[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3129":3,"related-3129":85},{"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":22,"tags":24,"primary_topic":30,"secondary_topics":36,"classification":37,"search_phrases":54,"slug":57,"view_count":58,"doi":59,"paper":60,"created_at":84},3129,"Vis\u002FNIR spectroscopy coupled with wavelength-optimized Monte Carlo simulation for non-destructive SSC detection of apples of different sizes","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112448","Vis\u002FNIR spectroscopy coupled with wavelength-optimized Monte Carlo simulation for non-destructive SSC detection of apples of different sizes。Computers and Electronics in Agriculture","可见\u002F近红外光谱（Vis\u002FNIR spectroscopy）结合波长优化的蒙特卡洛模拟用于不同大小苹果可溶性固形物含量（SSC）的无损检测。《计算机与电子农业》",null,"Computers and Electronics in Agriculture","2026-09-22T00:00:00Z","论文",10,false,81,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":13,"relevant":20,"comment":21},18,21,14,1,"核心期刊论文，提出波长优化蒙特卡洛模拟方法解决不同尺寸苹果可溶性固形物无损检测难题，方法新颖、结论可靠，对果园智能分选与品质检测有直接参考价值。",[23],{"name":10,"url":6},[25,26,27,28,29],"智慧农业","无损检测","苹果","可见近红外光谱","蒙特卡洛模拟",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},"B2","fruit","果树","\u002Ftopic\u002Fhorticulture\u002Ffruit","B",[],{"status":38,"locked":14,"version":39,"method":40,"evidence":41},"classified","2026-10-22.2","rules",{"candidates":42,"agricultural_evidence":45},[43,49],{"code":31,"score":44,"supported":45,"title":46,"abstract":47,"tags":48},4,true,[],[27],[27],{"code":50,"score":20,"supported":14,"title":51,"abstract":52,"tags":53},"I1",[],[],[25],[55,56],"苹果 SSC 无损检测","Vis NIR 光谱 苹果","苹果SSC无损检测-3129",5,"10.1016\u002Fj.compag.2026.112448",{"doi":59,"openalex_id":61,"authors":62,"venue":10,"cited_by_count":76,"oa_url":6,"card":77,"direction":81,"ingested_from":83},"W7213978130",[63,66,68,70,72,74],{"name":64,"orcid":65},"C. N. Sun","https:\u002F\u002Forcid.org\u002F0009-0003-9732-8570",{"name":67,"orcid":9},"An He",{"name":69,"orcid":9},"Lei Zhang",{"name":71,"orcid":9},"Yaxiang Peng",{"name":73,"orcid":9},"Zhiming Guo",{"name":75,"orcid":9},"Xiaobo Zou",0,{"tldr":78,"method":79,"finding":80,"direction":81,"opportunity":82},"结合可见\u002F近红外光谱与波长优化蒙特卡洛模拟，实现不同大小苹果可溶性固形物无损检测。","Vis\u002FNIR光谱结合波长优化蒙特卡洛模拟，建立不同尺寸苹果SSC预测模型。","波长优化蒙特卡洛模拟能校正苹果尺寸差异，提升SSC无损检测精度。","农业遥感与作物表型","可探索将尺寸自适应蒙特卡洛模拟推广至其他水果及多品质参数同步检测。","openalex","2026-09-22T23:30:01.856917Z",{"total":86,"page":20,"page_size":86,"items":87},6,[88,174,267,312,384,427],{"id":89,"title":90,"url":91,"summary":92,"summary_zh":93,"content":9,"source_name":94,"source_url":91,"published_at":95,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":96,"score_detail":97,"sources":102,"tags":104,"primary_topic":108,"secondary_topics":109,"classification":121,"search_phrases":151,"slug":154,"view_count":44,"doi":155,"paper":156,"created_at":173},3607,"Analysis of drought carry-over effect on apple trees using the Leafiness-LiDAR index","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.biosystemseng.2026.104603","Apple trees ( Malus × domestica Borkh.) are widely grown in Mediterranean regions, where drought-induced irrigation restrictions can impair canopy development and productivity. This study assessed the Leafiness-LiDAR Index (LLI), derived from terrestrial Light Detection and Ranging (LiDAR) point clouds, as a proxy for Leaf Area Index (LAI) and as a non-destructive indicator of canopy response and recovery following water deficit. An ‘Opal®’ apple orchard was monitored over three growing seasons (2023–2025), encompassing one drought year and two recovery years. In 2023, full irrigation (FI; 480 mm) was compared with deficit irrigation (DI; 300 mm; 37.5% less water) under two planting densities (0.5 and 1.0 m tree spacing). Mixed-effects models revealed significant Year × Irrigation interactions for LAI (p = 0.006) and LLI (p \u003C 0.001), but not for yield (p = 0.654), suggesting a partial decoupling between structural and productive recovery. During the drought year, DI reduced LLI by 37% and yield by 47%. Following irrigation restoration, LLI differences persisted, particularly in 2024, indicating lasting structural effects of water deficit. Higher planting density promoted canopy recovery and increased yield. LLI proved to be a valuable, non-destructive estimator of LAI for detecting drought legacy effects and tracking canopy recovery, supporting precision orchard management under Mediterranean water scarcity.","苹果树（Malus × domestica Borkh.）广泛种植于地中海地区，该地区因干旱导致的灌溉限制会损害树冠发育和生产力。本研究评估了基于地面激光雷达（LiDAR）点云衍生的叶量-激光雷达指数（Leafiness-LiDAR Index, LLI）作为叶面积指数（Leaf Area Index, LAI）的替代指标，以及作为水分亏缺后树冠响应与恢复的非破坏性指标的可行性。对一个‘Opal®’苹果园进行了三个生长季（2023—2025年）的监测，涵盖一个干旱年和两个恢复年。2023年，在两种种植密度（株距0.5 m和1.0 m）下，比较了充分灌溉（FI；480 mm）与亏缺灌溉（DI；300 mm；减少37.5%水量）。混合效应模型显示，LAI（p = 0.006）和LLI（p \u003C 0.001）存在显著的年×灌溉交互作用，而产量（p = 0.654）则无此交互作用，表明结构与产量恢复之间存在部分脱耦。在干旱年，DI使LLI降低37%，产量降低47%。灌溉恢复后，LLI差异持续存在，尤其在2024年，表明水分亏缺具有持久的结构性影响。较高的种植密度促进了树冠恢复并提高了产量。LLI被证明是一种有价值的、非破坏性的LAI估算指标，可用于检测干旱遗留效应并追踪树冠恢复，为地中海水资源短缺条件下的精准果园管理提供支持。","Biosystems Engineering","2026-09-26T00:00:00Z",77,{"impact":98,"substance":99,"depth":17,"authority":19,"freshness":100,"relevant":20,"comment":101},15,22,8,"地中海苹果园三年试验证实LiDAR叶量指数可无损监测干旱遗留效应与冠层恢复，方法新颖、数据扎实，对果园精准灌溉有参考价值。",[103],{"name":94,"url":91},[25,27,105,106,107],"遥感","果园管理","精准灌溉",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[110,116],{"code":111,"slug":112,"name":113,"path":114,"parent_code":115},"H7","climate","气候适应与防灾减灾","\u002Ftopic\u002Fenvironment\u002Fclimate","H",{"code":117,"slug":118,"name":119,"path":120,"parent_code":115},"H3","irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation",{"status":38,"locked":14,"version":39,"method":40,"evidence":122},{"candidates":123,"agricultural_evidence":45},[124,130,136,142,146],{"code":31,"score":17,"supported":45,"title":125,"abstract":127,"tags":129},[126],"apple",[33,27,128,126],"orchard",[27],{"code":111,"score":19,"supported":45,"title":131,"abstract":133,"tags":135},[132],"drought",[134,132],"干旱",[],{"code":117,"score":13,"supported":45,"title":137,"abstract":138,"tags":141},[],[139,140,118],"灌溉","水资源",[107],{"code":50,"score":20,"supported":14,"title":143,"abstract":144,"tags":145},[],[],[25],{"code":147,"score":20,"supported":14,"title":148,"abstract":149,"tags":150},"I3",[],[],[105],[152,153],"LiDAR 苹果园 干旱","Leafiness-LiDAR Index 苹果","LiDAR苹果园干旱-3607","10.1016\u002Fj.biosystemseng.2026.104603",{"doi":155,"openalex_id":157,"authors":158,"venue":94,"cited_by_count":76,"oa_url":91,"card":168,"direction":81,"ingested_from":83},"W7214458453",[159,162,165],{"name":160,"orcid":161},"Leire Sandonís-Pozo","https:\u002F\u002Forcid.org\u002F0000-0003-2472-0259",{"name":163,"orcid":164},"José Antonio Martínez-Casasnovas","https:\u002F\u002Forcid.org\u002F0000-0003-1480-3632",{"name":166,"orcid":167},"Miquel Pascual","https:\u002F\u002Forcid.org\u002F0000-0002-3329-4207",{"tldr":169,"method":170,"finding":171,"direction":81,"opportunity":172},"用LiDAR叶量指数追踪苹果园干旱遗留效应与冠层恢复。","三年果园试验，地面LiDAR点云提取LLI，混合效应模型分析。","亏缺灌溉使LLI降37%、产量降47%，复水后结构差异仍持续。","可探索LLI与多源遥感融合，构建果园干旱遗留效应早期预警与精准补灌决策模型。","2026-09-27T23:30:09.907348Z",{"id":175,"title":176,"url":177,"summary":178,"summary_zh":179,"content":9,"source_name":180,"source_url":177,"published_at":181,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":182,"sources":185,"tags":187,"primary_topic":191,"secondary_topics":192,"classification":199,"search_phrases":225,"slug":228,"view_count":20,"doi":229,"paper":230,"created_at":266},2656,"DeepPhenoTree-Apple Edition: a multi-site apple phenology RGB annotated dataset with deep learning baseline models","https:\u002F\u002Fdoi.org\u002F10.1186\u002Fs13007-026-01591-w","Abstract In machine learning-driven plant phenotyping, well-annotated image datasets are essential for developing robust models capable of capturing phenological variability across environments. Here, we introduce DeepPhenoTree-Apple Edition , a multi-site and multi-variety RGB image dataset dedicated to the detection of key phenological stages in apple trees. The dataset includes 48,320 time-stamped RGB images acquired across four European orchards of the Apple REFPOP consortium under biological, agronomic, and environmental variability, including differences in genotypes, orchard architectures, phenological development, temperature, and humidity conditions. From this large corpus, a carefully curated subset of 808 representative images was manually annotated. It includes 241,600 expert annotations covering developmental stages from dormant bud to fruit maturity. Images were acquired using a standardized tractor-mounted phenotyping platform equipped with active flash illumination. Active flash illumination was used to reduce illumination variability and homogenize exposure, shadows, and sunlight differences across sites. Phenological structures were annotated following the BBCH scale, with bounding boxes adapted to organ visibility and developmental stage. In addition to the dataset, we provide deep-learning baseline experiments to illustrate detection performance and detection performance across locations.","在机器学习驱动的植物表型分析中，标注良好的图像数据集对于开发能够捕捉不同环境下物候变异的稳健模型至关重要。在此，我们介绍DeepPhenoTree-Apple Edition，一个用于检测苹果树关键物候阶段的多地点、多品种RGB图像数据集。该数据集包含48,320张带有时间戳的RGB图像，采集自Apple REFPOP联盟的四个欧洲果园，涵盖了生物学、农艺学和环境变异，包括基因型、果园结构、物候发育、温度和湿度条件的差异。从这一大型语料库中，我们精心挑选了808张具有代表性的图像子集进行人工标注。该子集包含241,600条专家标注，覆盖从休眠芽到果实成熟的发育阶段。图像使用配备主动闪光照明（active flash illumination）的标准化拖拉机搭载表型分析平台采集。主动闪光照明用于减少光照变异性，并统一不同地点的曝光、阴影和阳光差异。物候结构按照BBCH scale（BBCH尺度）进行标注，边界框根据器官可见性和发育阶段进行调整。除数据集外，我们还提供了深度学习基线实验，以展示检测性能以及不同地点的检测性能。","Plant Methods","2026-09-15T00:00:00Z",{"impact":17,"substance":99,"depth":17,"authority":19,"freshness":183,"relevant":20,"comment":184},9,"多站点苹果物候RGB标注数据集，规模大、标注专业并附深度学习基线，对作物表型与智慧果园研究有实质参考价值。",[186],{"name":180,"url":177},[25,188,27,189,190],"农业人工智能","表型组学","图像数据集",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[193],{"code":194,"slug":195,"name":196,"path":197,"parent_code":198},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":38,"locked":14,"version":39,"method":40,"evidence":200},{"candidates":201,"agricultural_evidence":45},[202,206,214,221],{"code":31,"score":17,"supported":45,"title":203,"abstract":204,"tags":205},[126],[33,27,128,126],[27],{"code":194,"score":17,"supported":45,"title":207,"abstract":209,"tags":213},[208],"deep learning",[210,211,212],"深度学习","机器学习","machine learning",[188],{"code":215,"score":216,"supported":45,"title":217,"abstract":218,"tags":220},"F5",3,[],[219],"tractor",[],{"code":50,"score":20,"supported":14,"title":222,"abstract":223,"tags":224},[],[],[25],[226,227],"农业人工智能 图像数据集 智慧农业 表型组学","农业人工智能 图像数据集","农业人工智能图像数据集智慧农业表型组学-2656","10.1186\u002Fs13007-026-01591-w",{"doi":229,"openalex_id":231,"authors":232,"venue":180,"cited_by_count":76,"oa_url":177,"card":261,"direction":81,"ingested_from":83},"W7213246841",[233,236,238,240,243,246,249,251,253,255,257,259],{"name":234,"orcid":235},"Herearii Metuarea","https:\u002F\u002Forcid.org\u002F0009-0008-2716-0617",{"name":237,"orcid":9},"Abdoul-Djalil Ousseini-Hamza",{"name":239,"orcid":9},"Walter Guerra",{"name":241,"orcid":242},"Francesca Zuffa","https:\u002F\u002Forcid.org\u002F0009-0009-8797-0205",{"name":244,"orcid":245},"Francesco Panzeri","https:\u002F\u002Forcid.org\u002F0009-0005-8774-5201",{"name":247,"orcid":248},"Andrea Patocchi","https:\u002F\u002Forcid.org\u002F0000-0002-0919-2702",{"name":250,"orcid":9},"Lidia Lozano",{"name":252,"orcid":9},"Shauny Van Hoye",{"name":254,"orcid":9},"François Laurens",{"name":256,"orcid":9},"Jeremy Labrosse",{"name":258,"orcid":9},"Pejman Rasti",{"name":260,"orcid":9},"David Rousseau",{"tldr":262,"method":263,"finding":264,"direction":81,"opportunity":265},"发布多站点多品种苹果物候RGB图像数据集，并给出深度学习基线检测模型。","采集4个欧洲果园48320张图像，精选808张按BBCH标框标注，用主动闪光和拖","数据集覆盖从休眠芽到果实成熟的241600个标注，基线模型可跨地点检测物候期。","可基于该多站点数据研究跨环境域适应与物候期细粒度检测，提升模型泛化能力。","2026-09-16T23:30:24.293828Z",{"id":268,"title":269,"url":270,"summary":271,"summary_zh":9,"content":272,"source_name":273,"source_url":9,"published_at":274,"category":275,"cover_url":9,"hotness":13,"is_selected":14,"score":276,"score_detail":277,"sources":282,"tags":284,"primary_topic":289,"secondary_topics":290,"classification":291,"search_phrases":307,"slug":310,"view_count":76,"doi":9,"paper":9,"created_at":311},5516,"上海农科院葡萄团队赴银川参加第47届世界葡萄与葡萄酒大会","https:\u002F\u002Fwww.saas.sh.cn\u002Fhzjl\u002Fgjhz\u002Fcontent_57128","10月12日至16日第47届世界葡萄与葡萄酒大会在银川举办，智慧农业研究中心葡萄团队负责人奚晓军研究员作专题报告，阐明疏穗与环剥处理对果实糖、花青素及脱落酸积累的源库调控机制。团队还观摩酿酒葡萄AI综合作业机器人成果展示，与研发单位围绕葡萄智慧装备与果园智能化管理深入交流。","2026年10月12-16日，第47届世界葡萄与葡萄酒大会在银川举办，智慧农业研究中心葡萄团队负责人奚晓军研究员一行赴会交流。团队围绕“提升葡萄种植生产韧性与可持续发展能力”主题，向全球同行展示最新科研成果。\n\n会上，奚晓军作“Changes in sugar, anthocyanin and ABA accumulation in response to cluster thinning and girdling in ‘Jumeigui’grape”专题报告。报告围绕葡萄疏穗与环剥处理开展研究，阐明源库比对果实糖、花青素及脱落酸积累的调控机制，为葡萄优质栽培技术提供理论支撑，报告内容引发国内外园艺专家广泛研讨。参会期间，团队前往银川国际会展中心观摩酿酒葡萄 AI 综合作业机器人成果展示，详细了解该装备在葡萄园智能作业方面的技术特点与应用前景，并与研发单位围绕葡萄智慧装备研发、果园智能化管理等方向开展深入交流。\n\n本次参会是葡萄团队持续推进科研国际化、对标国际前沿开展研究的重要实践。","上海市农业科学院 2026-10-19","2026-10-19T00:00:00Z","报道",65,{"impact":278,"substance":279,"depth":280,"authority":280,"freshness":86,"relevant":20,"comment":281},16,17,13,"国际学术会议交流并涉及葡萄AI作业机器人观摩，有实质科研内容与行业参考价值，但属团队参会动态，影响面有限。",[283],{"name":273,"url":270},[25,285,286,287,288],"智能农机","葡萄","栽培技术","国际交流",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":14,"version":39,"method":40,"evidence":292},{"candidates":293,"agricultural_evidence":45},[294,299,303],{"code":31,"score":295,"supported":45,"title":296,"abstract":297,"tags":298},12,[286],[286],[286],{"code":50,"score":44,"supported":45,"title":300,"abstract":301,"tags":302},[],[25],[25],{"code":215,"score":20,"supported":14,"title":304,"abstract":305,"tags":306},[],[],[285],[308,309],"上海农科院 葡萄 银川","世界葡萄与葡萄酒大会 奚晓军","上海农科院葡萄银川-5516","2026-10-22T00:07:04.061911Z",{"id":313,"title":314,"url":315,"summary":316,"summary_zh":317,"content":9,"source_name":318,"source_url":315,"published_at":319,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":320,"score_detail":321,"sources":323,"tags":325,"primary_topic":329,"secondary_topics":330,"classification":331,"search_phrases":356,"slug":359,"view_count":76,"doi":360,"paper":361,"created_at":383},5401,"A HIERARCHICAL DISTRIBUTED EDGE AI FRAMEWORK FOR REAL-TIME APPLE LEAF DISEASE CLASSIFICATION","https:\u002F\u002Fdoi.org\u002F10.22190\u002Ffuacr260506002g","The application of artificial intelligence (AI) in agriculture has transformed crop management, particularly in the detection of plant diseases. Apple trees, a key agricultural commodity, are vulnerable to various diseases, which can severely impact crop yields. Traditional disease detection methods, often reliant on manual inspections, are time-consuming and prone to error. In response, this study proposes a novel two-stage edge AI framework for apple leaf disease classification that integrates RGB imagery with distributed edge computing. The first stage performs binary classification to distinguish between healthy and diseased leaves, achieving an F1 score of 95.50%. This optimization is achieved by utilizing lightweight models on edge devices, thereby enhancing computational efficiency. The second stage employs a consensus-based multiclass classification approach, achieving a 96.44% F1 score in identifying specific diseases. This dual-stage system, supported by an edge AI architecture, ensures real-time disease detection while minimizing resource consumption and enhancing scalability in large-scale agricultural environments. The full system achieved a 95.50% accuracy and F1 score on the special dataset. The results demonstrate the system’s efficacy in controlled laboratory conditions, offering a promising solution for precise, real-time agricultural monitoring. This study underscores the potential of distributed edge AI systems for scalable and efficient disease detection in precision agriculture.","人工智能（AI）在农业中的应用已深刻改变了作物管理方式，尤其是在植物病害检测方面。苹果树作为重要的农业经济作物，易受多种病害侵袭，严重影响作物产量。传统的病害检测方法通常依赖人工检查，耗时且易出错。为此，本研究提出了一种新颖的两阶段边缘AI框架，用于苹果叶片病害分类，该框架将RGB图像与分布式边缘计算相结合。第一阶段执行二分类以区分健康叶片与患病叶片，F1分数达到95.50%。该优化通过在边缘设备上采用轻量级模型实现，从而提升了计算效率。第二阶段采用基于共识的多类分类方法，在识别具体病害方面F1分数达到96.44%。该双阶段系统在边缘AI架构的支持下，实现了实时病害检测，同时最大限度地降低了资源消耗，并增强了在大规模农业环境中的可扩展性。完整系统在专用数据集上达到了95.50%的准确率和F1分数。结果表明，该系统在受控实验室条件下具有有效性，为精准、实时的农业监测提供了一种有前景的解决方案。本研究凸显了分布式边缘AI系统在精准农业中实现可扩展且高效病害检测的潜力。","Facta Universitatis Series Automatic Control and Robotics","2026-10-18T00:00:00Z",76,{"impact":17,"substance":18,"depth":279,"authority":295,"freshness":100,"relevant":20,"comment":322},"该研究提出两级边缘AI框架，在苹果叶片病害识别上取得95%以上F1值，方法新颖、数据可靠，对精准农业实时监测有参考价值，但尚处实验室验证阶段，产业影响有限。",[324],{"name":318,"url":315},[25,188,326,327,328],"边缘计算","作物病害识别","苹果病害",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":14,"version":39,"method":40,"evidence":332},{"candidates":333,"agricultural_evidence":45},[334,338,345,351],{"code":31,"score":17,"supported":45,"title":335,"abstract":336,"tags":337},[126],[33,27,126],[328],{"code":50,"score":339,"supported":45,"title":340,"abstract":341,"tags":344},7,[],[342,343],"精准农业","precision agriculture",[25],{"code":346,"score":339,"supported":45,"title":347,"abstract":348,"tags":350},"I5",[],[326,349],"edge computing",[326],{"code":194,"score":58,"supported":45,"title":352,"abstract":353,"tags":355},[],[354],"artificial intelligence",[327,188],[357,358],"苹果叶片病害 边缘AI","分布式边缘计算 病害分类","苹果叶片病害边缘AI-5401","10.22190\u002Ffuacr260506002g",{"doi":360,"openalex_id":362,"authors":363,"venue":318,"cited_by_count":76,"oa_url":315,"card":376,"direction":382,"ingested_from":83},"W7222964752",[364,367,370,373],{"name":365,"orcid":366},"Milan Grujev","https:\u002F\u002Forcid.org\u002F0009-0002-3211-6844",{"name":368,"orcid":369},"Dragan H. Stojanovic","https:\u002F\u002Forcid.org\u002F0000-0003-4893-3814",{"name":371,"orcid":372},"Miloš Ilić","https:\u002F\u002Forcid.org\u002F0000-0002-9696-2874",{"name":374,"orcid":375},"Aleksandar Milosavljević","https:\u002F\u002Forcid.org\u002F0000-0003-3057-7727",{"tldr":377,"method":378,"finding":379,"direction":380,"opportunity":381},"提出两级边缘AI框架，用RGB图像实时分类苹果叶片病害。","分布式边缘计算+轻量模型，先二分类再共识多分类。","两级系统准确率与F1均达95.50%，多分类F1为96.44%。","智慧农业 \u002F 农业物联网","仅在受控实验室验证，可延伸至田间复杂光照与多作物泛化及边缘能耗优化。","农业人工智能与决策模型","2026-10-20T23:30:33.830748Z",{"id":385,"title":386,"url":387,"summary":388,"summary_zh":9,"content":9,"source_name":389,"source_url":9,"published_at":390,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":391,"score_detail":392,"sources":394,"tags":396,"primary_topic":401,"secondary_topics":402,"classification":403,"search_phrases":414,"slug":417,"view_count":76,"doi":9,"paper":418,"created_at":426},5297,"高志永团队《基于特征优选与优化算法的干热河谷区柑橘蒸腾模拟》","https:\u002F\u002Fwww.sohu.com\u002Fa\u002F1087305323_122014422","《智慧农业(中英文)》2026年第8卷第4期刊载云南农业大学吴明清、高志永等团队论文,以10年生柑橘树为研究对象收集2020—2022年树干液流与环境因子数据;针对干热河谷加快建设智慧灌区背景下传统机理模型参数需求高、对部分参数高度敏感且误差来源复杂等难题,提出基于特征优选与优化算法的蒸腾模拟方法,可为优化灌区水分调控与配水策略提供决策支撑。","智慧农业(中英文)(2026,8(4))","2026-10-13T00:00:00Z",72,{"impact":278,"substance":18,"depth":279,"authority":280,"freshness":58,"relevant":20,"comment":393},"核心期刊论文，方法有创新且数据规模扎实，对干热河谷智慧灌区水分调控有决策参考价值，但属细分领域研究，时效性一般。",[395],{"name":389,"url":387},[25,397,398,399,400],"云南","柑橘","智慧灌区","蒸腾模拟",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":14,"version":39,"method":40,"evidence":404},{"candidates":405,"agricultural_evidence":45},[406,410],{"code":31,"score":295,"supported":45,"title":407,"abstract":408,"tags":409},[398],[398],[398],{"code":50,"score":44,"supported":45,"title":411,"abstract":412,"tags":413},[],[25],[25],[415,416],"云南农业大学 柑橘 蒸腾模拟","干热河谷 智慧灌区","云南农业大学柑橘蒸腾模拟-5297",{"doi":9,"openalex_id":9,"authors":419,"venue":9,"cited_by_count":76,"oa_url":9,"card":420,"direction":380,"ingested_from":425},[],{"tldr":421,"method":422,"finding":423,"direction":380,"opportunity":424},"用特征优选与优化算法模拟干热河谷区柑橘蒸腾。","基于2020—2022年树干液流与环境因子数据构建特征优选与优化算法模型。","该方法可降低机理模型参数依赖与敏感性，提升蒸腾模拟精度。","可探索将蒸腾模拟嵌入智慧灌区实时配水决策，研究多树种迁移与边缘部署。","agent","2026-10-19T00:07:48.135945Z",{"id":428,"title":429,"url":430,"summary":431,"summary_zh":9,"content":9,"source_name":432,"source_url":9,"published_at":433,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":434,"score_detail":435,"sources":438,"tags":440,"primary_topic":443,"secondary_topics":444,"classification":445,"search_phrases":464,"slug":467,"view_count":76,"doi":9,"paper":468,"created_at":475},5130,"DefoliationCAM:面向葡萄藤食叶严重度实时评估的边缘AI系统 [预印本]","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.20879","Fuchen Li等提出DefoliationCAM(D-CAM),一种太阳能供电的边缘AI系统,用于估算葡萄藤树冠食叶程度并通过LoRa将结果传输至Web仪表盘。流水线使用YOLOX-Nano在4K图像中定位葡萄藤主干,并使用基于MobileNet的轻量级通道注意力分类器对320×320像素的斑块进行分类。29,674个田间采集斑块被标注为背景或四种损伤等级之一;合并中度和重度类别将类别不平衡比从约40:1降至8.8:1。合成增强使macro-F1从0.768提升至0.838。分类器以更少的参数量(1.08M vs 23.52M)在macro-F1上优于ResNet-50。利用TensorRT FP16在NVIDIA Jetson Orin Nano上每张4K图像处理时间约1.5秒,完整运行周期57-60秒。两台设备为期五周的田间部署验证了自主太阳能运行、LoRa通信和远程食叶监测的可行性。","arXiv 2610.20879 2026 年 10 月 14 日","2026-10-14T00:00:00Z",75,{"impact":278,"substance":99,"depth":17,"authority":436,"freshness":100,"relevant":20,"comment":437},11,"预印本提出太阳能边缘AI系统，实现葡萄藤食叶严重度实时评估与LoRa远程监测，方法新颖、数据规模大、田间验证充分，具智慧农业应用价值。",[439],{"name":432,"url":430},[25,188,326,441,442],"葡萄藤","病害评估",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":14,"version":39,"method":40,"evidence":446},{"candidates":447,"agricultural_evidence":45},[448,452,456,460],{"code":31,"score":436,"supported":45,"title":449,"abstract":450,"tags":451},[286],[286],[],{"code":50,"score":20,"supported":14,"title":453,"abstract":454,"tags":455},[],[],[25],{"code":194,"score":20,"supported":14,"title":457,"abstract":458,"tags":459},[],[],[188],{"code":346,"score":20,"supported":14,"title":461,"abstract":462,"tags":463},[],[],[326],[465,466],"DefoliationCAM 葡萄藤 食叶","Jetson Orin Nano 边缘AI 葡萄","DefoliationCAM葡萄藤食叶-5130",{"doi":9,"openalex_id":9,"authors":469,"venue":9,"cited_by_count":76,"oa_url":9,"card":470,"direction":380,"ingested_from":425},[],{"tldr":471,"method":472,"finding":473,"direction":380,"opportunity":474},"提出太阳能边缘AI系统DefoliationCAM，实时评估葡萄藤食叶严重度并远程传输。","YOLOX-Nano定位主干，MobileNet通道注意力分类，TensorRT","轻量分类器macro-F1达0.838，优于ResNet-50，田间部署验证可行。","可探索多作物迁移、损伤等级细化及边缘模型自适应更新以提升泛化性。","2026-10-17T00:13:44.932340Z"]