[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-1499":3,"related-1499":74},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":8,"published_at":11,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":23,"tags":25,"primary_topic":31,"secondary_topics":37,"classification":38,"search_phrases":69,"slug":72,"view_count":53,"doi":8,"paper":8,"created_at":73},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。",null,"**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",10,true,89,{"impact":17,"substance":17,"depth":18,"authority":19,"freshness":20,"relevant":21,"comment":22},24,20,13,8,1,"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。",[24],{"name":10,"url":6},[26,27,28,29,30],"智慧农业","农业人工智能","棉花","无人机遥感","作物表型",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},"A6","cash-crops","棉麻糖与特色经作","\u002Ftopic\u002Ffield-crops\u002Fcash-crops","A",[],{"status":39,"locked":40,"version":41,"method":42,"evidence":43},"classified",false,"2026-10-22.2","rules",{"candidates":44,"agricultural_evidence":14},[45,51,58,64],{"code":32,"score":46,"supported":14,"title":47,"abstract":48,"tags":50},15,[28],[28,49],"cotton",[28],{"code":52,"score":53,"supported":14,"title":54,"abstract":55,"tags":57},"I1",4,[],[56],"precision agriculture",[26],{"code":59,"score":60,"supported":40,"title":61,"abstract":62,"tags":63},"I3",2,[],[],[30,29],{"code":65,"score":21,"supported":40,"title":66,"abstract":67,"tags":68},"I2",[],[],[27],[70,71],"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",{"total":75,"page":21,"page_size":75,"items":76},6,[77,142,196,288,371,416],{"id":78,"title":79,"url":80,"summary":81,"summary_zh":8,"content":8,"source_name":82,"source_url":8,"published_at":83,"category":84,"cover_url":8,"hotness":13,"is_selected":40,"score":85,"score_detail":86,"sources":92,"tags":94,"primary_topic":97,"secondary_topics":98,"classification":104,"search_phrases":127,"slug":130,"view_count":131,"doi":8,"paper":132,"created_at":141},5532,"精准棉花病害管理：融合无人机影像与定制YOLO深度学习框架","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.24182","研究提出单阶段全卷积检测器Cotton-Vision，融合幽灵瓶颈通道注意力与跨阶段部分融合三项轻量化设计，参数减少20%。在巴基斯坦旁遮普省7个棉田采集的2700余幅高分辨率无人机影像上测试，精确率97.7%、召回率77.7%、mAP@50为85.6%，较主流基线提升10至20个百分点。预印本，仅在巴基斯坦单一区域验证。","arXiv 预印本 2026-10-16","2026-10-16T00:00:00Z","论文",69,{"impact":87,"substance":88,"depth":89,"authority":90,"freshness":75,"relevant":21,"comment":91},16,21,17,9,"方法轻量化与实测数据有增量，但仅单区域预印本验证，属细分技术进展，可入精选备选。",[93],{"name":82,"url":80},[26,27,95,29,96],"目标检测","棉花病害",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[99],{"code":65,"slug":100,"name":101,"path":102,"parent_code":103},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":39,"locked":40,"version":41,"method":42,"evidence":105},{"candidates":106,"agricultural_evidence":14},[107,114,119,123],{"code":65,"score":108,"supported":14,"title":109,"abstract":112,"tags":113},18,[110,111],"深度学习","YOLO",[],[27,95],{"code":32,"score":115,"supported":14,"title":116,"abstract":117,"tags":118},11,[28],[49],[],{"code":52,"score":21,"supported":40,"title":120,"abstract":121,"tags":122},[],[],[26],{"code":59,"score":21,"supported":40,"title":124,"abstract":125,"tags":126},[],[],[29],[128,129],"Cotton-Vision 棉花病害","无人机影像 棉花 检测","Cotton-Vision棉花病害-5532",0,{"doi":8,"openalex_id":8,"authors":133,"venue":8,"cited_by_count":131,"oa_url":8,"card":134,"direction":138,"ingested_from":140},[],{"tldr":135,"method":136,"finding":137,"direction":138,"opportunity":139},"提出轻量化检测器Cotton-Vision，用无人机影像精准识别棉花病害。","基于YOLO改进，融合幽灵瓶颈通道注意力与跨阶段部分融合，用2700余幅无人机影","精确率97.7%、mAP@50达85.6%，较主流基线提升10至20个百分点。","农业遥感与作物表型","仅在巴基斯坦单一区域验证，可扩展至多区域多品种，并探索边缘设备实时部署。","agent","2026-10-22T00:07:09.816790Z",{"id":143,"title":144,"url":145,"summary":146,"summary_zh":8,"content":8,"source_name":147,"source_url":8,"published_at":8,"category":84,"cover_url":8,"hotness":13,"is_selected":40,"score":148,"score_detail":149,"sources":152,"tags":154,"primary_topic":157,"secondary_topics":158,"classification":160,"search_phrases":183,"slug":186,"view_count":131,"doi":8,"paper":187,"created_at":195},4966,"基于改进YOLO 11n模型的棉花田间复杂环境障碍物检测方法","http:\u002F\u002Fwww.qikanzj.com\u002Fhek\u002Fnyjxxb\u002Fmulu\u002F455619.html","韩科立、王振坤等(中国农业机械化科学研究院集团有限公司;现代农装科技股份有限公司;农业装备技术全国重点实验室)针对棉花田间复杂环境障碍物被遮挡致准确检测难、边缘设备算力有限的问题,提出一种基于改进YOLO 11n模型的田间障碍物检测方法。采用StarNet作为主要特征提取网络并引入DBA模块增强多尺度特征交互能力;使用KAGNConv替换C3k2瓶颈结构增强灵活性与可解释性;集成分离与增强注意力模块SEAM至检测头增强遮挡场景能力。试验结果表明,改进模型YOLO 11n-SKS精确率、召回率、mAP50、mAP50-95分别提升2.3、2.1、1.3、1.4个百分点,达到91.7%、88.3%、91.9%、62.3%。","《农业机械学报》",71,{"impact":87,"substance":88,"depth":108,"authority":150,"freshness":60,"relevant":21,"comment":151},14,"改进YOLO 11n实现棉花田间遮挡障碍物检测，方法新颖、指标提升明确，属农业人工智能细分领域实质进展，但发布日期未知、时效性偏弱。",[153],{"name":147,"url":145},[26,27,28,155,156],"障碍物检测","采棉机",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[159],{"code":65,"slug":100,"name":101,"path":102,"parent_code":103},{"status":39,"locked":40,"version":41,"method":42,"evidence":161},{"candidates":162,"agricultural_evidence":14},[163,168,172,179],{"code":32,"score":164,"supported":14,"title":165,"abstract":166,"tags":167},12,[28],[28],[28],{"code":65,"score":164,"supported":14,"title":169,"abstract":170,"tags":171},[111],[111],[27],{"code":173,"score":75,"supported":14,"title":174,"abstract":175,"tags":178},"F5",[],[176,177],"农业机械","机械化",[],{"code":52,"score":21,"supported":40,"title":180,"abstract":181,"tags":182},[],[],[26],[184,185],"中国农业机械化科学研究院 采棉机 障碍物检测","YOLO 11n 棉花 田间障碍物","中国农业机械化科学研究院采棉机障碍物检测-4966",{"doi":8,"openalex_id":8,"authors":188,"venue":8,"cited_by_count":131,"oa_url":8,"card":189,"direction":193,"ingested_from":140},[],{"tldr":190,"method":191,"finding":192,"direction":193,"opportunity":194},"提出改进YOLO 11n模型，实现棉花田间复杂遮挡环境下障碍物高精度检测。","以StarNet为骨干，引入DBA、KAGNConv与SEAM注意力模块，改进Y","改进模型精确率91.7%、召回率88.3%、mAP50达91.9%，各项指标均提升。","农业人工智能与决策模型","可探索轻量化模型在边缘设备实时部署，并扩展至多作物多类障碍物检测。","2026-10-15T00:06:08.577388Z",{"id":197,"title":198,"url":199,"summary":200,"summary_zh":201,"content":8,"source_name":202,"source_url":199,"published_at":203,"category":84,"cover_url":8,"hotness":13,"is_selected":40,"score":204,"score_detail":205,"sources":209,"tags":211,"primary_topic":214,"secondary_topics":215,"classification":220,"search_phrases":249,"slug":252,"view_count":53,"doi":253,"paper":254,"created_at":287},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。","Remote Sensing of Environment","2026-09-19T00:00:00Z",84,{"impact":108,"substance":206,"depth":207,"authority":46,"freshness":90,"relevant":21,"comment":208},23,19,"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。",[210],{"name":202,"url":199},[26,212,28,213,29],"农业遥感","精准农业",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[216],{"code":59,"slug":217,"name":218,"path":219,"parent_code":103},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":39,"locked":40,"version":41,"method":42,"evidence":221},{"candidates":222,"agricultural_evidence":14},[223,227,231,237,244],{"code":32,"score":90,"supported":14,"title":224,"abstract":225,"tags":226},[49],[],[28],{"code":52,"score":20,"supported":14,"title":228,"abstract":229,"tags":230},[],[213,56],[26,213],{"code":59,"score":20,"supported":14,"title":232,"abstract":233,"tags":236},[],[234,235],"遥感","remote sensing",[212,29],{"code":238,"score":75,"supported":14,"title":239,"abstract":240,"tags":243},"H3",[],[241,242],"灌溉","irrigation",[],{"code":65,"score":75,"supported":14,"title":245,"abstract":246,"tags":248},[],[110,247],"deep learning",[],[250,251],"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","10.1016\u002Fj.rse.2026.115674",{"doi":253,"openalex_id":255,"authors":256,"venue":202,"cited_by_count":131,"oa_url":199,"card":281,"direction":138,"ingested_from":286},"W7213661690",[257,260,262,264,266,268,271,274,276,279],{"name":258,"orcid":259},"Qing Li","https:\u002F\u002Forcid.org\u002F0009-0004-4580-7761",{"name":261,"orcid":8},"Dalei Hao",{"name":263,"orcid":8},"Jan Pisek",{"name":265,"orcid":8},"Zicheng Ji",{"name":267,"orcid":8},"Yanan Wei",{"name":269,"orcid":270},"Youngryel Ryu","https:\u002F\u002Forcid.org\u002F0000-0001-6238-2479",{"name":272,"orcid":273},"Jiarui Xu","https:\u002F\u002Forcid.org\u002F0000-0003-4925-2770",{"name":275,"orcid":8},"Yangmin Feng",{"name":277,"orcid":278},"Shaozhong Kang","https:\u002F\u002Forcid.org\u002F0000-0002-8019-2537",{"name":280,"orcid":8},"Yelu Zeng",{"tldr":282,"method":283,"finding":284,"direction":138,"opportunity":285},"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。","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",{"id":289,"title":290,"url":291,"summary":292,"summary_zh":293,"content":8,"source_name":294,"source_url":291,"published_at":295,"category":84,"cover_url":8,"hotness":13,"is_selected":40,"score":296,"score_detail":297,"sources":299,"tags":301,"primary_topic":304,"secondary_topics":305,"classification":307,"search_phrases":335,"slug":338,"view_count":326,"doi":339,"paper":340,"created_at":370},2288,"Field-based deep learning classification of cotton and weeds for machine-vision-assisted intra-row weed management","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.atech.2026.102567","Timely and precise weed management is essential for reducing crop-weed competition, labour requirements, and unnecessary weed-control inputs in cotton production. Reliable discrimination between cotton plants and weeds is a prerequisite for automated intra-row weed management. This study evaluated two pretrained convolutional neural network models, MobileNetV2 and DenseNet169, for binary classification of cotton and weeds using field-acquired RGB images. Images were collected from a farmer-managed cotton field in Haryana and an experimental cotton field at ICAR-Indian Agricultural Research Institute, New Delhi, during May-September 2025 under natural field conditions. The dataset comprised 2,195 weed images representing six predominant weed species and 1,211 cotton images. Images were classified into two operational classes, cotton and weed. Training images were augmented to address the original class imbalance, whereas validation and test images were retained without augmentation. Transfer learning was used to fine-tune both models, and performance was evaluated using accuracy, precision, recall, F1-score, confusion matrices, and inference time. Both models achieved high classification performance. DenseNet169 attained a test accuracy of 99.47%, compared with 98.27% for MobileNetV2. The results indicate that pretrained CNNs can provide accurate image-level discrimination between cotton and weed vegetation under the investigated field conditions. DenseNet169 therefore shows promise as a visual-perception component for machine-vision-assisted intra-row weed management. However, the present study is limited to image-level classification and does not demonstrate plant localization, continuous machine operation, actuator coordination, or field-scale weed removal. Further validation under independent locations, varying weed densities, illumination conditions, machine travel speeds, and complete perception-decision-actuation pipelines is required.","及时、精准的杂草管理对于减少棉花生产中的棉草竞争、劳动力需求和不必要的除草投入至关重要。可靠地区分棉花植株与杂草是实现行内自动化杂草管理的前提。本研究评估了两种预训练卷积神经网络模型——MobileNetV2和DenseNet169，利用田间采集的RGB图像对棉花与杂草进行二分类。图像于2025年5月至9月期间，在自然田间条件下，采集自哈里亚纳邦一处农民管理的棉田以及新德里ICAR-印度农业研究所的实验棉田。数据集包含2，195幅杂草图像，涵盖六种主要杂草种类，以及1，211幅棉花图像。图像被分为棉花和杂草两个操作类别。训练图像经过增强处理以解决原始类别不平衡问题，而验证和测试图像则保留未增强状态。采用迁移学习对两种模型进行微调，并使用准确率、精确率、召回率、F1分数、混淆矩阵和推理时间评估性能。两种模型均取得了较高的分类性能。DenseNet169的测试准确率达到99.47%，而MobileNetV2为98.27%。结果表明，预训练卷积神经网络能够在所研究的田间条件下实现棉花与杂草植被在图像层面的准确区分。因此，DenseNet169有望作为机器视觉辅助行内杂草管理的视觉感知组件。然而，本研究仅限于图像层面的分类，并未展示植株定位、机器连续作业、执行器协调或田间规模除草。仍需在独立地点、不同杂草密度、光照条件、机器行进速度以及完整的感知-决策-执行流程下进行进一步验证。","Smart Agricultural Technology","2026-09-11T00:00:00Z",67,{"impact":164,"substance":108,"depth":87,"authority":19,"freshness":20,"relevant":21,"comment":298},"基于田间RGB图像的棉花与杂草深度学习分类研究，DenseNet169测试准确率达99.47%，方法扎实但仅限图像级分类，尚缺定位与执行环节验证，属细分领域技术进展。",[300],{"name":294,"url":291},[26,27,28,302,303],"杂草识别","机器视觉",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[306],{"code":65,"slug":100,"name":101,"path":102,"parent_code":103},{"status":39,"locked":40,"version":41,"method":42,"evidence":308},{"candidates":309,"agricultural_evidence":14},[310,314,318,324,331],{"code":32,"score":46,"supported":14,"title":311,"abstract":312,"tags":313},[49],[28,49],[28],{"code":65,"score":13,"supported":14,"title":315,"abstract":316,"tags":317},[247],[],[27,303],{"code":319,"score":53,"supported":14,"title":320,"abstract":321,"tags":323},"F4",[],[322],"除草",[302],{"code":325,"score":326,"supported":14,"title":327,"abstract":328,"tags":330},"A4",3,[],[329],"花生",[],{"code":52,"score":21,"supported":40,"title":332,"abstract":333,"tags":334},[],[],[26],[336,337],"农业人工智能 智慧农业 机器视觉 杂草识别","农业人工智能 智慧农业","农业人工智能智慧农业机器视觉杂草识别-2288","10.1016\u002Fj.atech.2026.102567",{"doi":339,"openalex_id":341,"authors":342,"venue":294,"cited_by_count":131,"oa_url":291,"card":365,"direction":193,"ingested_from":286},"W7212315230",[343,345,348,351,354,356,359,361,363],{"name":344,"orcid":8},"Shaik Nasreen",{"name":346,"orcid":347},"Roaf Ahmad Parray","https:\u002F\u002Forcid.org\u002F0000-0002-8303-1990",{"name":349,"orcid":350},"Parveen Dhanger","https:\u002F\u002Forcid.org\u002F0000-0001-5250-0275",{"name":352,"orcid":353},"Rishi Raj","https:\u002F\u002Forcid.org\u002F0009-0002-7918-1141",{"name":355,"orcid":8},"Tapan Kumar Khura",{"name":357,"orcid":358},"P. Sahoo","https:\u002F\u002Forcid.org\u002F0000-0002-3888-8506",{"name":360,"orcid":8},"Tushar Dhar",{"name":362,"orcid":8},"Prajwal R",{"name":364,"orcid":8},"Sripriyanka S. Nalla",{"tldr":366,"method":367,"finding":368,"direction":193,"opportunity":369},"用MobileNetV2和DenseNet169对田间棉花与杂草图像做二分类，验证机器视觉除草可行性","迁移学习微调两种预训练CNN，使用2025年田间RGB图像共3406张。","DenseNet169测试准确率达99.47%，优于MobileNetV2的98.27%。","可延伸至植株定位、多光照与密度条件下的感知-决策-执行全流程田间验证。","2026-09-13T23:30:04.183782Z",{"id":372,"title":373,"url":374,"summary":375,"summary_zh":8,"content":8,"source_name":376,"source_url":8,"published_at":377,"category":12,"cover_url":8,"hotness":13,"is_selected":40,"score":378,"score_detail":379,"sources":383,"tags":385,"primary_topic":388,"secondary_topics":389,"classification":390,"search_phrases":411,"slug":414,"view_count":60,"doi":8,"paper":8,"created_at":415},2228,"棉花所联合西部农业研究中心发布全球首个棉花领域专属大语言模型\"棉芯1.0\"","https:\u002F\u002Fdy.163.com\u002Farticle\u002FL6HM1VUQ05199FC8.html","中国农业科学院棉花研究所联合西部农业研究中心8月下旬发布全球首个棉花领域专属知识大语言模型\"CottonMind1.0\",覆盖棉花种质资源、品种性状、栽培管理、加工利用等全产业链数据,标志着农业AI从通用模型向行业垂直深耕转向。","中国农业科学院 布瑞克农业数据","2026-09-10T16:00:00Z",85,{"impact":380,"substance":381,"depth":89,"authority":150,"freshness":75,"relevant":21,"comment":382},26,22,"全球首个棉花领域专属大语言模型，覆盖全产业链数据，标志农业AI向垂直深耕转型，产业级突破值得入选。",[384],{"name":376,"url":374},[26,27,386,387,28],"种业振兴","大语言模型",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":40,"version":41,"method":42,"evidence":391},{"candidates":392,"agricultural_evidence":14},[393,397,403,407],{"code":32,"score":164,"supported":14,"title":394,"abstract":395,"tags":396},[28],[28],[28],{"code":398,"score":53,"supported":14,"title":399,"abstract":400,"tags":402},"F1",[],[401],"种质资源",[386],{"code":65,"score":60,"supported":40,"title":404,"abstract":405,"tags":406},[],[],[27,387],{"code":52,"score":21,"supported":40,"title":408,"abstract":409,"tags":410},[],[],[26],[412,413],"农业人工智能 大语言模型 智慧农业 种业振兴","农业人工智能 大语言模型","农业人工智能大语言模型智慧农业种业振兴-2228","2026-09-13T00:04:00.640632Z",{"id":417,"title":418,"url":419,"summary":420,"summary_zh":421,"content":8,"source_name":422,"source_url":419,"published_at":423,"category":84,"cover_url":8,"hotness":13,"is_selected":40,"score":424,"score_detail":425,"sources":427,"tags":429,"primary_topic":431,"secondary_topics":432,"classification":434,"search_phrases":451,"slug":453,"view_count":326,"doi":454,"paper":455,"created_at":478},1878,"Decoding Electro-Priming responses in cotton using an integrated taguchi-machine learning framework for optimizing seed performance","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112362","Decoding Electro-Priming responses in cotton using an integrated taguchi-machine learning framework for optimizing seed performance。Computers and Electronics in Agriculture","利用集成田口-机器学习框架解析棉花电引发响应以优化种子性能。《农业中的计算机与电子》","Computers and Electronics in Agriculture","2026-09-07T00:00:00Z",62,{"impact":164,"substance":108,"depth":87,"authority":150,"freshness":60,"relevant":21,"comment":426},"研究结合田口法与机器学习优化棉花电引发种子处理，方法新颖，但发表于2026年9月7日，时效性较低，影响范围限于特定作物领域。",[428],{"name":422,"url":419},[26,27,28,430],"种子处理",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[433],{"code":65,"slug":100,"name":101,"path":102,"parent_code":103},{"status":39,"locked":40,"version":41,"method":42,"evidence":435},{"candidates":436,"agricultural_evidence":14},[437,441,447],{"code":32,"score":46,"supported":14,"title":438,"abstract":439,"tags":440},[49],[28,49],[28],{"code":65,"score":46,"supported":14,"title":442,"abstract":444,"tags":446},[443],"machine learning",[445,443],"机器学习",[27],{"code":52,"score":21,"supported":40,"title":448,"abstract":449,"tags":450},[],[],[26],[452,337],"农业人工智能 智慧农业 种子处理 棉花","农业人工智能智慧农业种子处理棉花-1878","10.1016\u002Fj.compag.2026.112362",{"doi":454,"openalex_id":456,"authors":457,"venue":422,"cited_by_count":131,"oa_url":8,"card":473,"direction":193,"ingested_from":286},"W7211870713",[458,461,464,466,468,471],{"name":459,"orcid":460},"Muhammad Aasım","https:\u002F\u002Forcid.org\u002F0000-0002-8524-9029",{"name":462,"orcid":463},"Ramazan Katırcı","https:\u002F\u002Forcid.org\u002F0000-0003-2448-011X",{"name":465,"orcid":8},"Salma Naimatullah Soomro",{"name":467,"orcid":8},"Sabeen Rehman Soomro",{"name":469,"orcid":470},"Ahmet Say","https:\u002F\u002Forcid.org\u002F0000-0001-5259-7580",{"name":472,"orcid":8},"Seyid Amjad Ali",{"tldr":474,"method":475,"finding":476,"direction":193,"opportunity":477},"用田口-机器学习框架优化棉花种子电引发处理，提升种子性能。","田口实验设计与机器学习集成框架。","电引发参数可优化，显著提升棉花种子性能。","可扩展至其他作物或种子处理方式，探索机器学习在农业实验优化中的应用。","2026-09-08T23:30:01.361561Z"]