[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3086":3,"related-3086":53},{"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":23,"tags":25,"search_phrases":31,"slug":34,"view_count":35,"doi":36,"paper":37,"created_at":52},3086,"UAV photogrammetry and remote sensing for coastal biodiversity and habitat conservation","https:\u002F\u002Fdoi.org\u002F10.6008\u002Fcbpc2318-2881.2026.001.0002","Coastal ecosystems support high biological diversity while experiencing rapid change caused by shoreline dynamics, sea-level rise, extreme events, pollution, urban development, and intensive resource use. Conventional field surveys provide essential ecological observations but often lack the spatial extent or repetition needed to describe heterogeneous and short-lived coastal conditions. This review evaluates how uncrewed aerial vehicle photogrammetry and remote sensing can support habitat assessment, species monitoring, restoration, and conservation decisions. A structured narrative synthesis was undertaken across studies on image-based mapping, multispectral and thermal observation, laser scanning, direct georeferencing, automated classification, and environmental change detection. The evidence shows that these platforms are most useful when surveys are designed around explicit ecological variables rather than image production alone. RGB imagery and structure-from-motion models provide detailed surface geometry; multispectral, thermal, and laser sensors add information on vegetation condition, moisture, temperature, and three-dimensional structure. Repeated surveys can reveal erosion, inundation, habitat fragmentation, restoration performance, and wildlife distribution at operational scales. Major constraints include variable illumination, water reflectance, wind, tides, positional uncertainty, disturbance risk, regulation, limited training data, and inconsistent validation. Effective programs therefore require standardized timing, field calibration, uncertainty reporting, ethical flight practice, and workflows that convert mapped patterns into management indicators. Future progress depends on sensor integration, explainable automation, interoperable time series, and sustained cooperation between remote-sensing specialists, ecologists, managers, and coastal communities.","沿海生态系统维持着高度的生物多样性，同时经历着由岸线动态、海平面上升、极端事件、污染、城市发展和密集资源利用所引发的快速变化。传统野外调查提供了重要的生态观测，但往往缺乏描述异质性和短生命周期沿海状况所需的空间范围或重复频次。本文综述评估了无人驾驶航空器摄影测量与遥感如何支持栖息地评估、物种监测、恢复和保护决策。我们对基于影像的制图、多光谱与热红外观测、激光扫描、直接地理配准、自动分类和环境变化检测等研究进行了结构化叙述性综合。证据表明，当调查围绕明确的生态变量而非仅以影像生产为目的进行设计时，这些平台最为有用。RGB影像和运动恢复结构（structure-from-motion）模型可提供详细的地表几何信息；多光谱、热红外和激光传感器则补充了植被状况、湿度、温度和三维结构信息。重复调查能够在业务尺度上揭示侵蚀、淹没、栖息地破碎化、恢复成效和野生动物分布。主要制约因素包括光照变化、水体反射、风、潮汐、位置不确定性、干扰风险、法规、训练数据有限以及验证不一致。因此，有效的项目需要标准化的时间安排、野外校准、不确定性报告、符合伦理的飞行实践，以及将制图格局转化为管理指标的工作流程。未来的进展取决于传感器集成、可解释的自动化、可互操作的时间序列，以及遥感专家、生态学家、管理者和沿海社区之间的持续合作。",null,"Nature and Conservation","2026-09-18T00:00:00Z","论文",10,false,64,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":17,"relevant":21,"comment":22},8,18,17,13,1,"综述系统梳理无人机摄影测量与遥感在海岸生境评估、物种监测与修复中的应用与局限，方法学价值明确，但偏生态保护领域，与农业信息化关联间接，属细分方向参考。",[24],{"name":10,"url":6},[26,27,28,29,30],"无人机","遥感","生物多样性","生态监测","海岸生态",[32,33],"无人机 摄影测量 海岸生态","UAV 遥感 生物多样性监测","无人机摄影测量海岸生态-3086",0,"10.6008\u002Fcbpc2318-2881.2026.001.0002",{"doi":36,"openalex_id":38,"authors":39,"venue":10,"cited_by_count":35,"oa_url":43,"card":44,"direction":50,"ingested_from":51},"W7213604527",[40],{"name":41,"orcid":42},"Murat Yakar","https:\u002F\u002Forcid.org\u002F0000-0002-2664-6251","https:\u002F\u002Fwww.natureandconservation.com\u002Findex.php\u002Fnature\u002Farticle\u002Fdownload\u002F8949\u002F5099",{"tldr":45,"method":46,"finding":47,"direction":48,"opportunity":49},"综述无人机摄影测量与遥感在海岸生物多样性和栖息地保护中的应用与局限。","结构化叙述性综述，涵盖RGB、多光谱、热红外、激光扫描及自动分类等研究。","围绕明确生态变量设计调查时最有效，但受光照、风潮、法规和验证不一致等制约。","农业遥感与作物表型","可探索多传感器融合与可解释自动化，构建标准化时间序列以支撑海岸管理指标。","数字乡村与农业信息化","openalex","2026-09-21T23:30:37.840826Z",{"total":54,"page":21,"page_size":54,"items":55},6,[56,150,181,217,268,321],{"id":57,"title":58,"url":59,"summary":60,"summary_zh":61,"content":9,"source_name":62,"source_url":59,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":63,"score_detail":64,"sources":69,"tags":71,"search_phrases":75,"slug":78,"view_count":35,"doi":79,"paper":80,"created_at":149},3082,"The PSInet Plant Water Potential Database: advancing new perspectives on plant water status, traits, and hydraulic processes","https:\u002F\u002Fdoi.org\u002F10.64898\u002F2026.09.17.752364","Water potential gradients drive water flow within and between soils and plants, and the internal plant water potential controls a wide range of physiological processes including photosynthesis, growth, and mortality. Notwithstanding this clear relevance for many critical aspects of ecosystem function, water potential data have historically been relatively inaccessible and unnetworked. The absence of a centralized repository for plant water potential time series limits our ability to integrate a wealth of ecophysiological information from other networks and from remote sensing. Closing this gap is necessary to address unresolved questions about plant responses to drought and heat stress, and to make confident predictions about plant and ecosystem function in a warming world. Here, we introduce the PSInet database -- a global collection of plant water potential time series from 285 datasets representing 523 species. We present the workflow that guided database development and evaluate its key features. Through a series of preliminary analyses, we then highlight the potential of the PSInet database for applications including: a) advancing plant water use strategy frameworks; b) disentangling the impacts of soil versus atmospheric drought stress; c) assessing the long-held assumption of pre-dawn equilibration of ecosystem water potential; d) understanding the risk of drought-driven mortality; and e) benchmarking remote-sensing data products and land-surface models.","水势梯度驱动着土壤与植物内部及二者之间的水分流动，而植物内部水势调控着包括光合作用、生长和死亡在内的一系列广泛生理过程。尽管水势数据与生态系统功能的诸多关键方面明显相关，但此类数据历来相对难以获取且缺乏网络化整合。植物水势时间序列缺乏集中式存储库，这限制了我们整合来自其他网络和遥感手段的大量生态生理信息的能力。弥合这一差距对于解答有关植物对干旱和热胁迫响应的未解问题，以及在全球变暖背景下对植物和生态系统功能作出可靠预测，都是必要的。在此，我们介绍PSInet数据库——一个全球性的植物水势时间序列集合，涵盖285个数据集、523个物种。我们展示了指导数据库开发的工作流程，并评估了其关键特征。通过一系列初步分析，我们进而凸显了PSInet数据库在以下应用方面的潜力：a) 推进植物水分利用策略框架；b) 区分土壤干旱胁迫与大气干旱胁迫的影响；c) 评估长期以来的生态系统水势黎明前平衡假设；d) 理解干旱驱动死亡的风险；以及e) 为遥感数据产品和陆面模型提供基准验证。","bioRxiv (Cold Spring Harbor Laboratory)",85,{"impact":65,"substance":66,"depth":18,"authority":67,"freshness":17,"relevant":21,"comment":68},22,23,14,"全球植物水势数据库整合285个数据集、523个物种，为干旱胁迫与遥感模型验证提供关键数据基础设施，专业价值突出。",[70],{"name":62,"url":59},[27,72,29,73,74],"干旱胁迫","植物水分","数据库",[76,77],"PSInet 植物水势数据库","植物水势 时间序列","PSInet植物水势数据库-3082","10.64898\u002F2026.09.17.752364",{"doi":79,"openalex_id":81,"authors":82,"venue":62,"cited_by_count":35,"oa_url":143,"card":144,"direction":48,"ingested_from":51},"W7213559802",[83,86,89,92,95,98,101,104,107,110,113,116,119,122,125,128,131,134,137,140],{"name":84,"orcid":85},"Jessica Guo","https:\u002F\u002Forcid.org\u002F0000-0002-9566-9182",{"name":87,"orcid":88},"Ana Maria Restrepo Acevedo","https:\u002F\u002Forcid.org\u002F0000-0003-4861-838X",{"name":90,"orcid":91},"Marvin Browne","https:\u002F\u002Forcid.org\u002F0000-0002-9640-0759",{"name":93,"orcid":94},"Daniel M. Johnson","https:\u002F\u002Forcid.org\u002F0000-0003-1015-9560",{"name":96,"orcid":97},"Katherine A. McCulloh","https:\u002F\u002Forcid.org\u002F0000-0003-0801-3968",{"name":99,"orcid":100},"Jesse B. Nippert","https:\u002F\u002Forcid.org\u002F0000-0002-7939-342X",{"name":102,"orcid":103},"Rafael Poyatos","https:\u002F\u002Forcid.org\u002F0000-0003-0521-2523",{"name":105,"orcid":106},"Steven A. Kannenberg","https:\u002F\u002Forcid.org\u002F0000-0002-4097-9140",{"name":108,"orcid":109},"Daniel P. Beverly","https:\u002F\u002Forcid.org\u002F0000-0002-1267-4147",{"name":111,"orcid":112},"K. Arthur Endsley","https:\u002F\u002Forcid.org\u002F0000-0001-9722-8092",{"name":114,"orcid":115},"Andrew F. Feldman","https:\u002F\u002Forcid.org\u002F0000-0003-1547-6995",{"name":117,"orcid":118},"Alexandra G. Konings","https:\u002F\u002Forcid.org\u002F0000-0002-2810-1722",{"name":120,"orcid":121},"Yanlan Liu","https:\u002F\u002Forcid.org\u002F0000-0001-5129-6284",{"name":123,"orcid":124},"Jordi Martínez‐Vilalta","https:\u002F\u002Forcid.org\u002F0000-0002-2332-7298",{"name":126,"orcid":127},"William M. Hammond","https:\u002F\u002Forcid.org\u002F0000-0002-2904-810X",{"name":129,"orcid":130},"Kevin R. Hultine","https:\u002F\u002Forcid.org\u002F0000-0001-9747-6037",{"name":132,"orcid":133},"Lauren E. L. Lowman","https:\u002F\u002Forcid.org\u002F0000-0003-2960-7095",{"name":135,"orcid":136},"Jeffrey S. Dukes","https:\u002F\u002Forcid.org\u002F0000-0001-9482-7743",{"name":138,"orcid":139},"Julia K. Green","https:\u002F\u002Forcid.org\u002F0000-0002-8466-2313",{"name":141,"orcid":142},"Lawren Sack","https:\u002F\u002Forcid.org\u002F0000-0002-7009-7202","https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2026\u002F09\u002F18\u002F2026.09.17.752364.full.pdf",{"tldr":145,"method":146,"finding":147,"direction":48,"opportunity":148},"构建全球植物水势时间序列数据库PSInet，整合285个数据集523个物种。","汇集全球植物水势时间序列数据，建立数据库并开展初步分析。","该数据库可支撑植物水分策略、干旱胁迫、遥感与模型基准等研究。","可基于该数据库融合遥感与陆面模型，发展作物水分状态监测与干旱预警方法。","2026-09-21T23:30:27.557264Z",{"id":151,"title":152,"url":153,"summary":154,"summary_zh":9,"content":9,"source_name":155,"source_url":9,"published_at":156,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":157,"score_detail":158,"sources":162,"tags":164,"search_phrases":168,"slug":171,"view_count":35,"doi":9,"paper":172,"created_at":180},2855,"UAV无人机高光谱图像土壤盐度制图(湿度校正)——MDPI Agronomy","https:\u002F\u002Fwww.mdpi.com\u002F2073-4395\u002F16\u002F18\u002F1812","研究评估了6种光谱变换方法(原始反射率Ref、一阶导数FDR、PDS、OSC、FDR+PDS、FDR+OSC),结合3种机器学习算法(KNN、SVR、MLP)。进一步开发了集成这些基础学习者的Stacking集成模型,以提高湿度干扰下土壤盐度反演的精度。结果表明,Stacking模型在评估模型中达到最高的精度和稳定性。FDR+OSC-Stacking组合实现最佳验证性能,R²p=0.87,RMSEP=0.67 mS·cm⁻¹,RPD=2.93。FDR+OSC-Stacking组合成功应用于UAV高光谱图像,用于EC1:5的空间制图。来自吉林大学。","MDPI Agronomy","2026-09-15T00:00:00Z",75,{"impact":159,"substance":160,"depth":19,"authority":20,"freshness":17,"relevant":21,"comment":161},16,21,"方法组合新颖、验证指标扎实的无人机高光谱盐分制图研究，属细分领域实质进展，值得精选。",[163],{"name":155,"url":153},[165,26,166,27,167],"智慧农业","机器学习","土壤盐渍化",[169,170],"土壤盐渍化 智慧农业 机器学习 无人机","土壤盐渍化 智慧农业","土壤盐渍化智慧农业机器学习无人机-2855",{"doi":9,"openalex_id":9,"authors":173,"venue":9,"cited_by_count":35,"oa_url":9,"card":174,"direction":48,"ingested_from":179},[],{"tldr":175,"method":176,"finding":177,"direction":48,"opportunity":178},"用无人机高光谱结合Stacking集成模型实现湿度干扰下的土壤盐度制图。","6种光谱变换与KNN、SVR、MLP及Stacking集成，基于UAV高光谱数据","FDR+OSC-Stacking最优，R²p=0.87、RMSEP=0.67 mS·cm⁻¹、RPD","可探索多时相\u002F多传感器融合与迁移学习，提升不同湿度与区域下盐度反演泛化性。","agent","2026-09-18T00:03:30.822732Z",{"id":182,"title":183,"url":184,"summary":185,"summary_zh":9,"content":9,"source_name":186,"source_url":184,"published_at":156,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":187,"score_detail":188,"sources":191,"tags":193,"search_phrases":196,"slug":199,"view_count":35,"doi":200,"paper":201,"created_at":216},2647,"Agricultural drone use, pesticide reduction, and biodiversity restoration: evidence from China","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs10109-026-00522-6","Agricultural drone use, pesticide reduction, and biodiversity restoration: evidence from China。Journal of Geographical Systems","Journal of Geographical Systems",77,{"impact":18,"substance":189,"depth":19,"authority":67,"freshness":17,"relevant":21,"comment":190},20,"基于中国证据的学术论文，探讨无人机施药与农药减量、生物多样性恢复的关系，方法新颖且结论具政策参考价值，但属细分领域研究，影响层级有限。",[192],{"name":186,"url":184},[165,194,27,195,28],"农业无人机","农药减量",[197,198],"农业无人机 生物多样性 农药减量 智慧农业","农业无人机 生物多样性","农业无人机生物多样性农药减量智慧农业-2647","10.1007\u002Fs10109-026-00522-6",{"doi":200,"openalex_id":202,"authors":203,"venue":186,"cited_by_count":35,"oa_url":9,"card":9,"direction":215,"ingested_from":51},"W7213342483",[204,207,210,213],{"name":205,"orcid":206},"Jianjun Tang","https:\u002F\u002Forcid.org\u002F0000-0002-6994-2093",{"name":208,"orcid":209},"Jingru Chen","https:\u002F\u002Forcid.org\u002F0009-0009-5773-5482",{"name":211,"orcid":212},"Jingyang Yan","https:\u002F\u002Forcid.org\u002F0000-0001-8330-6272",{"name":214,"orcid":9},"Fei Li","智慧农业 \u002F 农业物联网","2026-09-16T23:30:12.279104Z",{"id":218,"title":219,"url":220,"summary":221,"summary_zh":222,"content":9,"source_name":223,"source_url":220,"published_at":224,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":225,"score_detail":226,"sources":229,"tags":231,"search_phrases":234,"slug":237,"view_count":35,"doi":238,"paper":239,"created_at":267},2500,"Estimation of crop canopy nitrogen content using deep transfer learning with PROSAIL-PRO model and UAV hyperspectral imagery","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112385","Canopy nitrogen content (CNC) is a key indicator for assessing crop nitrogen status. The non-destructive and rapid estimation of CNC can be performed using unmanned aerial vehicle (UAV)-based hyperspectral remote sensing on large-scale; however, it is often constrained by the scarcity of ground truth data relative to model complexity, which can lead to overfitting and poor generalizability. To address these challenges, a novel inversion framework was proposed by integrating the PROSAIL-PRO physical model with deep transfer learning. Generalized physical features were extracted using pre-trained deep neural network on large-scale PROSAIL-PRO simulated spectra. Subsequently, a fine-tuning strategy was applied in which shallow-level parameters were frozen while deep-level parameters were updated, thereby effectively decoupling intrinsic physical features from site-specific variations. Four deep learning architectures including convolutional neural network (CNN), Residual Neural Network (ResNet18), and their respective channel attention-enhanced variants were evaluated and compared with six classical statistical models including a backpropagation neural network (BPNN). The results demonstrated that transfer-learning-optimized deep models significantly outperformed both baseline and traditional methods in terms of accuracy and generalizability. Specifically, the CNN-based transfer model achieved the best performance on the wheat dataset ( R 2 = 0.8597 and RMSECV = 1.7642), whereas the ResNet18-based transfer model achieved the best performance on the maize dataset ( R 2 = 0.6921 and RMSECV = 2.7944). These findings confirmed that PROSAIL-PRO driven deep transfer learning effectively mitigated overfitting in small-sample hyperspectral datasets. By ensuring high-precision inversion and robust generalization, the proposed physics-guided data-driven fusion approach provides a promising solution for crop nitrogen monitoring.","冠层氮含量（Canopy Nitrogen Content, CNC）是评估作物氮素状况的关键指标。基于无人机（UAV）高光谱遥感可以在大尺度上对CNC进行无损快速估测；然而，该任务常受限于地面真值数据相对模型复杂度而言较为稀缺的问题，这会导致过拟合和泛化能力较差。为应对这些挑战，该研究提出了一种将PROSAIL-PRO物理模型与深度迁移学习相结合的新型反演框架。利用在大规模PROSAIL-PRO模拟光谱上预训练的深度神经网络提取广义物理特征。随后，采用冻结浅层参数、更新深层参数的微调策略，从而有效解耦内在物理特征与站点特异性变异。研究评估了四种深度学习架构，包括卷积神经网络（CNN）、残差神经网络（ResNet18）及其各自的通道注意力增强变体，并与包括反向传播神经网络（BPNN）在内的六种经典统计模型进行了比较。结果表明，经迁移学习优化的深度模型在精度和泛化能力方面均显著优于基线和传统方法。具体而言，基于CNN的迁移模型在小麦数据集上取得了最佳性能（R² = 0.8597，RMSECV = 1.7642），而基于ResNet18的迁移模型在玉米数据集上取得了最佳性能（R² = 0.6921，RMSECV = 2.7944）。这些发现证实，PROSAIL-PRO驱动的深度迁移学习有效缓解了小样本高光谱数据集中的过拟合问题。通过确保高精度反演和稳健泛化，所提出的物理引导的数据驱动融合方法为作物氮素监测提供了一种有前景的解决方案。","Computers and Electronics in Agriculture","2026-09-14T00:00:00Z",81,{"impact":18,"substance":65,"depth":18,"authority":67,"freshness":227,"relevant":21,"comment":228},9,"将PROSAIL-PRO物理模型与深度迁移学习结合，缓解小样本高光谱反演过拟合，方法新颖且验证扎实，对作物氮素遥感监测有实用价值。",[230],{"name":223,"url":220},[165,26,232,27,233],"农业人工智能","作物氮素监测",[235,236],"作物氮素监测 农业人工智能 智慧农业 无人机","作物氮素监测 农业人工智能","作物氮素监测农业人工智能智慧农业无人机-2500","10.1016\u002Fj.compag.2026.112385",{"doi":238,"openalex_id":240,"authors":241,"venue":223,"cited_by_count":35,"oa_url":220,"card":262,"direction":48,"ingested_from":51},"W7212964562",[242,244,246,248,250,253,255,257,260],{"name":243,"orcid":9},"Jing Zhao",{"name":245,"orcid":9},"Hong Li",{"name":247,"orcid":9},"Junping Liu",{"name":249,"orcid":9},"Wei Chen",{"name":251,"orcid":252},"Xin Guo","https:\u002F\u002Forcid.org\u002F0000-0002-1583-5364",{"name":254,"orcid":9},"Yunlong Wu",{"name":256,"orcid":9},"Menglong Zhao",{"name":258,"orcid":259},"Junaid Nawaz Chauhdary","https:\u002F\u002Forcid.org\u002F0000-0001-7398-5646",{"name":261,"orcid":9},"Zhaoxia Yan",{"tldr":263,"method":264,"finding":265,"direction":48,"opportunity":266},"融合PROSAIL-PRO物理模型与深度迁移学习，用无人机高光谱估算作物冠层氮含量。","PROSAIL-PRO模拟光谱预训练CNN\u002FResNet18，冻结浅层微调深层，","迁移学习模型精度与泛化性最优，小麦R²=0.86、玉米R²=0.69，缓解小样本过拟合。","可探索多作物多生育期迁移、物理模型参数不确定性传播及跨传感器泛化能力。","2026-09-15T23:30:01.518007Z",{"id":269,"title":270,"url":271,"summary":272,"summary_zh":273,"content":9,"source_name":274,"source_url":271,"published_at":275,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":276,"score_detail":277,"sources":279,"tags":281,"search_phrases":283,"slug":286,"view_count":35,"doi":287,"paper":288,"created_at":320},2320,"Genotype-Aware Prediction of Soybean Seed Composition from Multimodal UAV Imagery of the Standing Crop","https:\u002F\u002Fdoi.org\u002F10.3390\u002Frs18183121","Geospatial artificial intelligence (GeoAI) integrates multimodal remote sensing with deep learning to model complex agricultural systems at scale. Within this framework, accurate and non-destructive prediction of seed composition from in-season standing crops is essential for breeding and precision agriculture. This study developed an end-to-end convolutional neural network (CNN) framework to estimate eight seed traits (protein, oil, sucrose, fiber, starch, ash, complex and simple carbohydrates) from UAV-based multisensor imagery and associated genotype and phenological metadata. A total of 372 soybean samples were collected over two growing seasons (2020–2021) from two fields in Missouri, with UAV flights capturing multispectral (MSI), thermal (THR), and LiDAR (LDR) data at four time points spanning vegetative to reproductive growth stages. CNN models were trained in single- and multi-date configurations, incorporating genotype (GEN) and days after sowing (DAS) as additional features. The highest accuracy was achieved for sucrose (R2 = 0.80), followed by simple carbohydrate (R2 = 0.70) and starch (R2 = 0.55), with notable gains from GEN and DAS. Multi-date models incorporating earlier acquisitions often matched or outperformed later or all-date combinations. Among modalities, MSI provided the most robust estimates, with limited added value from LDR or THR. Unlike feature-based pipelines prone to multicollinearity, this image-to-trait approach enables automated, scalable prediction of soybean seed composition for in-season, field-level assessment.","地理空间人工智能（GeoAI）将多模态遥感与深度学习相结合，以在大尺度上对复杂农业系统进行建模。在该框架下，对当季未收获作物进行准确且无损的种子成分预测，对于育种和精准农业至关重要。本研究开发了一种端到端的卷积神经网络（CNN）框架，利用基于无人机（UAV）的多传感器影像以及相关的基因型和物候元数据，估算八种种子性状（蛋白质、油分、蔗糖、纤维、淀粉、灰分、复杂碳水化合物和简单碳水化合物）。研究在2020—2021两个生长季内，从密苏里州两块田地共采集372份大豆样本，无人机飞行在从营养生长期到生殖生长期的四个时间点获取了多光谱（MSI）、热红外（THR）和激光雷达（LDR）数据。CNN模型以单日期和多日期配置进行训练，并将基因型（GEN）和播种后天数（DAS）作为附加特征纳入。蔗糖的估算精度最高（R² = 0.80），其次为简单碳水化合物（R² = 0.70）和淀粉（R² = 0.55），且GEN和DAS的加入带来了显著提升。纳入早期采集数据的多日期模型往往与后期或全日期组合的表现相当，甚至更优。在各模态中，MSI提供了最稳健的估算结果，而LDR或THR的附加价值有限。与易受多重共线性影响的特征工程流程不同，这种从图像到性状的方法能够实现大豆种子成分的自动化、可扩展预测，用于当季田块尺度的评估。","Remote Sensing","2026-09-11T00:00:00Z",80,{"impact":18,"substance":65,"depth":18,"authority":67,"freshness":17,"relevant":21,"comment":278},"基于多模态无人机影像与基因型信息的大豆籽粒成分无损预测研究，方法新颖、数据扎实，对智慧育种与精准农业有参考价值。",[280],{"name":274,"url":271},[165,26,232,27,282],"大豆育种",[284,285],"农业人工智能 大豆育种 智慧农业 无人机","农业人工智能 大豆育种","农业人工智能大豆育种智慧农业无人机-2320","10.3390\u002Frs18183121",{"doi":287,"openalex_id":289,"authors":290,"venue":274,"cited_by_count":35,"oa_url":271,"card":315,"direction":48,"ingested_from":51},"W7212223520",[291,294,297,300,303,305,307,310,313],{"name":292,"orcid":293},"Vasit Sagan","https:\u002F\u002Forcid.org\u002F0000-0003-4375-2096",{"name":295,"orcid":296},"Kristen Rhodes","https:\u002F\u002Forcid.org\u002F0000-0002-8469-5043",{"name":298,"orcid":299},"Sourav Bhadra","https:\u002F\u002Forcid.org\u002F0000-0002-5832-4695",{"name":301,"orcid":302},"Haireti Alifu","https:\u002F\u002Forcid.org\u002F0000-0002-7369-6657",{"name":304,"orcid":9},"Aviskar Giri",{"name":306,"orcid":9},"Ashutosh Pawar",{"name":308,"orcid":309},"Bishal Roy","https:\u002F\u002Forcid.org\u002F0000-0001-9912-5505",{"name":311,"orcid":312},"Supria Sarkar","https:\u002F\u002Forcid.org\u002F0000-0001-9467-5786",{"name":314,"orcid":9},"Felix Fritschi",{"tldr":316,"method":317,"finding":318,"direction":48,"opportunity":319},"用无人机多模态影像与基因型数据训练CNN，预测大豆八种种子成分。","372份大豆样本，多光谱\u002F热红外\u002FLiDAR影像加基因型与播后天数，端到端CNN","蔗糖预测最优(R²=0.80)，基因型与播期提升精度，多光谱最稳健。","可探索基因型-表型-环境交互建模，并迁移至其他作物与多时相早期预测。","2026-09-13T23:30:22.776177Z",{"id":322,"title":323,"url":324,"summary":325,"summary_zh":326,"content":9,"source_name":327,"source_url":324,"published_at":328,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":225,"score_detail":329,"sources":331,"tags":333,"search_phrases":336,"slug":339,"view_count":35,"doi":340,"paper":341,"created_at":367},2318,"Estimation of field-scale crop evapotranspiration from the mechanistic SIF-ET model using the UAV hyperspectral imagery","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.eja.2026.128332","Accurate estimation of evapotranspiration (ET) is critical for agricultural water management and understanding land-atmosphere interactions. Conventional thermal and optical remote sensing is a powerful tool for ET estimation, but existing methods remain constrained by empirical parameterization, calibration complexity, and limited applicability. As a direct indicator of vegetation photosynthesis, solar-induced chlorophyll fluorescence (SIF) enables consistent and accurate ET estimation through a mechanistically grounded framework that does not require site-specific empirical calibration of the SIF-GPP relationship. However, current SIF-based ET estimation mainly rely on coarse-resolution satellite data and its capacity to resolve high-resolution ET dynamics over farmland remains unexplored. To address this, the mechanistic light response model and water-carbon relationship was integrated to construct a SIF-ET model at field-scale using UAV narrow-band hyperspectra imagery. The principal conclusions are: (1) High-resolution crop (canola,soybean and wheat) canopy SIF 740 at 1-nm SR was retrieved from UAV hyperspectra imagery using the Photochemistry and Energy Fluxes (SCOPE) model; (2)The daily ET estimates from SIF-ET model were validated against the in-situ measurements across multiple growth stages and water-nitrogen treatments, with wheat exhibiting the highest precision (R²=0.72–0.94, RMSE = 0.04–0.11 mm\u002Fd, MAPE = 1.70–5.89%), followed by canola and soybean; (3) Cumulative ET errors across repeated UAV observations within each growth stage remained within acceptable bounds, indicating the stability of SIF-ET model in capturing long-term ET dynamics. Overall, the SIF-ET model from UAV hyperspectra imagery revealed fine-scale cropland ET spatial-temporal heterogeneity. These findings provide support for precision irrigation, rational water-nitrogen management, and stress diagnostics under changing environmental conditions.","准确估算蒸散发（ET）对农业水资源管理和理解陆气相互作用至关重要。传统的热红外与光学遥感是估算ET的有力工具，但现有方法仍受限于经验参数化、校准复杂性和适用性有限等问题。作为植被光合作用的直接指示因子，日光诱导叶绿素荧光（SIF）能够通过机理明确的框架实现一致且准确的ET估算，且无需对SIF-GPP关系进行站点特定的经验校准。然而，当前基于SIF的ET估算主要依赖粗分辨率卫星数据，其解析农田高分辨率ET动态的能力尚未得到探索。为此，本研究整合机理光响应模型与水碳关系，利用无人机窄波段高光谱影像构建了田块尺度的SIF-ET模型。主要结论如下：（1）利用光化学与能量通量（SCOPE）模型，从无人机高光谱影像中反演了1 nm光谱分辨率下油菜、大豆和小麦的高分辨率冠层SIF₇₄₀；（2）基于SIF-ET模型的日ET估算值在多个生育期和水氮处理下与原位观测进行了验证，其中小麦精度最高（R²=0.72–0.94，RMSE=0.04–0.11 mm\u002Fd，MAPE=1.70–5.89%），油菜和大豆次之；（3）各生育期内重复无人机观测的累积ET误差均在可接受范围内，表明SIF-ET模型在捕捉长期ET动态方面具有稳定性。总体而言，基于无人机高光谱影像的SIF-ET模型揭示了精细尺度的农田ET时空异质性。这些发现为精准灌溉、合理水氮管理以及变化环境条件下的胁迫诊断提供了支持。","European Journal of Agronomy","2026-09-12T00:00:00Z",{"impact":18,"substance":65,"depth":18,"authority":67,"freshness":227,"relevant":21,"comment":330},"该研究基于无人机高光谱与SIF-ET机理模型实现田块尺度作物蒸散发高精度估算，方法新颖、验证充分，对精准灌溉与水氮管理有实质参考价值，值得进入每日精选。",[332],{"name":327,"url":324},[165,26,27,334,335],"精准灌溉","蒸散发",[337,338],"智慧农业 精准灌溉 无人机 蒸散发","智慧农业 精准灌溉","智慧农业精准灌溉无人机蒸散发-2318","10.1016\u002Fj.eja.2026.128332",{"doi":340,"openalex_id":342,"authors":343,"venue":327,"cited_by_count":35,"oa_url":324,"card":362,"direction":48,"ingested_from":51},"W7212242584",[344,346,348,351,354,356,359],{"name":345,"orcid":9},"Ruiqi Du",{"name":347,"orcid":9},"Yonghong Zhang",{"name":349,"orcid":350},"Youzhen Xiang","https:\u002F\u002Forcid.org\u002F0000-0002-8268-1609",{"name":352,"orcid":353},"Fucang Zhang","https:\u002F\u002Forcid.org\u002F0000-0002-6659-3262",{"name":355,"orcid":9},"Jian Gao",{"name":357,"orcid":358},"Qiliang Yang","https:\u002F\u002Forcid.org\u002F0000-0002-3274-2119",{"name":360,"orcid":361},"Xianghui Lu","https:\u002F\u002Forcid.org\u002F0000-0003-0638-3068",{"tldr":363,"method":364,"finding":365,"direction":48,"opportunity":366},"利用无人机高光谱影像构建田间尺度SIF-ET机理模型，实现作物蒸散发高精度估算。","无人机窄波段高光谱结合SCOPE模型反演SIF，耦合光响应与水碳关系构建SIF-","小麦估算精度最高（R²=0.72–0.94），模型能稳定捕捉多生育期蒸散发动态与空间异质性。","可探索多作物多环境下的SIF-ET普适性，并融合热红外与机器学习提升胁迫诊断能力。","2026-09-13T23:30:22.677041Z"]