[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3620":3,"related-3620":70},{"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,"search_phrases":32,"slug":35,"view_count":36,"doi":37,"paper":38,"created_at":69},3620,"Assessment of corn chlorophyll content via UAV‐derived vegetative indices across growth stages","https:\u002F\u002Fdoi.org\u002F10.1002\u002Fagg2.70437","Abstract Traditional chlorophyll (Chl) assessment methods are labor‐intensive and spatially limited. This study evaluated unmanned aerial vehicle (UAV) multispectral imagery for nondestructive field‐scale canopy Chl estimation in corn ( Zea mays L.) to support precision nutrient management. Field experiments were conducted at two Virginia Tech research farms under two nitrogen (N) rates, 112 and 224 kg N ha − 1 , and five phosphorus (P) rates, 0, 56, 112, 168, and 224 kg P 2 O 5 ha − 1 . Canopy Chl was measured using a SPAD‐502 Plus chlorophyll meter (where SPAD is soil plant analysis development). UAV imagery was collected at three sampling times using a DJI Mavic 3 M: early vegetative (Ve‐E), late vegetative (Ve‐L), and reproductive stages, corresponding to V4–V6, V11–V13, and R3–R5 growth stages, respectively. Eight vegetation indices (VIs) were derived from green, red, red‐edge, and near‐infrared bands. Relationships between SPAD and spectral predictors were evaluated using Pearson correlation, simple and multiple linear regression, Lasso, and Elastic Net. Model performance was assessed using fivefold cross‐validated (CV) estimates repeated 30 times with CV R 2 , root mean square error, and relative RMSE. Predictive accuracy was moderate and varied by site and time, with strongest relationships during Ve‐L. At Ve‐L, Green Normalized Difference Vegetation Index (GNDVI) and Chlorophyll Index Red Edge were the best predictors at Orange and Kentland, respectively. Multivariate and regularized models performed comparably but did not improve accuracy over the best single‐VI models. Overall, GNDVI and red‐edge‐based indices were the most useful indicators of canopy Chl variation. These findings indicate that UAV‐derived GNDVI and red‐edge indices can provide moderately accurate and interpretable estimates of SPAD‐based Chl status.","传统叶绿素（Chl）评估方法费时费力且空间覆盖有限。本研究评估了无人机（UAV）多光谱影像在玉米（Zea mays L.）田块尺度冠层叶绿素无损估测中的应用，以支持精准养分管理。田间试验在弗吉尼亚理工大学的两个研究农场进行，设置两个氮（N）水平，分别为112和224 kg N ha⁻¹，以及五个磷（P）水平，分别为0、56、112、168和224 kg P₂O₅ ha⁻¹。使用SPAD-502 Plus叶绿素仪（SPAD即土壤植物分析开发）测定冠层叶绿素。使用DJI Mavic 3 M在三个采样时期采集无人机影像：营养生长早期（Ve-E）、营养生长晚期（Ve-L）和生殖生长阶段，分别对应V4–V6、V11–V13和R3–R5生育时期。从绿、红、红边和近红外波段提取了8种植被指数（VIs）。采用Pearson相关、简单和多元线性回归、Lasso及弹性网（Elastic Net）评估SPAD与光谱预测变量之间的关系。模型性能通过重复30次的五折交叉验证（CV）估计进行评估，指标包括交叉验证R²、均方根误差和相对均方根误差。预测精度为中等水平，且因地点和时间而异，其中Ve-L时期关系最强。在Ve-L时期，绿归一化差异植被指数（GNDVI）和红边叶绿素指数分别在Orange和Kentland表现最佳。多变量模型和正则化模型表现相当，但未能比最佳单植被指数模型提高精度。总体而言，GNDVI和基于红边的指数是冠层叶绿素变异最有用的指标。这些结果表明，无人机获取的GNDVI和红边指数能够对基于SPAD的叶绿素状况提供中等精度且可解释的估测。",null,"Agrosystems Geosciences & Environment","2026-09-24T00:00:00Z","论文",10,false,69,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},12,20,16,13,8,1,"基于无人机多光谱影像评估玉米冠层叶绿素，方法规范、结论明确，对精准养分管理有参考价值，但属细分领域研究，公共影响有限。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","玉米","遥感","氮肥管理","植被指数",[33,34],"无人机 玉米 叶绿素 遥感","Virginia Tech 玉米 氮肥 SPAD","无人机玉米叶绿素遥感-3620",0,"10.1002\u002Fagg2.70437",{"doi":37,"openalex_id":39,"authors":40,"venue":10,"cited_by_count":36,"oa_url":61,"card":62,"direction":66,"ingested_from":68},"W7214232972",[41,44,47,50,52,54,56,58],{"name":42,"orcid":43},"Aarati Khulal","https:\u002F\u002Forcid.org\u002F0000-0003-4405-1320",{"name":45,"orcid":46},"Huijie Gan","https:\u002F\u002Forcid.org\u002F0000-0001-6634-5704",{"name":48,"orcid":49},"Jitender Rathore","https:\u002F\u002Forcid.org\u002F0009-0006-5764-1652",{"name":51,"orcid":9},"Sheetal Kumari",{"name":53,"orcid":9},"Ivy Flory",{"name":55,"orcid":9},"Caleb Bishop",{"name":57,"orcid":9},"Santosh Rijal",{"name":59,"orcid":60},"Olga S. Walsh","https:\u002F\u002Forcid.org\u002F0000-0002-2958-931X","https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002Fpdfdirect\u002F10.1002\u002Fagg2.70437",{"tldr":63,"method":64,"finding":65,"direction":66,"opportunity":67},"用无人机多光谱植被指数评估玉米不同生育期冠层叶绿素含量。","DJI Mavic 3 M多光谱影像，8个植被指数，SPAD实测，线性回归与La","GNDVI与红边指数在营养生长后期预测SPAD最准，多变量模型未优于单指数。","农业遥感与作物表型","可探索多生育期时序融合与多源数据耦合，提升跨站点跨年份叶绿素估算泛化能力。","openalex","2026-09-27T23:30:35.468236Z",{"total":71,"page":22,"page_size":71,"items":72},6,[73,146,185,214,253,307],{"id":74,"title":75,"url":76,"summary":77,"summary_zh":78,"content":9,"source_name":79,"source_url":76,"published_at":80,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":81,"score_detail":82,"sources":88,"tags":90,"search_phrases":93,"slug":96,"view_count":36,"doi":97,"paper":98,"created_at":145},3603,"Uncertainty propagation and intercomparison of multi-sensor measurements of vegetation stress in sub-optimal conditions","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs11119-026-10455-1","Abstract Purpose This study evaluates the metrological consistency and uncertainty propagation of spectral reflectance and vegetation indices derived from multiple remote sensing sensors under sub-optimal and variable illumination conditions. While multi-sensor data fusion is increasingly common in precision farming, the extent to which sensor differences arise from biological variation versus measurement uncertainty remains poorly quantified. Methods and results Field measurements were conducted on spring wheat ( Triticum aestivum L.) using three ground-based field spectroradiometers and two uncrewed aerial vehicles (UAV)-mounted multispectral cameras. Following a standardised Guide to the Expression of Uncertainty in Measurement (GUM) framework, uncertainties from sensor noise, spatial plot heterogeneity, and transient cloud cover were propagated using Monte Carlo simulations. The results indicate that total reflectance uncertainty peaked at approximately 11% in the red-edge and near-infrared regions, primarily driven by plot-level heterogeneity and fluctuating irradiance. Among the evaluated indices, the Optimized Soil-Adjusted Vegetation Index (OSAVI) demonstrated the highest stability across platforms, whereas the Enhanced Vegetation Index (EVI) proved highly sensitive to environmental noise, leading to metrological breakdown in sensor interoperability. The findings demonstrate that under unstable atmospheric conditions, the window for reliable multi-sensor data integration is limited to synchronous acquisitions within minutes. Conclusion This research provides a rigorous statistical foundation for identifying the limits of sensor agreement, ensuring that management decisions in precision agriculture are based on true crop signals rather than measurement artifacts.","摘要 目的 本研究评估了在次优和变化光照条件下，来自多个遥感传感器的光谱反射率和植被指数的计量一致性与不确定度传播。尽管多传感器数据融合在精准农业中日益普遍，但传感器差异在多大程度上源于生物变异而非测量不确定度，仍缺乏充分的量化。方法与结果 使用三台地面野外光谱辐射计和两台无人机（UAV）搭载的多光谱相机，对春小麦（Triticum aestivum L.）进行了田间测量。依据测量不确定度表示指南（GUM）的标准框架，采用蒙特卡洛模拟对传感器噪声、空间小区异质性和瞬时云覆盖所产生的不确定度进行了传播分析。结果表明，总反射率不确定度在红边和近红外区域达到约11%的峰值，主要由小区尺度异质性和辐照度波动驱动。在评估的指数中，优化土壤调节植被指数（OSAVI）在不同平台间表现出最高的稳定性，而增强植被指数（EVI）对环境噪声高度敏感，导致传感器互操作性在计量学上失效。研究结果表明，在不稳定大气条件下，可靠的多传感器数据整合窗口仅限于数分钟内的同步采集。结论 本研究为识别传感器一致性的限度提供了严格的统计学基础，确保精准农业中的管理决策基于真实的作物信号而非测量伪影。","Precision Agriculture","2026-09-26T00:00:00Z",75,{"impact":17,"substance":83,"depth":84,"authority":85,"freshness":86,"relevant":22,"comment":87},22,18,14,9,"该研究量化了多传感器植被胁迫测量中的不确定性传播，方法严谨、结论对精准农业多源数据融合具有实质指导价值，但属细分领域学术进展，影响范围有限。",[89],{"name":79,"url":76},[27,29,31,91,92],"多光谱遥感","作物表性",[94,95],"春小麦 多光谱 遥感 不确定性","OSAVI EVI 传感器 互操作","春小麦多光谱遥感不确定性-3603","10.1007\u002Fs11119-026-10455-1",{"doi":97,"openalex_id":99,"authors":100,"venue":79,"cited_by_count":36,"oa_url":76,"card":140,"direction":66,"ingested_from":68},"W7214488126",[101,104,107,110,113,115,117,119,122,125,128,131,134,137],{"name":102,"orcid":103},"Mike Werfeli","https:\u002F\u002Forcid.org\u002F0000-0001-5768-8887",{"name":105,"orcid":106},"Michal Antala","https:\u002F\u002Forcid.org\u002F0000-0003-1294-9507",{"name":108,"orcid":109},"Abdallah Yussuf Ali Abdelmajeed","https:\u002F\u002Forcid.org\u002F0000-0002-3662-1824",{"name":111,"orcid":112},"Álvaro Sánchez-Virosta","https:\u002F\u002Forcid.org\u002F0000-0002-3842-3792",{"name":114,"orcid":9},"Zoe Halem",{"name":116,"orcid":9},"A. Merrington",{"name":118,"orcid":9},"Yousra El‐Mejjaouy",{"name":120,"orcid":121},"Bojana Petrović","https:\u002F\u002Forcid.org\u002F0000-0002-9901-3471",{"name":123,"orcid":124},"Andreas Hueni","https:\u002F\u002Forcid.org\u002F0000-0002-4283-2484",{"name":126,"orcid":127},"El Houssaine Bouras","https:\u002F\u002Forcid.org\u002F0000-0002-6973-6644",{"name":129,"orcid":130},"Shawn C. Kefauver","https:\u002F\u002Forcid.org\u002F0000-0002-1687-1965",{"name":132,"orcid":133},"Sahameh Shafiee","https:\u002F\u002Forcid.org\u002F0000-0002-3586-2327",{"name":135,"orcid":136},"Anshu Rastogi","https:\u002F\u002Forcid.org\u002F0000-0002-0953-7045",{"name":138,"orcid":139},"Laura Mihai","https:\u002F\u002Forcid.org\u002F0000-0003-3869-1890",{"tldr":141,"method":142,"finding":143,"direction":66,"opportunity":144},"评估多传感器植被胁迫测量在非理想条件下的不确定度传播与一致性。","三种地面光谱仪与两架无人机多光谱相机，基于GUM框架和蒙特卡洛模拟传播不确定度。","红边与近红外总反射率不确定度达11%，OSAVI跨平台最稳定，EVI易受环境噪声影响。","可研究分钟级同步采集协议与不确定度感知的传感器融合算法，提升多源数据互操作性。","2026-09-27T23:30:04.847804Z",{"id":147,"title":148,"url":149,"summary":150,"summary_zh":151,"content":9,"source_name":152,"source_url":149,"published_at":153,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":154,"score_detail":155,"sources":159,"tags":161,"search_phrases":164,"slug":167,"view_count":36,"doi":168,"paper":169,"created_at":184},3488,"NDAVI Improves Genotypic Discrimination in Dense Bread Wheat Canopies under Moderate Nitrogen Contrast","https:\u002F\u002Fdoi.org\u002F10.29278\u002Fazd.1972563","Objective: Rapid and non-destructive assessment of wheat canopy status is important for improving nitrogen management and field-based phenotyping. This study evaluated the ability of UAV-derived multispectral vegetation indices to detect canopy spectral variation associated with a moderate, non-zero nitrogen contrast and to discriminate among commercial bread wheat genotypes under dense canopy conditions during the reproductive stage. Materials and Methods: A field experiment was conducted during the 2024–2025 growing season in Bornova, İzmir, Türkiye, using ten commercial bread wheat cultivars grown under low-nitrogen (LN) and high-nitrogen (HN) treatments in a split-plot randomized complete block design with four replications. Multispectral imagery was acquired after heading and before anthesis using a DJI Matrice 350 RTK UAV equipped with a MicaSense RedEdge-P sensor. Four canopy vegetation indices, NDVI, GNDVI, CLRED, and NDAVI, were calculated from plot-level reflectance data. Each index was analyzed using linear mixed models, and index consistency was further evaluated using coefficient of variation, repeatability, and genotype-specific plasticity.Conclusion: Nitrogen treatment significantly affected NDVI, GNDVI, and NDAVI, with higher index values under HN than LN, whereas CLRED was not significantly affected by nitrogen. Among the evaluated indices, NDVI showed the strongest nitrogen response, indicating its usefulness for detecting overall nitrogen-related canopy differences. However, genotype effects were significant only for NDAVI, while NDVI, GNDVI, and CLRED did not provide reliable genotypic discrimination. NDAVI also showed the highest repeatability (0.791) and the lowest coefficient of variation (1.14%), supporting its superior consistency and discriminatory ability. UAV-derived multispectral indices successfully detected canopy spectral responses to moderate nitrogen differences in bread wheat, but nitrogen sensitivity and genotype discrimination differed substantially among indices. Among the evaluated indices, NDAVI appears to be the most promising index for detecting differences among wheat genotypes, particularly when conventional indices such as NDVI may be constrained by saturation.","目的：快速、无损地评估小麦冠层状态对于改进氮素管理和田间表型分析具有重要意义。本研究评估了无人机多光谱植被指数在生殖阶段密集冠层条件下检测与中等非零氮素差异相关的冠层光谱变异以及区分商业面包小麦基因型的能力。材料与方法：田间试验于2024—2025生长季在土耳其伊兹密尔博尔诺瓦进行，采用10个商业面包小麦品种，设置低氮（LN）和高氮（HN）处理，采用裂区随机完全区组设计，4次重复。在抽穗后至开花前，使用搭载MicaSense RedEdge-P传感器的DJI Matrice 350 RTK无人机获取多光谱影像。基于小区尺度反射率数据计算了4个冠层植被指数：NDVI、GNDVI、CLRED和NDAVI。各指数采用线性混合模型进行分析，并通过变异系数、重复性和基因型特异性可塑性进一步评估指数一致性。结论：氮素处理显著影响NDVI、GNDVI和NDAVI，高氮处理下指数值高于低氮处理，而CLRED未受氮素的显著影响。在评估的指数中，NDVI表现出最强的氮素响应，表明其可用于检测整体氮素相关的冠层差异。然而，基因型效应仅对NDAVI显著，而NDVI、GNDVI和CLRED未能提供可靠的基因型区分。NDAVI还表现出最高的重复性（0.791）和最低的变异系数（1.14%），支持其更优的一致性和区分能力。无人机多光谱指数成功检测了面包小麦对中等氮素差异的冠层光谱响应，但不同指数的氮素敏感性和基因型区分能力存在显著差异。在评估的指数中，NDAVI似乎是检测小麦基因型差异最有前景的指数，尤其是当NDVI等常规指数可能受到饱和限制时。","Akademik Ziraat Dergisi","2026-09-22T00:00:00Z",72,{"impact":17,"substance":156,"depth":157,"authority":20,"freshness":86,"relevant":22,"comment":158},21,17,"基于无人机多光谱的田间试验，提出NDAVI在密植小麦冠层中优于NDVI的基因型判别能力，方法新颖、数据扎实，对智慧农业表型与氮肥精准管理有参考价值。",[160],{"name":152,"url":149},[27,162,29,30,163],"小麦","无人机表型",[165,166],"NDAVI 小麦 基因型判别","无人机 多光谱 小麦 氮素","NDAVI小麦基因型判别-3488","10.29278\u002Fazd.1972563",{"doi":168,"openalex_id":170,"authors":171,"venue":152,"cited_by_count":36,"oa_url":178,"card":179,"direction":66,"ingested_from":68},"W7214030909",[172,175],{"name":173,"orcid":174},"Deniz İştipliler","https:\u002F\u002Forcid.org\u002F0000-0002-0887-1121",{"name":176,"orcid":177},"Aliye YILDIRIM","https:\u002F\u002Forcid.org\u002F0000-0002-8101-0803","https:\u002F\u002Fdergipark.org.tr\u002Fen\u002Fdownload\u002Farticle-file\u002F6117047",{"tldr":180,"method":181,"finding":182,"direction":66,"opportunity":183},"评估无人机多光谱植被指数在密植小麦中区分氮处理和基因型的能力。","无人机多光谱影像，四种指数，线性混合模型与重复性分析。","NDAVI重复性最高且能区分基因型，NDVI对氮响应最强但无法区分基因型。","可探索NDAVI在其它作物或更高密度冠层中的基因型区分能力及抗饱和机制。","2026-09-25T23:30:24.042515Z",{"id":186,"title":187,"url":188,"summary":189,"summary_zh":9,"content":9,"source_name":190,"source_url":9,"published_at":191,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":192,"score_detail":193,"sources":195,"tags":197,"search_phrases":200,"slug":203,"view_count":36,"doi":9,"paper":204,"created_at":213},3324,"Diag-STFN：全球收获前作物产量预测的诊断时空多模态融合网络——覆盖38国玉米29国小麦（Ecological Informatics 2026）","https:\u002F\u002Fm2.mtmt.hu\u002Fapi\u002Fpublication\u002F37354974?&&labelLang=hun","《Ecological Informatics》2026年第96期：Zhuang等提出Diag-STFN——一种诊断时空多模态融合网络，用于全球收获前作物产量预测。该网络基于数据集特征选择模型结构，以确定是否需要时间趋势耦合和空间模块激活。在三种前置期（早、中、晚季）下，基于覆盖38国玉米和29国小麦的CY-Bench基准数据集进行评估。结果表明，所提方法在所有前置期均实现了两种作物的最低汇总NRMSE，并在MAPE和KGE等补充指标上保持领先。消融研究表明诊断模块选择提供了主要的性能提升；方差分解显示性能差异在国家之间大于模型之间。","《Ecological Informatics》96 (2026) 103860","2026-09-17T00:00:00Z",78,{"impact":84,"substance":83,"depth":84,"authority":85,"freshness":71,"relevant":22,"comment":194},"方法新颖、覆盖38国玉米与29国小麦的全球收获前产量预测研究，学术价值突出但产业落地尚早，适合作为前沿技术资讯收录。",[196],{"name":190,"url":188},[27,198,199,162,28,29],"农业人工智能","产量预测",[201,202],"Diag-STFN 作物产量预测","CY-Bench 玉米 小麦","Diag-STFN作物产量预测-3324",{"doi":9,"openalex_id":9,"authors":205,"venue":9,"cited_by_count":36,"oa_url":9,"card":206,"direction":210,"ingested_from":212},[],{"tldr":207,"method":208,"finding":209,"direction":210,"opportunity":211},"提出诊断式时空多模态融合网络Diag-STFN，实现全球收获前玉米小麦产量预测。","基于CY-Bench基准，按数据特征诊断选择时间趋势与空间模块，覆盖38国玉米2","各前置期均取得最低NRMSE，诊断模块选择贡献最大，国家间差异大于模型间差异。","农业人工智能与决策模型","可探索自适应诊断机制迁移至其他作物，并针对国家间差异开展区域化建模与不确定性量化。","agent","2026-09-24T00:04:02.684732Z",{"id":215,"title":216,"url":217,"summary":218,"summary_zh":219,"content":9,"source_name":220,"source_url":217,"published_at":221,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":222,"score_detail":223,"sources":225,"tags":227,"search_phrases":229,"slug":232,"view_count":36,"doi":233,"paper":234,"created_at":252},3177,"A comparative analysis on maize yield prediction using sentinel 2A and Landsat 8 satellite image in Sundarganj, Gaibandha, Bangladesh","https:\u002F\u002Fdoi.org\u002F10.3329\u002Fbjar.v51i1.92530","Maize is an important cereal crops in Bangladesh. Over the last two decades, its cultivation has increased promisingly, especially in the Northern part of Bangladesh. The effective estimation of crop yields at a regional scale holds significant importance in facilitating decision-making within the agricultural sector, thereby ensuring grain security. The traditional ground-based measurement techniques suffer from inefficiencies, and there exists a need for a reliable, precise, and effective method for estimating regional crop yields. This study used remote sensing (RS) techniques for forecasting pre-harvest maize yield to improve the management system. Currently, the normalized difference vegetation index (NDVI) is widely used to predict crop yield including maize. However, the present study used Landsat 8 (~ 30 m) and Sentinel 2A (~ 10 m) high resolution data for 2018-2019 and 2019-2020 to predict maize yield based on the year 2020-2021 at Sundarganj Upazila in Gaibandha district. The single cloud free image acquisition date based on maximum NDVI for both satellite images was used for each maize growing period to develop a yield prediction model. A regression model was performed between NDVI values and 20 farmers field-level maize yields. The absolute mean error of prediction was about 10.30% for Landsat 8 and 6.70% for Sentinel 2A compared to the actual maize yield during 2020-2021. The study revealed that NDVI data extracted from Sentinel 2A high resolution satellite images can be successfully used to predict the maize yield with appreciable accuracy. Finally, this study has demonstrated the efficacy of combining multi-temporal remote sensing data for accurate maize yield estimation, aiding agricultural authorities and production enterprises in the timely formulation and refinement of cropping strategies and management policies for the ongoing season. Bangladesh J. Agril. Res. 51(1): 501-521, March 2026","玉米是孟加拉国重要的谷类作物。过去二十年间，其种植面积增长显著，尤其是在孟加拉国北部地区。在区域尺度上有效估算作物产量对于促进农业部门决策、进而保障粮食安全具有重要意义。传统的地面测量技术效率低下，亟需一种可靠、精确且有效的区域作物产量估算方法。本研究采用遥感（RS）技术预测收获前玉米产量，以改进管理体系。目前，归一化植被指数（NDVI）被广泛用于预测包括玉米在内的作物产量。然而，本研究利用Landsat 8（约30 m）和Sentinel 2A（约10 m）高分辨率数据，基于2018—2019年和2019—2020年的数据，对盖班达县孙达尔甘杰乌帕齐拉2020—2021年的玉米产量进行预测。在每个玉米生长期，选取两颗卫星影像中NDVI最大值对应的单幅无云影像获取日期，用于建立产量预测模型。对NDVI值与20户农民田块级玉米产量进行回归建模。与2020—2021年实际玉米产量相比，Landsat 8的绝对平均预测误差约为10.30%，Sentinel 2A约为6.70%。研究表明，利用Sentinel 2A高分辨率卫星影像提取的NDVI数据可成功用于预测玉米产量，且精度令人满意。最后，本研究证明了结合多时相遥感数据进行准确玉米产量估算的有效性，有助于农业主管部门和生产企业在当季及时制定和完善种植策略与管理政策。Bangladesh J. Agril. Res. 51(1): 501-521, March 2026","Bangladesh Journal of Agricultural Research","2026-09-21T00:00:00Z",65,{"impact":21,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":224},"基于Sentinel 2A与Landsat 8的玉米遥感估产对比研究，方法清晰、误差数据具体，对遥感估产有参考价值，但属区域小尺度研究，公共影响有限。",[226],{"name":220,"url":217},[27,199,28,29,228],"NDVI",[230,231],"Sentinel 2A Landsat 8 玉米产量预测","孟加拉国 Sundarganj 玉米遥感估产","Sentinel2ALandsat8玉米产量预测-3177","10.3329\u002Fbjar.v51i1.92530",{"doi":233,"openalex_id":235,"authors":236,"venue":220,"cited_by_count":36,"oa_url":217,"card":247,"direction":66,"ingested_from":68},"W7213918280",[237,239,241,243,245],{"name":238,"orcid":9},"N Mohammad",{"name":240,"orcid":9},"MA Islam",{"name":242,"orcid":9},"MG Mahboob",{"name":244,"orcid":9},"MM Rahman",{"name":246,"orcid":9},"I Ahmed",{"tldr":248,"method":249,"finding":250,"direction":66,"opportunity":251},"用Sentinel 2A与Landsat 8的NDVI回归模型预测孟加拉国玉米产量并比较精度。","基于最大NDVI单期影像与20个农户地块产量做回归，比较两种卫星。","Sentinel 2A预测绝对平均误差6.70%，优于Landsat 8的10.30%。","可探索多时相NDVI与机器学习融合，提升小农户尺度玉米估产精度与迁移性。","2026-09-22T23:30:23.551878Z",{"id":254,"title":255,"url":256,"summary":257,"summary_zh":258,"content":9,"source_name":259,"source_url":256,"published_at":260,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":261,"score_detail":262,"sources":264,"tags":266,"search_phrases":268,"slug":271,"view_count":22,"doi":272,"paper":273,"created_at":306},3006,"Explainable spectral–image fusion multi-task learning for maize canopy biochemical and structural trait retrieval","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112450","Accurate and interpretable estimation of multiple maize canopy traits is important for proximal crop monitoring and high-throughput phenotyping. This study developed a spectral–image fusion multi-task learning framework (MM-MTL) for the simultaneous retrieval of chlorophyll index (Chl index), leaf area index (LAI), nitrogen balance index (NBI), and anthocyanin index (Anth index). Proximal hyperspectral observations were collected using a Specim IQ camera covering 400–1000 nm with 204 spectral bands. For each observation, an ROI-mean spectral vector was extracted to retain fine-grained canopy reflectance information, while a co-registered pseudo-RGB image derived from visible bands of the same hyperspectral cube preserved two-dimensional canopy structure and visible appearance. MM-MTL integrates spectral and image feature extraction, task-specific fusion, and uncertainty-weighted multi-task learning to jointly estimate the four traits. A total of 1,023 valid samples collected from nine field campaigns across the 2024 and 2025 growing seasons were used for model development and evaluation. Under plot-grouped five-fold cross-validation, MM-MTL achieved R 2 values of 0.872, 0.885, 0.722, and 0.807 for Chl index, LAI, NBI, and Anth index, respectively, and consistently outperformed the single-task, single-representation, and conventional regression baselines. Performance decreased under more challenging generalization settings, with R 2 values ranging from 0.543 to 0.680 under leave-one-campaign-out validation and from 0.425 to 0.640 under bidirectional cross-year validation. Ablation and post-hoc analyses further showed that preserving image spatial organization improved prediction, while task-wise routing, input-representation masking, wavelength perturbation, and cross-fold stability analyses revealed trait-dependent use of spectral and spatial information. These results demonstrate that complementary spectral and spatial representations derived from the same hyperspectral observation can improve multi-trait maize canopy retrieval, while transfer across acquisition campaigns, years, and field environments remains an important direction for further improvement.","准确且可解释地估算多个玉米冠层性状，对于近地作物监测和高通量表型分析具有重要意义。本研究开发了一种光谱—图像融合多任务学习框架（MM-MTL），用于同时反演叶绿素指数（Chl index）、叶面积指数（LAI）、氮平衡指数（NBI）和花青素指数（Anth index）。近地高光谱观测使用Specim IQ相机采集，覆盖400–1000 nm，共204个光谱波段。对于每次观测，提取ROI均值光谱向量以保留细粒度冠层反射率信息，同时从同一高光谱立方体的可见光波段生成配准的伪RGB图像，以保留二维冠层结构和可见外观。MM-MTL集成了光谱与图像特征提取、任务特定融合以及不确定性加权多任务学习，以联合估算这四种性状。研究使用2024年和2025年生长季9次田间试验采集的共计1,023个有效样本进行模型开发与评估。在按小区分组的五折交叉验证下，MM-MTL对Chl index、LAI、NBI和Anth index的R²分别为0.872、0.885、0.722和0.807，且持续优于单任务、单表征和传统回归基线。在更具挑战性的泛化设置下，模型性能有所下降，留一试验验证的R²范围为0.543–0.680，双向跨年验证的R²范围为0.425–0.640。消融分析和事后分析进一步表明，保留图像空间组织可提升预测性能，而任务路由、输入表征掩蔽、波长扰动和跨折稳定性分析揭示了光谱与空间信息的性状依赖性利用方式。这些结果表明，从同一高光谱观测中提取的互补光谱与空间表征可改善多性状玉米冠层反演，而跨采集试验、年份和田间环境的迁移仍是未来改进的重要方向。","Computers and Electronics in Agriculture","2026-09-19T00:00:00Z",81,{"impact":84,"substance":83,"depth":84,"authority":85,"freshness":86,"relevant":22,"comment":263},"提出光谱-图像融合多任务学习框架，1023份样本跨两年验证，方法新颖且结论可靠，对作物高通量表型研究有实质参考价值。",[265],{"name":259,"url":256},[27,198,28,29,267],"高通量表型",[269,270],"玉米冠层 多任务学习 高光谱","Specim IQ 玉米 表型","玉米冠层多任务学习高光谱-3006","10.1016\u002Fj.compag.2026.112450",{"doi":272,"openalex_id":274,"authors":275,"venue":259,"cited_by_count":36,"oa_url":256,"card":301,"direction":66,"ingested_from":68},"W7213658705",[276,278,280,282,284,287,289,292,294,296,298],{"name":277,"orcid":9},"Penglei Zhang",{"name":279,"orcid":9},"Tianbo Hao",{"name":281,"orcid":9},"Zhuoyuan Zhao",{"name":283,"orcid":9},"Hong Sun",{"name":285,"orcid":286},"Yelu Zeng","https:\u002F\u002Forcid.org\u002F0000-0003-4267-1841",{"name":288,"orcid":9},"Zheng Cui",{"name":290,"orcid":291},"Ta Na","https:\u002F\u002Forcid.org\u002F0000-0002-1348-5655",{"name":293,"orcid":9},"Lang Qiao",{"name":295,"orcid":9},"Durval Dourado Neto",{"name":297,"orcid":9},"Feng Yang",{"name":299,"orcid":300},"Jingzhu Wu","https:\u002F\u002Forcid.org\u002F0000-0002-8386-1038",{"tldr":302,"method":303,"finding":304,"direction":66,"opportunity":305},"提出光谱-图像融合多任务学习框架，同时反演玉米冠层四个生化与结构性状。","Specim IQ高光谱与伪RGB融合，不确定性加权多任务学习，1023样本交叉","融合模型精度优于单任务基线，但跨年份与跨环境泛化性能明显下降。","可研究跨年份\u002F跨环境域适应与迁移学习，提升多性状反演泛化能力。","2026-09-20T23:30:01.739142Z",{"id":308,"title":309,"url":310,"summary":311,"summary_zh":312,"content":9,"source_name":313,"source_url":310,"published_at":314,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":315,"score_detail":316,"sources":318,"tags":320,"search_phrases":322,"slug":325,"view_count":36,"doi":326,"paper":327,"created_at":355},2660,"Red-Edge Information in Agricultural Remote Sensing: From Spectral Theory to Explainable Machine Learning","https:\u002F\u002Fdoi.org\u002F10.3390\u002Frs18183180","The red-edge (RE) spectral region has become a central component of agricultural remote sensing because it captures physiologically meaningful changes in chlorophyll content, canopy structure and vegetation functioning. The availability of dedicated RE bands on modern multispectral satellites and advances in hyperspectral sensing have stimulated widespread applications for crop monitoring, nutrient assessment, stress detection and yield prediction. However, reported improvements over conventional visible–near-infrared (VIS–NIR) approaches remain highly variable, and the mechanisms governing when and why RE information provides additional value are often poorly synthesised. This review presents a conceptual framework that links the physical and physiological basis of RE reflectance with its condition-dependent agronomic performance and its emerging role within modern machine learning (ML) systems. We first examine how pigment absorption, canopy structure and sensor characteristics jointly determine the representation of RE information from hyperspectral measurements to operational multispectral observations. We then synthesise evidence demonstrating that the agronomic value of RE information is strongly dependent on crop characteristics, phenological stage, environmental conditions and observation geometry, explaining much of the variability reported across previous studies. Finally, we show how recent advances in ML and explainable artificial intelligence have changed the interpretation of RE information. Rather than evaluating RE-derived vegetation indices in isolation, contemporary predictive frameworks integrate RE observations with complementary spectral, climatic, structural and temporal predictors, allowing their physiological contribution to be quantified within multidimensional models. We conclude that future value of RE remote sensing will require not only continued advances in spectral measurement and vegetation index development, but also improved interpretation, transferability and operational integration of physiologically meaningful RE information within explainable, multi-source agricultural monitoring systems.","红边（RE）光谱区已成为农业遥感的核心组成部分，因为它能够捕捉叶绿素含量、冠层结构和植被功能等方面具有生理意义的变化。现代多光谱卫星上专用红边波段的可用性以及高光谱传感技术的进步，推动了其在作物监测、养分评估、胁迫检测和产量预测中的广泛应用。然而，相较于传统可见光—近红外（VIS–NIR）方法所报道的改进效果仍高度可变，而关于红边信息何时以及为何提供额外价值的机制往往缺乏系统梳理。本综述提出了一个概念框架，将红边反射率的物理与生理基础与其条件依赖的农学表现及其在现代机器学习（ML）系统中新兴的作用联系起来。我们首先探讨色素吸收、冠层结构和传感器特性如何共同决定从高光谱测量到业务化多光谱观测中红边信息的表征。随后，我们综合证据表明，红边信息的农学价值强烈依赖于作物特征、物候阶段、环境条件和观测几何，这解释了以往研究中报道的大部分变异性。最后，我们展示了机器学习和可解释人工智能的最新进展如何改变了对红边信息的解读。当代预测框架不再孤立地评估红边衍生的植被指数，而是将红边观测与互补的光谱、气候、结构和时间预测因子相结合，从而在多维模型中量化其生理贡献。我们得出结论：红边遥感的未来价值不仅需要光谱测量和植被指数开发的持续进步，还需要在可解释的多源农业监测系统中改进对具有生理意义的红边信息的解读、可迁移性和业务化整合。","Remote Sensing","2026-09-16T00:00:00Z",82,{"impact":84,"substance":83,"depth":84,"authority":85,"freshness":13,"relevant":22,"comment":317},"系统综述红边遥感从光谱机理到可解释机器学习的农学价值条件，方法框架新颖、结论可靠，对作物监测与产量预测有实质参考意义。",[319],{"name":313,"url":310},[27,198,29,321,31],"作物监测",[323,324],"农业人工智能 作物监测 智慧农业 植被指数","农业人工智能 作物监测","农业人工智能作物监测智慧农业植被指数-2660","10.3390\u002Frs18183180",{"doi":326,"openalex_id":328,"authors":329,"venue":313,"cited_by_count":36,"oa_url":310,"card":350,"direction":66,"ingested_from":68},"W7213344870",[330,333,335,338,341,344,347],{"name":331,"orcid":332},"Ignacio Fuentes","https:\u002F\u002Forcid.org\u002F0000-0001-7066-7482",{"name":334,"orcid":9},"Nikolas Hoskin",{"name":336,"orcid":337},"Patrick Filippi","https:\u002F\u002Forcid.org\u002F0000-0003-3573-084X",{"name":339,"orcid":340},"Abhasha Joshi","https:\u002F\u002Forcid.org\u002F0000-0002-1422-465X",{"name":342,"orcid":343},"Yi Yu","https:\u002F\u002Forcid.org\u002F0000-0002-1140-2713",{"name":345,"orcid":346},"Thomas F. A. Bishop","https:\u002F\u002Forcid.org\u002F0000-0002-6723-7323",{"name":348,"orcid":349},"Dhahi Al-Shammari","https:\u002F\u002Forcid.org\u002F0000-0001-6608-8322",{"tldr":351,"method":352,"finding":353,"direction":66,"opportunity":354},"综述红边遥感在农业中的物理基础、条件依赖性与可解释机器学习中的新角色。","文献综述，整合光谱理论、多光谱\u002F高光谱数据与可解释AI方法。","红边信息的农学价值高度依赖作物、物候、环境与观测几何，需多源融合与可解释建模。","可研究红边信息在不同作物-物候-环境组合下的可迁移性，并构建可解释多源融合模型。","2026-09-16T23:30:28.719858Z"]