[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3406":3,"related-3406":103},{"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":32,"secondary_topics":38,"classification":39,"search_phrases":97,"slug":100,"view_count":101,"doi":8,"paper":8,"created_at":102},3406,"广东新技术在乡村找'跑道'——'铁柱2号'冬瓜占广东同类品种40%以上，荔枝AI诊断准确率达95%以上","https:\u002F\u002Fepaper.nfnews.com\u002Fnfdaily\u002Fhtml\u002F202609\u002F22\u002Fcontent_10182068.html","南方日报深度报道：广东省农科院蔬菜所'铁柱2号'冬瓜开创'铁心'冬瓜新类型，累计推广面积约300万亩、占广东同类品种40%以上；茂名荔枝产业大数据平台完成DeepSeek本地化部署，病虫害诊断准确率提升至95%以上、平均诊断时间从数小时缩短至5秒以内；河源东源县柳城镇下坝村万绿智慧无人农场由中国工程院院士罗锡文团队指导打造1500亩无人化核心区，亩产提升至500公斤以上；全省植保无人机保有量约9000架，日作业能力约440万亩。",null,"一粒种子，如何从实验室走向万亩良田？\n\n一片深海，如何将传统渔排升级为“数智牧场”？\n\n近日，以“创业兴村·向新而行”为主题的“农行杯”广东省第五届农村创业大赛总决赛在广州举行。经过现场路演和答辩，“AI超级蛋白工厂——医用蛋白‘宁德时代’”“合成生物技术赋能红景天富民工程”分别获得乡村新产业、农产品加工赛道一等奖，将代表广东参加2026年全国农村创业大赛。\n\n“感觉我们不是农业大赛，像科技大赛。”广东省第五届农村创业大赛总决赛专家评委组长曾准在点评中表示，本届比赛更加突出科技引领。人工智能、合成生物、智慧农业、种业创新……从获奖项目中可以窥见，新技术、新业态正深度融入农业生产和乡村产业发展之中。\n\n这场农村创业大赛，也是广东农业转型的缩影。透过赛场内外，可以清晰看到一条从科技创新到成果转化，再到农业新质生产力培育的完整路径。在广东推进“百县千镇万村高质量发展工程”的过程中，农业科技创新与产业创新实现深度融合，科技“关键变量”正在持续转化为乡村振兴的“最大增量”。\n\n“十五五”规划纲要明确提出，加快农业农村现代化，扎实推进乡村全面振兴，统筹发展科技农业、绿色农业、质量农业、品牌农业。科技创新是驱动乡村全面振兴的重要引擎，要加快科技成果高效转化，将科技创新关键变量转化为乡村全面振兴的最大增量，为实现共同富裕筑牢坚实根基。\n\n●南方日报记者 王悦阳\n\n大湾区的合成生物技术\n\n种到了高原\n\n禾虫是一种生长在沿海滩涂和咸淡水交汇稻田中的环节动物，在粤菜菜系中被视为滋补佳品，但传统养殖长期依赖自然条件，规模小、产量不稳定。乡村新产业赛道一等奖项目“AI超级蛋白工厂——医用蛋白‘宁德时代’”，通过育种创新、立体养殖设施和AI养殖系统，推动传统禾虫养殖向智能化、规模化发展，并进一步开发其蛋白价值。\n\n农产品加工赛道一等奖项目“合成生物技术赋能红景天富民工程”，则将合成生物技术应用于红景天育苗、种植和加工全链条。“我们把大湾区的合成生物创新技术种到了高原。”项目负责人陈绍强介绍，目前团队已在云南发展千亩以上种植基地，并通过提供种苗、技术和保底收购等方式与当地农户合作。\n\n人工智能也在重构农产品流通环节。获得乡村新产业赛道二等奖的“羊羊鲜供·粤港澳大湾区AI数智供应链创新平台”，将大模型应用于生鲜供应链。项目负责人刘洋2024年到清远连州创业，一年多跑了5万多公里，走访田间和市场，希望通过供应链改造减少流通损耗、提高效率，“让种菜的人赚到钱，让买菜的人安心买好菜”。\n\n传统特色产业同样在谋新求变。龙川县“车田山水豆腐”项目通过设备和加工工艺改造推动标准化生产，香云纱、沉香、水产加工等项目也通过技术、产品和经营模式创新拓展产业发展空间。\n\n广东省农村创业大赛自2021年创办以来已举办5届，累计吸引600余个项目参赛，孵化培育240多个优秀农村创业典型项目，持续发挥“以赛促学、以赛促创、以赛促融”作用。从赛场竞技到资源对接，从发现项目到培育人才，大赛已成为展示乡村产业创新成果、汇聚农村创业资源的重要平台。\n\n然而，正如曾准所言，技术最终要转化为产品和产业竞争力。科技成果转化是连接科技创新与农业农村现代化的关键桥梁，打通从技术突破到产业应用的“最后一公里”。\n\n那么，这些技术在广东大地上找到了怎样的“跑道”？\n\n智慧无人农场\n\n亩产提升至500公斤以上\n\n在广东，一批批农业新品种、新技术、新装备正在加速进入生产一线，直接推动生产、加工、流通、服务等环节的效率跃升。实验室中、创业大赛上涌现的科技“变量”，正在真实的产业场景中接受检验、完成转化。\n\n种业是农业的“芯片”。在广东，育种创新正在从实验室走向田间地头，游向深远海。\n\n广东海水鱼类苗种产量连续多年稳居全国首位，占全国超50%的比重。在潮州饶平，万佳水产与中山大学合作开展海鮸鱼全雄育种，通过分子标记辅助育种技术，将经济价值更高的雄性海鮸鱼比例大幅提升。“2023年以前，饶平的种苗长期依赖外地。”万佳水产董事长郑镇雄说，目前万佳水产已成功培育出海鮸鱼苗，年产苗约3000万尾，种苗实现本地化供应。\n\n在蔬菜领域，广东省农业科学院蔬菜研究所研究员谢大森和团队培育的“铁柱2号”冬瓜开创“铁心”冬瓜新类型，解决了黑皮冬瓜运输损耗高、发芽率低的产业痛点，累计推广面积约300万亩，占广东同类品种40%以上，是我国当前推广面积最大的黑皮冬瓜品种。一个品种的突破，带动的是整个冬瓜产业的标准化和商品化水平提升。\n\n新品种解决的是“种什么”，新技术解决的则是“怎么种”。在广东，新技术在广东农业中的应用正在从“单点试用”走向“系统嵌入”。\n\n在茂名，荔枝产业大数据平台完成人工智能大模型DeepSeek本地化部署，病虫害诊断从人工经验判断转向AI秒级分析，准确率提升至95%以上，生产效率提升30%，平均诊断时间从数小时缩短至5秒以内。在河源东源县柳城镇下坝村的万绿智慧无人农场，由中国工程院院士罗锡文团队指导打造的1500亩无人化核心区，配备无人驾驶旋耕机、插秧机、收割机等智能农机，已全面实现“耕、种、管、收”全流程云端远程操控，亩产提升至500公斤以上。\n\n广东多丘陵山地，六成以上耕地散落在山岭之间，大型农机进不去，传统人工耕作又苦又累。新装备的突破，正在改写这一困局。\n\n在茂名高州分界镇，果农谭锦威的荔枝园已扩至上千亩。他购入两架农业无人机后，600多亩果园中400亩需要深度作业的都靠无人机完成，谭锦威感叹：“两天就能打完一轮药，没有无人机，根本不敢种这么多。”在潮州凤凰山海拔近千米的高山茶园，23岁的“茶二代”韦镇辉组建了一支十几人的“00后”飞手团队，用农业无人机参与植保、飞防、施肥、吊送，服务凤凰镇及周边200多户茶农，累计覆盖茶园达5万亩。\n\n据广东省农业农村厅数据，全省植保无人机保有量约9000架，日作业能力约440万亩，登记在册的病虫害专业化防治服务组织1755个，从业人员约1.8万人。\n\n在海洋领域，新装备的迭代速度同样令人瞩目。近年来，湛江相继建成投入养殖的“海威”系列、“恒燚1号”等多个大型养殖平台，全省占比38%的养殖重器矩阵在此破浪——从半潜式到桁架式，从固定式到自航式，多品类多型号的“湛江造”重器持续领跑广东深远海装备发展。\n\n广东发挥雄厚的船舶与海工装备制造基础优势，推动“格盛1号”“伏羲一号”“湛江湾一号”等一批大型智能化养殖平台相继投产，相关技术和产品辐射主要沿海省份。截至8月2日，2026年全省已新建重力式网箱920个、桁架类网箱5个。\n\n从一粒种子到一片深海，从手机里的AI助手到高山上的无人机，新品种、新技术、新装备在广东的真实场景中释放出实实在在的产业价值。\n\n但一个更深层的问题随之浮现：这些技术场景为什么能在广东率先“跑通”？答案指向制度设计和政策推力。\n\n政策为技术落地“架桥铺路”\n\n农村科技特派员制度是广东打通技术落地“最后一公里”的关键一招。\n\n9月，潮州市饶平县东山镇的万亩茶园迎来秋茶采摘。驻东山镇科技特派员、华南农业大学张凌云教授团队穿梭于茶园、车间，指导茶农采茶做茶。“作为广东科技特派员，我长期扎根东山镇，把实验室的研究成果真正应用到茶叶生产过程中，帮助农户提高种茶制茶的技艺。”张凌云介绍，针对低档茶原料经济效益不高、所制茶类单一等问题，团队创新性地将单丛乌龙茶工艺改良为全发酵单丛红茶工艺，为低档茶原料开辟了新销路。\n\n从种业到技术再到装备，广东的政策体系正在系统性地为技术落地“架桥铺路”。\n\n广东省委农村工作会议明确提出，因地制宜、抓紧抓实“粤强种芯”“粤强农装”“粤强智农”工程，不断提升农业科技创新效能，大力发展农业新质生产力。在种业领域，全省系统收集保存农业种质资源36.8万份，位居全国前列；“拎包入住”式的现代化海洋牧场种业创新中心吸引全国63个顶尖科研团队入驻，针对41个适养品种开展联合攻关。在装备领域，广东陆续出台一系列政策推动低空经济高质量发展，支持农业无人机广泛应用于农林植保等综合场景应用。\n\n金融“活水”则为技术装备从实验室走向产业提供了关键支撑。\n\n近年来，广东印发了《广东省现代化海洋牧场设施设备险实施方案》，将设施设备纳入政策性保险范围，各级财政补贴保费75%，养殖主体保费自担25%，降低养殖主体生产风险。现代化海洋牧场养殖险养殖主体自担比例从40%降低至20%，减轻养殖主体负担。\n\n与此同时，农村创业大赛本身也是一种推动科技成果及时转化的制度设计。\n\n总决赛当天，中国农业银行广东省分行为参赛项目进行重点客户授信；仲恺农业工程学院科研团队与广东车田山水豆腐食品科技有限公司、广东马岭观花生态园有限公司等签订科技项目结对协议，围绕技术攻关、产品研发开展合作。从赛场竞技到资源对接，从发现项目到培育人才，“以赛促创”逐渐成为“百千万工程”助推广东农业加速变革的重要抓手。\n\n站在“十五五”开局之年新起点上，广东以“百千万工程”为总指引，以机制创新推动技术落地，以场景应用驱动新一轮的科技创新和成果转化，扎实推动乡村产业全面振兴，加快书写农业农村现代化的时代答卷。","南方日报 2026-09-22","2026-09-22T00:00:00Z","报道",10,false,76,{"impact":17,"substance":18,"depth":19,"authority":13,"freshness":20,"relevant":21,"comment":22},22,20,17,7,1,"以广东农村创业大赛为切口，系统呈现种业、AI诊断、无人农场、深远海装备与政策金融配套，数据与案例扎实，具省级产业参考价值。",[24],{"name":10,"url":6},[26,27,28,29,30,31],"智慧农业","农业人工智能","种业振兴","科技特派员","植保无人机","深远海养殖",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},"B2","fruit","果树","\u002Ftopic\u002Fhorticulture\u002Ffruit","B",[],{"status":40,"locked":14,"version":41,"method":42,"evidence":43},"classified","2026-10-22.2","rules",{"candidates":44,"agricultural_evidence":47},[45,52,59,66,72,77,82,87,92],{"code":33,"score":46,"supported":47,"title":48,"abstract":50,"tags":51},11,true,[49],"荔枝",[49],[],{"code":53,"score":54,"supported":47,"title":55,"abstract":56,"tags":58},"F4",4,[],[57],"植保",[30],{"code":60,"score":61,"supported":47,"title":62,"abstract":63,"tags":65},"B1",3,[],[64],"蔬菜",[],{"code":67,"score":61,"supported":47,"title":68,"abstract":69,"tags":71},"F6",[],[70],"无人农场",[],{"code":73,"score":21,"supported":14,"title":74,"abstract":75,"tags":76},"D2",[],[],[31],{"code":78,"score":21,"supported":14,"title":79,"abstract":80,"tags":81},"F1",[],[],[28],{"code":83,"score":21,"supported":14,"title":84,"abstract":85,"tags":86},"G1",[],[],[29],{"code":88,"score":21,"supported":14,"title":89,"abstract":90,"tags":91},"I1",[],[],[26],{"code":93,"score":21,"supported":14,"title":94,"abstract":95,"tags":96},"I2",[],[],[27],[98,99],"铁柱2号 冬瓜 广东","荔枝AI 病虫害诊断 茂名","铁柱2号冬瓜广东-3406",5,"2026-09-25T00:09:30.408382Z",{"total":104,"page":21,"page_size":104,"items":105},6,[106,157,234,285,394,463],{"id":107,"title":108,"url":109,"summary":110,"summary_zh":8,"content":111,"source_name":112,"source_url":8,"published_at":113,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":114,"score_detail":115,"sources":120,"tags":122,"primary_topic":125,"secondary_topics":126,"classification":127,"search_phrases":152,"slug":155,"view_count":20,"doi":8,"paper":8,"created_at":156},3387,"从会种粮到'慧'种粮——中联重科岳麓智慧农场、常州艾宝机器人、温氏华系种猪、牧原智能猪舍AI兽医集体亮相","https:\u002F\u002Fnews.cyol.com\u002Fgb\u002Fkeji\u002Farticles\u002F2026-09\u002F23\u002Fcontent_v6vKznCP2x.html","中联重科岳麓智慧农场'天空地人机'协同智慧作业模式搭载多光谱相机巡田无人机最高飞120米、20分钟完成整片地块巡检，长势图精度达3米×3米网格；常州艾宝机器人四臂采摘猕猴桃机器人经第三方检测适合山坡丘陵地形，一台机器能节约7至8个人工；温氏股份、德康农牧'华系种猪育种技术与核心种源创制及应用'项目获国家科学技术进步奖一等奖；牧原股份智能化猪舍AI兽医全天候值守。","◎记者 刘立 王乔琪\n\n又是一年丰收季。田野之间，沉甸甸的果实背后，农业生产逻辑正在发生深刻变化。\n\n今年5月，国务院印发的《加快农业农村现代化“十五五”规划》明确提出：“推进人工智能运用和智慧农业发展。加快农业人工智能技术创新、应用场景拓展和产业生态营造。”\n\n近期，上海证券报记者在对部分农业种养殖龙头企业和农业展会的调研中发现，从种子实验室到果园大田，智能化工具正在把农业从经验驱动推向数据驱动。AI不再只是实验室概念，它正从育种、田间种植延伸到畜牧水产全链条，改写着传统农业依靠经验、看天吃饭的旧模式。\n\n**以AI打磨农业“芯片”**\n\n种业被称作农业的“芯片”。记者在采访中发现，快速发展的AI技术，正在缩短育种探索的漫长周期。\n\n在近日举办的全国种子双交会上，中种集团展台上一台ELISA蛋白全自动分析检测工作站设备吸引不少参会者驻足。据工作人员介绍，传统育种蛋白检测多采用人工、半自动化操作，通量低、稳定性差，而这台设备针对生物育种性状鉴定、蛋白定量筛查场景，可实现实验全流程无人自动化运行，日检测通量比人工高5倍以上，成本降低50%，且完全国产化。\n\n记者在采访中发现，AI正在把复杂的农业科研数据转化成通俗直观的结论。育种不再完全依靠科研人员肉眼观察记录，而是由仪器采集数据，AI完成解析筛选。\n\n上海泽泉科技股份有限公司研发的花粉活力仪可以应用于玉米、小麦、果树、大豆杂交育种项目，帮助科研人员精准把握授粉窗口，稳定后代品质。公司副总经理张凯峰对记者说：“过去做大豆、玉米、小麦等杂交育种，收集花粉之后，不知道花粉活性。我们的设备可以对每一粒花粉活性做量化测定，活性不达标的花粉直接淘汰。随着科技的普及，我相信，未来这些智能设备都会逐步下沉到普通农户。”\n\n一位农业专家对记者表示，AI并非颠覆传统育种，而是对育种体系的升级赋能。智能育种的核心，是依靠高通量设备获取标准化的基因组、表型组数据，依托算法挖掘基因与性状之间的关联，推动育种从过去依赖经验的“试错筛选”，转向数据驱动的“精准设计”，助力我国种业向育种4.0阶段迈进。\n\n**“空天地一体化”重构农业生产模式**\n\n在位于湖南长沙的中联重科岳麓智慧农场，中联智慧农业打造的“天空地人机”协同智慧作业模式，正在改写大田管护方式。\n\n以往人工巡查四五百亩稻田，要耗费一至两小时。中联智慧农业这套搭载多光谱相机的巡田无人机最高可飞120米，20分钟就能完成整片地块巡检，变焦可达100多倍，捕捉到虫害、长势异常等疑点便低空补拍核验。影像实时回传云端后，AI算法输出水稻长势图，精度可达3米乘以3米网格，明确标注地块补水、补肥位置与用量。\n\n天上完成巡查，地上设备随即落地执行。中联智慧农业部署的物联网灌排设备、微型气象站同步采集风、雨、光照数据，农户通过手机软件就能查看农事日历、操控田间设备。这种“按数据决策”的模式，改变了传统农业“凭经验跑田”的粗放管理方式。\n\n除了天上飞的无人机，地上走的机器人也开始应用到更多农业生产场景。\n\n在北京平谷的2026世界农业科技创新大会上，常州艾宝机器人有限公司研发的猕猴桃采摘机器人吸引了不少观众。公司工程师赵炳宇向记者介绍，这款四臂采摘机器人，经第三方机构检测，适合山坡丘陵地形，一台机器能够节约7至8个人工。现阶段设备尚处在定制阶段，已有3家企业完成定制采购。\n\n“我们主要从事AI智能水果采摘机器人研发，已突破多臂协同、视觉感知、自主导航等关键技术，已经推出苹果、葡萄、猕猴桃采摘等系列产品，目的就是推动采摘机器人从技术示范走向生产落地。”赵炳宇说。\n\n**农牧业智能化驶入快车道**\n\n中国是全球最大的猪肉消费国，年消费猪肉超过5000万吨。庞大的产业规模背后，是管理规模大、场景复杂的生猪养殖体系。如今，人工智能正加速渗透进这个最传统的行业。\n\n畜牧种业是畜牧业的“芯片”，在很长一段时间，国内要从海外进口种猪，还要高价采购海外生猪基因芯片，支付高昂的知识产权费。通常一头外引种猪的综合成本高达3万元至5万元。\n\n这一局面如今已被打破。日前，温氏股份、德康农牧等作为主要完成单位参与的“华系种猪育种技术与核心种源创制及应用”项目，荣获国家科学技术进步奖一等奖。该项目通过基因组选择、表型精准测定等技术创新，构建了华系种猪自主育种体系，创制了具有自主知识产权的核心种猪群体，标志着我国生猪核心种源实现高标准自主可控，彻底打破国外长期垄断格局。\n\n在河南，畜牧业龙头企业牧原股份的智能化猪舍里，AI兽医已投入全天候值守。\n\n“过去发现猪不吃食，饲养员找兽医、翻手册、凭经验判断，平均响应时间需要个把小时；现在从发现异常到推荐用药的闭环，仅需数秒。”牧原股份技术负责人介绍，名为“小牧助手”的AI应用，融合企业30余年养殖知识与全产业链330万套智能装备每日产生的20亿条数据，被封装为可嵌入日常流程的AI智能体。目前，牧原与阿里云合作共建的养猪大模型“猪小牧”已向全行业开放共享，助力行业高质量发展。\n\n此外，类似变革正在更多养殖场景中铺开。比如在水产养殖领域，广西防城港东兴市红树林农业有限公司的养殖基地引入AI“厂长”，集成AI算法、高清水下摄像头与传感器网络，24小时实时采集虾群数据，自动调控水阀与投料，每日精准投喂300余次。目前，该基地一年可养对虾5茬，年产量35万至40万公斤。\n\n【责任编辑：母建鑫】","中青在线 2026-09-23","2026-09-23T00:00:00Z",85,{"impact":116,"substance":17,"depth":117,"authority":118,"freshness":20,"relevant":21,"comment":119},26,18,12,"紧扣十五五规划AI+农业主线，覆盖育种、种植、养殖全链条，案例与数据扎实，具行业风向标价值。",[121],{"name":112,"url":109},[26,27,123,28,124],"智能农机","智慧养殖",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":128},{"candidates":129,"agricultural_evidence":47},[130,135,139,144,148],{"code":33,"score":61,"supported":47,"title":131,"abstract":132,"tags":134},[],[133],"猕猴桃",[],{"code":78,"score":21,"supported":14,"title":136,"abstract":137,"tags":138},[],[],[28],{"code":140,"score":21,"supported":14,"title":141,"abstract":142,"tags":143},"F5",[],[],[123],{"code":88,"score":21,"supported":14,"title":145,"abstract":146,"tags":147},[],[],[26],{"code":93,"score":21,"supported":14,"title":149,"abstract":150,"tags":151},[],[],[27],[153,154],"中联重科 岳麓智慧农场","温氏 华系种猪","中联重科岳麓智慧农场-3387","2026-09-25T00:09:27.645047Z",{"id":158,"title":159,"url":160,"summary":161,"summary_zh":162,"content":8,"source_name":163,"source_url":160,"published_at":164,"category":165,"cover_url":8,"hotness":13,"is_selected":14,"score":15,"score_detail":166,"sources":170,"tags":172,"primary_topic":176,"secondary_topics":177,"classification":178,"search_phrases":204,"slug":207,"view_count":208,"doi":209,"paper":210,"created_at":233},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","论文",{"impact":117,"substance":167,"depth":19,"authority":118,"freshness":168,"relevant":21,"comment":169},21,8,"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。",[171],{"name":163,"url":160},[26,27,173,174,175],"边缘计算","作物病害识别","苹果病害",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":179},{"candidates":180,"agricultural_evidence":47},[181,187,193,199],{"code":33,"score":117,"supported":47,"title":182,"abstract":184,"tags":186},[183],"apple",[35,185,183],"苹果",[175],{"code":88,"score":20,"supported":47,"title":188,"abstract":189,"tags":192},[],[190,191],"精准农业","precision agriculture",[26],{"code":194,"score":20,"supported":47,"title":195,"abstract":196,"tags":198},"I5",[],[173,197],"edge computing",[173],{"code":93,"score":101,"supported":47,"title":200,"abstract":201,"tags":203},[],[202],"artificial intelligence",[174,27],[205,206],"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",0,"10.22190\u002Ffuacr260506002g",{"doi":209,"openalex_id":211,"authors":212,"venue":163,"cited_by_count":208,"oa_url":160,"card":225,"direction":231,"ingested_from":232},"W7222964752",[213,216,219,222],{"name":214,"orcid":215},"Milan Grujev","https:\u002F\u002Forcid.org\u002F0009-0002-3211-6844",{"name":217,"orcid":218},"Dragan H. Stojanovic","https:\u002F\u002Forcid.org\u002F0000-0003-4893-3814",{"name":220,"orcid":221},"Miloš Ilić","https:\u002F\u002Forcid.org\u002F0000-0002-9696-2874",{"name":223,"orcid":224},"Aleksandar Milosavljević","https:\u002F\u002Forcid.org\u002F0000-0003-3057-7727",{"tldr":226,"method":227,"finding":228,"direction":229,"opportunity":230},"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","openalex","2026-10-20T23:30:33.830748Z",{"id":235,"title":236,"url":237,"summary":238,"summary_zh":8,"content":8,"source_name":239,"source_url":8,"published_at":240,"category":165,"cover_url":8,"hotness":13,"is_selected":14,"score":241,"score_detail":242,"sources":245,"tags":247,"primary_topic":250,"secondary_topics":251,"classification":252,"search_phrases":272,"slug":275,"view_count":208,"doi":8,"paper":276,"created_at":284},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":243,"substance":17,"depth":117,"authority":46,"freshness":168,"relevant":21,"comment":244},16,"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。",[246],{"name":239,"url":237},[26,27,173,248,249],"葡萄藤","病害评估",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":253},{"candidates":254,"agricultural_evidence":47},[255,260,264,268],{"code":33,"score":46,"supported":47,"title":256,"abstract":258,"tags":259},[257],"葡萄",[257],[],{"code":88,"score":21,"supported":14,"title":261,"abstract":262,"tags":263},[],[],[26],{"code":93,"score":21,"supported":14,"title":265,"abstract":266,"tags":267},[],[],[27],{"code":194,"score":21,"supported":14,"title":269,"abstract":270,"tags":271},[],[],[173],[273,274],"DefoliationCAM 葡萄藤 食叶","Jetson Orin Nano 边缘AI 葡萄","DefoliationCAM葡萄藤食叶-5130",{"doi":8,"openalex_id":8,"authors":277,"venue":8,"cited_by_count":208,"oa_url":8,"card":278,"direction":229,"ingested_from":283},[],{"tldr":279,"method":280,"finding":281,"direction":229,"opportunity":282},"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。","agent","2026-10-17T00:13:44.932340Z",{"id":286,"title":287,"url":288,"summary":289,"summary_zh":290,"content":8,"source_name":291,"source_url":288,"published_at":240,"category":165,"cover_url":8,"hotness":13,"is_selected":14,"score":292,"score_detail":293,"sources":297,"tags":299,"primary_topic":303,"secondary_topics":308,"classification":315,"search_phrases":367,"slug":370,"view_count":21,"doi":371,"paper":372,"created_at":393},4988,"Hierarchical cross-modal spatiotemporal attention network for crop yield prediction in complex Himalayan agroecosystems","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffpls.2026.1933033","Introduction Accurate crop yield prediction is essential for precision agriculture, climate-resilient farm management, and timely decision-making. However, yield prediction remains challenging because of complex, nonlinear, and multi-scale interactions among crop physiology, soil conditions, weather variability, and management practices. Conventional statistical, machine learning, and deep learning approaches, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and long short-term memory (LSTM) networks, often have limitations in capturing long-range temporal dependencies, hierarchical spatial relationships, heterogeneous data modalities, and predictive uncertainty. Methods This study proposes a Hierarchical Cross-Modal Spatio-Temporal Attention Network (HCM-STAN) for crop yield prediction using a unified attention-based framework for integrating heterogeneous agro-environmental data. The architecture incorporates four principal components: (i) hierarchical spatio-temporal attention operating across tree, block, orchard, and regional scales; (ii) a cross-modal attention module for adaptive fusion of IoT-based soil sensor observations, weather data, plant physiological measurements, and drone-based multispectral imagery; (iii) a soil-aware attention head that explicitly models soil memory, hysteresis effects, and root-zone dynamics; and (iv) an uncertainty-aware prediction module combining Monte Carlo dropout and quantile regression to generate calibrated prediction intervals. The framework was evaluated using a multi-source dataset collected from Himalayan apple orchards during 2023–2026, comprising 1,247 monitored trees across three commercial orchards. Results The proposed HCM-STAN achieved an R 2 of 0.89 for four-week-ahead crop yield prediction, representing a 15.6% improvement over the CNN-LSTM baseline. Furthermore, zero-shot transfer to mango orchards achieved an R 2 of 0.67, corresponding to approximately 75% of the performance obtained under full training. Discussion The results demonstrate that integrating hierarchical spatio-temporal representation learning, cross-modal attention, soil-aware modelling, and uncertainty estimation can effectively address the heterogeneous and dynamic nature of crop yield prediction in complex mountain agroecosystems. The observed zero-shot transfer performance further indicates the potential of HCM-STAN to generalize across crop systems without crop-specific retraining. Overall, the proposed framework provides a promising foundation for reliable, uncertainty-aware yield forecasting and can support precision agriculture, climate-smart farm management, and data-driven decision-making in heterogeneous agroecosystems.","引言 准确的作物产量预测对于精准农业、气候适应性农场管理以及及时决策至关重要。然而，由于作物生理、土壤条件、天气变异和管理措施之间复杂、非线性且多尺度的相互作用，产量预测仍然具有挑战性。传统的统计方法、机器学习以及深度学习方法，包括卷积神经网络（CNN）、循环神经网络（RNN）和长短期记忆（LSTM）网络，在捕捉长程时间依赖关系、层次化空间关系、异构数据模态以及预测不确定性方面往往存在局限。方法 本研究提出了一种用于作物产量预测的层次化跨模态时空注意力网络（HCM-STAN），采用统一的基于注意力的框架来整合异构农业环境数据。该架构包含四个主要组成部分：（i）在树、地块、果园和区域尺度上运行的层次化时空注意力；（ii）用于自适应融合基于物联网的土壤传感器观测、天气数据、植物生理测量和无人机多光谱影像的跨模态注意力模块；（iii）显式建模土壤记忆、滞后效应和根区动态的土壤感知注意力头；（iv）结合蒙特卡洛 dropout 和分位数回归以生成校准预测区间的不确定性感知预测模块。该框架使用2023—2026年在喜马拉雅苹果园采集的多源数据集进行了评估，该数据集包含三个商业果园中1，247棵监测树木。结果 所提出的 HCM-STAN 在提前四周作物产量预测中达到了0.89的 R²，相较于 CNN-LSTM 基线提升了15.6%。此外，零样本迁移至芒果园达到了0.67的 R²，相当于完整训练下所获性能的约75%。讨论 结果表明，整合层次化时空表征学习、跨模态注意力、土壤感知建模和不确定性估计，能够有效应对复杂山地农业生态系统中作物产量预测的异构性和动态性。观察到的零样本迁移性能进一步表明，HCM-STAN 具有在无需作物特定再训练的情况下跨作物系统泛化的潜力。总体而言，该 p","Frontiers in Plant Science",81,{"impact":117,"substance":17,"depth":117,"authority":294,"freshness":295,"relevant":21,"comment":296},14,9,"提出分层跨模态时空注意力网络，融合物联网土壤传感、气象、生理与无人机多光谱数据，苹果园四周产量预测R²达0.89并实现芒果园零样本迁移，方法新颖、数据扎实，对智慧农业产量预报有参考价值。",[298],{"name":291,"url":288},[26,27,300,301,302],"产量预测","多模态融合","遥感",{"code":93,"slug":304,"name":305,"path":306,"parent_code":307},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[309,310],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"code":311,"slug":312,"name":313,"path":314,"parent_code":307},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":40,"locked":14,"version":41,"method":42,"evidence":316},{"candidates":317,"agricultural_evidence":47},[318,326,332,338,342,349,355,361],{"code":93,"score":46,"supported":47,"title":319,"abstract":320,"tags":325},[],[321,322,323,324],"深度学习","机器学习","machine learning","deep learning",[27,301],{"code":33,"score":295,"supported":47,"title":327,"abstract":328,"tags":331},[],[185,329,330,183],"芒果","orchard",[],{"code":311,"score":168,"supported":47,"title":333,"abstract":334,"tags":337},[],[335,336],"无人机多光谱","multispectral",[300,302],{"code":88,"score":20,"supported":47,"title":339,"abstract":340,"tags":341},[],[190,191],[26],{"code":343,"score":104,"supported":47,"title":344,"abstract":345,"tags":348},"H2",[],[346,347],"土壤","soil",[],{"code":194,"score":104,"supported":47,"title":350,"abstract":351,"tags":354},[],[352,353],"物联网","IoT",[],{"code":356,"score":61,"supported":47,"title":357,"abstract":358,"tags":360},"H6",[],[359],"农业生态",[],{"code":362,"score":61,"supported":47,"title":363,"abstract":364,"tags":366},"H7",[],[365],"气候适应",[],[368,369],"喜马拉雅 苹果园 产量预测","HCM-STAN 作物产量预测","喜马拉雅苹果园产量预测-4988","10.3389\u002Ffpls.2026.1933033",{"doi":371,"openalex_id":373,"authors":374,"venue":291,"cited_by_count":208,"oa_url":288,"card":388,"direction":229,"ingested_from":232},"W7221795850",[375,378,380,382,384,386],{"name":376,"orcid":377},"Shabir Ahmad Mir","https:\u002F\u002Forcid.org\u002F0000-0003-2311-218X",{"name":379,"orcid":8},"Umarfarooque Momin",{"name":381,"orcid":8},"Sudeep Kumar E",{"name":383,"orcid":8},"Itfaq Ahmad Mir",{"name":385,"orcid":8},"Ab Rouf Khan",{"name":387,"orcid":8},"Ghulam Mohammad Mir",{"tldr":389,"method":390,"finding":391,"direction":231,"opportunity":392},"提出分层跨模态时空注意力网络HCM-STAN，融合多源农业数据预测喜马拉雅山区苹果产量。","用IoT土壤、气象、生理和无人机多光谱数据，结合分层时空与跨模态注意力及不确定性","四周前产量预测R²达0.89，比CNN-LSTM提升15.6%，零样本迁移芒果R²为0.67。","可探索跨作物零样本迁移的领域自适应机制，并验证模型在更多山地农业生态系统的泛化能力。","2026-10-15T23:30:08.750140Z",{"id":395,"title":396,"url":397,"summary":398,"summary_zh":399,"content":8,"source_name":400,"source_url":397,"published_at":401,"category":165,"cover_url":8,"hotness":13,"is_selected":14,"score":402,"score_detail":403,"sources":406,"tags":408,"primary_topic":412,"secondary_topics":413,"classification":416,"search_phrases":436,"slug":439,"view_count":21,"doi":440,"paper":441,"created_at":462},4808,"Early Detection of Apple Scab in Orchards and Mildew in Vineyards Using A Novel Deep Learning Model and Multispectral Imagery","https:\u002F\u002Fdoi.org\u002F10.15832\u002Fankutbd.1898342","Agricultural diseases are a significant problem for growers as they cause substantial damage to fruits and leaves, leading to yield losses. Therefore, developing systems for early detection of plant diseases is a crucial issue. In this study, a new deep learning-based hybrid model is presented for the detection and segmentation of plant diseases, specifically apple scab disease in apple orchards and mildew disease in vineyards. Multispectral imagery data collected in agricultural areas of Tekirdag province in Turkey via drones between May 2023 and December 2024 were used in developing the early disease detection system. The datasets contain 3625 images of apple orchards and 5625 images of vineyards. DJI Phantom 4 Multispectral drone, equipped with five spectral bands (Blue, Green, Red, Red Edge, and Near Infrared), was utilized to capture both spectral richness and temporal progression. This study introduces a novel deep learning architecture developed specifically for time series-based disease detection and segmentation using multispectral drone imagery. Changes in plants over time provide important information about the occurrence of plant diseases. For this reason, time series were used in this study to extract features from the changes in plants over time. The proposed model architecture was specifically designed to leverage time series information, enabling robust tracking of crop health changes over time. The model trained with the dataset collected for apple diseases achieved an average Intersection Over Unit (IoU) value of 82.05%, while the model trained with the dataset collected for vineyard diseases reached an IoU value of 79.67%. The findings highlight the effectiveness of integrating drone-acquired multispectral time-series data with advanced deep learning models for scalable, accurate, and timely plant disease detection in precision agriculture.","农业病害是种植者面临的重大问题，会对果实和叶片造成严重损害，导致产量损失。因此，开发植物病害早期检测系统是一个至关重要的问题。本研究提出了一种基于深度学习的新型混合模型，用于植物病害的检测与分割，具体针对苹果园中的苹果黑星病和葡萄园中的霜霉病。该早期病害检测系统的开发使用了2023年5月至2024年12月期间通过无人机在土耳其泰基尔达省农业区域采集的多光谱影像数据。数据集包含3625幅苹果园图像和5625幅葡萄园图像。所用DJI Phantom 4多光谱无人机配备五个光谱波段（蓝、绿、红、红边和近红外），用于捕捉光谱丰富度和时间变化过程。本研究提出了一种专门开发的深度学习架构，用于基于时间序列的多光谱无人机影像病害检测与分割。植物随时间的变化提供了关于植物病害发生的重要信息。因此，本研究使用时间序列从植物随时间的变化中提取特征。所提出的模型架构专门设计以利用时间序列信息，从而能够稳健地跟踪作物健康状况随时间的变化。使用苹果病害数据集训练的模型达到了82.05%的平均交并比（IoU）值，而使用葡萄园病害数据集训练的模型达到了79.67%的IoU值。研究结果凸显了将无人机获取的多光谱时间序列数据与先进深度学习模型相结合，在精准农业中实现可扩展、准确且及时的植物病害检测方面的有效性。","Tarım Bilimleri Dergisi","2026-10-12T00:00:00Z",77,{"impact":243,"substance":167,"depth":117,"authority":404,"freshness":295,"relevant":21,"comment":405},13,"该研究提出基于多光谱时序影像的新型深度学习模型，实现果园与葡萄园病害早期检测，数据规模大、方法新颖，对精准农业病害预警具有参考价值。",[407],{"name":400,"url":397},[26,409,27,410,411],"无人机","遥感监测","病害预警",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[414,415],{"code":93,"slug":304,"name":305,"path":306,"parent_code":307},{"code":311,"slug":312,"name":313,"path":314,"parent_code":307},{"status":40,"locked":14,"version":41,"method":42,"evidence":417},{"candidates":418,"agricultural_evidence":47},[419,423,428,432],{"code":33,"score":19,"supported":47,"title":420,"abstract":421,"tags":422},[183],[185,257,183],[],{"code":93,"score":424,"supported":47,"title":425,"abstract":426,"tags":427},15,[324],[321,324],[27],{"code":311,"score":118,"supported":47,"title":429,"abstract":430,"tags":431},[336],[336],[410],{"code":88,"score":20,"supported":47,"title":433,"abstract":434,"tags":435},[],[190,191],[26],[437,438],"苹果黑星病 无人机 多光谱","葡萄园 霜霉病 深度学习","苹果黑星病无人机多光谱-4808","10.15832\u002Fankutbd.1898342",{"doi":440,"openalex_id":442,"authors":443,"venue":400,"cited_by_count":208,"oa_url":455,"card":456,"direction":229,"ingested_from":232},"W7221558726",[444,447,450,452],{"name":445,"orcid":446},"Batuhan Aşıroğlu","https:\u002F\u002Forcid.org\u002F0000-0003-0767-6348",{"name":448,"orcid":449},"Aydın Kağan Turkoglu","https:\u002F\u002Forcid.org\u002F0009-0001-8383-8807",{"name":451,"orcid":8},"Fatih Sinan Bir",{"name":453,"orcid":454},"Sibel Senan","https:\u002F\u002Forcid.org\u002F0000-0001-6773-0428","https:\u002F\u002Fdergipark.org.tr\u002Fen\u002Fdownload\u002Farticle-file\u002F5761152",{"tldr":457,"method":458,"finding":459,"direction":460,"opportunity":461},"提出一种基于无人机多光谱时序影像的深度学习混合模型，实现苹果黑星病和葡萄霉病的早期检测与分割。","DJI Phantom 4多光谱无人机采集时序影像，构建时序深度学习分割模型。","苹果病IoU达82.05%，葡萄病达79.67%，验证多光谱时序数据有效性。","农业遥感与作物表型","可探索多作物、多病害的时序多光谱通用模型，并融合气象与地面数据提升早期预警能力。","2026-10-13T23:30:10.242467Z",{"id":464,"title":465,"url":466,"summary":467,"summary_zh":468,"content":8,"source_name":469,"source_url":466,"published_at":470,"category":165,"cover_url":8,"hotness":13,"is_selected":14,"score":471,"score_detail":472,"sources":474,"tags":476,"primary_topic":479,"secondary_topics":480,"classification":482,"search_phrases":498,"slug":501,"view_count":208,"doi":502,"paper":503,"created_at":527},4744,"An empirical performance comparison of deep learning models for apple leaf disease recognition","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs10791-026-10573-4","Currently, Biotic and abiotic factors, in agriculture, are estimated to be responsible for around 22% of the total losses in crop production. It is therefore very important, but at the same time very difficult for farmers to identify these constraints at the earliest possible stage. The most recent developments in computer vision have made it possible to identify as well as classify plant lesions at a primary level. Various deep learning techniques have made it possible to detect biotic stress in apple plant leaves with a very high degree of accuracy. Hence, automated segmentation of images of diseased leaves has become a leading research theme all over the world. In this paper, a dataset from FGVC7, which is an open, source dataset and contains four different classes of leaf diseases of the apple crop is used to measure the performance of the proposed model. A three, step image preprocessing procedure is conducted, which involves image enhancement, removal of background noise, and object identification through a variety of approaches. Using UNet, PSPNet, and UNet++, disease areas are identified. UNet + + delivering the most precise object segmentation. The segmented patch data are then fed into a fusion, based classification model as input. Patch segmentation makes it possible to separate the various disease areas, thus increasing the classification accuracy. The proposed framework combines several CNN architectures, namely, VGG16, InceptionV3, AlexNet, and GoogleNet, in order to take advantage of their complementary strengths, then a Vision Transformer (ViT) is used to identify distinct local features via early feature fusion. After this, the efficiency of the proposed model is check in comparison with the pre-trained CNN models individually. Comparing with all other models the proposed model has shown the accuracy of highest order i.e. 98.85%, clearly out performing individual CNN models.","目前，农业中的生物和非生物因素估计约占作物生产总损失的22%。因此，农民尽早识别这些限制因素非常重要，但同时也非常困难。计算机视觉的最新发展使得在初级水平上识别和分类植物病变成为可能。各种深度学习技术使得以极高准确度检测苹果植株叶片的生物胁迫成为可能。因此，患病叶片图像的自动分割已成为世界范围内的前沿研究主题。本文使用来自FGVC7的数据集来衡量所提出模型的性能，该数据集是一个开放源数据集，包含苹果作物的四类不同叶片病害。进行了三步图像预处理，包括图像增强、背景噪声去除以及通过多种方法进行目标识别。使用UNet、PSPNet和UNet++识别病害区域，其中UNet++提供了最精确的目标分割。然后将分割后的图像块数据作为输入馈入基于融合的分类模型。图像块分割使得能够分离不同的病害区域，从而提高分类准确率。所提出的框架结合了多种CNN架构，即VGG16、InceptionV3、AlexNet和GoogleNet，以利用它们互补的优势，然后使用视觉Transformer（ViT）通过早期特征融合来识别不同的局部特征。此后，将所提出模型的效率与各个预训练CNN模型进行比较。与所有其他模型相比，所提出的模型显示出最高阶的准确率，即98.85%，明显优于各个单独的CNN模型。","Discover Computing","2026-10-10T00:00:00Z",69,{"impact":118,"substance":18,"depth":243,"authority":404,"freshness":168,"relevant":21,"comment":473},"方法组合（UNet++分割+CNN与ViT融合）与98.85%准确率有参考价值，但属实验室数据集验证，产业落地影响有限，可作为技术前沿资讯收录。",[475],{"name":469,"url":466},[26,27,477,321,478],"计算机视觉","苹果病害识别",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[481],{"code":93,"slug":304,"name":305,"path":306,"parent_code":307},{"status":40,"locked":14,"version":41,"method":42,"evidence":483},{"candidates":484,"agricultural_evidence":47},[485,490,494],{"code":93,"score":18,"supported":47,"title":486,"abstract":487,"tags":489},[324],[321,477,324,488],"computer vision",[27,321,477],{"code":33,"score":294,"supported":47,"title":491,"abstract":492,"tags":493},[183],[185,183],[],{"code":88,"score":21,"supported":14,"title":495,"abstract":496,"tags":497},[],[],[26],[499,500],"苹果叶片病害 深度学习","FGVC7 苹果病害 数据集","苹果叶片病害深度学习-4744","10.1007\u002Fs10791-026-10573-4",{"doi":502,"openalex_id":504,"authors":505,"venue":469,"cited_by_count":208,"oa_url":521,"card":522,"direction":229,"ingested_from":232},"W7221353656",[506,508,511,513,515,518],{"name":507,"orcid":8},"Apoorva Arora",{"name":509,"orcid":510},"Vinay Gautam","https:\u002F\u002Forcid.org\u002F0000-0002-0258-5132",{"name":512,"orcid":8},"Anand Muni Mishra",{"name":514,"orcid":8},"Santar Pal Singh",{"name":516,"orcid":517},"Yadvendra Pratap Singh","https:\u002F\u002Forcid.org\u002F0000-0001-6396-3355",{"name":519,"orcid":520},"Mukund Pratap Singh","https:\u002F\u002Forcid.org\u002F0000-0001-5877-9510","https:\u002F\u002Flink.springer.com\u002Fcontent\u002Fpdf\u002F10.1007\u002Fs10791-026-10573-4.pdf",{"tldr":523,"method":524,"finding":525,"direction":231,"opportunity":526},"用UNet++分割苹果病叶并融合多种CNN与ViT分类，实现98.85%识别准确率。","FGVC7数据集，UNet\u002FPSPNet\u002FUNet++分割，VGG16等CNN与","UNet++分割最准，融合模型准确率达98.85%，优于单个CNN模型。","可探索轻量化分割-分类联合模型在田间移动端的实时部署与多作物泛化。","2026-10-12T23:30:09.091475Z"]