[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4304":3,"related-4304":90},{"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":32,"secondary_topics":38,"classification":39,"search_phrases":64,"slug":67,"view_count":22,"doi":68,"paper":69,"created_at":89},4304,"A novel phenotyping approach for reconciling precision and variance in disease severity estimates from high-resolution imaging","https:\u002F\u002Fdoi.org\u002F10.1186\u002Fs13007-026-01593-8","Abstract Accurate quantification of plant disease is essential for resistance breeding, variety testing, and precision agriculture, yet visual ratings are limited by subjectivity, low precision, and restricted throughput. Image-based phenotyping can address these limitations, but field applications are challenging due to spatial heterogeneity and miniature diagnostic features. High-resolution imagery with a limited field of view and a shallow depth of field is therefore needed, restricting the analyzed leaf area. This introduces a fundamental trade-off: high-resolution images provide precise local measurements of disease, but spot-level estimates can be highly variable within experimental units. A key challenge is therefore to understand this variability and to develop sampling strategies that translate precise local observations into reliable plot-level measurements. Here, we analyzed spot-level estimates of septoria tritici blotch and brown rust severity derived from 16,650 images acquired in 15 experimental plots over two consecutive days to quantify the statistical distribution and spatial dependence of local estimates of disease. High-resolution macro-scale images were obtained at multiple positions around a plot and at multiple heights. Focus bracketing was evaluated as a practical strategy to increase the sampled leaf area without additional operator effort. Autocorrelation in severity estimates within focal image stacks and across positions within a plot was comparable, with 10 focal stack images or 10 positions per plot contributing approximately 2.5 independent observations each. Modeling plot-level severity as a latent Beta-distributed variable provided robust estimates of mean disease severity and its associated uncertainty, highlighting the importance of dense spatial sampling, particularly at advanced stages of disease development. Obtaining a precise understanding of the correlation structure and an accurate quantification of achievable precision gains from repeated measures will depend on larger experiments. Nevertheless, our results indicate that combining dense spatial sampling with focus bracketing and appropriate hierarchical statistical models can substantially improve the precision of plot-level disease estimates without sacrificing throughput.","摘要 植物病害的准确定量对于抗性育种、品种测试和精准农业至关重要，然而视觉评级受主观性、低精度和通量受限的制约。基于图像的表型分析可以解决这些局限，但田间应用因空间异质性和微小诊断特征而面临挑战。因此需要具有有限视场和浅景深的高分辨率图像，这限制了可分析的叶面积。这引入了一个根本性的权衡：高分辨率图像可提供病害的精确局部测量，但样点水平的估计值在试验单元内可能高度变异。因此，一个关键挑战是理解这种变异性，并开发采样策略，将精确的局部观测转化为可靠的小区水平测量。本研究分析了由连续两天在15个试验小区获取的16，650张图像得出的小麦叶枯病（septoria tritici blotch）和褐锈病（brown rust）严重度的样点水平估计值，以量化病害局部估计值的统计分布和空间依赖性。在小区周围的多个位置和多个高度获取高分辨率宏观尺度图像。评估了焦点堆叠（focus bracketing）作为一种实用策略，以在不增加操作者负担的情况下增加采样叶面积。焦点图像堆栈内以及小区内不同位置之间严重度估计值的自相关性相当，每个小区10张焦点堆栈图像或10个位置各贡献约2.5个独立观测值。将小区水平严重度建模为潜在的Beta分布变量，提供了病害平均严重度及其相关不确定性的稳健估计，凸显了密集空间采样的重要性，尤其是在病害发展的后期阶段。要精确理解相关结构并准确量化重复测量可实现的精度提升，将依赖于更大规模的试验。尽管如此，我们的结果表明，将密集空间采样与焦点堆叠及适当的层次统计模型相结合，可以在不牺牲通量的情况下大幅提高小区水平病害估计的精度。",null,"Plant Methods","2026-10-05T00:00:00Z","论文",10,false,77,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},16,22,18,13,8,1,"基于16650张高分辨率图像量化病害严重度分布与空间相关性，提出密集采样结合焦点包围曝光与分层统计模型提升小区级病害估计精度，方法新颖、数据规模可观，对作物抗病育种与精准农业有参考价值。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","抗病育种","病害检测","植物表型","高分辨率成像",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},"A2","wheat","小麦","\u002Ftopic\u002Ffield-crops\u002Fwheat","A",[],{"status":40,"locked":14,"version":41,"method":42,"evidence":43},"classified","2026-10-22.2","rules",{"candidates":44,"agricultural_evidence":48},[45,54,59],{"code":46,"score":47,"supported":48,"title":49,"abstract":50,"tags":53},"I1",7,true,[],[51,52],"精准农业","precision agriculture",[27],{"code":33,"score":55,"supported":48,"title":56,"abstract":57,"tags":58},3,[],[35],[],{"code":60,"score":22,"supported":14,"title":61,"abstract":62,"tags":63},"F2",[],[],[28],[65,66],"小麦 叶斑病 表型分析","高分辨率成像 病害严重度","小麦叶斑病表型分析-4304","10.1186\u002Fs13007-026-01593-8",{"doi":68,"openalex_id":70,"authors":71,"venue":10,"cited_by_count":81,"oa_url":6,"card":82,"direction":86,"ingested_from":88},"W7220426885",[72,75,78],{"name":73,"orcid":74},"Radek Zenkl","https:\u002F\u002Forcid.org\u002F0009-0000-4099-1361",{"name":76,"orcid":77},"Bruce Alan McDonald","https:\u002F\u002Forcid.org\u002F0000-0002-5332-2172",{"name":79,"orcid":80},"Jonas Anderegg","https:\u002F\u002Forcid.org\u002F0000-0002-3345-4696",0,{"tldr":83,"method":84,"finding":85,"direction":86,"opportunity":87},"通过高分辨率成像与焦点包围曝光，结合分层统计模型，提升小区级病害严重度估计精度。","16,650张高分辨率图像，焦点包围曝光，空间自相关与Beta分层模型。","密集空间采样与焦点包围曝光可显著提高小区级病害估计精度且不牺牲通量。","农业遥感与作物表型","可探索自适应采样策略与多尺度模型，平衡精度与通量并推广至其他病害。","openalex","2026-10-06T23:30:17.356095Z",{"total":91,"page":22,"page_size":91,"items":92},6,[93,167,258,317,383,431],{"id":94,"title":95,"url":96,"summary":97,"summary_zh":98,"content":9,"source_name":99,"source_url":96,"published_at":100,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":101,"sources":104,"tags":106,"primary_topic":109,"secondary_topics":110,"classification":117,"search_phrases":149,"slug":152,"view_count":55,"doi":153,"paper":154,"created_at":166},1430,"Hyperspectral Imaging for Disease Detection in Wheat Crops: A Comprehensive Survey","https:\u002F\u002Fdoi.org\u002F10.18805\u002Fijare.a-6533","Hyperspectral imaging (HSI) has emerged as a game-changing technology for precision agriculture because it captures detailed spectral signatures over hundreds of finely-resolved, continuous wavelength bands. This feature makes possible a detailed description of species-specific plant physiological states to enable early, precise and non-destructive identification of diseases in crops like wheat. With the rising demands worldwide for food security and healthy cultivation, the application of HSI in agro-diagnostics has expanded considerably. This paper provides a comprehensive and state-of-the-art review of hyperspectral imaging strategies devoted to wheat disease discrimination. It essentially introduces the theoretical backgrounds of HSI, such as data acquisition, preprocessing and spectral-spatial feature extraction. The survey further details a plethora of analytical approaches from classical statistical learning methods to deep learning and their utility in modelling HSI data. In particular, a comparative study of these methods is carried out and discussed for distinguishing healthy and diseased wheat, as well as different types of diseases under diverse environmental conditions. The paper also considers the benchmark datasets, sensors and platforms (field\u002Flaboratory-based) for which there are practical limitations. Key challenges are addressed, such as data dimensionality, variability as a consequence of atmospheric conditions and the requirement for online implementation in open-field scenarios. A set of suggestions for applying HSI in other domains has been proposed, such as the fusion of HSI with additional remote sensing information, introduction of compact models to edge devices and construction of a scalable and economical solution of HSI in commercial agriculture.","高光谱成像（HSI）已成为精准农业领域的一项变革性技术，因为它能够在数百个精细分辨、连续分布的波段上捕获详细的光谱特征。这一特性使得对物种特异性植物生理状态进行细致描述成为可能，从而能够对小麦等作物病害实现早期、精准且非破坏性的识别。随着全球对粮食安全和健康栽培需求的日益增长，HSI在农业诊断中的应用已显著扩展。本文对用于小麦病害区分的高光谱成像策略进行了全面且前沿的综述。文章首先介绍了HSI的理论基础，包括数据采集、预处理及光谱-空间特征提取。随后，综述详细探讨了从经典统计学习方法到深度学习的众多分析方法及其在HSI数据建模中的适用性。特别地，文中对这些方法进行了比较研究，并讨论了其在区分健康与患病小麦，以及在不同环境条件下识别不同类型病害方面的表现。本文还考虑了基准数据集、传感器及平台（田间\u002F实验室）在实际应用中存在的局限性。针对数据维度、大气条件引起的变异性以及开放田间场景下在线实施的需求等关键挑战进行了阐述。最后，提出了将HSI应用于其他领域的一系列建议，例如将HSI与额外遥感信息融合、将紧凑模型引入边缘设备，以及构建在商业农业中可扩展且经济可行的HSI解决方案。","Indian Journal of Agricultural Research","2026-09-02T00:00:00Z",{"impact":19,"substance":18,"depth":19,"authority":102,"freshness":47,"relevant":22,"comment":103},12,"高光谱成像用于小麦病害检测的综述，系统性强，方法比较全面，对智慧农业病害诊断有参考价值。",[105],{"name":99,"url":96},[27,107,35,108,29],"农业人工智能","遥感",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[111],{"code":112,"slug":113,"name":114,"path":115,"parent_code":116},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",{"status":40,"locked":14,"version":41,"method":42,"evidence":118},{"candidates":119,"agricultural_evidence":48},[120,126,131,135,142],{"code":112,"score":19,"supported":48,"title":121,"abstract":123,"tags":125},[122],"hyperspectral",[108,124,122],"remote sensing",[108],{"code":33,"score":127,"supported":48,"title":128,"abstract":129,"tags":130},15,[34],[35,34],[35],{"code":46,"score":47,"supported":48,"title":132,"abstract":133,"tags":134},[],[51,52],[27],{"code":136,"score":47,"supported":48,"title":137,"abstract":138,"tags":141},"I2",[],[139,140],"深度学习","deep learning",[107],{"code":143,"score":91,"supported":48,"title":144,"abstract":145,"tags":148},"A8",[],[146,147],"粮食安全","food security",[],[150,151],"农业人工智能 智慧农业 病害检测 小麦","农业人工智能 智慧农业","农业人工智能智慧农业病害检测小麦-1430","10.18805\u002Fijare.a-6533",{"doi":153,"openalex_id":155,"authors":156,"venue":99,"cited_by_count":81,"oa_url":96,"card":161,"direction":86,"ingested_from":88},"W7205005591",[157,159],{"name":158,"orcid":9},"M. Deepak",{"name":160,"orcid":9},"Gopal K. Shyam",{"tldr":162,"method":163,"finding":164,"direction":86,"opportunity":165},"综述高光谱成像在小麦病害检测中的应用，涵盖方法、挑战与未来方向。","综述数据采集、预处理、特征提取及统计学习与深度学习方法。","高光谱成像可早期、无损识别小麦病害，但面临维度高、环境变化和实时性挑战。","可探索高光谱与多源遥感融合、轻量化模型部署于边缘设备，以及低成本商业化方案。","2026-09-02T23:30:51.057495Z",{"id":168,"title":169,"url":170,"summary":171,"summary_zh":172,"content":9,"source_name":173,"source_url":170,"published_at":174,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":175,"sources":179,"tags":181,"primary_topic":186,"secondary_topics":187,"classification":198,"search_phrases":234,"slug":237,"view_count":81,"doi":238,"paper":239,"created_at":257},5558,"Estimation of Soil Water Content in Winter Wheat Field at Jointing Stage Using Multi-Source Features and Machine Learning","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fagronomy16202071","Accurate and timely monitoring of soil water content (SWC) plays an essential supporting role in crop irrigation management and smart agricultural practice. Remote sensing technology provides rapid and convenient approaches to large-scale farmland SWC estimation or inversion. However, existing mechanistic modeling methods are limited by parameter localization and land surface heterogeneity, while machine learning data-driven methods lack quite good physical interpretability. To address deficiencies in single data-driven methods and single vegetation microwave scattering models, and explore the estimation effect of different feature variables in machine learning. This study proposes an innovative estimation model that integrates machine learning strategies and multi-source features, including spectral indices and features derived from the classic water cloud model (WCM). The novelty of the proposed model lies in balancing physical interpretability and data-driven accuracy, namely extracting relevant soil backscattering parameters through WCM, which are then used as input features in the machine learning. A combination of field-measured data and unmanned aerial vehicle (UAV) multi-source remote sensing data, including multispectral and synthetic aperture radar (SAR) data, was acquired synchronously at the jointing stage of winter wheat. Through extracting variables such as the SAR microwave backscattering coefficient and the optical vegetation index, and conducting feature screening and parameter sensitivity analysis, we optimized the input variable sets of models based on back-propagation (BP) neural network, support vector regression (SVR) and random forest (RF) algorithms. The study results showed that the established estimation model had excellent estimation performance, especially for the RF algorithm, with the highest R2 of 0.855, lowest MAE of 0.0212 cm3\u002Fcm3, and lowest RMSE of 0.0253 cm3\u002Fcm3. It was also shown that different feature input schemes have obvious effects on SWC estimation performance. On the whole, RF had the best estimation accuracy, followed by SVR and then BPNN. This study demonstrated that models integrating multi-source remote sensing data and machine learning could enhance SWC estimation ability for winter wheat fields, and could also serve as a promising approach for SWC monitoring in winter wheat fields in the North China Plain.","准确、及时地监测土壤含水量（SWC）对作物灌溉管理和智慧农业实践具有重要的支撑作用。遥感技术为大规模农田土壤含水量估算或反演提供了快速便捷的手段。然而，现有机理建模方法受参数本地化和地表异质性限制，机器学习数据驱动方法则缺乏良好的物理解释性。针对单一数据驱动方法和单一植被微波散射模型的不足，并探究不同特征变量在机器学习中的估算效果，本研究提出了一种融合机器学习策略与多源特征的创新估算模型，所采用特征包括光谱指数和经典水云模型（WCM）衍生的特征。该模型的新颖性在于平衡物理解释性与数据驱动精度，即通过WCM提取相关土壤后向散射参数，再将其作为机器学习的输入特征。研究在冬小麦拔节期同步获取了田间实测数据与无人机（UAV）多源遥感数据，包括多光谱和合成孔径雷达（SAR）数据。通过提取SAR微波后向散射系数和光学植被指数等变量，并进行特征筛选和参数敏感性分析，优化了基于反向传播（BP）神经网络、支持向量回归（SVR）和随机森林（RF）算法的模型输入变量集。研究结果表明，所建立的估算模型具有优良的估算性能，尤其是RF算法，最高R²为0.855，最低MAE为0.0212 cm³\u002Fcm³，最低RMSE为0.0253 cm³\u002Fcm³。研究还表明，不同特征输入方案对土壤含水量估算性能有明显影响。总体而言，RF估算精度最佳，SVR次之，BPNN再次之。本研究证明，融合多源遥感数据与机器学习的模型能够提升冬小麦田土壤含水量估算能力，也可为华北平原冬小麦田土壤含水量监测提供一种有前景的方法。","Agronomy","2026-10-21T00:00:00Z",{"impact":17,"substance":176,"depth":177,"authority":20,"freshness":13,"relevant":22,"comment":178},21,17,"该研究融合多源遥感与机器学习估算冬小麦拔节期土壤含水量，方法有创新、结论可靠，对智慧灌溉有参考价值，但属细分领域论文，影响范围有限。",[180],{"name":173,"url":170},[27,182,183,184,185],"机器学习","遥感监测","土壤墒情","冬小麦",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[188,194],{"code":189,"slug":190,"name":191,"path":192,"parent_code":193},"H2","soil","土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",{"code":136,"slug":195,"name":196,"path":197,"parent_code":116},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",{"status":40,"locked":14,"version":41,"method":42,"evidence":199},{"candidates":200,"agricultural_evidence":48},[201,207,212,217,222,229],{"code":33,"score":202,"supported":48,"title":203,"abstract":205,"tags":206},26,[204,34],"winter wheat",[35,204,34],[185],{"code":189,"score":127,"supported":48,"title":208,"abstract":209,"tags":211},[190],[210,190],"土壤",[184],{"code":136,"score":127,"supported":48,"title":213,"abstract":215,"tags":216},[214],"machine learning",[182,214],[182],{"code":112,"score":13,"supported":48,"title":218,"abstract":219,"tags":221},[],[108,124,220],"multispectral",[183],{"code":223,"score":91,"supported":48,"title":224,"abstract":225,"tags":228},"H3",[],[226,227],"灌溉","irrigation",[],{"code":46,"score":230,"supported":48,"title":231,"abstract":232,"tags":233},4,[],[27],[27],[235,236],"冬小麦 土壤含水量 遥感","多源遥感 机器学习 墒情","冬小麦土壤含水量遥感-5558","10.3390\u002Fagronomy16202071",{"doi":238,"openalex_id":240,"authors":241,"venue":173,"cited_by_count":81,"oa_url":170,"card":251,"direction":256,"ingested_from":88},"W7223156204",[242,245,247,249],{"name":243,"orcid":244},"Mingliang Jiang","https:\u002F\u002Forcid.org\u002F0000-0002-6486-6087",{"name":246,"orcid":9},"Yi Zhang",{"name":248,"orcid":9},"WEI Lei",{"name":250,"orcid":9},"Chengcai Zhang",{"tldr":252,"method":253,"finding":254,"direction":86,"opportunity":255},"融合WCM物理特征与多源遥感，用机器学习估算冬小麦拔节期土壤含水量。","无人机多光谱与SAR数据，WCM参数+光谱指数，BP\u002FSVR\u002FRF建模。","RF最优，R²达0.855，RMSE为0.0253 cm³\u002Fcm³，特征方案影响显著。","可探索物理约束与深度学习耦合，并迁移至多生育期、多作物及不同土壤质地验证。","智慧农业 \u002F 农业物联网","2026-10-22T11:20:18.887301Z",{"id":259,"title":260,"url":261,"summary":262,"summary_zh":9,"content":9,"source_name":263,"source_url":9,"published_at":174,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":264,"score_detail":265,"sources":268,"tags":270,"primary_topic":275,"secondary_topics":276,"classification":283,"search_phrases":304,"slug":307,"view_count":22,"doi":9,"paper":308,"created_at":316},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":19,"substance":18,"depth":19,"authority":266,"freshness":13,"relevant":22,"comment":267},14,"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。",[269],{"name":263,"url":261},[27,271,272,273,274],"农业遥感","作物表型","无人机多光谱","小麦渍害",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[277,278],{"code":112,"slug":113,"name":114,"path":115,"parent_code":116},{"code":279,"slug":280,"name":281,"path":282,"parent_code":193},"H7","climate","气候适应与防灾减灾","\u002Ftopic\u002Fenvironment\u002Fclimate",{"status":40,"locked":14,"version":41,"method":42,"evidence":284},{"candidates":285,"agricultural_evidence":48},[286,291,295,300],{"code":33,"score":287,"supported":48,"title":288,"abstract":289,"tags":290},11,[35],[35],[],{"code":112,"score":287,"supported":48,"title":292,"abstract":293,"tags":294},[273],[],[272,271,273],{"code":279,"score":21,"supported":48,"title":296,"abstract":298,"tags":299},[297],"渍害",[],[],{"code":46,"score":22,"supported":14,"title":301,"abstract":302,"tags":303},[],[],[27],[305,306],"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":309,"venue":9,"cited_by_count":81,"oa_url":9,"card":310,"direction":86,"ingested_from":315},[],{"tldr":311,"method":312,"finding":313,"direction":86,"opportunity":314},"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":318,"title":319,"url":320,"summary":321,"summary_zh":322,"content":9,"source_name":323,"source_url":320,"published_at":324,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":325,"sources":327,"tags":329,"primary_topic":332,"secondary_topics":333,"classification":335,"search_phrases":354,"slug":357,"view_count":81,"doi":358,"paper":359,"created_at":382},5367,"Integration of multi-source UAV remote sensing features and derived features for winter wheat aboveground biomass estimation","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.atech.2026.102656","Accurate estimation of winter wheat ( Triticum aestivum L.) aboveground biomass (AGB) is important for crop growth monitoring and field management. However, unmanned aerial vehicle (UAV)-based AGB estimation remains challenging due to variations in canopy conditions across growth stages, and different remote sensing features can capture complementary characteristics related to AGB estimation. This study integrated multi-source UAV-derived features, including vegetation indices (VIs), texture features (TFs), light detection and ranging (LiDAR)-derived features, and derived features (DFs) generated from the original feature sets, with four machine learning algorithms for winter wheat AGB estimation. Results showed that TFs provided better prediction performance than other single-source feature sets. Compared with single-source feature sets, the integration of VIs, TFs, LiDAR-derived features, and DFs further improved AGB estimation, and the random forest (RF) model achieved the best performance among the evaluated models (R² = 0.923, RMSE = 1.731 Mg ha⁻¹). Incremental R² analysis based on a stage-only baseline model showed that the RF model explained additional variation in AGB beyond growth-stage information, with an incremental R² of 0.479. Stage-specific evaluation indicated that model performance varied among growth stages, with the highest accuracy observed at the booting stage (R² = 0.632, RMSE = 1.425 Mg ha⁻¹). Feature contribution analysis based on the full-feature fusion model using all growth-stage data identified canopy coverage and several DFs as important predictors, while stage-specific analyses showed differences in dominant predictors across growth stages. The integration of multi-source UAV-derived features and DFs with machine learning provides an effective approach for winter wheat AGB estimation, while model performance remains strongly dependent on growth stage.","准确估算冬小麦（Triticum aestivum L.）地上生物量（aboveground biomass, AGB）对作物生长监测和田间管理具有重要意义。然而，由于不同生育期冠层条件存在差异，且不同遥感特征能够捕捉与AGB估算相关的互补信息，基于无人机（unmanned aerial vehicle, UAV）的AGB估算仍面临挑战。本研究将多源无人机衍生特征，包括植被指数（vegetation indices, VIs）、纹理特征（texture features, TFs）、激光雷达（light detection and ranging, LiDAR）衍生特征以及由原始特征集生成的衍生特征（derived features, DFs），与四种机器学习算法相结合，用于冬小麦AGB估算。结果表明，TFs的预测性能优于其他单一来源特征集。与单一来源特征集相比，融合VIs、TFs、LiDAR衍生特征和DFs进一步提高了AGB估算精度，其中随机森林（random forest, RF）模型在所评估的模型中表现最佳（R² = 0.923，RMSE = 1.731 Mg ha⁻¹）。基于仅含生育期信息的基线模型进行的增量R²分析表明，RF模型在生育期信息之外解释了AGB的额外变异，增量R²为0.479。分生育期评估表明，模型性能在不同生育期之间存在差异，其中在孕穗期观察到最高精度（R² = 0.632，RMSE = 1.425 Mg ha⁻¹）。基于使用全部生育期数据的全特征融合模型进行的特征贡献分析识别出冠层覆盖度和若干DFs为重要预测因子，而分生育期分析则表明不同生育期的主导预测因子存在差异。将多源无人机衍生特征和DFs与机器学习相结合，为冬小麦AGB估算提供了一种有效方法，但模型性能仍强烈依赖于生育期。","Smart Agricultural Technology","2026-10-17T00:00:00Z",{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":326},"该研究融合无人机多源遥感特征与衍生特征，用随机森林估算冬小麦地上生物量，方法新颖、结论可靠，对作物长势监测有参考价值。",[328],{"name":323,"url":320},[27,330,183,185,331],"无人机","生物量估算",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[334],{"code":112,"slug":113,"name":114,"path":115,"parent_code":116},{"status":40,"locked":14,"version":41,"method":42,"evidence":336},{"candidates":337,"agricultural_evidence":48},[338,342,346,350],{"code":33,"score":202,"supported":48,"title":339,"abstract":340,"tags":341},[204,34],[35,204,34],[185],{"code":112,"score":17,"supported":48,"title":343,"abstract":344,"tags":345},[124],[108,124],[331,183],{"code":136,"score":91,"supported":48,"title":347,"abstract":348,"tags":349},[],[182,214],[],{"code":46,"score":22,"supported":14,"title":351,"abstract":352,"tags":353},[],[],[27],[355,356],"无人机 多源遥感 冬小麦 生物量","冬小麦 地上生物量 随机森林","无人机多源遥感冬小麦生物量-5367","10.1016\u002Fj.atech.2026.102656",{"doi":358,"openalex_id":360,"authors":361,"venue":323,"cited_by_count":81,"oa_url":320,"card":377,"direction":86,"ingested_from":88},"W7222806066",[362,364,366,368,371,373,375],{"name":363,"orcid":9},"Guangtao Wang",{"name":365,"orcid":9},"Sumei Yao",{"name":367,"orcid":9},"Yanzheng Xie",{"name":369,"orcid":370},"Anzhen Qin","https:\u002F\u002Forcid.org\u002F0000-0002-2550-0015",{"name":372,"orcid":9},"Xiangdong Chen",{"name":374,"orcid":9},"Yuhao Zhang",{"name":376,"orcid":9},"Lina Jiang",{"tldr":378,"method":379,"finding":380,"direction":86,"opportunity":381},"融合无人机多源遥感特征与衍生特征，用机器学习估算冬小麦地上生物量。","无人机植被指数、纹理、LiDAR特征及衍生特征结合四种机器学习算法建模。","多源特征融合优于单一特征，随机森林最优（R²=0.923），精度随生育期变化。","可探索生育期自适应建模与特征选择，提升跨期生物量估算的稳健性与可迁移性。","2026-10-20T23:30:03.106267Z",{"id":384,"title":385,"url":386,"summary":387,"summary_zh":9,"content":9,"source_name":388,"source_url":9,"published_at":324,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":389,"score_detail":390,"sources":392,"tags":394,"primary_topic":398,"secondary_topics":399,"classification":400,"search_phrases":419,"slug":422,"view_count":81,"doi":9,"paper":423,"created_at":430},5365,"基于经济型多光谱成像与知识蒸馏模型压缩的小麦线条花叶病毒早期检测","https:\u002F\u002Fwww.ebiotrade.com\u002Fnewsf\u002F2026-10\u002F20261017000601916.htm","研究人员利用配备六个光谱滤光片的消费级数码单反(DSLR)相机在自然环境条件下获取了一个新的小麦线条花叶病毒(WhSMV)多光谱数据集。评估十二个深度学习模型识别 WhSMV 感染不同阶段的性能,并首次将模型压缩技术应用于多光谱图像用于 WhSMV 感染的早期检测。比较了深度学习算法与压缩模型的性能,揭示压缩模型达到与大型深度学习模型相当的性能。WhSMV 是小麦土传媒介传播病毒,巴西与南非均有报道。","Smart Agricultural Technology 2026-10-17",78,{"impact":19,"substance":18,"depth":177,"authority":20,"freshness":21,"relevant":22,"comment":391},"该研究构建了新的多光谱数据集，并首次将模型压缩用于小麦病毒早期检测，方法新颖、结论可靠，对智慧农业植保具有参考价值。",[393],{"name":388,"url":386},[27,107,395,396,397],"多光谱成像","小麦病害","模型压缩",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":401},{"candidates":402,"agricultural_evidence":48},[403,407,411,415],{"code":33,"score":287,"supported":48,"title":404,"abstract":405,"tags":406},[35],[35],[],{"code":136,"score":230,"supported":48,"title":408,"abstract":409,"tags":410},[],[139],[107],{"code":46,"score":22,"supported":14,"title":412,"abstract":413,"tags":414},[],[],[27],{"code":112,"score":22,"supported":14,"title":416,"abstract":417,"tags":418},[],[],[395],[420,421],"小麦线条花叶病毒 多光谱 检测","知识蒸馏 模型压缩 小麦","小麦线条花叶病毒多光谱检测-5365",{"doi":9,"openalex_id":9,"authors":424,"venue":9,"cited_by_count":81,"oa_url":9,"card":425,"direction":86,"ingested_from":315},[],{"tldr":426,"method":427,"finding":428,"direction":86,"opportunity":429},"用经济型多光谱成像结合知识蒸馏压缩模型，实现小麦线条花叶病毒早期检测。","消费级单反加六波段滤光片采集多光谱数据，评估12个深度学习模型并做模型压缩。","压缩模型性能与大型深度学习模型相当，可用于WhSMV感染早期识别。","可探索低成本多光谱设备与轻量模型在田间病害早期预警中的部署与跨区域泛化。","2026-10-20T02:47:54.487590Z",{"id":432,"title":433,"url":434,"summary":435,"summary_zh":9,"content":9,"source_name":436,"source_url":9,"published_at":437,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":438,"score_detail":439,"sources":441,"tags":443,"primary_topic":447,"secondary_topics":448,"classification":449,"search_phrases":468,"slug":471,"view_count":81,"doi":9,"paper":472,"created_at":479},5362,"深度语义分割模型的时序泛化评估:无人机小麦倒伏监测 5 年跨年测试","https:\u002F\u002Fbioengineer.org\u002Fai-models-trained-on-one-year-of-wheat-fail-the-next-five-year-drone-study-shows\u002F","Zhang G., Wang X., Wang D., Sun D., Zhang Y., Zhang D. (2026) 利用 5 年田间试验评估深度语义分割模型在无人机(UAV)小麦倒伏监测中的时序泛化能力。研究发现:同年内高精度不能保证跨年可靠性,模型从训练年份迁移到其他年份时性能显著下降,基于注意力的模型通常比全卷积网络更稳健,可能因为层级窗口自注意力能整合更长范围上下文,而卷积强调局部模式;即便最优架构在大时序漂移下也出现严重退化。强调时序泛化测试应成为农业 AI 模型部署前的必备环节。DOI: 10.1016\u002Fj.atech.2026.102631。","Smart Agricultural Technology Vol.15 Article 102631 2026-10-16","2026-10-16T00:00:00Z",79,{"impact":19,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":440},"基于5年跨年田间试验揭示农业AI模型时序泛化瓶颈，结论扎实且具部署指导价值，值得入选。",[442],{"name":436,"url":434},[27,107,444,445,446],"无人机遥感","小麦倒伏","模型泛化",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":450},{"candidates":451,"agricultural_evidence":48},[452,456,460,464],{"code":33,"score":287,"supported":48,"title":453,"abstract":454,"tags":455},[35],[35],[],{"code":46,"score":22,"supported":14,"title":457,"abstract":458,"tags":459},[],[],[27],{"code":136,"score":22,"supported":14,"title":461,"abstract":462,"tags":463},[],[],[107],{"code":112,"score":22,"supported":14,"title":465,"abstract":466,"tags":467},[],[],[444],[469,470],"无人机 小麦倒伏 监测","深度语义分割 时序泛化","无人机小麦倒伏监测-5362",{"doi":9,"openalex_id":9,"authors":473,"venue":9,"cited_by_count":81,"oa_url":9,"card":474,"direction":86,"ingested_from":315},[],{"tldr":475,"method":476,"finding":477,"direction":86,"opportunity":478},"用5年田间试验评估深度语义分割模型在无人机小麦倒伏监测中的跨年泛化能力。","5年无人机小麦倒伏影像，对比注意力模型与全卷积网络的跨年迁移表现。","同年内高精度不能保证跨年可靠，注意力模型比全卷积网络更稳健，但大时序漂移下仍严重退化。","可研究时序域自适应与跨年增量学习，建立农业AI模型部署前的时序泛化评测基准。","2026-10-20T02:47:54.289085Z"]