[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-5345":3,"related-5345":70},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":8,"source_name":9,"source_url":8,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":15,"sources":23,"tags":25,"primary_topic":31,"secondary_topics":37,"classification":38,"search_phrases":64,"slug":67,"view_count":68,"doi":8,"paper":8,"created_at":69},5345,"上海农科院历时 10 年选育沪翠甜 6 号哈密瓜在甘肃张掖发布","https:\u002F\u002Ffinance.sina.com.cn\u002Fjjxw\u002F2026-10-14\u002Fdoc-inivctrv8581700.shtml","上海市农业科学院垂直农业研究中心西甜瓜创新团队首席科学家张永平研究员带领团队历时 10 年选育的哈密瓜新品种沪翠甜 6 号于 10 月 13 日在甘肃张掖正式发布。该品种果肉呈翠绿色,口感酥脆、汁水充足,带淡淡奶香,单瓜重量约 2 公斤,果腔小、糖度梯度小,中心糖度最高可达 18 度以上、边糖 10 度以上。最大特点是采摘即食,秋冬季采收后存放 30 天仍可保持脆甜口感。已在甘肃、内蒙古、宁夏、山东、河南、上海、海南等全国甜瓜主要产区布局种植,基地全部采用现代化温室大棚模式。",null,"新浪财经(上观新闻转载) 2026-10-14","2026-10-14T00:00:00Z","报道",10,false,67,{"impact":16,"substance":17,"depth":18,"authority":19,"freshness":20,"relevant":21,"comment":22},18,20,14,9,6,1,"省级科研机构历时十年育成耐储运、采摘即食的甜瓜新品种，并已在全国主要产区布局，具备产业推广价值，但属单一品种发布，影响范围有限。",[24],{"name":9,"url":6},[26,27,28,29,30],"设施农业","种业振兴","品种推广","西甜瓜育种","采摘即食",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},"B7","protected-horticulture","设施园艺与植物工厂","\u002Ftopic\u002Fhorticulture\u002Fprotected-horticulture","B",[],{"status":39,"locked":13,"version":40,"method":41,"evidence":42},"classified","2026-10-22.2","rules",{"candidates":43,"agricultural_evidence":45},[44,51,58],{"code":32,"score":20,"supported":45,"title":46,"abstract":47,"tags":50},true,[],[48,49],"温室","垂直农业",[],{"code":52,"score":53,"supported":45,"title":54,"abstract":55,"tags":57},"B1",3,[],[56],"甜瓜",[],{"code":59,"score":60,"supported":13,"title":61,"abstract":62,"tags":63},"F1",2,[],[],[28,27],[65,66],"上海农科院 沪翠甜6号","沪翠甜6号 哈密瓜 张掖","上海农科院沪翠甜6号-5345",0,"2026-10-20T02:47:44.034119Z",{"total":20,"page":21,"page_size":20,"items":71},[72,132,173,219,296,362],{"id":73,"title":74,"url":75,"summary":76,"summary_zh":8,"content":8,"source_name":77,"source_url":8,"published_at":78,"category":79,"cover_url":8,"hotness":12,"is_selected":13,"score":80,"score_detail":81,"sources":87,"tags":89,"primary_topic":94,"secondary_topics":95,"classification":100,"search_phrases":118,"slug":121,"view_count":68,"doi":8,"paper":122,"created_at":131},5536,"日光温室番茄全生育期环境特征解析与智能调控决策支持方法","https:\u002F\u002Fpaper.sciencenet.cn\u002Fhtmlpaper\u002F2026\u002F10\u002F20261021145441802156759.shtm","研究解析日光温室番茄全生育期环境特征，发现该类温室气候缓冲能力较强、有效积温与番茄生理需求呈双峰匹配，但相对增益指标揭示单位时间热量供给失衡、深冬热量不足以及光能结构性不足、湿度调控昼夜失衡等问题。作者建议构建温度—光照—湿度耦合的智能闭环控制系统。","Agriculture 2026-10-21","2026-10-21T00:00:00Z","论文",77,{"impact":82,"substance":83,"depth":84,"authority":85,"freshness":12,"relevant":21,"comment":86},16,21,17,13,"论文解析日光温室番茄全生育期环境特征并提出温光湿耦合智能调控方案，结论有新意，对设施农业信息化有参考价值。",[88],{"name":77,"url":75},[90,26,91,92,93],"智慧农业","环境调控","温室番茄","智能决策",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[96],{"code":52,"slug":97,"name":98,"path":99,"parent_code":36},"vegetables","蔬菜","\u002Ftopic\u002Fhorticulture\u002Fvegetables",{"status":39,"locked":13,"version":40,"method":41,"evidence":101},{"candidates":102,"agricultural_evidence":45},[103,107,113],{"code":32,"score":85,"supported":45,"title":104,"abstract":105,"tags":106},[48],[48],[92,91],{"code":52,"score":108,"supported":45,"title":109,"abstract":111,"tags":112},11,[110],"番茄",[110],[],{"code":114,"score":21,"supported":13,"title":115,"abstract":116,"tags":117},"I1",[],[],[90],[119,120],"日光温室 番茄 环境调控","温室番茄 智能闭环控制","日光温室番茄环境调控-5536",{"doi":8,"openalex_id":8,"authors":123,"venue":8,"cited_by_count":68,"oa_url":8,"card":124,"direction":128,"ingested_from":130},[],{"tldr":125,"method":126,"finding":127,"direction":128,"opportunity":129},"解析日光温室番茄全生育期环境特征并提出智能调控决策支持方法。","基于全生育期环境监测数据，分析积温匹配与相对增益指标。","温室缓冲力强但深冬热量不足、光能结构性不足、湿度昼夜失衡。","智慧农业 \u002F 农业物联网","可研发温度—光照—湿度耦合的智能闭环控制算法，并验证其对番茄产量与能耗的协同优化效果。","agent","2026-10-22T00:07:10.129353Z",{"id":133,"title":134,"url":135,"summary":136,"summary_zh":8,"content":137,"source_name":138,"source_url":8,"published_at":139,"category":140,"cover_url":8,"hotness":12,"is_selected":13,"score":141,"score_detail":142,"sources":144,"tags":146,"primary_topic":150,"secondary_topics":151,"classification":152,"search_phrases":168,"slug":171,"view_count":21,"doi":8,"paper":8,"created_at":172},5257,"北京发布《北京市2026年智慧设施(种植)建设指南》分级建设\"数智京园\"","https:\u002F\u002Fk.sina.com.cn\u002Farticle_7517400647_1c0126e4705909clmq.html","北京市农业农村局印发《2026年智慧设施(种植)建设指南》,按基础版、升级版分级建设,适配不同主体不同设施不同生产需求,坚持\"优先选用适用技术,避免过度智能化浪费\";依托\"数智京园\"开展国产化智能控制技术\"赛马制\"验证,目前连栋温室国产系统产量与对照系统逐步齐平、商品果率提升。","设备好不好用，模型能不能适应自家大棚，经营主体更愿意到现场看一看。市场上智慧农业产品种类繁多，质量与售后不一，导致“不会选”。“数智京园”把验证、示范、选型推荐连起来，让农户先看实效再决定。\n\n在示范园区，合作社理事长、家庭农场主走进温室，查看智能调控效果，体验系统操作流程。不少园区在观摩后主动联系，希望接入“数智京园”。和合园作为集成展示点，集中呈现环境感知、卷膜卷被、水肥一体化、高压微雾，以及多光谱表型监测、智能植保、采摘机器人等装备，面向“头雁”、设施产业集群和产业园主体开展观摩，避免盲目跟风买高配、不适配设备。\n\n让农户放心选择，先要把技术的实际能力测清楚。首农翠湖智慧农业创新工场（以下简称“翠湖工场”）使用“数智京园”开展数字化管理，并另行开展连栋温室国产化智能控制技术“赛马制”验证。“验证不仅要看设备能否执行指令，还要看执行得是否及时、调控是否高效。”翠湖工场科技总监王利利介绍，国产系统产量与对照系统逐步齐平、商品果率提升后，园区选用国产系统也更有底气。\n\n让技术在真实场景中经受检验，也是“数智京园”推进应用的重要做法。围绕番茄、草莓、黄瓜、叶菜等作物，以及土壤、基质等栽培方式，在不同区域、不同茬口开展对照验证，检验环境控制、水肥调控的效果，再把成熟技术集成到“数智京园”中，形成可供不同园区选择的方案。2026年，北京市农业农村局印发了《北京市2026年智慧设施（种植）建设指南》，按照基础版、升级版分级建设，适配不同主体、不同设施和不同生产需求，坚持“优先选用适用技术，避免过度智能化浪费”，解决“不会选”。\n\n验证之后，还要让农户看得见、学得会。京郊的示范园区成为现场课堂，经营主体进棚看设备运行、体验农事排产，了解改造投入和生产收益。技术服务人员开展手把手培训，配合图文操作手册，帮助农户掌握使用方法。设备出现异常，通过远程诊断和现场维修处理，减少“坏了没人管”的顾虑。京品码追溯、智能采收秤等把生产、采收、包装数据打通，既方便劳动力考核，也方便消费者扫码看全过程。\n\n从验证到示范，再到推广，“数智京园”正把技术选择、生产应用和后续服务连成一条线。随着这套模式在更多设施大棚落地生根，智能管控将在京郊的一茬茬农事里持续发挥作用，让省下来的人工、节约的水肥和增加的收益，结出更多硕果，为首都乡村全面振兴注入强劲的数字动能。\n\n特别声明：以上文章内容仅代表作者本人观点，不代表新浪网观点或立场。如有关于作品内容、版权或其它问题请于作品发表后的30日内与新浪网联系。","新浪网转载(2026-10-19)","2026-10-19T00:00:00Z","政策",70,{"impact":16,"substance":17,"depth":82,"authority":20,"freshness":12,"relevant":21,"comment":143},"省级智慧设施建设指南，含分级建设、验证示范与推广服务链条等实质内容，对设施农业数字化有参考价值，但来源为商业门户转载，权威性一般。",[145],{"name":138,"url":135},[147,90,26,148,149],"数字乡村","北京","建设指南",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":13,"version":40,"method":41,"evidence":153},{"candidates":154,"agricultural_evidence":45},[155,159,163],{"code":32,"score":53,"supported":45,"title":156,"abstract":157,"tags":158},[],[48],[],{"code":114,"score":21,"supported":13,"title":160,"abstract":161,"tags":162},[],[],[90],{"code":164,"score":21,"supported":13,"title":165,"abstract":166,"tags":167},"I6",[],[],[147],[169,170],"北京 数智京园 建设指南","北京 智慧设施 种植 分级建设","北京数智京园建设指南-5257","2026-10-19T00:07:31.752116Z",{"id":174,"title":175,"url":176,"summary":177,"summary_zh":8,"content":8,"source_name":178,"source_url":8,"published_at":179,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":180,"score_detail":181,"sources":185,"tags":187,"primary_topic":190,"secondary_topics":191,"classification":193,"search_phrases":214,"slug":217,"view_count":53,"doi":8,"paper":8,"created_at":218},3935,"知识与数据双驱动赋能温室番茄生长精准预测——中国农科院环发所研究成果发表","https:\u002F\u002Fwww.caas.cn\u002Fxwzx\u002Fkyhd\u002F613bca00d9e84cfeb977251a606af346.htm","近日，中国农业科学院农业环境与可持续发展研究所设施植物环境工程创新团队构建了知识与数据双驱动模型，实现温室番茄生长的高精度无损预测，研究成果发表在《农业计算机与电子学（Computers and Electronics in Agriculture）》上。科研团队提出一种尺度自适应时序卷积混合模型，根据番茄不同生育期动态调整时序特征提取尺度，结合机理模型合成数据预训练与生理阈值约束，实现番茄不同器官干物质及叶面积指数的精准预测。","中国农业科学院·2026年10月","2026-10-01T00:00:00Z",82,{"impact":16,"substance":182,"depth":16,"authority":183,"freshness":19,"relevant":21,"comment":184},22,15,"国家级科研机构在核心期刊发表的知识与数据双驱动温室番茄生长预测模型，方法新颖、结论可靠，对智慧农业与设施种植有实质参考价值。",[186],{"name":178,"url":176},[90,188,26,92,189],"农业人工智能","生长预测",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[192],{"code":52,"slug":97,"name":98,"path":99,"parent_code":36},{"status":39,"locked":13,"version":40,"method":41,"evidence":194},{"candidates":195,"agricultural_evidence":45},[196,201,205,209],{"code":32,"score":197,"supported":45,"title":198,"abstract":199,"tags":200},12,[48],[48],[92],{"code":52,"score":108,"supported":45,"title":202,"abstract":203,"tags":204},[110],[110],[],{"code":114,"score":21,"supported":13,"title":206,"abstract":207,"tags":208},[],[],[90],{"code":210,"score":21,"supported":13,"title":211,"abstract":212,"tags":213},"I2",[],[],[188],[215,216],"中国农科院环发所 温室番茄 生长预测","知识与数据双驱动 番茄 模型","中国农科院环发所温室番茄生长预测-3935","2026-10-02T11:53:11.319506Z",{"id":220,"title":221,"url":222,"summary":223,"summary_zh":224,"content":8,"source_name":225,"source_url":222,"published_at":226,"category":79,"cover_url":8,"hotness":12,"is_selected":13,"score":227,"score_detail":228,"sources":231,"tags":233,"primary_topic":237,"secondary_topics":238,"classification":239,"search_phrases":271,"slug":274,"view_count":60,"doi":275,"paper":276,"created_at":295},3874,"Exploring aquaponics systems and greenhouse gas emissions: an agent-based model case study","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffsufs.2026.1862992","Aquaponics is the combination of aquaculture (i.e., propagation of aquatic species) and hydroponics (i.e., soil-less propagation of plants), which is being investigated as a method for more sustainable food production. Along with ensuring the continued improvement of the technology itself, educating the public about aquaponics using a systems-thinking approach is equally important. Agent-based modeling was used to develop an aquaponics model that will allow any student to have an active learning experience with a generalized operation of the system while also exploring systems-thinking principles. By developing a model, individuals interested in learning are not limited by what their educational institutions can provide, which is often restricted by a lack of resources. The aquaponics agent-based model presented in this study allows the user to change the fish and plant types, climate, and season and display the corresponding greenhouse gas emissions when the theoretical system is operating. The number of plants harvested and the total greenhouse gas emissions are the two stochastic outputs of the model, given potential variations in timelines, system efficiencies, and general human error. Greenhouse gas emissions were compared with those reported in the relevant literature to inform parameter selection. The overall goal of this model is to provide an interactive and broadly accessible educational opportunity.","鱼菜共生（Aquaponics）是水产养殖（即水生物种的繁殖）与水培（即无土栽培植物）的结合，目前正被研究作为一种更可持续的粮食生产方式。在确保该技术本身持续改进的同时，利用系统思维方法向公众普及鱼菜共生知识同样重要。本研究采用基于主体的建模（Agent-based modeling）方法开发了一个鱼菜共生模型，使任何学生都能通过该系统的广义操作获得主动学习体验，同时探索系统思维原则。通过开发这一模型，有兴趣的学习者不再受限于其教育机构所能提供的条件——这些条件往往因资源匮乏而受到制约。本研究提出的鱼菜共生基于主体的模型允许用户更改鱼类和植物类型、气候和季节，并展示理论系统运行时的相应温室气体排放量。考虑到时间线、系统效率和一般人为误差的潜在变化，收获植物数量和温室气体排放总量是该模型的两个随机输出。温室气体排放量已与相关文献中报告的数据进行比较，以指导参数选择。该模型的总体目标是提供一种具有交互性且可广泛获取的教育机会。","Frontiers in Sustainable Food Systems","2026-09-30T00:00:00Z",61,{"impact":229,"substance":16,"depth":82,"authority":85,"freshness":20,"relevant":21,"comment":230},8,"该论文提出基于智能体的鱼菜共生教学模型，可模拟鱼类、植物、气候与季节变化并输出温室气体排放，方法新颖且具教育推广价值，但属细分领域学术成果，公共影响有限。",[232],{"name":225,"url":222},[90,26,234,235,236],"温室气体","水产养殖","系统思维",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":13,"version":40,"method":41,"evidence":240},{"candidates":241,"agricultural_evidence":45},[242,248,256,262,267],{"code":32,"score":84,"supported":45,"title":243,"abstract":245,"tags":247},[244],"greenhouse",[48,246,244],"无土栽培",[],{"code":249,"score":250,"supported":45,"title":251,"abstract":252,"tags":255},"D",7,[],[253,254],"水产","aquaculture",[235],{"code":257,"score":53,"supported":45,"title":258,"abstract":259,"tags":261},"H2",[],[260],"soil",[],{"code":263,"score":21,"supported":13,"title":264,"abstract":265,"tags":266},"H4",[],[],[234],{"code":114,"score":21,"supported":13,"title":268,"abstract":269,"tags":270},[],[],[90],[272,273],"鱼菜共生 温室气体 模型","智慧农业 水产养殖 温室气体 系统思维","鱼菜共生温室气体模型-3874","10.3389\u002Ffsufs.2026.1862992",{"doi":275,"openalex_id":277,"authors":278,"venue":225,"cited_by_count":68,"oa_url":222,"card":288,"direction":292,"ingested_from":294},"W7214975686",[279,282,284,286],{"name":280,"orcid":281},"Marissa Breitenstein","https:\u002F\u002Forcid.org\u002F0009-0005-2148-8812",{"name":283,"orcid":8},"Elisabeth Bautista",{"name":285,"orcid":8},"Alexis Daniels",{"name":287,"orcid":8},"Andrea Hicks",{"tldr":289,"method":290,"finding":291,"direction":292,"opportunity":293},"开发鱼菜共生系统智能体模型，模拟不同鱼、植物、气候和季节下的温室气体排放，用于教学。","基于智能体的建模（ABM），参数参考文献，输出随机性结果。","模型可交互展示鱼菜共生系统的温室气体排放，促进系统思维学习。","农业绿色发展与碳","可扩展模型纳入更多环境与经济指标，或开发面向公众的在线交互平台。","openalex","2026-10-01T23:30:07.298849Z",{"id":297,"title":298,"url":299,"summary":300,"summary_zh":301,"content":8,"source_name":302,"source_url":299,"published_at":303,"category":79,"cover_url":8,"hotness":12,"is_selected":13,"score":304,"score_detail":305,"sources":307,"tags":309,"primary_topic":312,"secondary_topics":313,"classification":319,"search_phrases":345,"slug":348,"view_count":53,"doi":349,"paper":350,"created_at":361},2682,"Machine Learning-Based Decision Support System for Greenhouse Crop Management Under Mite Infestation Conditions","https:\u002F\u002Fdoi.org\u002F10.36099\u002Fjess.v1i3.001","This paper presents an integrated machine learning-based Decision Support System (DSS) for greenhouse crop management under mite infestation conditions, specifically designed for Sri Lankan agricultural contexts. The research addresses critical challenges faced by greenhouse farmers regarding pest management and crop productivity optimization through a comprehensive system combining NetLogo simulation for synthetic data generation, ensemble machine learning models, and a web-based interface. Field research with Sri Lankan greenhouse farmers revealed that mite infestations cause up to 40% crop losses, driving panic-induced pesticide overuse and knowledge gaps in pest management timing. The system integrates environmental monitoring, pest prediction, and crop yield forecasting to provide actionable recommendations for farmers. The mite infestation prediction model achieved 86% accuracy, while the system successfully addresses data scarcity challenges through agent-based modeling. The DSS demonstrates potential for transforming reactive farming practices into predictive, data-driven approaches while accommodating the technological constraints of developing agricultural contexts.","本文提出了一种基于机器学习的集成决策支持系统（DSS），用于螨虫侵染条件下的温室作物管理，专为斯里兰卡农业情境设计。该研究针对温室农户在害虫管理和作物生产力优化方面面临的关键挑战，通过一个综合系统加以解决，该系统结合了用于合成数据生成的NetLogo仿真、集成机器学习模型以及基于网络的界面。针对斯里兰卡温室农户的实地研究表明，螨虫侵染可导致高达40%的作物损失，进而引发恐慌性农药过度使用以及害虫管理时机方面的知识缺口。该系统整合了环境监测、害虫预测和作物产量预测，为农户提供可操作的推荐建议。螨虫侵染预测模型达到了86%的准确率，同时该系统通过基于智能体的建模成功应对了数据稀缺的挑战。该决策支持系统展现出将被动应对式耕作实践转变为预测性、数据驱动方法的潜力，同时兼顾了发展中农业情境的技术约束。","Journal of Environmental and Sustainability Science","2026-09-16T00:00:00Z",74,{"impact":183,"substance":17,"depth":84,"authority":197,"freshness":12,"relevant":21,"comment":306},"将机器学习与智能体仿真结合用于温室螨害预测与决策支持，方法新颖、数据翔实，对设施农业植保信息化有参考价值。",[308],{"name":302,"url":299},[90,188,26,310,311],"决策支持系统","病虫害预警",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[314],{"code":210,"slug":315,"name":316,"path":317,"parent_code":318},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":39,"locked":13,"version":40,"method":41,"evidence":320},{"candidates":321,"agricultural_evidence":45},[322,330,334,341],{"code":210,"score":323,"supported":45,"title":324,"abstract":327,"tags":329},27,[325,326],"machine learning","decision support",[328,325,326],"机器学习",[188,310],{"code":32,"score":18,"supported":45,"title":331,"abstract":332,"tags":333},[244],[48,244],[],{"code":335,"score":20,"supported":45,"title":336,"abstract":337,"tags":340},"F4",[],[338,339],"农药","pesticide",[],{"code":114,"score":21,"supported":13,"title":342,"abstract":343,"tags":344},[],[],[90],[346,347],"农业人工智能 决策支持系统 病虫害预警 智慧农业","农业人工智能 决策支持系统","农业人工智能决策支持系统病虫害预警智慧农业-2682","10.36099\u002Fjess.v1i3.001",{"doi":349,"openalex_id":351,"authors":352,"venue":302,"cited_by_count":68,"oa_url":299,"card":355,"direction":359,"ingested_from":294},"W7213235680",[353],{"name":354,"orcid":8},"S. Nasiketha",{"tldr":356,"method":357,"finding":358,"direction":359,"opportunity":360},"为斯里兰卡温室农户开发基于机器学习的决策支持系统，预测螨害并优化作物管理。","NetLogo仿真生成合成数据，集成机器学习模型与网页界面。","螨害预测准确率达86%，可缓解数据稀缺并减少农药滥用。","农业人工智能与决策模型","可探索小样本下合成数据与迁移学习结合，提升发展中国家温室病虫害预测泛化能力。","2026-09-16T23:30:51.573509Z",{"id":363,"title":364,"url":365,"summary":366,"summary_zh":367,"content":8,"source_name":368,"source_url":365,"published_at":303,"category":79,"cover_url":8,"hotness":12,"is_selected":13,"score":369,"score_detail":370,"sources":372,"tags":374,"primary_topic":377,"secondary_topics":378,"classification":379,"search_phrases":401,"slug":404,"view_count":53,"doi":405,"paper":406,"created_at":424},2638,"Full shuffle and p-rectified semi-inner powerful IoU-based chili pepper flower recognition with environment-aware YOLO11","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffpls.2026.1935123","As a common greenhouse-grown commercial crop, chili pepper yields have always been a focus of attention. Effective management is essential for both environmental sustainability and high productivity in greenhouses. Whether for growth monitoring, yield estimates, and automated production, precise identification of chili flowers is critical. To this goal, this paper works upon the YOLO11 object detection model, focusing on the precise detection of chili flowers. The diversity of samples across various scenarios is increased by utilizing a self-built dataset of chili flowers in greenhouses and integrating data augmentation. To address YOLO11’s limitations in this task, this paper proposes a unified framework that integrates three modules: (1) full shuffle to enhance information exchange between model channels and optimize weights; (2) Since YOLO11 cannot incorporate external environmental data during training, the environment-aware C3k2 is introduced; and (3) The proposed p-rectified Semi-inner Powerful IoU accelerates model convergence and flexibility. Experiments show that our method obtains 84.8% mAP50, 50.2% mAP50-95, 81.1% Precision, and 75.6% Recall, outperforming the baseline YOLO11’s 77.3% by 7.5 percentage points, as well as YOLOv8, YOLO12, RTDETR, and Faster R-CNN under the same experimental conditions. Therefore, in terms of performance, our method generally surpasses existing algorithms for chili flower detection. Research on detecting chili flowers in greenhouses remains limited. The study offers valuable insights for the advancement of smart agriculture. Future work will further explore the model’s generalization capabilities across multiple varieties and growth stages, as well as deploy it on embedded devices for practical application.","作为常见的温室商业化种植作物，辣椒的产量一直备受关注。有效的管理对于温室的環境可持续性和高生产力都至关重要。无论是生长监测、产量估算还是自动化生产，辣椒花朵的精准识别都至关重要。为实现这一目标，本文基于YOLO11目标检测模型，聚焦辣椒花朵的精准检测。通过利用自建的温室辣椒花朵数据集并结合数据增强，增加了不同场景下样本的多样性。针对YOLO11在此任务中的局限性，本文提出了一个集成三个模块的统一框架：（1）完全混洗（full shuffle），以增强模型通道间的信息交换并优化权重；（2）由于YOLO11在训练过程中无法纳入外部环境数据，引入了环境感知C3k2（environment-aware C3k2）；（3）提出的p-rectified Semi-inner Powerful IoU加速了模型收敛并提升了灵活性。实验表明，本方法取得了84.8%的mAP50、50.2%的mAP50-95、81.1%的精确率和75.6%的召回率，较基线YOLO11的77.3%提升了7.5个百分点，并在相同实验条件下优于YOLOv8、YOLO12、RTDETR和Faster R-CNN。因此，在性能方面，本方法总体上超越了现有的辣椒花朵检测算法。目前关于温室辣椒花朵检测的研究仍然有限。本研究为智慧农业的发展提供了有价值的见解。未来工作将进一步探索模型在多个品种和生长阶段上的泛化能力，并将其部署到嵌入式设备上以实现实际应用。","Frontiers in Plant Science",76,{"impact":183,"substance":83,"depth":84,"authority":85,"freshness":12,"relevant":21,"comment":371},"基于YOLO11的辣椒花检测新方法，mAP50提升7.5个百分点，对设施农业智能监测有参考价值，但属细分技术进展，影响范围有限。",[373],{"name":368,"url":365},[90,188,26,375,376],"目标检测","辣椒",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":13,"version":40,"method":41,"evidence":380},{"candidates":381,"agricultural_evidence":45},[382,387,391,396],{"code":114,"score":250,"supported":45,"title":383,"abstract":384,"tags":386},[],[90,385],"smart agriculture",[90],{"code":32,"score":20,"supported":45,"title":388,"abstract":389,"tags":390},[],[48,244],[],{"code":210,"score":392,"supported":45,"title":393,"abstract":394,"tags":395},5,[],[375],[188,375],{"code":52,"score":397,"supported":45,"title":398,"abstract":399,"tags":400},4,[],[376],[376],[402,403],"农业人工智能 智慧农业 目标检测 设施农业","农业人工智能 智慧农业","农业人工智能智慧农业目标检测设施农业-2638","10.3389\u002Ffpls.2026.1935123",{"doi":405,"openalex_id":407,"authors":408,"venue":368,"cited_by_count":68,"oa_url":365,"card":419,"direction":128,"ingested_from":294},"W7213351973",[409,411,413,416],{"name":410,"orcid":8},"Cui-Ping Zhang",{"name":412,"orcid":8},"Zhi-Yong Wang",{"name":414,"orcid":415},"Xuewei Wang","https:\u002F\u002Forcid.org\u002F0000-0001-9604-3045",{"name":417,"orcid":418},"Zhi Li","https:\u002F\u002Forcid.org\u002F0000-0001-5571-0518",{"tldr":420,"method":421,"finding":422,"direction":359,"opportunity":423},"基于YOLO11改进，实现温室辣椒花精准检测。","自建数据集+数据增强，引入全混洗、环境感知C3k2和p校正IoU。","mAP50达84.8%，比基线YOLO11提升7.5个百分点，优于多个对比模型。","温室辣椒花检测研究少，可探索多品种、多生长期泛化及嵌入式部署。","2026-09-16T23:30:09.868848Z"]