[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-1445":3,"related-1445":72},{"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":22,"tags":24,"primary_topic":9,"secondary_topics":28,"classification":29,"search_phrases":51,"slug":54,"view_count":20,"doi":55,"paper":56,"created_at":71},1445,"DETECTION OF METAL-INDUCED VEGETATION ANOMALIES IN THE MINING AREA USING REMOTE SENSING INDICES","https:\u002F\u002Fdoi.org\u002F10.36306\u002Fkonjes.1699608","A lot of information can be obtained about vegetation with remote sensing technologies and multispectral satellite data. This study used Landsat-7 ETM+ (Enhanced Thematic Mapper) satellite data and remote sensing indices to identify stress-related anomalies in the vegetation at the mining area. Four different remote sensing indices were used: Vegetation Index considering Greenness and Shortwave infrared (VIGS), Normalized Pigment Chlorophyll Ratio Index (NPCRI), Enhanced Vegetation Index (EVI) and Global Environmental Monitoring Index (GEMI). Box plot, independent sample t-test and mean\u002Fstandard deviation value methods were used to compare the values taken from the sample points at mining area and non-mining area. The box plots of the indices show that the median VIGS values at mining area were higher than those non-mining area in both July and October. The differences between the median values were lowest at the EVI index. Independent samples t-test results revealed significant differences at p \u003C 0.05 between mining area and non-mining area. No anomalies were detected in the VIGS and NPCRI index results when comparing mean\u002F standard deviation values. The lower mean\u002F standard deviation values of the EVI and GEMI indices during October indicate an anomaly caused by stress. The findings demonstrated that multiple indices, temporal and statistical analysis approaches can be used to determine vegetation stress in mining areas.","利用遥感技术和多光谱卫星数据可以获取大量植被信息。本研究采用Landsat-7 ETM+（增强型专题制图仪）卫星数据及遥感指数，识别矿区植被中与胁迫相关的异常现象。研究使用了四种不同的遥感指数：考虑绿度和短波红外的植被指数（VIGS）、归一化色素叶绿素比值指数（NPCRI）、增强型植被指数（EVI）和全球环境监测指数（GEMI）。采用箱线图、独立样本t检验及均值\u002F标准差法，对矿区和矿区外样点所取数值进行比较。各指数的箱线图显示，7月和10月矿区的VIGS中位数值均高于矿区外。各指数中，EVI的中位数差异最小。独立样本t检验结果显示，矿区与矿区外之间在p \u003C 0.05水平上存在显著差异。在比较均值\u002F标准差时，VIGS和NPCRI指数结果未检测到异常。10月期间EVI和GEMI指数的较低均值\u002F标准差表明存在由胁迫引起的异常。研究结果表明，多种指数、时间序列及统计分析方法的结合可用于确定矿区植被胁迫状况。",null,"Konya Journal of Engineering Sciences","2026-09-01T00:00:00Z","论文",10,false,50,{"impact":17,"substance":18,"depth":18,"authority":17,"freshness":19,"relevant":20,"comment":21},8,15,4,1,"利用多遥感指数识别矿区植被胁迫，方法有参考价值，但影响范围有限。",[23],{"name":10,"url":6},[25,26,27],"农业遥感","植被监测","矿区生态",[],{"status":30,"locked":14,"version":31,"method":32,"evidence":33},"needs_review","2026-10-22.2","rules",{"candidates":34,"agricultural_evidence":14,"reason":50},[35,45],{"code":36,"score":37,"supported":38,"title":39,"abstract":41,"tags":44},"I3",19,true,[40],"remote sensing",[42,40,43],"遥感","multispectral",[25,26],{"code":46,"score":20,"supported":14,"title":47,"abstract":48,"tags":49},"H6",[],[],[27],"农业相关性需要复核",[52,53],"农业遥感 植被监测 矿区生态","农业遥感 植被监测","农业遥感植被监测矿区生态-1445","10.36306\u002Fkonjes.1699608",{"doi":55,"openalex_id":57,"authors":58,"venue":10,"cited_by_count":62,"oa_url":63,"card":64,"direction":68,"ingested_from":70},"W7204927298",[59],{"name":60,"orcid":61},"Emre Yücer","https:\u002F\u002Forcid.org\u002F0000-0003-0417-9338",0,"https:\u002F\u002Fdergipark.org.tr\u002Fen\u002Fdownload\u002Farticle-file\u002F4871537",{"tldr":65,"method":66,"finding":67,"direction":68,"opportunity":69},"利用Landsat-7数据和遥感指数检测矿区植被金属胁迫异常。","使用VIGS、NPCRI、EVI、GEMI四种遥感指数及箱线图、t检验等方法。","VIGS在矿区中值较高，EVI和GEMI在10月显示异常，表明存在胁迫。","农业遥感与作物表型","可探索结合高光谱或时序数据提高矿区植被胁迫检测精度，并区分金属类型。","openalex","2026-09-02T23:30:55.283048Z",{"total":73,"page":20,"page_size":73,"items":74},6,[75,158,226,290,389,446],{"id":76,"title":77,"url":78,"summary":79,"summary_zh":80,"content":9,"source_name":81,"source_url":78,"published_at":82,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":83,"score_detail":84,"sources":88,"tags":90,"primary_topic":93,"secondary_topics":98,"classification":99,"search_phrases":140,"slug":143,"view_count":130,"doi":144,"paper":145,"created_at":157},3846,"Integrating Earth Observation Data for Assessing the Impact of Mining Ponds on Land Use and Land Cover Change","https:\u002F\u002Fdoi.org\u002F10.56201\u002Fijgem.vol.11.no10.2025.pg136.153","This study examines the relationship between mining ponds and land use and land cover (LULC) dynamics, emphasizing both the environmental challenges and the socio-economic opportunities they present. Earth observation data from Landsat and questionnaire administration were used to evaluate the spatial and socio-environmental impacts of mining activities in Jos South Local Government Area (LGA). Supervised Maximum Likelihood Classification was applied to multitemporal satellite imagery to determine LULC changes, while nearest neighborhood analysis assessed the spatial distribution of mining ponds. A stratified random sampling method was used to collect responses from five districts Du, Zawan, Kuru, Vwang, and Gyel. Results revealed that mining ponds accounted for approximately 2.03% (10.20 km²) of the total land area in 1990, showing a slight decline to 2.00% (10.04 km²) by 2021. Despite their negative impacts, such as land degradation, erosion, and pollution, mining ponds also contribute positively to local livelihoods. An all-year-round supply of water by these ponds makes activities such as irrigation farming, fish farming, block making, recreation and livestock husbandry possible at all times. These benefits generate a wide range of opportunities, which attract investments from private companies, all channeled towards the socio-economic development of Jos-south. We recommended prioritizing the adoption of modern technologies such as GIS and remote sensing by the government for consistent supervision of the expansion of these mining ponds, towards sustainable environmental development of the Jos-South local government area.","本研究考察了矿坑与土地利用和土地覆盖（LULC）动态之间的关系，重点关注其带来的环境挑战与社会经济机遇。研究利用Landsat地球观测数据和问卷调查，评估了乔斯南部地方政府辖区（LGA）采矿活动的空间及社会环境的影响。研究对多时相卫星影像采用监督最大似然分类法以确定土地利用和土地覆盖变化，同时运用最近邻分析评估矿坑的空间分布。采用分层随机抽样方法，从Du、Zawan、Kuru、Vwang和Gyel五个区收集了调查问卷。结果显示，1990年矿坑约占土地总面积的2.03%（10.20 km²），到2021年略微下降至2.00%（10.04 km²）。尽管矿坑带来了土地退化、侵蚀和污染等负面影响，但也对当地生计作出了积极贡献。这些矿坑全年供水，使得灌溉农业、养鱼、制砖、休闲娱乐和畜牧等活动得以常年开展。这些效益产生了广泛的机遇，吸引了私营企业的投资，全部用于乔斯南部的社会经济发展。我们建议政府优先采用地理信息系统（GIS）和遥感等现代技术，对这些矿坑的扩张进行持续监管，以促进乔斯南部地方政府辖区的环境可持续发展。","IIARD INTERNATIONAL JOURNAL OF GEOGRAPHY AND ENVIRONMENTAL MANAGEMENT","2026-09-28T00:00:00Z",60,{"impact":17,"substance":85,"depth":18,"authority":13,"freshness":86,"relevant":20,"comment":87},18,9,"基于Landsat遥感与问卷评估尼日利亚矿区池塘对土地利用变化的影响，方法规范但属区域案例，对国内三农信息化参考价值有限。",[89],{"name":81,"url":78},[25,91,92,27],"遥感监测","土地利用",{"code":36,"slug":94,"name":95,"path":96,"parent_code":97},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",[],{"status":100,"locked":14,"version":31,"method":32,"evidence":101},"classified",{"candidates":102,"agricultural_evidence":38},[103,107,114,121,128,135],{"code":36,"score":17,"supported":38,"title":104,"abstract":105,"tags":106},[],[42,40],[25,91],{"code":108,"score":73,"supported":38,"title":109,"abstract":110,"tags":113},"C",[],[111,112],"畜牧","livestock",[],{"code":115,"score":73,"supported":38,"title":116,"abstract":117,"tags":120},"H3",[],[118,119],"灌溉","irrigation",[],{"code":122,"score":73,"supported":38,"title":123,"abstract":124,"tags":127},"I4",[],[125,126],"地理信息","GIS",[],{"code":129,"score":130,"supported":38,"title":131,"abstract":132,"tags":134},"D",3,[],[133],"fish farming",[],{"code":46,"score":136,"supported":14,"title":137,"abstract":138,"tags":139},2,[],[],[92,27],[141,142],"Jos South 矿区 土地利用","Landsat 遥感 土地覆盖","JosSouth矿区土地利用-3846","10.56201\u002Fijgem.vol.11.no10.2025.pg136.153",{"doi":144,"openalex_id":146,"authors":147,"venue":81,"cited_by_count":62,"oa_url":151,"card":152,"direction":68,"ingested_from":70},"W7214571622",[148],{"name":149,"orcid":150},"Momoh Khalifa Adeiza","https:\u002F\u002Forcid.org\u002F0009-0000-8594-7372","https:\u002F\u002Fiiardjournals.org\u002Fget\u002FIJGEM\u002FVOL. 11 NO. 10 2025\u002FIntegrating Earth Observation 136-153.pdf",{"tldr":153,"method":154,"finding":155,"direction":68,"opportunity":156},"用Landsat影像与问卷评估矿区池塘对土地利用变化及社会经济的影响。","Landsat多时相影像、最大似然分类、最近邻分析与分层随机抽样问卷。","矿塘面积占比由1990年2.03%微降至2021年2.00%，但带来退化与生计双重效应。","可结合时序遥感与农户调查，量化矿塘对灌溉农业与生计的长期耦合影响。","2026-09-30T23:30:29.520262Z",{"id":159,"title":160,"url":161,"summary":162,"summary_zh":163,"content":9,"source_name":164,"source_url":161,"published_at":165,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":166,"score_detail":167,"sources":172,"tags":174,"primary_topic":177,"secondary_topics":178,"classification":179,"search_phrases":194,"slug":197,"view_count":130,"doi":198,"paper":199,"created_at":225},3166,"Case Studies of Environmental Monitoring Based on the Integrated Use of Bioindicators and Remote Sensing","https:\u002F\u002Fdoi.org\u002F10.3390\u002Frs18183227","This narrative review examines how plant bioindication can be integrated with remote sensing to support the preliminary screening of soil contamination, framed as an environmental situational awareness problem addressed through multi-scale imagery and field validation. Seven case studies—illegal waste deposits, pipeline leaks, landfill impacts, industrial areas, agrochemical drift, oil-spills in coastal wetlands, and acid mine drainage—were selected based on joint documentation of a contamination source or exposure condition, a measurable plant response, and a remotely detected signal related to vegetation stress. This synthesis clarifies how vegetation response can serve as a proxy for large-scale contamination screening. A common contamination–vegetation–remote sensing logic emerges across the cases examined, linking contamination drivers and exposure pathways to canopy responses detectable as spectral, thermal, spatial, or temporal anomalies. Recurring spatial patterns of vegetation anomalies are identified as first-order interpretive cues rather than diagnostic signatures. Vegetation stress responses lack spectral specificity, making spectral equifinality the primary operational challenge for vegetation-based biomonitoring. Future workflows should integrate spectral, spatial, temporal, multi-sensor, and ancillary data validated against ground-truth. Future research should expand the evidence base through formal literature searches, multi-site validation, standardized protocols, and infrastructures integrating plant phenotyping and remote sensing to support quantitatively validated screening approaches.","本叙述性综述探讨了如何将植物生物指示与遥感相结合，以支持土壤污染的初步筛查，并将其构建为一个通过多尺度影像和实地验证来解决的环境态势感知问题。基于对污染源或暴露条件的联合记录、可测量的植物响应以及与植被胁迫相关的遥感信号，选取了七个案例研究——非法废物堆放、管道泄漏、垃圾填埋场影响、工业区、农用化学品飘移、沿海湿地溢油和酸性矿山排水。本综述阐明了植被响应如何能够作为大规模污染筛查的替代指标。在所考察的案例中，浮现出一种共同的污染—植被—遥感逻辑，将污染驱动因素和暴露途径与可被检测为光谱、热、空间或时间异常的冠层响应联系起来。植被异常的重复性空间格局被识别为一级解释线索，而非诊断性特征。植被胁迫响应缺乏光谱特异性，使得光谱等终性成为基于植被的生物监测面临的首要操作挑战。未来的工作流程应整合光谱、空间、时间、多传感器和辅助数据，并以地面真值进行验证。未来研究应通过正式文献检索、多站点验证、标准化协议以及整合植物表型分析与遥感的基础设施来扩展证据基础，以支持经过定量验证的筛查方法。","Remote Sensing","2026-09-19T00:00:00Z",77,{"impact":168,"substance":169,"depth":85,"authority":170,"freshness":17,"relevant":20,"comment":171},16,21,14,"综述性论文，系统梳理植被生物指示与遥感融合筛查土壤污染的七个案例，方法学与结论对农业环境遥感监测有参考价值，但非全国性政策或突破性成果。",[173],{"name":164,"url":161},[25,42,175,26,176],"环境监测","土壤污染",{"code":36,"slug":94,"name":95,"path":96,"parent_code":97},[],{"status":100,"locked":14,"version":31,"method":32,"evidence":180},{"candidates":181,"agricultural_evidence":38},[182,187],{"code":36,"score":183,"supported":38,"title":184,"abstract":185,"tags":186},17,[40],[42,40],[25,26,42],{"code":188,"score":73,"supported":38,"title":189,"abstract":190,"tags":193},"H2",[],[191,192],"土壤","soil",[],[195,196],"植被生物指示 遥感 土壤污染","Remote Sensing 植被胁迫 遥感监测","植被生物指示遥感土壤污染-3166","10.3390\u002Frs18183227",{"doi":198,"openalex_id":200,"authors":201,"venue":164,"cited_by_count":62,"oa_url":161,"card":220,"direction":68,"ingested_from":70},"W7213930509",[202,205,208,211,214,217],{"name":203,"orcid":204},"Marco De Mizio","https:\u002F\u002Forcid.org\u002F0009-0009-6556-2606",{"name":206,"orcid":207},"Donato Amitrano","https:\u002F\u002Forcid.org\u002F0000-0002-2355-4503",{"name":209,"orcid":210},"Massimiliano Gargiulo","https:\u002F\u002Forcid.org\u002F0000-0002-6783-366X",{"name":212,"orcid":213},"Sara Parrilli","https:\u002F\u002Forcid.org\u002F0000-0002-7225-1269",{"name":215,"orcid":216},"Claudia Savarese","https:\u002F\u002Forcid.org\u002F0000-0003-0161-2407",{"name":218,"orcid":219},"Massimiliano Lega","https:\u002F\u002Forcid.org\u002F0000-0002-4842-6049",{"tldr":221,"method":222,"finding":223,"direction":68,"opportunity":224},"综述植物生物指示与遥感结合用于土壤污染初步筛查的七个案例，提出污染-植被-遥感逻辑。","叙事性综述，选取七类污染案例，整合多尺度影像与地面验证。","植被胁迫光谱缺乏特异性，光谱等终性是植被生物监测的主要操作挑战。","可构建标准化植物表型-遥感集成平台，开展多站点验证以量化污染筛查。","2026-09-22T23:30:20.917796Z",{"id":227,"title":228,"url":229,"summary":230,"summary_zh":231,"content":9,"source_name":232,"source_url":229,"published_at":233,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":234,"score_detail":235,"sources":238,"tags":240,"primary_topic":243,"secondary_topics":249,"classification":250,"search_phrases":270,"slug":272,"view_count":136,"doi":273,"paper":274,"created_at":289},1740,"Spatio-Temporal Dynamics of Vegetation Response to Climatic Variability in Akinyele Local Government Area, Oyo State, Nigeria","https:\u002F\u002Fdoi.org\u002F10.33003\u002Ffjs-2026-1016-5660","Although vegetation is very sensitive to climatic variability, there is limited evidence on a local scale in many tropical areas. This study has evaluated the spatio-temporal variability of vegetation response to climatic variability in Akinyele Local Government Area, Oyo State, Nigeria using NDVI, Rainfall, LST data of multi-temporal satellite image for the years 2015, 2020 and 2025. Google Earth Engine was used to process the sentinel-2 imagery, CHIRPS rainfall data, and MODIS LST products. NDVI was categorized into 3 classes (sparse, moderate and dense vegetation). The data set consisted of 5,991 sample points with which statistical analyses (Pearson correlation, multiple linear regression, ANOVA) were carried out. Results indicated that from 2015 to 2020 the density of vegetation decreased by 126.45 km² but increased by 158.55 km² until 2025, in accordance with the climatic changes. Mean NDVI decreased from 0.629 in 2015 to 0.611 in 2020, then increased to 0.654 in 2025. LST had a consistently high negative correlation (r = -0.650 to -0.669, p \u003C 0.001) with NDVI, whereas there was a relatively weak positive correlation with rainfall (r = 0.291–0.336). Regression models accounted for 43%–45% of the variability in NDVI, with LST being the most significant predictor (p \u003C 0.001). The results provide a basis for understanding how temperature is the dominant climatic factor controlling vegetation in the study area, and its implications for land use planning, climate change adaptation, sustainable agriculture, and urban green infrastructure in the urbanising landscapes of Nigeria.","尽管植被对气候变率非常敏感，但在许多热带地区，关于局部尺度的证据仍然有限。本研究利用2015年、2020年和2025年的多时相卫星影像数据，包括归一化植被指数（NDVI）、降雨量和地表温度（LST），评估了尼日利亚奥约州阿基涅尔地方政府区域植被对气候变率的时空响应。研究采用谷歌地球引擎（Google Earth Engine）处理哨兵二号（Sentinel-2）影像、CHIRPS降雨数据和MODIS地表温度产品。NDVI被划分为三个等级（稀疏植被、中等植被和茂密植被）。数据集包含5，991个样本点，并据此进行了统计分析（皮尔逊相关分析、多元线性回归、方差分析）。结果表明，从2015年到2020年，植被密度减少了126.45平方公里，但到2025年又增加了158.55平方公里，这与气候变化相一致。平均NDVI从2015年的0.629降至2020年的0.611，随后在2025年上升至0.654。地表温度与NDVI始终呈高度负相关（r = -0.650至-0.669，p \u003C 0.001），而降雨量与NDVI呈相对较弱的正相关（r = 0.291–0.336）。回归模型解释了NDVI变异的43%–45%，其中地表温度是最显著的预测因子（p \u003C 0.001）。研究结果为理解温度作为控制研究区植被的主导气候因子提供了基础，并揭示了其对尼日利亚城市化景观中土地利用规划、气候变化适应、可持续农业和城市绿色基础设施建设的启示意义。","FUDMA Journal of Sciences","2026-09-03T00:00:00Z",57,{"impact":17,"substance":236,"depth":85,"authority":17,"freshness":130,"relevant":20,"comment":237},20,"地方尺度植被对气候响应的遥感研究，数据详实，但影响范围有限，时效性较低。",[239],{"name":232,"url":229},[25,241,242,26],"气候变化","NDVI",{"code":244,"slug":245,"name":246,"path":247,"parent_code":248},"H7","climate","气候适应与防灾减灾","\u002Ftopic\u002Fenvironment\u002Fclimate","H",[],{"status":100,"locked":14,"version":31,"method":32,"evidence":251},{"candidates":252,"agricultural_evidence":38},[253,259,266],{"code":244,"score":254,"supported":38,"title":255,"abstract":256,"tags":258},7,[],[241,257],"climate change",[241],{"code":260,"score":73,"supported":38,"title":261,"abstract":262,"tags":265},"H8",[],[263,264],"可持续农业","sustainable agriculture",[],{"code":36,"score":130,"supported":14,"title":267,"abstract":268,"tags":269},[],[],[242,25,26],[271,53],"农业遥感 植被监测 气候变化 NDVI","农业遥感植被监测气候变化NDVI-1740","10.33003\u002Ffjs-2026-1016-5660",{"doi":273,"openalex_id":275,"authors":276,"venue":232,"cited_by_count":62,"oa_url":283,"card":284,"direction":68,"ingested_from":70},"W7207552979",[277,279,281],{"name":278,"orcid":9},"Monday Ghandi Daniel",{"name":280,"orcid":9},"Ojodugbowa Shedrach Omachoko",{"name":282,"orcid":9},"Iyam Ubi Effiom","https:\u002F\u002Ffjs.fudutsinma.edu.ng\u002Findex.php\u002Ffjs\u002Farticle\u002Fdownload\u002F5660\u002F3848",{"tldr":285,"method":286,"finding":287,"direction":68,"opportunity":288},"利用遥感数据评估尼日利亚某地植被对气候变化的时空响应。","GEE处理Sentinel-2、CHIRPS、MODIS数据，统计相关与回归分析","温度是主导因子，与NDVI强负相关，降雨弱正相关。","可延伸至热带城市化区域植被-气候耦合模型及适应性管理策略研究。","2026-09-05T23:30:27.920627Z",{"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":302,"tags":304,"primary_topic":309,"secondary_topics":315,"classification":322,"search_phrases":357,"slug":360,"view_count":62,"doi":361,"paper":362,"created_at":388},5573,"Improving alfalfa nitrogen estimation with canopy structural priors from DSSAT–PROSAIL and UAV hyperspectral data","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.eja.2026.128375","Accurate estimation of nitrogen (N) concentration in alfalfa ( Medicago sativa L .) supports forage quality assessment and harvest scheduling. Empirical remote sensing models often overfit because of confounding effects of three-dimensional canopy structure. Incorporating structural parameters can stabilize biochemical inversions, but concurrent in situ morphological measurements are difficult to acquire at scale. We developed the Morphology-Aware Latent Embedding Network (MALENet), a hybrid framework integrating physiological and morphological mechanisms with hyperspectral data. The Decision Support System for Agrotechnology Transfer (DSSAT), coupled with the PROSAIL radiative transfer model, generated a structurally rich synthetic hyperspectral prior. A convolutional neural network (CNN) with a Squeeze-and-Excitation (SE) attention mechanism, was pre-trained on these data to distill ecophysiological knowledge into a dense latent representation. This mechanistically derived embedding was then fused with empirical hyperspectral measurements collected under diverse field conditions. Evaluation using multi-year field quadrats in the Hexi Corridor showed improved predictive performance ( R² = 0.71, RMSE = 0.30%) relative to conventional machine learning and deep learning models (LASSO-ANN: R² = 0.61; CNN: R² = 0.66). Feature attribution indicated that MALENet used near-infrared multiple scattering (58.3% attribution) as a structural proxy to calibrate nitrogen concentration retrieval against the confounding effects of canopy architecture. Despite constraints imposed by sample size and PROSAIL's 1D canopy assumption, these findings demonstrate the potential of physically guided deep learning to use structural information for agricultural trait retrieval in precision forage management.","准确估算紫花苜蓿（Medicago sativa L.）的氮浓度有助于饲草品质评估和收获期安排。经验性遥感模型常因三维冠层结构的混杂效应而出现过拟合。引入结构参数可以稳定生化反演，但同步开展原位形态学测量难以大规模获取。我们开发了形态感知潜在嵌入网络（Morphology-Aware Latent Embedding Network，MALENet），这是一个将生理与形态机制同高光谱数据相结合的混合框架。农业技术转移决策支持系统（Decision Support System for Agrotechnology Transfer，DSSAT）与PROSAIL辐射传输模型耦合，生成了结构信息丰富的合成高光谱先验数据。在此基础上，预训练了一个带有挤压—激励（Squeeze-and-Excitation，SE）注意力机制的卷积神经网络（convolutional neural network，CNN），将生态生理学知识提炼为稠密潜在表征。随后，将这一机制性导出的嵌入与在不同田间条件下采集的经验性高光谱测量数据相融合。利用河西走廊多年田间样方进行的评估显示，相较于传统机器学习和深度学习模型（LASSO-ANN：R² = 0.61；CNN：R² = 0.66），预测性能有所提升（R² = 0.71，RMSE = 0.30%）。特征归因表明，MALENet利用近红外多次散射（归因占比58.3%）作为结构代理，以校准氮浓度反演，抵御冠层结构的混杂效应。尽管受样本量和PROSAIL一维冠层假设的限制，这些发现表明，物理引导的深度学习有潜力利用结构信息，在精准饲草管理中进行农业性状反演。","European Journal of Agronomy","2026-10-21T00:00:00Z",80,{"impact":168,"substance":300,"depth":85,"authority":170,"freshness":13,"relevant":20,"comment":301},22,"该研究将作物模型与辐射传输模型耦合生成结构先验，并结合无人机高光谱数据反演苜蓿氮素，方法新颖、田间验证扎实，对精准饲草管理有参考价值，值得进入每日精选。",[303],{"name":296,"url":293},[305,306,25,307,308],"智慧农业","农业人工智能","氮素监测","紫花苜蓿",{"code":310,"slug":311,"name":312,"path":313,"parent_code":314},"A7","forage-cropping","饲草与耕作制度","\u002Ftopic\u002Ffield-crops\u002Fforage-cropping","A",[316,317],{"code":36,"slug":94,"name":95,"path":96,"parent_code":97},{"code":318,"slug":319,"name":320,"path":321,"parent_code":108},"C4","feed","饲料与饲草","\u002Ftopic\u002Flivestock\u002Ffeed",{"status":100,"locked":14,"version":31,"method":32,"evidence":323},{"candidates":324,"agricultural_evidence":38},[325,330,336,342,352],{"code":36,"score":85,"supported":38,"title":326,"abstract":328,"tags":329},[327],"hyperspectral",[42,40,327],[25],{"code":310,"score":18,"supported":38,"title":331,"abstract":333,"tags":335},[332],"alfalfa",[334,332],"苜蓿",[308],{"code":318,"score":13,"supported":38,"title":337,"abstract":338,"tags":341},[],[339,334,340],"饲草","forage",[308],{"code":343,"score":13,"supported":38,"title":344,"abstract":345,"tags":351},"I2",[],[346,347,348,349,350],"深度学习","机器学习","machine learning","deep learning","decision support",[306],{"code":353,"score":20,"supported":14,"title":354,"abstract":355,"tags":356},"I1",[],[],[305],[358,359],"DSSAT PROSAIL 苜蓿 氮素","无人机 高光谱 苜蓿","DSSATPROSAIL苜蓿氮素-5573","10.1016\u002Fj.eja.2026.128375",{"doi":361,"openalex_id":363,"authors":364,"venue":296,"cited_by_count":62,"oa_url":293,"card":383,"direction":68,"ingested_from":70},"W7223154576",[365,367,369,371,373,376,378,381],{"name":366,"orcid":9},"Shuai Fu",{"name":368,"orcid":9},"Yunhao Li",{"name":370,"orcid":9},"Chunli Miao",{"name":372,"orcid":9},"Jie Liu",{"name":374,"orcid":375},"Tiangang Liang","https:\u002F\u002Forcid.org\u002F0000-0001-5599-6587",{"name":377,"orcid":9},"Yongjia Hu",{"name":379,"orcid":380},"Qisheng Feng","https:\u002F\u002Forcid.org\u002F0009-0000-1391-9591",{"name":382,"orcid":9},"吴彩霞",{"tldr":384,"method":385,"finding":386,"direction":68,"opportunity":387},"构建MALENet融合DSSAT-PROSAIL结构先验与无人机高光谱，提升苜蓿氮浓度估算精度。","DSSAT耦合PROSAIL生成合成高光谱先验，预训练CNN-SE网络，再融合田","MALENet精度优于传统机器学习和深度学习模型，R²达0.71，近红外多次散射作为结构代理贡献58","可探索将作物模型结构先验迁移至其他牧草或作物生化参数反演，并缓解PROSAIL一维冠层假设局限。","2026-10-22T11:20:39.622844Z",{"id":390,"title":391,"url":392,"summary":393,"summary_zh":9,"content":9,"source_name":394,"source_url":9,"published_at":297,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":395,"score_detail":396,"sources":398,"tags":400,"primary_topic":404,"secondary_topics":409,"classification":412,"search_phrases":433,"slug":436,"view_count":20,"doi":9,"paper":437,"created_at":445},5535,"基于无人机多光谱图像与VGG21模型的小麦渍害调控效果识别","https:\u002F\u002Ffinance.sina.cn\u002F2026-10-16\u002Fdetail-inivmprm8363597.d.html","江苏省农科院农业信息研究所联合中国农科院环发所与湖北省农科院粮作所，在小麦拔节至抽穗、抽穗至灌浆两个阶段设置对照、渍水胁迫、硅肥与氨基酸调控试验，用大疆精灵4采集冠层多光谱影像。VGG21模型对硅肥调控识别正确率超91%，精度96.42%、召回率89.53%。","智慧农业（中英文）2026-10-21",82,{"impact":85,"substance":300,"depth":85,"authority":170,"freshness":13,"relevant":20,"comment":397},"省级科研机构联合攻关，方法新颖、数据扎实，对渍害遥感识别与调控评估有实质参考价值，值得入选。",[399],{"name":394,"url":392},[305,25,401,402,403],"作物表型","无人机多光谱","小麦渍害",{"code":405,"slug":406,"name":407,"path":408,"parent_code":314},"A2","wheat","小麦","\u002Ftopic\u002Ffield-crops\u002Fwheat",[410,411],{"code":36,"slug":94,"name":95,"path":96,"parent_code":97},{"code":244,"slug":245,"name":246,"path":247,"parent_code":248},{"status":100,"locked":14,"version":31,"method":32,"evidence":413},{"candidates":414,"agricultural_evidence":38},[415,420,424,429],{"code":405,"score":416,"supported":38,"title":417,"abstract":418,"tags":419},11,[407],[407],[],{"code":36,"score":416,"supported":38,"title":421,"abstract":422,"tags":423},[402],[],[401,25,402],{"code":244,"score":17,"supported":38,"title":425,"abstract":427,"tags":428},[426],"渍害",[],[],{"code":353,"score":20,"supported":14,"title":430,"abstract":431,"tags":432},[],[],[305],[434,435],"江苏省农科院 小麦渍害 多光谱","VGG21 小麦 硅肥调控","江苏省农科院小麦渍害多光谱-5535",{"doi":9,"openalex_id":9,"authors":438,"venue":9,"cited_by_count":62,"oa_url":9,"card":439,"direction":68,"ingested_from":444},[],{"tldr":440,"method":441,"finding":442,"direction":68,"opportunity":443},"用无人机多光谱图像和VGG21模型识别小麦渍害后硅肥与氨基酸调控效果。","大疆精灵4采集冠层多光谱影像，构建VGG21深度学习分类模型。","VGG21对硅肥调控识别正确率超91%，精度96.42%、召回率89.53%。","可扩展多生育期、多调控组合与轻量化模型，探索渍害胁迫等级与调控效果的同步识别。","agent","2026-10-22T00:07:10.070916Z",{"id":447,"title":448,"url":449,"summary":450,"summary_zh":451,"content":9,"source_name":452,"source_url":449,"published_at":453,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":454,"score_detail":455,"sources":458,"tags":460,"primary_topic":464,"secondary_topics":467,"classification":468,"search_phrases":486,"slug":489,"view_count":62,"doi":490,"paper":491,"created_at":521},5399,"Spatial Heterogeneity and Nonlinear Environmental Associations of Positive Climatic Moisture Deficit with Implications for Sustainable Water Resource Assessment: A Case Study of Anyang","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fsu182010595","Positive climatic moisture deficit (CMD+) characterizes the seasonal imbalance between precipitation supply and atmospheric water demand, yet its spatial heterogeneity and associations with environmental and human-related factors remain insufficiently understood. Taking Anyang, China, as a case study, we calculated annual CMD+ for 2000–2020 using 1 km monthly precipitation and potential evapotranspiration data and applied an extreme gradient boosting (XGBoost)–SHapley Additive exPlanations (SHAP) framework to the corresponding long-term mean fields to examine climatological spatial heterogeneity. Five predictors were considered, including elevation, normalized difference vegetation index (NDVI), irrigation fraction, built-up fraction, and population density. Nested spatial-block cross-validation showed good model generalization. Long-term mean CMD+ was generally lower in the western mountainous area and higher across the central and eastern plains. The digital elevation model (DEM) accounted for 66.10% of the normalized mean absolute SHAP importance, followed by NDVI (13.47%) and irrigation fraction (9.72%). A DEM-excluded sensitivity model retained a spatial cross-validated R2 of 0.781, compared with 0.898 for the full model. SHAP dependence analysis revealed pronounced nonlinear responses, with primary local model response transition points at approximately 297.1 m for DEM, 0.812 for NDVI, and 23.1% for irrigation fraction. The strongest pairwise SHAP interaction occurred between NDVI and irrigation fraction, accounting for 21.87% of total pairwise interaction strength. These results show that the spatial heterogeneity of CMD+ in Anyang is closely associated with topographic background, while vegetation status and irrigated agriculture provide additional nonlinear and interactive explanatory information. The identified spatial patterns and model-response transitions provide spatial information for understanding regional climatic moisture deficits and for subsequent sustainable water resource assessment.","正向气候水分亏缺（CMD+）刻画了降水供给与大气水分需求之间的季节性失衡，但其空间异质性及其与环境因素和人为因素的关联仍缺乏充分认识。以中国安阳为案例区，本研究利用1 km月降水量与潜在蒸散量数据计算了2000—2020年的年CMD+，并将极端梯度提升（XGBoost）—SHapley加性解释（SHAP）框架应用于相应的长期均值场，以考察气候态空间异质性。研究考虑了5个预测因子，包括高程、归一化植被指数（NDVI）、灌溉面积比例、建成区比例和人口密度。嵌套空间分块交叉验证表明模型具有良好的泛化能力。长期平均CMD+总体表现为西部山区较低、中部和东部平原较高。数字高程模型（DEM）占归一化平均绝对SHAP重要性的66.10%，其次为NDVI（13.47%）和灌溉面积比例（9.72%）。剔除DEM的敏感性模型保持了0.781的空间交叉验证R²，而完整模型为0.898。SHAP依赖分析揭示了显著的非线性响应，主要局部模型响应转变点分别约为DEM 297.1 m、NDVI 0.812和灌溉面积比例23.1%。最强的成对SHAP交互作用出现在NDVI与灌溉面积比例之间，占总成对交互强度的21.87%。结果表明，安阳CMD+的空间异质性与地形背景密切相关，而植被状况和灌溉农业提供了额外的非线性和交互解释信息。所识别的空间格局和模型响应转变点为理解区域气候水分亏缺及后续可持续水资源评估提供了空间信息。","Sustainability","2026-10-19T00:00:00Z",64,{"impact":17,"substance":85,"depth":168,"authority":456,"freshness":86,"relevant":20,"comment":457},13,"以安阳为案例，用遥感与XGBoost-SHAP揭示气候水分亏缺的空间异质性，方法有新意、结论可靠，但属区域案例研究，公共影响有限。",[459],{"name":452,"url":449},[25,347,461,462,463],"灌溉管理","水资源评估","气候干旱",{"code":115,"slug":119,"name":465,"path":466,"parent_code":248},"水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation",[],{"status":100,"locked":14,"version":31,"method":32,"evidence":469},{"candidates":470,"agricultural_evidence":38},[471,478,482],{"code":115,"score":85,"supported":38,"title":472,"abstract":474,"tags":477},[473],"water resource",[118,475,119,473,476],"水资源","evapotranspiration",[461],{"code":343,"score":20,"supported":14,"title":479,"abstract":480,"tags":481},[],[],[347],{"code":36,"score":20,"supported":14,"title":483,"abstract":484,"tags":485},[],[],[25],[487,488],"安阳 气候水分亏缺 遥感","XGBoost SHAP 水资源评估","安阳气候水分亏缺遥感-5399","10.3390\u002Fsu182010595",{"doi":490,"openalex_id":492,"authors":493,"venue":452,"cited_by_count":62,"oa_url":449,"card":515,"direction":520,"ingested_from":70},"W7222973420",[494,496,499,502,505,507,509,511,513],{"name":495,"orcid":9},"Yan Li",{"name":497,"orcid":498},"Xiaohua Yang","https:\u002F\u002Forcid.org\u002F0000-0001-8387-5213",{"name":500,"orcid":501},"Dehui Bian","https:\u002F\u002Forcid.org\u002F0000-0001-6921-1875",{"name":503,"orcid":504},"Qi Wang","https:\u002F\u002Forcid.org\u002F0000-0002-3156-9246",{"name":506,"orcid":9},"Lequn Gu",{"name":508,"orcid":9},"Ailing Zhang",{"name":510,"orcid":9},"Wei Gao",{"name":512,"orcid":9},"Wenjie Qi",{"name":514,"orcid":9},"Yayun Ma",{"tldr":516,"method":517,"finding":518,"direction":68,"opportunity":519},"以安阳为例，用XGBoost-SHAP分析2000—2020年气候水分亏缺的空间异质性及其环境关联。","1 km月降水与潜在蒸散数据计算CMD+，结合XGBoost-SHAP与嵌套空间","CMD+西部山区低、中东部平原高；高程贡献66.1%，NDVI与灌溉比例呈显著非线性交互。","可引入多源遥感与作物种植结构，探究CMD+非线性阈值对灌溉需水与水资源配置的传导机制。","数字乡村与农业信息化","2026-10-20T23:30:23.927575Z"]