and Matthew’s correlation coefficient. Agricultural land estimates varied from 1,000.26 km² (21.78%) for SVM to 1,099.12 km² (23.93%) for ANN. SVM achieved the strongest overall performance, recording 88.5% sensitivity, 85.2% precision, 75.0% specificity, 83.3% overall accuracy, 81.7% balanced accuracy, and a Matthews correlation coefficient of 0.643. CNN produced the lowest overall accuracy of 74.3%. The findings demonstrate that increased model complexity does not necessarily translate into superior classification performance and establish SVM as an effective approach for regional agricultural land delineation under heterogeneous tropical landscape conditions. Keywords: agricultural land mapping; machine learning; deep learning; Support Vector Machine; Random Forest; artificial neural network; convolutional neural network; remote sensing","摘要——准确划定农业用地是农业规划、粮食安全评估、土地资源管理和土地利用变化监测的基础。然而，尼日利亚东南部农业景观的异质性和破碎化特征给卫星图像分类带来了巨大挑战。本研究比较评估了随机森林（RF）、支持向量机（SVM）、人工神经网络（ANN）和卷积神经网络（CNN）在尼日利亚阿南布拉州农业用地制图中的表现。利用这四种算法将遥感影像分类为水体、密林、农业用地、建成区和裸地。使用210个验证样本和多种混淆矩阵指标评估模型性能，包括灵敏度、精确率、特异度、阴性预测值、总体精度、平衡精度和马修斯相关系数。农业用地估计值从SVM的1,000.26 km²（21.78%）到ANN的1,099.12 km²（23.93%）不等。SVM取得了最强的总体表现，灵敏度为88.5%，精确率为85.2%，特异度为75.0%，总体精度为83.3%，平衡精度为81.7%，马修斯相关系数为0.643。CNN的总体精度最低，为74.3%。研究结果表明，模型复杂度的增加并不必然带来更优的分类性能，并确立了SVM作为异质性热带景观条件下区域农业用地划定的有效方法。关键词：农业用地制图；机器学习；深度学习；支持向量机；随机森林；人工神经网络；卷积神经网络；遥感","International Journal of Emerging Trends in Engineering and Development",25,61,{"impact":118,"substance":105,"depth":189,"authority":118,"freshness":57,"relevant":22,"comment":234},"尼日利亚区域案例研究，方法对比扎实但影响范围限于学术圈，可作为遥感与农业AI主题的参考素材。",[236,237],{"name":230,"url":227},{"name":230,"url":238},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23106954",[170,27,28,29,240],"农地制图",{"code":40,"slug":173,"name":174,"path":175,"parent_code":176},[],{"status":185,"locked":14,"version":35,"method":36,"evidence":244},{"candidates":245,"agricultural_evidence":42},[246,252,256,263,269],{"code":40,"score":247,"supported":42,"title":248,"abstract":250,"tags":251},27,[44,249],"deep learning",[192,28,44,249],[27,28],{"code":49,"score":106,"supported":42,"title":253,"abstract":254,"tags":255},[],[29,52],[29],{"code":257,"score":258,"supported":42,"title":259,"abstract":260,"tags":262},"A8",3,[],[261],"粮食安全",[],{"code":264,"score":258,"supported":42,"title":265,"abstract":266,"tags":268},"J1",[],[267],"农业规划",[],{"code":206,"score":22,"supported":14,"title":270,"abstract":271,"tags":272},[],[],[170],[274,275],"农业人工智能 农地制图 智慧农业 机器学习","农业人工智能 农地制图","农业人工智能农地制图智慧农业机器学习-4238",2,"10.5281\u002Fzenodo.23106955",{"doi":278,"openalex_id":280,"authors":281,"venue":230,"cited_by_count":83,"oa_url":227,"card":284,"direction":89,"ingested_from":91},"W7219591984",[282],{"name":283,"orcid":9},"J.I. Igbokwe, C.E Ejikeme, J.O and Obi",{"tldr":285,"method":286,"finding":287,"direction":89,"opportunity":288},"比较RF、SVM、ANN、CNN在尼日利亚农业用地制图中的表现","遥感影像分类，210个验证样本，多种混淆矩阵指标评估","SVM总体精度最高（83.3%），CNN最低（74.3%），模型复杂度不保证性能","在碎片化热带景观中，可探索轻量级集成学习或迁移学习以平衡精度与效率","2026-10-05T23:30:27.987196Z",{"id":291,"title":292,"url":293,"summary":294,"summary_zh":295,"content":9,"source_name":296,"source_url":293,"published_at":297,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":298,"score_detail":299,"sources":303,"tags":305,"primary_topic":9,"secondary_topics":308,"classification":309,"search_phrases":321,"slug":324,"view_count":277,"doi":325,"paper":326,"created_at":350},3076,"Research on the Inversion Method of Total Phosphorus Concentration in Water Bodies Based on PSO-Adam-BP Neural Network Model","https:\u002F\u002Fdoi.org\u002F10.15244\u002Fpjoes\u002F220960","This study investigated Baiyangdian Lake in the Xiong’an New Area to invert total phosphorus (TP) concentrations using Sentinel-2 multispectral imagery and in situ measurements, aiming to support water-quality assessment and eutrophication management. Based on the multispectral remote sensing data of Sentinel-2 and measured total phosphorus data of water bodies, the study used specific feature combinations such as NDTI, B5, B11-B12 difference, and sensitive combination bands of measured data as model inputs to construct a PSO-Adam-BP neural network machine learning model for total phosphorus concentration inversion. Compared with the traditional BP and PSO-BP baseline models, the proposed framework significantly improved the accuracy of the model, with an R2 value reaching 0.9351. Moreover, it successfully reduced the average relative error by up to 53.5%, from 4.80% to 2.24%, and decreased the maximum relative error by up to 31.7%, from 11.21% to 7.66%, demonstrating the model’s highly robust and precise inversion performance. This study provides a new method for water quality detection in Baiyangdian Lake and is of great significance to the protection and development of the water environment in Xiong’an New Area.","本研究以雄安新区白洋淀为研究对象，利用Sentinel-2多光谱影像和实地测量数据反演总磷（TP）浓度，旨在为水质评价和富营养化管理提供支持。基于Sentinel-2多光谱遥感数据和白洋淀水体总磷实测数据，研究采用NDTI、B5、B11-B12差值等特征组合及实测数据的敏感组合波段作为模型输入，构建了PSO-Adam-BP神经网络机器学习模型用于总磷浓度反演。与传统BP和PSO-BP基准模型相比，所提出的框架显著提高了模型精度，R²值达到0.9351。此外，该模型成功将平均相对误差最多降低53.5%，从4.80%降至2.24%，并将最大相对误差最多降低31.7%，从11.21%降至7.66%，展现出高度稳健且精确的反演性能。本研究为白洋淀水质检测提供了新方法，对雄安新区水环境保护与开发具有重要意义。","Polish Journal of Environmental Studies","2026-09-18T00:00:00Z",72,{"impact":50,"substance":300,"depth":301,"authority":20,"freshness":21,"relevant":22,"comment":302},21,17,"基于Sentinel-2与PSO-Adam-BP模型实现白洋淀总磷浓度高精度反演，方法新颖、数据可靠，对雄安水环境智慧监测有实用价值。",[304],{"name":296,"url":293},[27,28,29,306,307],"水质监测","白洋淀",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":310},{"candidates":311,"agricultural_evidence":14,"reason":69},[312,317],{"code":49,"score":13,"supported":42,"title":313,"abstract":314,"tags":316},[],[29,52,315],"multispectral",[29],{"code":40,"score":118,"supported":42,"title":318,"abstract":319,"tags":320},[],[28,44],[27,28],[322,323],"白洋淀 总磷 遥感反演","Sentinel-2 水质 反演","白洋淀总磷遥感反演-3076","10.15244\u002Fpjoes\u002F220960",{"doi":325,"openalex_id":327,"authors":328,"venue":296,"cited_by_count":83,"oa_url":344,"card":345,"direction":89,"ingested_from":91},"W7213537374",[329,331,333,336,339,341],{"name":330,"orcid":9},"Guanxing Wang",{"name":332,"orcid":9},"Cui Jia",{"name":334,"orcid":335},"Linghan Gao","https:\u002F\u002Forcid.org\u002F0000-0002-8537-8787",{"name":337,"orcid":338},"Shan An","https:\u002F\u002Forcid.org\u002F0000-0001-7796-6952",{"name":340,"orcid":9},"Jia Xi",{"name":342,"orcid":343},"Yaxue Liu","https:\u002F\u002Forcid.org\u002F0009-0006-9025-8030","https:\u002F\u002Fwww.pjoes.com\u002Fpdf-220960-145347?filename=Research-on-the-Inversion.pdf",{"tldr":346,"method":347,"finding":348,"direction":89,"opportunity":349},"用PSO-Adam-BP神经网络结合Sentinel-2影像反演白洋淀总磷浓度。","Sentinel-2多光谱与实测数据，NDTI等特征组合，PSO-Adam-BP","R²达0.9351，平均相对误差由4.80%降至2.24%，精度显著优于BP与PSO-BP。","可迁移至其他内陆水体与多参数水质反演，探索时序泛化与跨区域迁移能力。","2026-09-21T23:30:25.856035Z",{"id":352,"title":353,"url":354,"summary":355,"summary_zh":356,"content":9,"source_name":357,"source_url":354,"published_at":358,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":359,"score_detail":360,"sources":362,"tags":364,"primary_topic":366,"secondary_topics":367,"classification":377,"search_phrases":416,"slug":419,"view_count":201,"doi":420,"paper":421,"created_at":441},2659,"Application of Remote Sensing and Machine Learning in Sustainable Agriculture","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fsu18189472","Global agriculture is undergoing a period of profound transformation, driven by the need to increase food production in a context characterized by climate change, the degradation of natural resources and increasing pressure on agricultural ecosystems [...]","全球农业正经历一场深刻变革，其驱动力是在气候变化、自然资源退化以及农业生态系统压力日益增大的背景下提高粮食产量的需求。[...]","Sustainability","2026-09-16T00:00:00Z",77,{"impact":19,"substance":105,"depth":301,"authority":20,"freshness":57,"relevant":22,"comment":361},"发表于核心期刊的遥感与机器学习综述，方法视角新颖、时效性强，对智慧农业技术路线有参考价值，值得进入每日精选。",[363],{"name":357,"url":354},[170,27,28,365,29],"可持续农业",{"code":40,"slug":173,"name":174,"path":175,"parent_code":176},[368,373],{"code":369,"slug":370,"name":371,"path":372,"parent_code":183},"H8","sustainable-agriculture","可持续与保护性农业","\u002Ftopic\u002Fenvironment\u002Fsustainable-agriculture",{"code":49,"slug":374,"name":375,"path":376,"parent_code":176},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":185,"locked":14,"version":35,"method":36,"evidence":378},{"candidates":379,"agricultural_evidence":42},[380,384,389,393,399,406,412],{"code":40,"score":13,"supported":42,"title":381,"abstract":382,"tags":383},[44],[],[27,28],{"code":369,"score":57,"supported":42,"title":385,"abstract":387,"tags":388},[386],"sustainable agriculture",[],[365],{"code":49,"score":57,"supported":42,"title":390,"abstract":391,"tags":392},[52],[],[29],{"code":65,"score":21,"supported":42,"title":394,"abstract":395,"tags":398},[],[396,397],"气候变化","climate change",[],{"code":400,"score":21,"supported":42,"title":401,"abstract":402,"tags":405},"J3",[],[403,404],"全球农业","global agriculture",[],{"code":407,"score":258,"supported":42,"title":408,"abstract":409,"tags":411},"H6",[],[410],"农业生态",[],{"code":206,"score":22,"supported":14,"title":413,"abstract":414,"tags":415},[],[],[170],[417,418],"农业人工智能 可持续农业 智慧农业 机器学习","农业人工智能 可持续农业","农业人工智能可持续农业智慧农业机器学习-2659","10.3390\u002Fsu18189472",{"doi":420,"openalex_id":422,"authors":423,"venue":357,"cited_by_count":83,"oa_url":354,"card":436,"direction":89,"ingested_from":91},"W7213301703",[424,427,430,433],{"name":425,"orcid":426},"Mihai Valentin Herbei","https:\u002F\u002Forcid.org\u002F0000-0002-3884-3658",{"name":428,"orcid":429},"Ana-Cornelia Badea","https:\u002F\u002Forcid.org\u002F0000-0003-4521-5403",{"name":431,"orcid":432},"Aleksandar Ristić","https:\u002F\u002Forcid.org\u002F0000-0003-0979-3345",{"name":434,"orcid":435},"Paul Sestraș","https:\u002F\u002Forcid.org\u002F0000-0002-8554-0924",{"tldr":437,"method":438,"finding":439,"direction":89,"opportunity":440},"综述遥感与机器学习在可持续农业中的应用现状与前景。","综述遥感数据与机器学习方法在农业中的应用。","遥感结合机器学习可提升农业监测与可持续管理能力。","可探索多源遥感与可解释机器学习融合，用于小农户精准决策与碳核算。","2026-09-16T23:30:28.640661Z",{"id":443,"title":444,"url":445,"summary":446,"summary_zh":447,"content":9,"source_name":448,"source_url":445,"published_at":449,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":450,"score_detail":451,"sources":453,"tags":455,"primary_topic":9,"secondary_topics":457,"classification":458,"search_phrases":471,"slug":474,"view_count":258,"doi":475,"paper":476,"created_at":495},2433,"Hierarchical spectral ensemble with physics-informed augmentation for global water quality retrieval from hyperspectral remote sensing","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffrsen.2026.1860176","Retrieving water quality variables from remotely sensed reflectance spectra (Rrs) with global-scale, cross-waterbody applicability remains a grand challenge in environmental remote sensing. Here we introduce Hierarchical Spectral Ensemble (HSE), a machine learning pipeline for concurrent retrieval of four ecologically relevant water quality parameters (chlorophyll-a (Chl-a), total suspended solids (TSS), coloured dissolved organic matter absorption coefficient at 440 nm (aCDOM(440)), and Secchi depth (Zsd)), applied to the GLORIA 2022 global dataset of 7,572 co-located hyperspectral in situ ground truth measurements spanning six continents. HSE leverages a combination of five diverse base learners trained with 10-fold out-of-fold stacking, and integrated with a diversity-constrained non-negative least squares (NNLS) meta-learner, supported by a 291-dimensional feature suite spanning spectral, spatial, and temporal representations. We propose Interpolation-based Spectral Data Augmentation (ISDA), an ecologically inspired, class-balance oversampling methodology applied to the training set after the initial stratified split to prevent information leakage. Evaluated on the held-out global test set, HSE attains R2 = 0.822, 0.704, 0.841, and 0.962 for Chl-a, TSS, aCDOM(440), and Zsd respectively (mean R2 = 0.832; all in original physical units following back-transformation). Stratified analysis on a per-quartile basis reveals negative values of R2 in low-concentration regimes for Chl-a, TSS, and aCDOM(440), illustrating how global metrics can mask failures in retrieval across a majority of the distribution, specifically in the oligotrophic regime. This constitutes the primary known limitation of the method: reliable prediction in low-concentration, low-optical-signal regimes remains elusive and is demonstrated only in high-concentration, eutrophic samples where a measurable optical signal exists.","从遥感反射光谱（Rrs）中反演水质变量并实现全球尺度、跨水体的适用性，仍是环境遥感领域的一项重大挑战。本文提出分层光谱集成（Hierarchical Spectral Ensemble, HSE），一种机器学习流程，用于同时反演四个与生态相关的水质参数（叶绿素a（Chl-a）、总悬浮固体（TSS）、440 nm处有色溶解有机物吸收系数（aCDOM(440)）和透明度（Zsd）），并应用于GLORIA 2022全球数据集，该数据集包含横跨六大洲的7,572组同步高光谱原位地面实测数据。HSE结合了五种不同的基学习器，采用10折折外堆叠进行训练，并与多样性约束的非负最小二乘（NNLS）元学习器集成，辅以涵盖光谱、空间和时间表示的291维特征集。我们提出基于插值的光谱数据增强（Interpolation-based Spectral Data Augmentation, ISDA），这是一种受生态学启发的类平衡过采样方法，在初始分层划分后应用于训练集以防止信息泄漏。在留出的全球测试集上评估，HSE在Chl-a、TSS、aCDOM(440)和Zsd上分别达到R2 = 0.822、0.704、0.841和0.962（平均R2 = 0.832；均在反变换后以原始物理单位表示）。基于四分位数的分层分析揭示了Chl-a、TSS和aCDOM(440)在低浓度条件下R2为负值，说明全球指标可能掩盖分布中大多数区域的检索失败，特别是在贫营养条件下。这构成了该方法已知的主要局限性：在低浓度、低光学信号条件下实现可靠预测仍然难以实现，仅在存在可测量光学信号的高浓度、富营养化样本中得到验证。","Frontiers in Remote Sensing","2026-09-11T00:00:00Z",79,{"impact":19,"substance":18,"depth":19,"authority":20,"freshness":118,"relevant":22,"comment":452},"基于GLORIA全球高光谱数据集提出分层光谱集成方法，可同步反演叶绿素a、悬浮物等四项水质参数，方法新颖、数据规模大，但低浓度水体反演失效的局限也交代清楚，对农业水环境遥感监测有参考价值。",[454],{"name":448,"url":445},[27,28,29,306,456],"水环境",[],{"status":34,"locked":14,"version":35,"method":36,"evidence":459},{"candidates":460,"agricultural_evidence":14,"reason":69},[461,467],{"code":49,"score":462,"supported":42,"title":463,"abstract":465,"tags":466},26,[52,464],"hyperspectral",[29,52,464],[29],{"code":40,"score":118,"supported":42,"title":468,"abstract":469,"tags":470},[],[28,44],[27,28],[472,473],"农业人工智能 机器学习 水质监测 水环境","农业人工智能 机器学习","农业人工智能机器学习水质监测水环境-2433","10.3389\u002Ffrsen.2026.1860176",{"doi":475,"openalex_id":477,"authors":478,"venue":448,"cited_by_count":83,"oa_url":489,"card":490,"direction":89,"ingested_from":91},"W7212323204",[479,481,483,485,487],{"name":480,"orcid":9},"Amirthalakshmi TM",{"name":482,"orcid":9},"Hemanth S",{"name":484,"orcid":9},"Ganesan PV",{"name":486,"orcid":9},"Rahul SG",{"name":488,"orcid":9},"Gayathri M","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fremote-sensing\u002Farticles\u002F10.3389\u002Ffrsen.2026.1860176\u002Fpdf",{"tldr":491,"method":492,"finding":493,"direction":89,"opportunity":494},"提出分层光谱集成模型HSE，从高光谱遥感反射率中全球尺度反演四种水质参数。","用GLORIA 2022全球7572条高光谱数据，结合10折堆叠集成、NNLS元","整体R²达0.832，但低浓度贫营养水体中Chl-a、TSS、aCDOM(440)的R²为负，反演失","低浓度、弱光学信号水体的反演仍是空白，可探索物理约束与少样本学习提升贫营养水体精度。","2026-09-14T23:30:27.361699Z"]