[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3014":3,"related-3014":73},{"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":72},3014,"Detecting diurnal dynamics of cotton leaf inclination angle under water-salt stress","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.rse.2026.115674","Leaf inclination angle (LIA) dynamics act as a rapid response mechanism to abiotic stress, regulating canopy energy balance and water use efficiency. While the adaptive value of diurnal LIA plasticity (e.g., paraheliotropism) is well-recognized in ecology, most current remote sensing algorithms and ecosystem models still treat canopy architecture as static and neglect stress-induced geometric adjustments. Furthermore, the diurnal dynamics of LIA under combined abiotic stresses, such as concurrent water deficit and salinity, still remain poorly understood. Recent advances in unmanned aerial vehicle (UAV) photogrammetry offer a promising approach for capturing LIA dynamics at high spatial and temporal resolution. However, accurately resolving fine scale, dynamic leaf movements in real environments using UAVs remains challenging. To address these gaps, we developed the Constraint-Assisted Point cloud fusion for Leaf scale Analysis (CAPLA), an integrated UAV analytical workflow that combines deep learning with Structure from Motion (SfM). CAPLA employs 2D semantic masks to strictly constrain 3D mesh reconstruction, effectively mitigating motion-induced artifacts. Independent validation against 19 plot level mean leaf angle (MLA) observations collected at 9:30 am and 12:00 pm yielded an R 2 of 0.89 and an RMSE of 0.9°, supporting plot level MLA estimation under the validated acquisition conditions. CAPLA was subsequently applied across five observation times to characterize diurnal canopy structural dynamics. Importantly, repeated measures analysis of the high frequency observations revealed significant effects of irrigation, salinity, and observation time on MLA, together with a significant irrigation × time interaction ( P = 0.0109), indicating that diurnal MLA trajectories differed among irrigation levels. In contrast, neither the irrigation × salinity interaction ( P = 0.8800) nor the irrigation × salinity × time interaction ( P = 0.9086) was significant. Descriptive differences in within-day variability were nevertheless observed among individual treatment combinations, highlighting the value of time-resolved structural monitoring for characterizing canopy responses to combined water and salinity stresses. These findings highlight the complex structural plasticity of canopies under interacting stresses, emphasizing the critical need to transition from static canopy assumptions to dynamic structural monitoring for improving ecosystem models and precision agriculture.","叶片倾角（LIA）动态变化是植物对非生物胁迫的快速响应机制，调控冠层能量平衡与水分利用效率。尽管昼夜LIA可塑性（如避日运动）的适应价值在生态学中已得到广泛认可，但当前大多数遥感算法和生态系统模型仍将冠层结构视为静态，忽略了胁迫诱导的几何调整。此外，在水分亏缺与盐分胁迫等复合非生物胁迫条件下，LIA的昼夜动态变化仍知之甚少。近年来无人机（UAV）摄影测量技术的进展为在高时空分辨率下捕捉LIA动态提供了有前景的方法。然而，利用无人机在真实环境中精确解析精细尺度的动态叶片运动仍具挑战性。为弥补上述不足，我们开发了约束辅助点云融合叶片尺度分析流程（CAPLA），这是一种集成了深度学习与运动恢复结构（SfM）的无人机综合分析工作流。CAPLA利用二维语义掩膜严格约束三维网格重建，有效减轻了运动诱导的伪影。基于上午9：30和中午12：00采集的19个样地水平平均叶倾角（MLA）观测值进行独立验证，结果R²为0.89，RMSE为0.9°，支持在验证采集条件下进行样地水平MLA估算。随后将CAPLA应用于五个观测时段以表征冠层结构的昼夜动态变化。重要的是，对高频观测的重复测量分析揭示了灌溉、盐分和观测时间对MLA的显著影响，以及显著的灌溉×时间交互效应（P = 0.0109），表明不同灌溉水平下MLA的昼夜变化轨迹存在差异。相比之下，灌溉×盐分交互效应（P = 0.8800）和灌溉×盐分×时间交互效应（P = 0.9086）均不显著。尽管如此，在各处理组合之间仍观察到日内变异性的描述性差异，凸显了时间分辨结构监测在表征冠层对水分与盐分复合胁迫响应方面的价值。这些发现揭示了冠层在交互胁迫下的复杂结构可塑性，强调亟需从静态冠层假设转向动态结构监测，以改进生态系统模型和精准农业。",null,"Remote Sensing of Environment","2026-09-19T00:00:00Z","论文",10,false,84,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},18,23,19,15,9,1,"该研究提出CAPLA无人机点云融合方法，实现水盐胁迫下棉花叶倾角昼夜动态的高精度监测，方法新颖、数据可靠，对作物表型与精准农业有实质参考价值。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业遥感","棉花","精准农业","无人机遥感",[33,34],"无人机 棉花 叶倾角 水盐胁迫","CAPLA 冠层结构 动态监测","无人机棉花叶倾角水盐胁迫-3014",0,"10.1016\u002Fj.rse.2026.115674",{"doi":37,"openalex_id":39,"authors":40,"venue":10,"cited_by_count":36,"oa_url":6,"card":65,"direction":69,"ingested_from":71},"W7213661690",[41,44,46,48,50,52,55,58,60,63],{"name":42,"orcid":43},"Qing Li","https:\u002F\u002Forcid.org\u002F0009-0004-4580-7761",{"name":45,"orcid":9},"Dalei Hao",{"name":47,"orcid":9},"Jan Pisek",{"name":49,"orcid":9},"Zicheng Ji",{"name":51,"orcid":9},"Yanan Wei",{"name":53,"orcid":54},"Youngryel Ryu","https:\u002F\u002Forcid.org\u002F0000-0001-6238-2479",{"name":56,"orcid":57},"Jiarui Xu","https:\u002F\u002Forcid.org\u002F0000-0003-4925-2770",{"name":59,"orcid":9},"Yangmin Feng",{"name":61,"orcid":62},"Shaozhong Kang","https:\u002F\u002Forcid.org\u002F0000-0002-8019-2537",{"name":64,"orcid":9},"Yelu Zeng",{"tldr":66,"method":67,"finding":68,"direction":69,"opportunity":70},"提出CAPLA无人机点云融合方法，监测水盐胁迫下棉花叶倾角昼夜动态。","结合深度学习与SfM，用2D语义掩膜约束3D网格重建，无人机高频观测。","灌溉、盐分和时间显著影响叶倾角，灌溉×时间交互显著，昼夜轨迹因灌溉而异。","农业遥感与作物表型","可将动态叶倾角参数化嵌入作物模型，提升水盐胁迫下冠层结构与蒸散模拟精度。","openalex","2026-09-20T23:30:21.262698Z",{"total":74,"page":22,"page_size":74,"items":75},6,[76,103,138,169,203,231],{"id":77,"title":78,"url":79,"summary":80,"summary_zh":9,"content":81,"source_name":82,"source_url":9,"published_at":83,"category":84,"cover_url":9,"hotness":13,"is_selected":85,"score":86,"score_detail":87,"sources":93,"tags":95,"search_phrases":98,"slug":101,"view_count":22,"doi":9,"paper":9,"created_at":102},1499,"中国农大马韫韬教授团队 AI 驱动棉花高通量表型解析三项系列论文：覆盖花器官检测、单株表型、吐絮动态评估","https:\u002F\u002Fnews.cau.edu.cn\u002Fkxyj\u002F287ffb5af8464b76bd61d1db9d408af3.htm","中国农业大学土地科学与技术学院马韫韬教授团队围绕棉花关键生育时期的表型智能识别与量化分析，在 Computers and Electronics in Agriculture、Plant Phenomics 和 Precision Agriculture 等国际权威期刊上连续发表三篇研究论文，题目分别为 MS-R outperforms RGB: Lightweight CYOLO-BiCNet enables efficient detection and storage optimization of cotton flowers，Scalable phenotyping and yield estimation via stability index and single-plant variability using a vision-based large model framework 和 Assessing Cotton Boll-opening Concentration for Harvest Decision-making via Foundation Model-enhanced Cross-scale Phenotyping。","**中国农大新闻网讯**近日，中国农业大学土地科学与技术学院马韫韬教授团队在AI驱动的棉花高通量表型解析领域取得系列重要进展。团队围绕棉花关键生育时期的表型智能识别与量化分析，在 _Computers and Electronics in Agriculture_、_Plant Phenomics_ 和 _Precision Agriculture_ 等国际权威期刊上连续发表三篇研究论文，题目分别为[_MS-R outperforms RGB: Lightweight CYOLO-BiCNet enables efficient detection and storage optimization of cotton flowers_](https:\u002F\u002Flink.springer.com\u002Farticle\u002F10.1007\u002Fs11119-026-10396-9)_，[Scalable phenotyping and yield estimation via stability index and single-plant variability using a vision-based large model framework](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fabs\u002Fpii\u002FS0168169925014061)_ 和[_Assessing Cotton Boll-opening Concentration for Harvest Decision-making via Foundation Model-enhanced Cross-scale Phenotyping_](https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS264365152600107X)。三篇论文构建了覆盖“花器官检测—单株表型解析—吐絮动态评估”的棉花全生育期AI表型技术链条，为推动棉花智慧育种和机械化收获决策提供了重要的方法学支撑与技术方案。\n\n团队在作物表型组学与智能农业方向具有深厚的研究积累。近年来，又将研究视野从大田粮食作物拓展至经济作物领域，与中国农业科学院棉花研究所杜雄明研究员、何守朴研究员团队建立了紧密的合作关系。合作团队围绕棉花种质资源评价、株型调控与机械化适配等核心问题，联合开展了大量田间表型试验与数据采集工作，为AI表型技术的落地提供了丰富的多源、多尺度、多时段数据基础和育种应用场景。在此基础上，马韫韬教授团队充分发挥在深度学习建模、无人机遥感与高通量表型解析方面的技术优势，逐步形成了面向棉花全生育期的智能化表型研究体系。\n\n此次发表的三篇系列论文，分别从棉花不同生育阶段的关键表型需求出发，构建了一条由花器官快速检测、单株尺度多维表型解析到吐絮动态评估与收获决策的技术闭环。论文一针对棉花花期花朵检测的效率与存储瓶颈，提出了轻量化检测网络CYOLO-BiCNet，证实独立获取的多光谱红波段（MS-R）在花朵检测精度与存储效率上均显著优于传统RGB图像，为大田尺度花器官高通量监测提供了低成本、高效率的数据-模型组合方案。\n\n![Image 1: 图片1.png](https:\u002F\u002Fnews.cau.edu.cn\u002Fimages\u002F2026-09\u002F8ed95462d59c45a8ad68d69bb913d44e.png)\n\n图1 基于CYOLO-BiCNet模型对不同数据类型、多个时期棉花花的推断结果分析\n\n图1展示了CYOLO-BiCNet模型在MS-R、RGB及RGB-R三种数据上的可视化推理结果。整体来看，MS-R数据的漏检花朵数量最少，检测效果最优；RGB与 RGB-R数据漏检相对较多。从不同采集日期来看，7月30日三种数据的漏检数分别为11、16、19朵；8月8日降至4、6、7朵；8月15日为3、7、5朵。可视化结果直观表明，MS-R数据在各时段均表现出最佳的花朵检测性能，漏检情况显著少于RGB和RGB-R数据。\n\n![Image 2: 图片2.png](https:\u002F\u002Fnews.cau.edu.cn\u002Fimages\u002F2026-09\u002F31e657d8287840d198aff233328adebe.png)\n\n图2 基于视觉大模型的棉花单株多维表型解析与高产种质筛选技术流程\n\n论文二聚焦单株尺度表型解析这一育种核心需求，开发了视觉大模型框架TopoRefineSAM，融合YOLOv12检测与SAM2分割能力，实现了复杂田间条件下棉花单株的精准实例分割与多性状反演；同时创新性地提出稳定性指标组（SIG），将单株间的差异转化为小区尺度的稳定性特征，显著提升了产量估算和品种筛选的准确性与可解释性。\n\n![Image 3: 图片3.png](https:\u002F\u002Fnews.cau.edu.cn\u002Fimages\u002F2026-09\u002F76d4db4425564fd28a022cfd32166839.png)\n\n图3 有无稳定性指数组时，产量反演精度和特征重要性之间的差异\n\n图3展示了稳定性指数组（SIG）对小区产量反演精度的提升效果。引入SIG后，全生育期决定系数R²由0.344–0.629提升至0.512–0.701，RMSE与MAE同步下降。生育前期精度偏低，7月3日与10日R²分别由0.473、0.440升至0.512、0.520；随生育进程推进，模型表现持续改善，8月23日R²达全季最高0.701（无稳定性指数组时R²为0.629）。特征重要性分析显示，RHa_mean始终为最关键预测因子，而Ta_stability、Tl_stability、RHa_stability与 Tc_stability均进入前十，稳定性特征整体贡献超过61%。结果表明，SIG有效整合了株间变异信息，显著增强了模型对产量差异的解释能力与全生育期预测精度。\n\n![Image 4: 图片4.png](https:\u002F\u002Fnews.cau.edu.cn\u002Fimages\u002F2026-09\u002F1395532013ea4c71a7612cd15fbd7773.png)\n\n图4 棉花吐絮进程动态监测与基于CTSI指数的机械化收获决策框架\n\n论文三则瞄准棉花机械化收获中吐絮集中度评价这一产业痛点，开发了基于视觉基础模型的DINO-BollGX检测框架，结合两年期383个品种的多时相无人机影像，重建了小区尺度吐絮动态时序曲线，提出了棉花吐絮时间稳定性指数（CTSI），并将其与时间风险函数耦合生成收获决策曲线，为品种适宜机收性评价和最优收获窗口确定提供了定量化工具。\n\n![Image 5: 图片5.png](https:\u002F\u002Fnews.cau.edu.cn\u002Fimages\u002F2026-09\u002F6711154c55a84f5c8dd2f980c6a7f9e3.png)\n\n图5 383个品种棉花吐絮时空分布特征及代表性品种动态吐絮曲线聚类分析\n\n图5展示了多时相无人机棉铃吐絮计数的群体与品种尺度动态。群体尺度上，吐絮在时间分布上呈后期集中态势：观测初期（8月中下旬）各小区吐絮量极低，中位数均不足峰值的5%，箱线图四分位距狭窄，表明吐絮进程缓慢且表达微弱；进入9月中下旬后中位数快速攀升，四分位距显著拓宽，标志着吐絮进入加速期；10月14日至20日为吐絮高峰窗口，中位数由131跃升至277铃\u002F小区，约半数季节最大吐絮量在此短期内完成；11月初中位数小幅回落至244，提示吐絮基本完成并伴有少量损耗或遮挡。品种尺度上，383个品种整体表现为前期缓慢、后期快速增长的动态模式，但吐絮起始时间与后期增速差异显著。基于标准化动态特征的K-means聚类进一步将品种划分为两类：紧凑高量型吐絮窗口短（中位6天）、峰值高（中位460铃\u002F小区）、速率快（35铃\u002F天）；延续型窗口长（约60天）、峰值低（144铃\u002F小区）、速率缓（2.4铃\u002F天），两组差异均达极显著水平（p\u003C0.001）。\n\n三篇论文沿棉花“花—株—铃”的生育主线层层递进，形成了从器官识别、个体解析到群体决策的完整技术体系。这一系列成果的核心意义在于，将人工智能与高通量表型技术深度融合，为棉花育种从传统的经验选择向数据驱动的精准筛选转型提供了系统性解决方案。当前，我国棉花种质资源丰富但表型评价手段仍相对滞后，大量优异种质因缺乏高效、标准化的表型鉴定而未能被充分发掘利用。未来，团队将聚焦更多元化的棉花种质资源群体，结合新疆、河南等不同生态区的目标环境特征，拓展表型解析框架在不同棉区和种植制度下的适用性与泛化能力；同时，进一步整合数字孪生、作物生长模型与基因组信息，构建贯通“表型—基因型—环境—管理”的棉花智能设计体系，为我国棉花种业振兴和智慧农业的高质量发展提供核心技术支撑。\n\n上述三篇论文的第一作者均为土地科学与技术学院博士研究生陈勉，通讯作者为马韫韬教授。合作者包括中国农业科学院棉花研究所杜雄明研究员、何守朴研究员、耿晓丽副研究员、胡道武副研究员；中国农业科学院生物技术研究所张锐研究员；中国农业大学农学院田晓莉教授等，研究得到了国家重点研发计划、国家自然科学基金等项目的资助支持。","中国农业大学新闻网","2026-09-01T00:00:00Z","报道",true,89,{"impact":88,"substance":88,"depth":89,"authority":90,"freshness":91,"relevant":22,"comment":92},24,20,13,8,"中国农大团队在棉花AI表型领域发表三篇系列论文，构建全生育期技术链条，方法新颖、数据详实，对智慧育种和机收决策有重要支撑。",[94],{"name":82,"url":79},[27,96,29,31,97],"农业人工智能","作物表型",[99,100],"农业人工智能 无人机遥感 作物表型 智慧农业","农业人工智能 无人机遥感","农业人工智能无人机遥感作物表型智慧农业-1499","2026-09-03T00:06:43.550281Z",{"id":104,"title":105,"url":106,"summary":107,"summary_zh":9,"content":9,"source_name":108,"source_url":106,"published_at":109,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":110,"score_detail":111,"sources":114,"tags":116,"search_phrases":118,"slug":121,"view_count":36,"doi":122,"paper":123,"created_at":137},1270,"Tendencias en agricultura y silvicultura de precisión: un análisis bibliométrico de la integración de datos, el apoyo a la toma de decisiones y la sostenibilidad","https:\u002F\u002Fdoi.org\u002F10.69639\u002Farandu.v13i3.2452","Este estudio analiza las tendencias y la estructura conceptual de la investigación sobre agricultura y silvicultura de precisión, con énfasis en la integración de datos, los sistemas de apoyo a la toma de decisiones y la sostenibilidad. Se desarrolló un análisis bibliométrico de documentos indexados en Web of Science y Scopus, recuperados mediante una estrategia de búsqueda orientada a identificar estudios relacionados con tecnologías digitales, inteligencia artificial, teledetección, IoT, modelización predictiva y gestión sostenible. El proceso de selección documental siguió criterios de depuración basados en PRISMA, clasificación por cuartiles y revisión de metadatos, obteniéndose un corpus final de 411 documentos publicados entre 2003 y 2026. Los resultados evidencian un crecimiento acelerado de la producción científica, con una alta concentración de literatura reciente y una estructura temática organizada en torno a temas motores, básicos, de nicho y emergentes. Los clústeres de precision agriculture y smart agriculture se identificaron como núcleos articuladores del campo, mientras que inteligencia artificial, IoT y seguridad alimentaria funcionaron como bases transversales. Asimismo, la agricultura digital, la gobernanza tecnológica, el aprendizaje por refuerzo y las redes neuronales convolucionales aparecen como líneas especializadas o en desarrollo. Se concluye que el mapa temático permite reconocer patrones de centralidad y densidad que diferencian tendencias consolidadas, especializadas y emergentes, aportando una visión ordenada para orientar futuras investigaciones sobre sistemas agroforestales inteligentes, adaptativos y sostenibles.","Arandu-UTIC.","2026-08-29T00:00:00Z",69,{"impact":17,"substance":89,"depth":17,"authority":13,"freshness":112,"relevant":22,"comment":113},3,"基于411篇文献的计量分析，揭示精准农业与林业研究趋势，对智慧农业领域有参考价值。",[115],{"name":108,"url":106},[27,96,28,117,30],"可持续发展",[119,120],"农业人工智能 可持续发展 农业遥感 智慧农业","农业人工智能 可持续发展","农业人工智能可持续发展农业遥感智慧农业-1270","10.69639\u002Farandu.v13i3.2452",{"doi":122,"openalex_id":124,"authors":125,"venue":108,"cited_by_count":36,"oa_url":129,"card":130,"direction":136,"ingested_from":71},"W7204668132",[126],{"name":127,"orcid":128},"Carlos Arturo Carvajal Chávez","https:\u002F\u002Forcid.org\u002F0000-0002-2781-6953","https:\u002F\u002Frevista.utic.edu.py\u002Frevista.ojs\u002Findex.php\u002Frevistas\u002Farticle\u002Fdownload\u002F2452\u002F3991",{"tldr":131,"method":132,"finding":133,"direction":134,"opportunity":135},"通过文献计量分析，梳理精准农业与林业的研究趋势、主题结构和热点方向。","基于Web of Science和Scopus，采用PRISMA筛选，对411篇","精准农业和智慧农业是核心主题，AI、IoT和食品安全为基础，数字农业、强化学习等为新兴方向。","农业人工智能与决策模型","可深入探索强化学习与卷积神经网络在智能农林业系统中的应用，结合数据集成与可持续性，填补新兴技术整合研究的空白。","智慧农业 \u002F 农业物联网","2026-09-01T04:03:13.088508Z",{"id":139,"title":140,"url":141,"summary":142,"summary_zh":9,"content":9,"source_name":143,"source_url":9,"published_at":144,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":145,"score_detail":146,"sources":150,"tags":152,"search_phrases":156,"slug":159,"view_count":36,"doi":9,"paper":160,"created_at":168},3049,"土壤压实与灌溉管理：对精准农业中土壤水力变化的启示","https:\u002F\u002Fwww.mdpi.com\u002F2073-4395\u002F16\u002F18\u002F1853","意大利帕多瓦大学A.C.与L.B.评估土壤压实通过改变土壤水力特性对精准农业灌溉管理的综合影响。研究维护土壤结构作为维持土壤水力功能、提升灌溉效率与农业系统长期可持续性最有效途径，使用HYPROP水力特性分析仪测定田间持水量（FC）、永久萎蔫点（PWP）、饱和水力传导度（Ksat）等关键参数，结合无人机遥感（UAV）与决策支持系统（DSS）实现精准灌溉调度。研究获SOILWAT（BIRD 2026）项目资助，为精准农业管理决策提供可量化水力参数基础。","MDPI Agronomy 16(18):1853","2026-09-20T00:00:00Z",68,{"impact":147,"substance":17,"depth":148,"authority":90,"freshness":21,"relevant":22,"comment":149},12,16,"学术论文，方法结合HYPROP与无人机遥感，对精准灌溉有参考价值，但属细分领域研究，公共影响有限。",[151],{"name":143,"url":141},[153,30,31,154,155],"决策支持系统","智慧灌溉","土壤压实",[157,158],"帕多瓦大学 土壤压实 灌溉","HYPROP 水力特性 精准灌溉","帕多瓦大学土壤压实灌溉-3049",{"doi":9,"openalex_id":9,"authors":161,"venue":9,"cited_by_count":36,"oa_url":9,"card":162,"direction":136,"ingested_from":167},[],{"tldr":163,"method":164,"finding":165,"direction":136,"opportunity":166},"评估土壤压实改变水力特性对精准灌溉管理的影响，并提出维护土壤结构的对策。","用HYPROP测FC、PWP、Ksat，结合无人机遥感与决策支持系统调度灌溉。","维护土壤结构是保持水力功能、提升灌溉效率与长期可持续性的最有效途径。","可探索压实-水力参数-遥感反演耦合模型，实现压实风险与灌溉调度的实时协同优化。","agent","2026-09-21T00:04:39.395594Z",{"id":170,"title":171,"url":172,"summary":173,"summary_zh":174,"content":9,"source_name":175,"source_url":172,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":176,"score_detail":177,"sources":180,"tags":182,"search_phrases":185,"slug":188,"view_count":36,"doi":189,"paper":190,"created_at":202},3019,"PSPE-UNet: Projection-based Similarity Prototype Embedding UNet for Apple Leaf Disease Segmentation","https:\u002F\u002Fdoi.org\u002F10.22266\u002Fijies2026.1031.18","Apple leaf disease segmentation plays a significant role in precision agriculture by enabling the accurate identification and localization of infected regions at the pixel level.However, diverse apple leaf diseases exhibit similar symptoms, such as overlapping lesions makes it challenging to distinguish between various disease classes.In this research, a Projection-based Similarity Prototype Embedding UNet (PSPE-UNet) is proposed to segment apple leaf diseases.Employing a projection head with a similarity prototype embedding in UNet enhances feature discrimination by mapping pixel-level representations into a normalized embedding space.This ensures better separation between healthy and disease regions, even when the regions exhibit similar texture and chromatic characteristics.Three learnable prototypes corresponding to healthy, disease, and boundary regions are used.The boundary prototype act as learnable auxiliary feature prototype within the auxiliary boundary branch to compute boundary probability map during training while disease prediction is based on healthy and disease prototypes.In addition, this method enhances the boundary delineation for irregular and small lesions by refining the feature alignment.Hence, the proposed PSPE-UNet achieves a high Pixel Accuracy (PA) of 98.96%, which is compared to existing methods such as the AS-DeepLabV3+ on the Apple Tree Leaf Disease Segmentation Dataset (ATLDSD).Moreover, proposed PSPE-UNet obtains an inference time of 0.0217s per batch (8 images), corresponding to 0.0027s per image on ATLDSD dataset compared to traditional methods like UNet.","苹果叶片病害分割在精准农业中具有重要意义，能够在像素级别上准确识别和定位感染区域。然而，不同苹果叶片病害表现出相似的症状，例如病灶重叠使得区分不同病害类别具有挑战性。本研究提出了一种基于投影的相似性原型嵌入UNet（PSPE-UNet）用于苹果叶片病害分割。在UNet中采用带有相似性原型嵌入的投影头，通过将像素级表示映射到归一化嵌入空间来增强特征判别能力。这确保了健康和病害区域之间更好的分离，即使这些区域表现出相似的纹理和色彩特征。使用三个可学习原型分别对应健康、病害和边界区域。边界原型在辅助边界分支中作为可学习辅助特征原型，在训练期间计算边界概率图，而病害预测则基于健康和病害原型。此外，该方法通过细化特征对齐增强了对不规则和小病灶的边界描绘。因此，所提出的PSPE-UNet在苹果树叶病害分割数据集（ATLDSD）上达到了98.96%的高像素精度（PA），并与现有方法如AS-DeepLabV3+进行了比较。此外，所提出的PSPE-UNet在ATLDSD数据集上获得了每批次（8张图像）0.0217秒的推理时间，相当于每张图像0.0027秒，与UNet等传统方法相比具有优势。","International journal of intelligent engineering and systems",70,{"impact":147,"substance":89,"depth":178,"authority":147,"freshness":21,"relevant":22,"comment":179},17,"提出基于相似度原型嵌入的UNet分割方法，在苹果叶病害数据集上取得98.96%像素精度，方法新颖、数据明确，但属细分算法研究，产业影响有限。",[181],{"name":175,"url":172},[27,96,30,183,184],"图像分割","苹果病害",[186,187],"PSPE-UNet 苹果叶病害 分割","苹果叶病害 数据集 ATLDSD","PSPE-UNet苹果叶病害分割-3019","10.22266\u002Fijies2026.1031.18",{"doi":189,"openalex_id":191,"authors":192,"venue":175,"cited_by_count":36,"oa_url":172,"card":197,"direction":134,"ingested_from":71},"W7213634285",[193,195],{"name":194,"orcid":9},"Vedamurthy Hadavanahalli Kumaraiah",{"name":196,"orcid":9},"Shrinivasacharya Purohit",{"tldr":198,"method":199,"finding":200,"direction":134,"opportunity":201},"提出PSPE-UNet，用投影相似原型嵌入分割苹果叶片病害区域。","UNet+投影头+可学习原型（健康\u002F病害\u002F边界），ATLDSD数据集。","像素精度98.96%，单图推理0.0027秒，优于AS-DeepLabV3+和UNet。","可探索原型嵌入在相似症状多病害区分及轻量化边缘部署中的泛化能力。","2026-09-20T23:30:34.933307Z",{"id":204,"title":205,"url":206,"summary":207,"summary_zh":9,"content":9,"source_name":208,"source_url":9,"published_at":209,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":210,"score_detail":211,"sources":214,"tags":216,"search_phrases":219,"slug":222,"view_count":36,"doi":9,"paper":223,"created_at":230},3001,"UAV多光谱不同空间分辨率匹配春小麦多性状监测","https:\u002F\u002Fwww.mdpi.com\u002F2073-4395\u002F16\u002F18\u002F1811","天津师范大学张程程等联合天津市农科院农业资源与环境研究所，从原生0.07 m四波段UAV多光谱影像通过像素聚合重采样生成14种空间分辨率（0.07-3.03 m），耦合PROSAIL辐射传输模型与随机森林评估尺度依赖反演性能。研究揭示了叶面积指数（LAI）、叶绿素含量（Cab）和冠层水分含量（Cw）反演精度对空间分辨率的非单调响应，提出物候阶段自适应分辨率策略并开发Heterogeneity-Scale Game Model（HSGM）刻画最优聚合尺度形成机制。","MDPI Agronomy 16(18):1811","2026-09-15T00:00:00Z",74,{"impact":20,"substance":212,"depth":17,"authority":90,"freshness":74,"relevant":22,"comment":213},22,"方法新颖、数据扎实的作物遥感反演研究，对精准农业变量施药与无人机监测有参考价值，但属细分领域学术进展，公共影响有限。",[215],{"name":208,"url":206},[27,30,217,97,218],"遥感","春小麦",[220,221],"天津师范大学 春小麦 多光谱","UAV 多光谱 空间分辨率","天津师范大学春小麦多光谱-3001",{"doi":9,"openalex_id":9,"authors":224,"venue":9,"cited_by_count":36,"oa_url":9,"card":225,"direction":69,"ingested_from":167},[],{"tldr":226,"method":227,"finding":228,"direction":69,"opportunity":229},"用无人机多光谱重采样14种分辨率，结合PROSAIL与随机森林，研究春小麦多性状反演的空间尺度效应。","UAV四波段多光谱像素聚合重采样，耦合PROSAIL模型与随机森林反演LAI、C","反演精度对空间分辨率呈非单调响应，提出物候自适应分辨率策略与HSGM模型。","可探索不同作物与物候下最优分辨率普适规律，并将尺度自适应策略嵌入实时无人机监测系统。","2026-09-20T00:03:08.168753Z",{"id":232,"title":233,"url":234,"summary":235,"summary_zh":9,"content":9,"source_name":236,"source_url":9,"published_at":237,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":238,"score_detail":239,"sources":242,"tags":244,"search_phrases":247,"slug":250,"view_count":36,"doi":9,"paper":251,"created_at":258},2997,"基于无人机多光谱图像和VGG21模型的小麦渍害调控效果识别方法","https:\u002F\u002Fwww.toutiao.com\u002Farticle\u002F7685741381196825088","江苏省农业科学院农业信息研究所梁万杰等联合中国农科院农业环境与可持续发展研究所、湖北粮作所、扬州大学等团队，针对小麦渍害防控提出基于无人机多光谱图像和VGG21模型的快速无损识别方法。在小麦拔节-抽穗和抽穗-灌浆两个阶段开展对照、渍水胁迫、硅肥调控和氨基酸调控4个类别数据集，大疆精灵4多光谱无人机采集小麦冠层多光谱图像，测产评估调控效果。","智慧农业(中英文)2026,8(4):60-69","2026-09-15T12:42:00Z",78,{"impact":17,"substance":212,"depth":17,"authority":240,"freshness":74,"relevant":22,"comment":241},14,"多机构协作提出无人机多光谱结合VGG21的小麦渍害无损识别方法，方法新颖、数据扎实，对智慧农业植保监测有参考价值。",[243],{"name":236,"url":234},[27,96,31,245,246],"小麦渍害","多光谱成像",[248,249],"江苏省农科院 小麦渍害 无人机多光谱","VGG21 小麦 渍害识别","江苏省农科院小麦渍害无人机多光谱-2997",{"doi":9,"openalex_id":9,"authors":252,"venue":9,"cited_by_count":36,"oa_url":9,"card":253,"direction":69,"ingested_from":167},[],{"tldr":254,"method":255,"finding":256,"direction":69,"opportunity":257},"用无人机多光谱图像和VGG21模型识别小麦渍害调控效果。","大疆精灵4多光谱无人机采集冠层图像，构建VGG21分类模型。","该方法可快速无损识别渍害及硅肥、氨基酸调控效果。","可探索多光谱与深度学习结合评估其他逆境调控措施，并迁移至多作物场景。","2026-09-20T00:03:07.858899Z"]