[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-1667":3,"related-1667":70},{"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":24,"tags":26,"primary_topic":32,"secondary_topics":38,"classification":39,"search_phrases":65,"slug":68,"view_count":21,"doi":8,"paper":8,"created_at":69},1667,"钦州市答复人大第 5 号建议：支持桂鸟先飞·滴滴打药平台建设灵山荔枝产业数字化示范基地","http:\u002F\u002Fnyncj.qinzhou.gov.cn\u002Fzfxxgk\u002Ffdzdgknr\u002Fzcyjd\u002Ft28095649.shtml","钦州市农业农村局答复市六届人大八次会议第 5 号代表建议。答复指出，市级层面将人工智能发展列为全市\"九个突破\"之首，出台《钦州市人工智能发展突破行动三年实施方案(2025—2027)》等文件，明确将农业作为重点赋能领域。灵山县已将\"AI+农业\"\"低空经济+智慧农业\"等新业态纳入县数字经济发展规划。广西钦州桂鸟数字科技有限公司 6 月 26 日揭牌，平台荣获广西智慧农业数字乡村创新大赛最佳潜力奖。",null,"黄川代表：\n\n您提出的《关于支持桂鸟先飞·滴滴打药平台建设灵山荔枝产业数字化示范基地 推动全市荔枝产业高质量发展的政策建议》收悉。经认真研究，并综合各协办单位意见，现答复如下：\n\n一、关于出台相关政策支持，多方协同推动平台建设的建议\n\n（一）系统谋划构建政策体系。**一是**市级层面强化顶层设计。我市将人工智能发展列为全市“九个突破”之首，成立由市委、市政府主要领导担任指挥长的专项行动指挥部，出台《钦州市人工智能发展突破行动三年实施方案（2025—2027）》等文件，明确将农业作为重点赋能领域，相关部门公布《钦州市人工智能开放场景清单》，涵盖农业、制造、教育等领域，为智慧农业发展提供坚实政策保障。**二是**县级层面细化落地举措。灵山县已将“AI+农业”“低空经济＋智慧农业”等新业态纳入县数字经济发展规划及专项资金重点支持方向，为平台建设提供顶层设计和政策支撑。\n\n（二）深化多方协同联动。**一是**国企赋能推动平台发展。2026 年 6 月 26 日，由广西钦州乡村振兴投资发展集团有限公司与广西灵山桂鸟先飞团队共同组建的广西钦州桂鸟数字科技有限公司正式揭牌，标志着“桂鸟先飞”项目在钦州进入国企赋能、平台运营、产业协同的新阶段。**二是**多方联动凝聚发展合力。市数据发展局联合广西钦州乡村振兴投资发展集团有限公司、广西钦州桂鸟数字科技有限公司等多方主体开展专题座谈，围绕平台运营优化、农业人工智能落地场景打磨等内容深度磋商，加快形成市县联动、部门协同、政企合作的常态化工作机制，共同推动荔枝数字化示范基地建设。**三是**积极争取项目资金支持。灵山县通过广西乡村科技特派员县团经费、钦州农业新品种后补助资金等渠道，为桂鸟先飞争取科技资金约 10 万元，用于宣传推介平台、购置无人机飞防设备、举办飞手培训等。组织广西灵山千年农业科技有限公司征集《桂鸟先飞—滴滴打药平台智能调度算法研发及产业化应用》市级科技项目建议，目前该项目已纳入 2026 年钦州市科技计划，正在开展申报工作。\n\n（三）积极培育典型场景。**一是**平台创新成效获多方认可。推动“桂鸟先飞·滴滴打药平台”在 2025 年广西 AI 赋能千行百业超级联赛——智慧农业（数字乡村）创新大赛中荣获“最佳潜力奖”；《人民日报》、央视 13 套《新闻调查》、人民网等主流媒体先后对平台创新模式与应用成效进行深度报道，品牌影响力持续提升。**二是**入选自治区级典型场景。2026 年 5 月，培育推荐的滴滴打药平台场景入选广西“人工智能+农业”典型应用场景。\n\n（四）夯实算力数字根基。**一是**已建成算力基础设施。市大数据发展局已建成广西首个全栈国产化政务云、昇腾人工智能算力集群，完成满血版 Deepseek 大模型部署落地。**二是**持续推进算力扩容升级。引入开元云高性能计算平台，联想 2000P 智算中心项目已签约开工建设。**三是**强化平台应用支撑。为“桂鸟先飞·滴滴打药”平台荔枝植保作业监测、农事数据采集、病虫害 AI 识别、产销数字化管控、云端调度管理等全场景应用提供算力保障与人工智能技术底层支撑。\n\n（五）完善产业政策供给。**一是**市大数据发展局正加快拟定人工智能+农业、农业特种植保机器人专项扶持政策，争取将无人机打药、智慧农事管控等应用纳入政策扶持范畴，积极协助企业申报自治区大数据发展局年度人工智能赋能千行百业专项补助资金。**二是**灵山县积极协助企业申报国家、自治区及市级数字经济、乡村振兴领域试点示范项目。\n\n二、关于建设荔枝数字化示范基地，形成“平台+基地+农户”的智慧农业模式的建议\n\n（一）加大财政资金投入。**一是**积极统筹各级财政资金支持荔枝产业发展。根据市人民政府出台的《钦州市“一镇一品”建设三年行动方案（2023—2025 年）》，市财政局三年来共统筹资金 1.25 亿元支持荔枝等 9 大特色产业发展。加快做好荔枝品种结构调整，推动丰产稳产的妃子笑面积扩至 30 万亩，全市荔枝良种覆盖率超 90%；支持灵山县建成 2000 亩标准化设施栽培基地，对大棚、避雨棚等设施给予补助；支持全市完成低产果园改造 52 万亩，创建国家级标准示范园 82 个，推广标准化生产 50 万亩。积极争取一批荔枝产业集群、产业强镇、示范园区等项目落地，全市建成县级以上现代特色农业（荔枝）示范园区 4 个，其中自治区级 3 个、县级 1 个。**二是**灵山县整合上级资金 1000 万元，建成广西首个标准化数字化智能化荔枝种植基地，集成土壤水分仪、气象站、虫情测报灯、智能孢子仪等设备，构建“地块—监测—研判—处理”生产管理闭环，实现农药使用量降低 15%、病虫害预警提前 7 天、施肥精准度提升 90%。\n\n（二）完善财政金融服务机制。**一是**加大信贷资金支持力度。将荔枝种植主体纳入信贷直通车范围，对符合条件的设施农业项目进行贴息奖补。2025 年 7 月至 2026 年 5 月，累计为 798 户农林牧渔业经营主体提供 9.28 亿元融资支持。灵山县农村信用合作联社、邮储银行灵山支行、桂林银行灵山支行等三家银行发行“荔枝贷”，2024 年至 2026 年 6 月累计为 369 户荔枝种植主体提供 0.88 亿元贷款支持。**二是**落实农机购置与飞防作业普惠补助。桂鸟科技采购植保无人机、果园 AI 监测设备、数字溯源终端等农机装备，可按照广西农机补贴统一政策申报补贴；农户开展荔枝无人机飞防，可申领农业社会化服务作业补助。\n\n三、关于提升荔枝品质、品牌与市场竞争力的建议\n\n（一）强化品质保障，夯实品牌根基。**一是**推广绿色实用技术，实现产业节本增效。在全国首创推广“光驱避蛀蒂虫技术”，实现虫果率“零”突破，减少化学农药使用 40%，获农业农村部绿色防控技术推广认证。灵山县引进价值 1200 万元的荔枝光谱分拣线，实现按糖度、果径智能分级，优果率从 70%跃升至 95%。**二是**推广气微保鲜技术，延长产品货架期。大力推广“曹氏”荔枝气微保鲜技术，荔枝保鲜期从 3 天延长到 27 天，显著提升荔枝保鲜效果，有效扩大了荔枝的销售半径和销售周期。\n\n（二）强化品牌宣传，拓宽市场渠道。**一是**借力头部直播平台实现热销。主动对接国内主流电商平台，借力“与辉同行”专场直播实现本土特色产品热销，观看人数破 10 万人，产品销量超 4.2 万件，销售额超 400 万元。**二是**积极参加展销活动拓展市场。组织企业参加 2026 年荔枝上行京东快递合作推介会、2026 广西荔枝品牌推介暨顺丰荔枝行业解决方案发布会、2026CCFA 零售业供应链大会等展销活动，以及 2026 年“桂字号”农业品牌夏季水果丰收季暨新派茶饮产品推广活动，宣传推介钦州荔枝。**三是**开展“探源千年古荔之乡”网络名人采风活动，邀请区外网络达人赴灵山荔枝示范园、大芦村采风创作，在抖音、今日头条等平台开展达人内容创作与信息流投放，覆盖广西及江浙沪重点消费区域，助力荔枝产销对接与品牌提升。\n\n（三）强化数字化赋能，拓宽销售渠道。**一是**率先在全区创新预售模式。2025 年，开发钦州水果地图小程序，发布钦州荔枝采购指南，利用平台提供荔枝产品线上服务，推出“包园预售”、“荔枝卡预售”等模式，全市优质荔枝预订总量突破 40%以上。**二是**电商销售取得新突破。 2026 年荔枝节期间，灵山县组织 60 余家电商企业、800 余家微商、7000 余名荔枝电商从业人员参与线上销售，荔枝快递发货量较荔枝产量相近的 2024 年同比增长 106.6%，电商销售创历史新高。\n\n（五）拓展东盟市场，推动品牌外向化。**一是**创新监管服务，指导 9 家果园及包装厂通过出口注册资质认定，推广“公司+基地+标准化”模式，从源头保障出口荔枝品质。**二是**推荐昊扬食品、益天下等企业参与自治区商务厅“共享大市场出口中国”“东盟水果汇聚广西”专项活动，为灵山荔枝等农产品拓展东盟市场、夯实外贸渠道奠定基础。\n\n四、下一步工作计划\n\n下一步，我市将重点抓好以下工作：**一是**总结“桂鸟 AI 飞巡—作物监测系统”和“滴滴打药平台”成熟经验，形成可复制推广的数字化农事服务标准，逐步向全市荔枝主产区推广。**二是**加大对广西钦州桂鸟数字科技有限公司的培育力度，指导企业规范经营管理、推动上规入统，支持企业拓展智慧植保、数字溯源、品牌营销一体化业务，并依托中马钦州产业园区区位优势开发面向东盟的智慧农事服务场景。**三是**持续跟进灵山县荔枝智慧种植管理示范项目实施，统筹现有资金渠道积极争取上级专项转移支付资金，用好“桂惠贷”和“荔枝贷”等金融产品引导社会资本参与。四是深化品牌营销，深挖荔枝文化内涵，创新数字化营销模式，持续提升“钦州荔枝”品牌影响力和市场竞争力。\n\n感谢您对我市荔枝产业发展的关心和支持。\n\n钦州市农业农村局\n\n2026 年 8 月 2 8 日","钦州市农业农村局","2026-09-04T00:00:00Z","政策",10,false,74,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},20,22,18,12,2,1,"地市级政策答复，内容详实，涉及AI+农业、数字化基地建设及产业扶持，但时效性较低。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","AI+农业","荔枝产业","政策扶持","数字化基地",{"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},[45,52,58],{"code":33,"score":46,"supported":47,"title":48,"abstract":50,"tags":51},8,true,[49],"荔枝",[],[],{"code":53,"score":54,"supported":47,"title":55,"abstract":56,"tags":57},"I1",4,[],[27],[27],{"code":59,"score":60,"supported":47,"title":61,"abstract":62,"tags":64},"I6",3,[],[63],"数字乡村",[],[66,67],"数字化基地 政策扶持 智慧农业 荔枝产业","数字化基地 政策扶持","数字化基地政策扶持智慧农业荔枝产业-1667","2026-09-05T00:04:35.881903Z",{"total":71,"page":22,"page_size":71,"items":72},6,[73,126,170,248,291,339],{"id":74,"title":75,"url":76,"summary":77,"summary_zh":8,"content":78,"source_name":79,"source_url":8,"published_at":80,"category":81,"cover_url":8,"hotness":13,"is_selected":14,"score":82,"score_detail":83,"sources":87,"tags":89,"primary_topic":92,"secondary_topics":93,"classification":94,"search_phrases":121,"slug":124,"view_count":22,"doi":8,"paper":8,"created_at":125},3092,"天上无人机 地上机器狗 AI生成\"体检单\"——东莞打造\"1+3+9\"智慧果园 荔枝小年减产 65.94% 销售均价反涨 193%","https:\u002F\u002Fwww.toutiao.com\u002Farticle\u002F7688141623238066732\u002F","9-22 南方都市报报道东莞市农业农村局打造\"1+3+9\"智慧果园应用场景抢占荔枝产业\"智\"高地：1 个 500 亩省级智慧果园核心区（莞荔园）+ 3 大特色荔枝产区（观音绿\u002F冰荔\u002F糯米糍覆盖 5000 亩）+ 9 个市级智慧果园（樟木头\u002F厚街\u002F大岭山\u002F大朗）。今年 7 月举办的\"低空+智慧农业\"应用场景发布会展示了植保无人机喷洒、吊运无人机 1 分钟从山头到山顶、巡检无人机半小时采集百亩果园生长数据、机器狗在陡坡草丛自动巡检等多场景协同。在 2026 年荔枝\"小年\"同比减产 65.94% 的不利条件下，凭借科技赋能与品牌加持，东莞荔枝销售均价达 44 元\u002F斤，同比增加 193%。","![Image 1](https:\u002F\u002Fp3-sign.toutiaoimg.com\u002Ftos-cn-i-axegupay5k\u002F4d59596f045542389e8e5857d28dfb36~tplv-tt-origin-web:gif.jpeg?_iz=58558&from=article.pc_detail&lk3s=953192f4&x-expires=1790640358&x-signature=9XA5NxoeRN6ZAuw3YYyOaUcU%2BjI%3D)![Image 2](https:\u002F\u002Fp3-sign.toutiaoimg.com\u002Ftos-cn-i-tjoges91tu\u002F5f33bad24f2f01bbd4e7a2ff663b7776~tplv-tt-origin-web:gif.jpeg?_iz=58558&from=article.pc_detail&lk3s=953192f4&x-expires=1790640358&x-signature=bPrJsnbYjihBVX658a44IiukjXo%3D)\n东莞市农业科学研究中心的莞荔园里，植保无人机开展喷洒作业。\n\n![Image 3](https:\u002F\u002Fp3-sign.toutiaoimg.com\u002Ftos-cn-i-tjoges91tu\u002F1f7d7ad95566e8dd4d40c1ffaf2cb9de~tplv-tt-origin-web:gif.jpeg?_iz=58558&from=article.pc_detail&lk3s=953192f4&x-expires=1790640358&x-signature=0Ko9xgpOWi0DOpi%2FxfZANKAjizA%3D)\n东莞市农业科学研究中心的莞荔园里，机器狗在斜坡灵活行动。\n\n![Image 4](https:\u002F\u002Fp3-sign.toutiaoimg.com\u002Ftos-cn-i-tjoges91tu\u002Fb1e87a5f810ee89df8d6819202611e95~tplv-tt-origin-web:gif.jpeg?_iz=58558&from=article.pc_detail&lk3s=953192f4&x-expires=1790640358&x-signature=AUrUkHg4xmK0MQkvdICV0V2oPm8%3D)\n岭南荔园的双臂协同荔枝采摘机器人。\n\n![Image 5](https:\u002F\u002Fp3-sign.toutiaoimg.com\u002Ftos-cn-i-tjoges91tu\u002Fe5c3a1ff6c1ef2b5dd8d87d01692f48f~tplv-tt-origin-web:gif.jpeg?_iz=58558&from=article.pc_detail&lk3s=953192f4&x-expires=1790640358&x-signature=kOu74t5Fs45cECRvNGL%2FIN0T8CE%3D)\n东莞桂味荔枝。\n\n开栏语 近年来，广东深入实施“百千万工程”，大力发展农业新质生产力，持续推进农业数字化转型与数字乡村建设，各地抢抓发展机遇，推动人工智能技术嵌入农业生产、产业发展、乡村治理等方面，积极探索人工智能赋能乡村振兴的实践路径。南都深入企业与农村，推出相关报道，介绍各地以“AI+”赋能乡村振兴的经验做法。\n\n抢抓“人工智能+农业”发展新机遇，东莞荔枝产业正在悄然发生变化。南都记者从东莞市农业农村局获悉，近年来，东莞探索打造“1+3+9”智慧果园应用场景，让荔枝生产从“看天吃饭”走向“数据决策”。\n\n据了解，2026年，在“荔枝小年”同比减产65.94%的情况下，通过科技赋能、品质提升与品牌加持，东莞荔枝销售均价达44元\u002F斤，同比增加193%。\n\n**“1+3+9”**\n\n**一张智慧果园的网络正在铺开**\n\n今年7月9日，东莞举办了“低空+智慧农业”应用场景发布会暨农技人员知识更新培训会。\n\n现场观摩环节，在东莞市农业科学研究中心的莞荔园里，随着技术人员的遥控操作，植保无人机率先向山头飞去，抵达密集林间并开展喷洒作业。另一边，吊运无人机同步开展吊运演示，肥料、农具平稳挂载起降，从山头到山顶仅花费1分钟。\n\n紧随其后，巡检无人机沿着预设航线自动飞巡，仅需半个小时，就对百亩果园的果树生长数据进行了全面采集，并依靠遥感数据精准定位病虫害隐患点位，自动生成可视化果园数字档案。\n\n现场还来了一位“客人”——机器狗，随着技术人员的遥控，它不受地形的影响，能在陡坡上、草丛间灵活行动，为果园的地面自动化巡检、无人运输等提供新的解决方案，配合无人机低空技术，还可以丰富空天地一体化协作的应用场景，解决以往大型农机设备在果园移动难、不灵活的问题。\n\n这是东莞市农业农村局抢抓“低空+智慧农业”发展机遇的一个缩影。近年来，东莞探索打造“1+3+9”智慧果园应用场景，抢占荔枝产业发展“智”高地。\n\n简单来说，“1”，是指一个500亩的省级智慧果园核心区，位于东莞市农科中心莞荔园；“3”，是指观音绿、冰荔、优质糯米糍三大特色荔枝产区，覆盖面积约5000亩；“9”，则是在樟木头、厚街、大岭山和大朗四个荔枝主产镇，挑选基础条件好的果园，建设9个市级智慧果园应用场景。\n\n从“1”到“3”再到“9”，一张智慧果园的网络正在东莞铺开。\n\n**AI算法**\n\n**精准判断每棵荔枝树的“健康状况”**\n\n无人机定时巡航，孢子捕捉仪识别病害，AI虫情灯分析虫害，微型气象站监测气象……眼下，在东莞的荔枝林里，这套全生长周期的智能监测网络，让果园环境、树体长势、病虫害情况全天候“在线”，数据识别准确率超过90%。\n\n更令人惊奇的是，东莞依托无人机系统实施智慧巡园，推动数据迭代升级，通过AI算法，系统能精准判断每一棵荔枝树的“健康状况”，自动生成并分析“体检报告”，并给予一对一指导方案，巡检效率提升超30倍。\n\n**精准用药**\n\n**从“一季鲜果”走向“全年产业”**\n\n荔枝要好吃，用药安全至关重要。东莞还构建精准用药应用场景，在荔枝花期划定“禁药期”，构建起“智能感知—智慧决策—精准作业”的应用场景，病虫害防治精准率提升到90%。推广植保无人机病虫害统防统治服务，实现作业效率比人工提升7倍，农药使用量下降20%。\n\n采摘之后，荔枝的“旅程”并未结束。东莞还开展荔枝保鲜加工研究，建设荔枝采后实验室，配置荔枝冻眠保鲜、烘干加工等设备并联接物联网，推动荔枝从“一季鲜果”走向“全年产业”。\n\n**保险+科技农服**\n\n**农户上传照片，小程序可自动诊断病虫害**\n\n技术再先进，最终还是要落到果农手里。\n\n东莞打造了“保险+科技农服”创新试点，配套线上小程序，农户上传照片就能自动诊断病虫害，遇到疑难问题还能直连农业专家。管理效率大幅提升、人工成本显著降低；政府引导、保险护航、科技支撑、农户受益的创新模式正在逐步形成。\n\n同时，东莞与省农科院对接，组建了一支涵盖栽培管理、病虫害防控、智慧农业技术、数据平台运维及农业生产资料服务等多领域的复合型服务队伍，招募17名特聘农技员，把智慧果园的经验向基层延伸。\n\n此外，建立20多个荔枝示范基地、105个(次)绿色防控技术示范点，围绕栽培管理、病虫害防治、宜机化改造等开展协同创新，帮果农解决实实在在的难题。\n\n东莞还通过承办国家荔枝龙眼产业技术体系大湾区(东莞)荔枝人工智能技术应用培训交流会、东莞市“低空+智慧农业”应用场景发布会等，邀请高等院校、科研院所、AI企业专家学者现场授课、分享前沿成果，推动人工智能从“概念”变为果农手中的“新农具”。\n\n采写:南都记者 田玲玲\n\n供图:东莞市农业农村局","南方都市报","2026-09-21T23:56:00Z","报道",77,{"impact":17,"substance":18,"depth":84,"authority":85,"freshness":85,"relevant":22,"comment":86},17,9,"东莞“1+3+9”智慧果园落地细节与减产65.94%却均价涨193%的数据兼具产业价值与传播性，值得进入每日精选。",[88],{"name":79,"url":76},[63,27,90,91,29],"低空经济","农业人工智能",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":95},{"candidates":96,"agricultural_evidence":47},[97,102,106,112,117],{"code":33,"score":98,"supported":47,"title":99,"abstract":100,"tags":101},11,[49],[49],[],{"code":53,"score":54,"supported":47,"title":103,"abstract":104,"tags":105},[],[27],[27],{"code":107,"score":60,"supported":47,"title":108,"abstract":109,"tags":111},"F4",[],[110],"植保",[],{"code":113,"score":22,"supported":14,"title":114,"abstract":115,"tags":116},"I2",[],[],[91],{"code":59,"score":22,"supported":14,"title":118,"abstract":119,"tags":120},[],[],[63],[122,123],"东莞 智慧果园 荔枝","东莞 低空 智慧农业 无人机","东莞智慧果园荔枝-3092","2026-09-22T00:05:33.048940Z",{"id":127,"title":128,"url":129,"summary":130,"summary_zh":8,"content":131,"source_name":132,"source_url":8,"published_at":133,"category":81,"cover_url":8,"hotness":13,"is_selected":14,"score":134,"score_detail":135,"sources":139,"tags":141,"primary_topic":146,"secondary_topics":147,"classification":148,"search_phrases":164,"slug":167,"view_count":168,"doi":8,"paper":8,"created_at":169},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",65,{"impact":136,"substance":84,"depth":137,"authority":137,"freshness":71,"relevant":22,"comment":138},16,13,"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。",[140],{"name":132,"url":129},[27,142,143,144,145],"智能农机","葡萄","栽培技术","国际交流",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":149},{"candidates":150,"agricultural_evidence":47},[151,155,159],{"code":33,"score":20,"supported":47,"title":152,"abstract":153,"tags":154},[143],[143],[143],{"code":53,"score":54,"supported":47,"title":156,"abstract":157,"tags":158},[],[27],[27],{"code":160,"score":22,"supported":14,"title":161,"abstract":162,"tags":163},"F5",[],[],[142],[165,166],"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",0,"2026-10-22T00:07:04.061911Z",{"id":171,"title":172,"url":173,"summary":174,"summary_zh":175,"content":8,"source_name":176,"source_url":173,"published_at":177,"category":178,"cover_url":8,"hotness":13,"is_selected":14,"score":179,"score_detail":180,"sources":183,"tags":185,"primary_topic":189,"secondary_topics":190,"classification":191,"search_phrases":219,"slug":222,"view_count":168,"doi":223,"paper":224,"created_at":247},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",76,{"impact":19,"substance":181,"depth":84,"authority":20,"freshness":46,"relevant":22,"comment":182},21,"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。",[184],{"name":176,"url":173},[27,91,186,187,188],"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":192},{"candidates":193,"agricultural_evidence":47},[194,200,207,213],{"code":33,"score":19,"supported":47,"title":195,"abstract":197,"tags":199},[196],"apple",[35,198,196],"苹果",[188],{"code":53,"score":201,"supported":47,"title":202,"abstract":203,"tags":206},7,[],[204,205],"精准农业","precision agriculture",[27],{"code":208,"score":201,"supported":47,"title":209,"abstract":210,"tags":212},"I5",[],[186,211],"edge computing",[186],{"code":113,"score":214,"supported":47,"title":215,"abstract":216,"tags":218},5,[],[217],"artificial intelligence",[187,91],[220,221],"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":223,"openalex_id":225,"authors":226,"venue":176,"cited_by_count":168,"oa_url":173,"card":239,"direction":245,"ingested_from":246},"W7222964752",[227,230,233,236],{"name":228,"orcid":229},"Milan Grujev","https:\u002F\u002Forcid.org\u002F0009-0002-3211-6844",{"name":231,"orcid":232},"Dragan H. Stojanovic","https:\u002F\u002Forcid.org\u002F0000-0003-4893-3814",{"name":234,"orcid":235},"Miloš Ilić","https:\u002F\u002Forcid.org\u002F0000-0002-9696-2874",{"name":237,"orcid":238},"Aleksandar Milosavljević","https:\u002F\u002Forcid.org\u002F0000-0003-3057-7727",{"tldr":240,"method":241,"finding":242,"direction":243,"opportunity":244},"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":249,"title":250,"url":251,"summary":252,"summary_zh":8,"content":8,"source_name":253,"source_url":8,"published_at":254,"category":178,"cover_url":8,"hotness":13,"is_selected":14,"score":255,"score_detail":256,"sources":258,"tags":260,"primary_topic":265,"secondary_topics":266,"classification":267,"search_phrases":278,"slug":281,"view_count":168,"doi":8,"paper":282,"created_at":290},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":136,"substance":181,"depth":84,"authority":137,"freshness":214,"relevant":22,"comment":257},"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。",[259],{"name":253,"url":251},[27,261,262,263,264],"云南","柑橘","智慧灌区","蒸腾模拟",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":268},{"candidates":269,"agricultural_evidence":47},[270,274],{"code":33,"score":20,"supported":47,"title":271,"abstract":272,"tags":273},[262],[262],[262],{"code":53,"score":54,"supported":47,"title":275,"abstract":276,"tags":277},[],[27],[27],[279,280],"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":8,"openalex_id":8,"authors":283,"venue":8,"cited_by_count":168,"oa_url":8,"card":284,"direction":243,"ingested_from":289},[],{"tldr":285,"method":286,"finding":287,"direction":243,"opportunity":288},"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":292,"title":293,"url":294,"summary":295,"summary_zh":8,"content":8,"source_name":296,"source_url":8,"published_at":297,"category":178,"cover_url":8,"hotness":13,"is_selected":14,"score":298,"score_detail":299,"sources":301,"tags":303,"primary_topic":306,"secondary_topics":307,"classification":308,"search_phrases":327,"slug":330,"view_count":168,"doi":8,"paper":331,"created_at":338},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":136,"substance":18,"depth":19,"authority":98,"freshness":46,"relevant":22,"comment":300},"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。",[302],{"name":296,"url":294},[27,91,186,304,305],"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":309},{"candidates":310,"agricultural_evidence":47},[311,315,319,323],{"code":33,"score":98,"supported":47,"title":312,"abstract":313,"tags":314},[143],[143],[],{"code":53,"score":22,"supported":14,"title":316,"abstract":317,"tags":318},[],[],[27],{"code":113,"score":22,"supported":14,"title":320,"abstract":321,"tags":322},[],[],[91],{"code":208,"score":22,"supported":14,"title":324,"abstract":325,"tags":326},[],[],[186],[328,329],"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":332,"venue":8,"cited_by_count":168,"oa_url":8,"card":333,"direction":243,"ingested_from":289},[],{"tldr":334,"method":335,"finding":336,"direction":243,"opportunity":337},"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",{"id":340,"title":341,"url":342,"summary":343,"summary_zh":344,"content":8,"source_name":345,"source_url":342,"published_at":297,"category":178,"cover_url":8,"hotness":13,"is_selected":14,"score":346,"score_detail":347,"sources":350,"tags":352,"primary_topic":356,"secondary_topics":361,"classification":368,"search_phrases":420,"slug":423,"view_count":22,"doi":424,"paper":425,"created_at":446},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":19,"substance":18,"depth":19,"authority":348,"freshness":85,"relevant":22,"comment":349},14,"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。",[351],{"name":345,"url":342},[27,91,353,354,355],"产量预测","多模态融合","遥感",{"code":113,"slug":357,"name":358,"path":359,"parent_code":360},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[362,363],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"code":364,"slug":365,"name":366,"path":367,"parent_code":360},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":40,"locked":14,"version":41,"method":42,"evidence":369},{"candidates":370,"agricultural_evidence":47},[371,379,385,391,395,402,408,414],{"code":113,"score":98,"supported":47,"title":372,"abstract":373,"tags":378},[],[374,375,376,377],"深度学习","机器学习","machine learning","deep learning",[91,354],{"code":33,"score":85,"supported":47,"title":380,"abstract":381,"tags":384},[],[198,382,383,196],"芒果","orchard",[],{"code":364,"score":46,"supported":47,"title":386,"abstract":387,"tags":390},[],[388,389],"无人机多光谱","multispectral",[353,355],{"code":53,"score":201,"supported":47,"title":392,"abstract":393,"tags":394},[],[204,205],[27],{"code":396,"score":71,"supported":47,"title":397,"abstract":398,"tags":401},"H2",[],[399,400],"土壤","soil",[],{"code":208,"score":71,"supported":47,"title":403,"abstract":404,"tags":407},[],[405,406],"物联网","IoT",[],{"code":409,"score":60,"supported":47,"title":410,"abstract":411,"tags":413},"H6",[],[412],"农业生态",[],{"code":415,"score":60,"supported":47,"title":416,"abstract":417,"tags":419},"H7",[],[418],"气候适应",[],[421,422],"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":424,"openalex_id":426,"authors":427,"venue":345,"cited_by_count":168,"oa_url":342,"card":441,"direction":243,"ingested_from":246},"W7221795850",[428,431,433,435,437,439],{"name":429,"orcid":430},"Shabir Ahmad Mir","https:\u002F\u002Forcid.org\u002F0000-0003-2311-218X",{"name":432,"orcid":8},"Umarfarooque Momin",{"name":434,"orcid":8},"Sudeep Kumar E",{"name":436,"orcid":8},"Itfaq Ahmad Mir",{"name":438,"orcid":8},"Ab Rouf Khan",{"name":440,"orcid":8},"Ghulam Mohammad Mir",{"tldr":442,"method":443,"finding":444,"direction":245,"opportunity":445},"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"]