[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2929":3,"related-2929":51},{"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":24,"tags":26,"search_phrases":32,"slug":35,"view_count":36,"doi":37,"paper":38,"created_at":50},2929,"A REAL-TİME AI-DRİVEN AGRİCULTURAL ROVER INTEGRATİNG PLANT DİSEASE DETECTİON AND GEO-REFERENCED SOİL MOİSTURE ANALYSİS","https:\u002F\u002Fdoi.org\u002F10.30546\u002Femnaa.2026.02.28.123","This paper presents an autonomous agricultural ground robot for real-time monitoring of plant health and soil moisture in large-scale crop fields.The proposed system integrates a deep learning-based perception subsystem with autonomous navigation and a custom ground control station (GCS) to enable continuous and geo-referenced field analysis.Visual data are acquired using an onboard camera and processed in real time on a Raspberry Pi using an object detection model (ODM) to identify disease-related visual symptoms such as discoloration, deformation and leaf degradation.Each detected instance is associated with a confidence score and accurately geo-tagged using GPS data.In parallel, a contact-based soil moisture sensor performs localized measurements at fixed spatial intervals along a grid-based coverage trajectory.All perception outputs are synchronized with navigation data and transmitted via a telemetry link to the GCS where live video with detection overlays, rover trajectory, mission status and sensor telemetry are visualized and logged for postmission analysis.Field experiments conducted under real operating conditions demonstrate stable autonomous operation and achieve an overall plant disease detection accuracy of 85-90%, confirming the effectiveness of the proposed system for precision agriculture applications.","本文提出了一种用于大规模农田植物健康和土壤湿度实时监测的自主农业地面机器人。该系统将基于深度学习的感知子系统与自主导航及自定义地面控制站（GCS）相结合，实现连续且带地理参考的田间分析。视觉数据通过机载相机采集，并利用目标检测模型（ODM）在树莓派上实时处理，以识别与病害相关的视觉症状，如变色、变形和叶片退化。每个检测到的实例均关联置信度分数，并通过GPS数据精确标注地理位置。与此同时，基于接触式的土壤湿度传感器沿网格化覆盖轨迹以固定空间间隔进行局部测量。所有感知输出与导航数据同步，并通过遥测链路传输至地面控制站，在此可视化并记录带有检测叠加层的实时视频、漫游车轨迹、任务状态和传感器遥测数据，以供任务后分析。在实际运行条件下进行的田间实验证明了稳定的自主运行能力，并实现了85-90%的植物病害整体检测准确率，验证了所提系统在精准农业应用中的有效性。",null,"Scientific Journal","2026-09-18T00:00:00Z","论文",10,false,77,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},18,21,17,13,8,1,"集成深度学习病害识别与地理参考土壤墒情监测的自主农业机器人论文，田间实测准确率85-90%，方法新颖且数据可靠，对精准农业有参考价值。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业人工智能","农业机器人","植物病害检测","土壤墒情监测",[33,34],"农业机器人 病害检测 土壤墒情","Raspberry Pi 植物病害识别","农业机器人病害检测土壤墒情-2929",0,"10.30546\u002Femnaa.2026.02.28.123",{"doi":37,"openalex_id":39,"authors":40,"venue":10,"cited_by_count":36,"oa_url":6,"card":43,"direction":47,"ingested_from":49},"W7213559917",[41],{"name":42,"orcid":9},"Gasimov V.A., Dadashov F.H., Hasanov H.B., Huseynov N.E",{"tldr":44,"method":45,"finding":46,"direction":47,"opportunity":48},"开发实时AI农业机器人，集成植物病害检测与地理参考土壤湿度分析。","Raspberry Pi上部署目标检测模型，结合GPS和接触式土壤湿度传感器。","田间试验实现85-90%的植物病害检测准确率，并稳定自主运行。","智慧农业 \u002F 农业物联网","可探索多模态传感器融合与边缘计算优化，提升复杂田间环境下的实时检测鲁棒性。","openalex","2026-09-19T23:30:11.232025Z",{"total":52,"page":22,"page_size":52,"items":53},6,[54,80,102,153,186,207],{"id":55,"title":56,"url":57,"summary":58,"summary_zh":9,"content":59,"source_name":60,"source_url":9,"published_at":61,"category":62,"cover_url":9,"hotness":13,"is_selected":14,"score":63,"score_detail":64,"sources":69,"tags":71,"search_phrases":75,"slug":78,"view_count":36,"doi":9,"paper":9,"created_at":79},2555,"金华市农业农村局 金华市发改委推介农业农村领域开放场景","http:\u002F\u002Ffgw.jinhua.gov.cn\u002Fcol\u002Fcol1229169632\u002Fart\u002F2026\u002Fart_219d8d45f5484630a2535d67a5ab4a0d.html","金华市推出基于低空+AI的农事服务应用示范场景与低空AI赋能和美乡村建设场景。已建成全省首家低空+AI农事服务中心实体载体；部署多型号无人机、田间虫情与环境物联监测设备；搭建农业时空数据图谱与6层技术平台架构，拥有658TB+低空影像、1PB+农业结构化数据资源；自研80类农业AI模型，取得3项发明专利、33项软件著作权、44项数据知识产权。计划到2026年底在全国建成50家标准化低空AI农事服务中心。","**场景****1****：**基于“低空+AI”的农事服务应用 示范 场景\n\n**场景描述**：聚焦粮食稳产保供与农业社会化服务升级战略定位，破解传统农事人工巡田成本高、病虫害发现滞后、农机调度低效、多源农业数据孤岛等突出问题。依托无人机低空遥感、农业多模态大模型、时空数据图谱技术，构建集田间管护、农机智慧调度、粮食监测监管于一体的数智农事服务体系，打通“地块-作物-农机-服务”全业务链路。通过构建“AI 算万物”模型，释放低空海量数据算力，重构农业生产、管理与服务体系，探索农业数据要素资产化路径，推动农事作业由经验驱动向数据智能驱动转型，全面赋能现代农业全产业链高质量发展。计划到 2026 年底在全国建成 50 家标准化低空 AI 农事服务中心，助力区域农业降本增效，夯实粮食安全保障能力。\n\n**建设基础**：已建成全省首家“低空+AI”农事服务中心实体载体；部署多型号无人机、田间虫情与环境物联监测设备，具备大规模低空影像采集能力；搭建农业时空数据图谱与 6 层技术平台架构，拥有 658TB+低空影像、1PB+农业结构化数据资源；自研 80 类农业 AI 模型，取得 3 项发明专利、33 项软件著作权、44 项数据知识产权，获得浙江省软件首台套、2026 智慧农业创新大赛无人机巡田解决方案赛道第一名、浙江 省 2026“数据要素×”大赛现代农业赛道一等奖；已与高校、运营商建立协同合作关系，数据产品已在多家数据交易所上架，具备跨区域试点落地实践基础。\n\n**开放合作对象**：规模农业经营主体、高校、农业科研机构\n\n**合作方式**：试验基地共建、联合研发迭代、项目建设、技术服务 等\n\n**场景搭建****单位****：**金华浙农信息技术有限公司\n\n**联系人及联系方式：**郑先生，15857959533\n\n**场景****2****：**低空 AI 赋能和美乡村建设场景\n\n**场景描述**：聚焦和美乡村与数字乡村建设战略定位，面向乡村治理现代化发展需求，破解乡村多源数据割裂、生态人居巡查人力压力大、乡村新业态监管服务手段不足等关键问题。依托无人机低空遥感、时空大数据、AI 智能解译感知技术，搭建“天空地”一体化乡村智治服务体系。发挥低空设备空中巡检能力，实现人居环境、山林河湖、乡村基建动态监测，赋能乡村文旅新业态数字化升级，完善基层智慧治理链条，打造可复制输出的和美乡村数字化建设样板，助力乡村全面振兴。\n\n**建设基础**：具备乡村全域遥感数据获取、多源涉农数据汇聚解析技术能力；依托全省首家“低空+AI”农事服务中心实体载体，复用成熟的低空影像采集硬件资源；拥有 3 项发明专利、22 项软件著作权，无人机影像云管理系统获浙江省首版次认定，具备航测乙级资质；平台具备标准化开放接口，可对接基层治理相关业务系统；项目团队已积累多区县乡村数字化落地实践经验，具备开展乡村生态监测、业态研判的技术条件；已取得多项相关知识产权与省级荣誉资质，可支撑和美乡村多类业务场景迭代拓展。\n\n**开放合作对象**：民企、高校、科研院所\n\n**合作方式**：采购服务、项目建设、联合研发 等\n\n**场景搭建****单位****：**金华浙农信息技术有限公司\n\n**联系人及联系方式：**郑先生，1585795953\n\n**场景****3****：**金华双龙实验室自主导航田间转运机器人示范场景\n\n**场景描述**：聚焦金华地区设施农业与丘陵山地田间转运环节劳动力短缺、效率低下等痛点，建设一个集自主导航、智能调度、无人化转运于一体的现代农业机器人应用示范场景。针对传统人工搬运劳动强度大、现有 农机 设备跨 区域 作业难、缺乏数字化管理等问题，依托多传感器融合感知与云端协同调度技术，部署具备跨区域建图、动态路径规划、自动避障等功能的田间转运机器人，实现种子、种苗、肥料及果蔬等物资的自动化配送与 转运。预期将显著提升转运效率，降低人工成本，构建田间 农机 数字化管控网络，打造 设施农业 及 丘陵山区的智能化 农机示范场景，推动农业机器人产业发展。\n\n**建设基础**：已 在 金华市婺城区长山乡建成双龙实验室基地，核心区面积 1408 亩，涵盖玻璃温室、连栋大棚、丘陵山地果园及粮油大田等多样场景。已部署 3 台 不同类型的 自主导航田间转运机器人，额定载重 200kg 以上，搭载激光雷达、双目相机、IMU 等传感器，障碍物感知距离误差≤10cm，导航路径误差≤10cm。其中 ZNJ-DP01 转运 机器人获农业农村部首届智慧农业创新大赛温室搬运机器人赛道第一名，具备扎实的研发与场景验证能力。\n\n**开放合作对象**：企业、高校、科研院所\n\n**合作方式**：联合 场景开发验证、技术合作、项目共建、标准共研\n\n**场景搭建单位：**金华市农业科学研究院\n\n**联系人及联系方式：**郑先生，13645795434\n\n**场景****4****：**金华市现代农机检测鉴定场景\n\n**场景描述**：本场景聚焦金华丘陵山区农机装备产业集群 的 产品 质量监管 与 技术服务 的实际 需求，旨在 建设一个集农机性能测试、推广鉴定、零部件检测与标准化技术研究 于 一体的综合性科研与服务平台。依托 先进的实验设备与完善的测试手段，为新型农机具、新能源农业机械、AI 农机等现代农业机械的 研发 提供技术支持 与检测保障，提升农机产品质量与性能，推动农业机械化水平持续提高，并培养相关专业技术人才，为国家丘陵山区适用小型农业机械推广应用先导区建设注入新动能。\n\n**建设基础**：目前已在浙江省农业机械研究院开展检测与鉴定中心的建设工作，组建了专业的检验检测与推广鉴定团队，建成了农机产品质量检验检测实验室、液压传动与控制实验室、三维设计与仿真实验室、自动化智能装备实验室等，现有实验室面积 800 平方米，后续将扩增至 3000 平方米以上；已采购 200 余台（套）专业检测仪器，并完成实验室资质认定与计量认证（CMA），取得微耕机、插秧机等 19 个浙江省主要农机产品的检验检测资质能力，后续将扩增至 50 个以上。此外，该机构已被浙江省农业农村厅指定为农机鉴定机构。\n\n**开放合作对象**：政府机构、农机及配件生产企业、农机研发机构、农事服务中心等\n\n**合作方式**：采购服务、技术协作、项目建设、标准共研\n\n**场景搭建单位：**浙江省农业机械研究院\n\n**联系人及联系方式：**黄 先生，13750992539\n\n**场景****5****：**双龙实验室农业科技创新和产业创新融合改革示范场景\n\n**场景描述**：聚焦“城乡融合体制机制改革”重大任务，立足我市“名特优农产品丰富”的优势，以全省首个综合性农业市实验室“双龙实验室”为主引擎，建设具有金华辨识度的农业科技创新与产业创新融合改革示范场景。同步建设崖州湾国家实验室金华粮油作物创新平台、浙江省国家区域性农作物品种测试评价站、中非（金华）农业科创园等高能级科创平台，精准匹配区域特色农业产业需求与科技创新方向，助推农业延链补链强链。规划总占地 1 万亩、建筑面积 5 万平方米，核心区面积 1408 亩，计划到 2026 年底建成 7 个专业实验室、7 个产业技术中心、5 个物种园和 1 个科研示范基地，将双龙实验室打造成为浙中西 部 特色农业科技创新中心。\n\n**建设基础**：已完成 13861 平方米主体实验大楼、实验室专用仪器设备招投标、12000 平方米玻璃温室、5 万平方米联栋大棚的建设，已聘请 20 余位知名院士和国家产业技术体系首席（岗位专家）担任指导专家，累计引进推广新技术 113 项、新品种 227 个，解决产业技术难题 180 个。实验室支撑地方“两新融合”成效入选 2025 年度浙江农村改革十大案例。其中，浙江省国家区域农作物品种测试评价站于 2025 年 8 月获批中央预算内投资计划项目，核心区域面积 449 亩；崖州湾国家实验室金华粮油作物创新平台于 2026 年 5 月授牌成立，已开展 130 亩的水稻试验示范；中非（金华）农业科创园已建成中非农业科技交流中心，举办两届中非农业科技合作交流会，累计接待外宾、国内专家学者及社会各界人士超 1000 人次。\n\n**开放合作对象**：民企、高校、科研院所\n\n**合作方式**：项目建设、联合研发、标准共研\n\n**场景搭建单位：**金华市农业科学研究院（浙江省农业机械研究院）\n\n**联系人及联系方式：**陈先生，0579-82050456\n\n**场景****6****：**双龙实验室金华佛手综合开发利用技术创新中心中试平台\n\n**场景描述**：立足金华佛手特色产业基础，打造产学研用一体化佛手精深加工中试平台，打通实验室成果到产业化的转化通道。针对佛手精深加工工艺不成熟、实验室成果难以落地、香气活性物质提取损耗大、中小主体缺少中试试制条件等痛点，建设以佛手精油提取设备为核心的中试线，配套佛手果汁、佛手果酱等加工设备，实现佛手全值化利用，助力金华佛手从鲜果销售向精油、香氛等高附加值产品升级。\n\n**建设基础**：该中试线总面积 550 m 2，配置原料榨汁、精油高速离心冷提取、SCC 低温香气回收、枝叶精油及香气提取等成套设备，严格依据食品饮料行业现行国家标准及食品生产许可 SC 认证规范开展设计与建设。日处理佛手原料 1.5-2 吨。按年生产中试 100 天计算，可以年加工佛手 200 吨，年产出佛手汁 40 吨、佛手膳食纤维 50 吨、10ml 精油 4 万瓶、佛手香氛水（纯露）20 吨，香料产品 5 万袋。预计年产值约 380 万元。\n\n**开放合作对象**：民企、高校、科研院所\n\n**合作方式**：采购服务、采购产品、联合研发、标准共研\n\n**场景搭建单位：**金华市农业科学研究院\n\n**联系人及联系方式：**王先生，13566768758\n\n**场景****7****：**金线莲生物育种—种苗繁育—现代加工标准赋能场景\n\n**场景描述**：立足金华珍稀食药用植物金线莲特色产业基础，破解优异种质挖掘不足、生物育种技术迭代慢、精深加工产品供给不足 等痛点。构建“种质资源保护—生物育种创新—现代农产品精深加工”全链条体系，开展种质活性成分、药效药理 评价，搭建加工中试转化载体，迭代完善种苗、栽培、加工、食品安全系列标准，打通科研—种苗生产—健康食品开发的产业化通道，打造食药用植物“育种—种苗—加工”协同示范样板，推动特色农业提质增效、带动山区农户增收。\n\n**建设基础**：已形成“科研院所+龙头企业+基地+农户”的联动运营模式，各环节均落地实体应用场景。在金华、兰溪布局组培育苗车间与驯化苗圃，配套“金康 1 号”优势品种标准化繁育规程，年产优质种苗 2700 万株，同时 配套遮荫保湿、水肥管控、病虫害绿色防控等田间管护措施，建成 10 余个栽培 模式 示范 基地，可稳定保障农户用苗需求与基地 原料供应；联合攻关种苗提质、活性成分调控、健康饮品加工工艺等关键技术，建立成果许可与利益共享机制，具备 面向种植主体提供常态化技术服务 能力，推动特色农业高质量发展。\n\n**开放合作对象**：民企、高校、科研院所\n\n**合作方式**：联合研发、标准共研、项目建设\n\n**场景搭建单位：**金华市农业科学研究院\n\n**联系人及联系方式：**吴女士，13645790562\n\n## **场景****8****：**金华水稻全生物降解地膜覆盖控草绿色种植示范场景\n\n**场景描述**：聚焦粮食安全与农业绿色低碳发展，构建“适配 移栽稻 田的全生物降解地膜+覆膜插秧一体化装备+标准化农艺融合”三位一体水稻绿色种植示范场景。针对传统稻作化学除草剂依赖度高、草害防控成本高、农田面源污染、稻米品质提升受限等突出问题，以物理抑草替代化学除草，完善地膜材料、专用农机 装备及 田间 栽培 技术体系。联动科研机构、材料装备企业与各类种粮经营主体，探索技术 服务、优质稻米订单等落地模式。\n\n**建设基础**：已形成产学研用协同的技术与示范载体基础：已建成水稻绿色种植技术试验示范载体，配套开展 移栽稻田 材料、农机田间试验；研发适配水田的黑色全生物降解地膜，配套覆膜插秧一体化装备，可同步完成铺膜、破膜、插秧作业，日作业能力超 30 亩。已形成田块整理、水肥管控、残膜还田成套机艺技术规程，拥有相关发明专利。已对接地膜生产企业、农机制造单位，联动家庭农场、种粮大户开展试点应用；相关技术被列为金华市农业主推技术，入选全国绿色防控典型案例，具备技术输出与规模化示范实施条件。\n\n**开放合作对象**：高校、科研院所、民企、农事服务中心、专业合作社、规模化种植大户\n\n**合作方式**：采购服务、采购产品、项目建设、联合研发\n\n**场景搭建单位：**金华市农业科学研究院\n\n**联系人及联系方式：**朱 女士，13735656369\n\n**场景****9****：**磐安县尚湖镇低空无人机助老送餐民生示范场景\n\n**场景描述：**立足磐安山区“九山半水半分田”地理特征，践行“科技+养老”发展定位，打造山区低空无人机助老送餐示范场景。针对偏远山村高龄独居、失能老人做饭难、传统山路送餐耗时长、餐食易冷却等痛点，构建“中心供餐-无人机低空配送-村级接力上门”服务体系。依托低空物流技术，定制保温配送装备，规划山区专属飞行航线，优化飞行调度与末端分发流程。后续逐步扩大服务行政村覆盖范围，拓展应急药品、生活物资附带配送能力，打造山区县低空经济赋能养老民生样板，实现山区老年群体助餐服务可及性显著提升。\n\n**建设基础**：已在尚湖镇尚路研村、铜钿村开展无人机助餐试点工作，尚湖镇颐安养老院作为供餐载体，统一完成餐食加工制作。与中科云图开展合作，投入低空物流无人机，配套定制餐食保温箱，完成试点村庄飞行航线规划，布设村级无人机取餐降落点位，建立村级人员接力分发机制。依托磐安县县级低空经济指挥中心、空天地一体化综合应用平台，具备飞行调度、状态监控技术能力。项目已完成启航示范运行，可实现山区跨山配送，试点服务 30 余位山区老人，验证山区低空送餐的实际可行性。\n\n**开放合作对象**：民企、高校、科研院所\n\n**合作方式**：采购产品、采购服务、联合研发、标准共研\n\n**场景搭建单位：**金华智飞互联科技有限公司\n\n**联系人及联系方式：**厉先生，15088281874\n\n**场景****10****：**珍珠数字网络养殖及三产一体化示范场景\n\n**场景描述：**围绕珍珠渔业养殖数字化、文旅体验提质，依托 AIOT 智慧渔业硬件、数字养殖控制系统、云端互动引流平台，打造一体化珍珠产业数智示范场景。以智能化养鱼养蚌车间、全自动水环境监测设备、云端 AI 中控系统为硬件支撑，打通全链条业务，形成集水质智能监测、养殖数据溯源、文创销售于一体的三产融合闭环方案。依托珍珠产业数字知识库与实时监测算法，实现养殖风险智能预警、水产养护精准管控、线上流量持续转化、线下体验高频复访，构建乡村珍珠产业数字化标杆。\n\n**建设基础：**已建成标准化数字智慧养殖车间，搭载 AIOT 设备，实现水体环境 24 小时自动检测、异常数据实时预警、养殖工况远程可控，覆盖珍珠三产全周期智能化；搭建云端智慧互动平台，支持用户云端互动参与，实现线上持续引流蓄客；落地无人智能垂钓系统，实现自助扫码、计时计费、全域监控、无人化运维，降低运营人力成本；线下已成熟运营珍珠数字化养殖体验车间、开蚌盲盒体验、珍珠 DIY、螺钿手作研学，实现业态共创、人才集聚、流量共享。系统已完成养殖数据、客流数据、消费数据、体验数据互联互通，形成产业数据台账与全流程溯源体系。\n\n**开放合作对象：**研发企业、运营企业、平台服务商\n\n**合作方式：**场景共建、技术赋能、流量合作、项目联合运营\n\n**场景搭建单位：**兰溪诸葛厚伦方村、卧龙源水产\n\n**联系人及联系方式：**张先生，15305897301","金华市发改委 2026-09","2026-09-15T01:00:00Z","报道",73,{"impact":17,"substance":65,"depth":66,"authority":13,"freshness":67,"relevant":22,"comment":68},20,16,9,"金华市集中推介六个农业农村领域开放场景，涵盖低空AI农事服务、田间转运机器人、农机检测鉴定等，建设基础与数据指标详实，具备较强产业参考价值。",[70],{"name":60,"url":57},[72,27,73,28,29,74],"数字乡村","低空经济","农机检测",[76,77],"农业人工智能 农业机器人 低空经济 农机检测","农业人工智能 农业机器人","农业人工智能农业机器人低空经济农机检测-2555","2026-09-16T00:03:45.244399Z",{"id":81,"title":82,"url":83,"summary":84,"summary_zh":9,"content":85,"source_name":86,"source_url":9,"published_at":87,"category":62,"cover_url":9,"hotness":13,"is_selected":14,"score":88,"score_detail":89,"sources":93,"tags":95,"search_phrases":98,"slug":100,"view_count":36,"doi":9,"paper":9,"created_at":101},2446,"智能农机装备研发创新与验证推广实务培训班 9-20~9-23 杭州萧山举办","http:\u002F\u002Fwww.amic.agri.cn\u002FsecondLevelPage\u002Finfo\u002F3\u002F224557","农业农村部农业机械化总站发出通知(农机化总站〔2026〕81 号),拟于 2026 年 9 月 20 日至 9 月 23 日在浙江省杭州市萧山区举办'智能农机装备研发创新与验证推广实务培训班'。培训内容涵盖农业人工智能发展专题(农业机器人、智能农机标准体系等)、智能农机关键核心零部件与算法产业化应用(农业芯片、机器视觉、北斗定位导航等)、典型应用场景(大田、畜禽、水产、设施种植)以及实地观摩与农业机器人现场展示。培训对象包括各省农机中心、试验鉴定机构、推广机构、生产企业等。","农机化总站〔2026〕81号\n\n各相关单位：\n\n为贯彻落实中央一号文件精神及农业农村部关于加快农业人工智能发展的系列部署，深入推进人工智能与农机融合发展，着力提升智能农机装备的自主创新水平，发挥典型应用场景的示范引领作用，总站拟于2026年9月20日至9月23日在浙江省杭州市萧山区举办“智能农机装备研发创新与验证推广实务培训班”。现将有关事项通知如下。\n\n一、培训内容\n\n（一）农业人工智能发展专题报告\n\n1、“人工智能+农机”发展现状与趋势\n\n2、农业机器人发展实践与应用\n\n3、智能农机装备标准体系架构\n\n4、智能机器人安全实践对农机装备智能化发展的启示\n\n5、智能网联汽车关键核心技术对智能农机装备的借鉴与启示\n\n（二）智能农机关键核心零部件与算法产业化应用专题报告\n\n1、农业芯片核心技术发展与产业应用现状分析\n\n2、农业传感器在智能农机装备和农业机器人中的实践与应用\n\n3、机器视觉设备与算法在智能农机发展中的应用\n\n4、北斗定位与导航技术在农业精准作业领域中的应用\n\n5、智能农机串行控制和通信数据网络技术要求\n\n（三）智能农机装备在典型应用场景中的实践专题报告\n\n1、大田智能农机通用性关键性技术与装备\n\n2、畜禽养殖智能化技术与装备\n\n3、水产智慧养殖机械化技术与装备\n\n4、设施种植智能化机械装备集成与应用\n\n（四）人工智能与大数据应用场景实地观摩与农业机器人现场展示交流\n\n二、培训对象\n\n各省（自治区、直辖市）农机中心、农机试验鉴定机构、农机化技术推广机构、高等院校、科研院所、行业协会、检测机构、智能农机装备生产制造企业、农业生产经营主体、金融投资机构等相关人员。\n\n三、时间地点\n\n（一）培训时间：9月20日报到，9月21日至9月22日培训，9月23日疏散。\n\n（二）培训地点：杭州市萧山区宝盛宾馆（浙江省杭州市萧山区市心中路618号，联系电话：潘瑶 15906715852，洪燕芳 13588705700）。\n\n四、报名及培训费用\n\n（一）报名方式。请使用微信扫描下方二维码，按要求填写信息后提交。报名截止时间为9月16日。\n\n![Image 1](http:\u002F\u002F202.127.42.160:3009\u002Fupload_file\u002F2026\u002F08\u002F10\u002F20260810101025836.png)\n\n报名二维码\n\n（二）培训费用。培训班收取培训费2000元\u002F人(含培训、教材、培训证书、用餐等费用)，餐饮统一安排，交通费、住宿费（340元\u002F晚）自理，不安排接送站。\n\n（三）缴费方式。培训费采用银行汇款或报到时刷银行卡、支付宝或微信支付，现场不收取现金。银行汇款请务必在备注栏标明“智能农机培训”，并在报到时出示汇款凭证复印件，汇款单位名称与开票单位名称需保持一致，如不一致，还请备注参训人员单位名称、姓名，并开具证明提供发票信息。\n\n收款单位：农业农村部农业机械化总站；\n\n开户银行：中国农业银行股份有限公司北京十里河支行；\n\n银行账号：11220701040017219。\n\n五、其他事项\n\n（一）为统筹农业机器人室外展区布展工作，请有意参展的单位于2026年8月31日（含）前将产品资料（产品图片、实地作业视频、关键技术介绍等）、企业联系人及联系方式发送至邮 箱njznc@agri.gov.cn。我们将对所有报送材料进行择优筛选，并于9月7日（含）前向通过遴选的对象发出布展通知。\n\n（二）请参训学员严格遵守培训纪律，培训期间注意人身和财产安全。\n\n（三）总站将为参训学员颁发培训证书。\n\n（四）培训期间，要严格落实中央八项规定及其实施细则精神，不得安排与培训内容无关的事项，严禁外出参加各种聚会、拜访、宴请等活动，不得饮酒。\n\n（五）联系人：\n\n李 苗 010-59199179，18753469583；\n\n赵泽明 010-59199016，15201628716。\n\n附件：乘车路线\n\n农业农村部农业机械化总站\n\n2026年8月6日\n\n附件\n\n乘车路线\n\n一、杭州萧山国际机场。酒店距萧山国际机场约22公里。\n\n1.打车\u002F网约车，30—40分钟，费用：预估30—45元；\n\n2.地铁，“萧山国际机场”乘地铁7号线“吴山广场”方向至“建设三路”，同站转2号线“朝阳”方向至“人民广场”D口出站，往南步行约10分钟。\n\n二、杭州东站。酒店距杭州东站约16公里。\n\n1.打车\u002F网约车，30—40分钟，费用：预估25—35元；\n\n2.地铁，“火车东站”乘地铁4号线“浦沿”方向至“钱江路”，同站转2号线“朝阳”方向至“人民广场”D口出站，往南步行约10分钟。\n\n三、杭州站。酒店距杭州站约15公里。\n\n1.打车\u002F网约车，30—40分钟，费用：预估35—50元；\n\n2.地铁，“城站”乘地铁5号线“姑娘桥”方向至“人民广场”D口出站，往南步行约10分钟。\n\n四、杭州南站。酒店距杭州南站约5公里。\n\n1.打车\u002F网约车，15—25分钟，费用：预估20—30元；\n\n2.地铁，“火车南站”乘地铁5号线“南湖东”方向至“人民广场”D口出站，往南步行约10分钟。\n\n五、杭州西站。酒店距杭州南站约40公里。\n\n1.打车\u002F网约车，80—90分钟，费用：预估100—160元；\n\n2.地铁，“火车西站”乘地铁19号线“永盛路”方向至“沈塘桥”，同站转2号线“朝阳”方向至“人民广场”D口出站，往南步行约10分钟。","中国农业机械化信息网 2026-09-15","2026-09-14T16:00:00Z",68,{"impact":17,"substance":66,"depth":90,"authority":91,"freshness":21,"relevant":22,"comment":92},12,14,"农业农村部农机化总站主办的全国性智能农机培训通知，课程覆盖农业AI、农业芯片、传感器、北斗导航与典型场景，具备行业指导价值，但属会议培训类事务性通知，信息增量有限。",[94],{"name":86,"url":83},[27,28,29,96,97],"智能农机","农机培训",[99,77],"农业人工智能 农业机器人 农机培训 智慧农业","农业人工智能农业机器人农机培训智慧农业-2446","2026-09-15T00:04:20.009285Z",{"id":103,"title":104,"url":105,"summary":106,"summary_zh":107,"content":9,"source_name":108,"source_url":105,"published_at":109,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":110,"score_detail":111,"sources":113,"tags":115,"search_phrases":118,"slug":121,"view_count":36,"doi":122,"paper":123,"created_at":152},2285,"PetalSpot: an open-source two-stage deep-learning workflow for pixel-level quantification of petal lesions","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112421","PetalSpot: an open-source two-stage deep-learning workflow for pixel-level quantification of petal lesions。Computers and Electronics in Agriculture","PetalSpot：一种用于花瓣病斑像素级量化的开源两阶段深度学习工作流程。","Computers and Electronics in Agriculture","2026-09-11T00:00:00Z",75,{"impact":66,"substance":65,"depth":19,"authority":91,"freshness":21,"relevant":22,"comment":112},"开源两阶段深度学习流程实现花瓣病斑像素级量化，方法新颖且可复用，对花卉病害智能监测有参考价值。",[114],{"name":108,"url":105},[27,28,116,117,30],"花卉产业","开源工具",[119,120],"农业人工智能 植物病害检测 开源工具 智慧农业","农业人工智能 植物病害检测","农业人工智能植物病害检测开源工具智慧农业-2285","10.1016\u002Fj.compag.2026.112421",{"doi":122,"openalex_id":124,"authors":125,"venue":108,"cited_by_count":36,"oa_url":9,"card":146,"direction":150,"ingested_from":49},"W7212311236",[126,128,130,132,134,136,138,141,143],{"name":127,"orcid":9},"Yao Huang",{"name":129,"orcid":9},"Xiaoqian Cao",{"name":131,"orcid":9},"Fangqi Liu",{"name":133,"orcid":9},"Hong Sha",{"name":135,"orcid":9},"Phurisorn Watcharatpong",{"name":137,"orcid":9},"Ruoheng Jian",{"name":139,"orcid":140},"Wen Chen","https:\u002F\u002Forcid.org\u002F0000-0001-8493-0157",{"name":142,"orcid":9},"Yiqian Fu",{"name":144,"orcid":145},"Zhao Zhang","https:\u002F\u002Forcid.org\u002F0000-0002-7323-5500",{"tldr":147,"method":148,"finding":149,"direction":150,"opportunity":151},"提出开源两阶段深度学习流程PetalSpot，实现花瓣病斑像素级量化。","两阶段深度学习工作流，开源代码，用于花瓣病斑分割与量化。","该流程能对花瓣病斑进行像素级精确量化，且开源可复现。","农业人工智能与决策模型","可迁移至其他作物器官病斑量化，并融合多模态数据提升泛化性。","2026-09-13T23:30:02.086637Z",{"id":154,"title":155,"url":156,"summary":157,"summary_zh":158,"content":9,"source_name":159,"source_url":156,"published_at":160,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":161,"score_detail":162,"sources":165,"tags":167,"search_phrases":169,"slug":171,"view_count":36,"doi":172,"paper":173,"created_at":185},2050,"The use of artificial intelligence in agriculture: Global practice","https:\u002F\u002Fdoi.org\u002F10.26794\u002F3030-7097-2026-2-3-16-25","This article is devoted to the analysis of current trends and practices of the application of artificial intelligence (AI) in agriculture based on peer-reviewed scientific sources of 2022–2026. The purpose of the work is a comprehensive study of the problems and key trends of the development of AI in the agricultural sector, as well as the systematization of quantitative data confirming the effectiveness of the implemented technologies. The article discusses the main areas of AI use: crop yield forecasting based on neural network algorithms (LSTM, CNN), plant health monitoring and precise resource application using computer vision (ResNet, YOLO), robotization of production processes, and the introduction of intelligent systems into the economy and management of the agro-industrial complex. Based on the analysis of empirical studies, the article systematizes performance indicators: the accuracy of plant disease diagnosis reaches 99.2%, the reduction of pesticide use is up to 90%, water resources are saved by up to 46%, and farm income increases by 15–20%. Special attention is paid to a comparative analysis of the barriers to the implementation of AI in different groups of countries. In developed countries, the main problems are technological fragmentation and a shortage of qualified personnel. In BRICS countries, there are infrastructure limitations and a gap between science and production. In developing countries, the key obstacles are the lack of basic infrastructure, the low solvency of small farms, and a lack of digital literacy. The final part identifies understudied aspects that require further research, such as socio-psychological barriers to technology adoption, the environmental impact of AI solutions, issues related to data sovereignty and monetization, economic efficiency for small-scale farmers, cybersecurity, and ethical dilemmas in breeding.","本文基于2022—2026年经同行评审的科学文献，分析人工智能（AI）在农业中应用的当前趋势与实践。研究目的是全面探讨AI在农业领域发展中的问题与主要趋势，并系统整理证实所实施技术有效性的定量数据。文章讨论了AI应用的主要方向：基于神经网络算法（LSTM、CNN）的作物产量预测，利用计算机视觉（ResNet、YOLO）进行植物健康监测与精准资源施用，生产过程的机器人化，以及智能系统在农工综合体的经济与管理中的引入。基于对实证研究的分析，文章系统整理了绩效指标：植物病害诊断准确率高达99.2%，农药使用量减少达90%，水资源节约达46%，农场收入增加15—20%。文章特别关注对不同国家组别中AI实施障碍的比较分析。在发达国家，主要问题是技术碎片化和合格人员短缺。在金砖国家，存在基础设施限制以及科学与生产之间的脱节。在发展中国家，关键障碍是缺乏基础基础设施、小农场支付能力低以及数字素养不足。最后一部分指出了需要进一步研究的薄弱环节，如技术采用的社会心理障碍、AI解决方案的环境影响、数据主权与货币化相关问题、小规模农户的经济效率、网络安全以及育种中的伦理困境。","Digital Solutions and Artificial Intelligence Technologies","2026-09-07T00:00:00Z",80,{"impact":163,"substance":163,"depth":17,"authority":90,"freshness":52,"relevant":22,"comment":164},22,"基于2022—2026年同行评审文献系统梳理AI在农业的应用成效与国别障碍，数据翔实、结论可靠，对智慧农业研究与政策制定有较高参考价值。",[166],{"name":159,"url":156},[72,27,28,29,168],"精准农业",[170,77],"农业人工智能 农业机器人 数字乡村 智慧农业","农业人工智能农业机器人数字乡村智慧农业-2050","10.26794\u002F3030-7097-2026-2-3-16-25",{"doi":172,"openalex_id":174,"authors":175,"venue":159,"cited_by_count":36,"oa_url":179,"card":180,"direction":47,"ingested_from":49},"W7211943654",[176],{"name":177,"orcid":178},"Albina Kh. Shelepaeva","https:\u002F\u002Forcid.org\u002F0000-0002-4678-9671","https:\u002F\u002Fwww.digitarin.ru\u002Fjour\u002Farticle\u002Fdownload\u002F71\u002F52",{"tldr":181,"method":182,"finding":183,"direction":150,"opportunity":184},"综述2022-2026年AI在农业的应用趋势、成效与各国推广障碍。","基于同行评议文献综述，分析LSTM、CNN、ResNet、YOLO等AI技术应用","AI使病害诊断准确率达99.2%，农药减90%、节水46%、收入增15-20%，但各国障碍不同。","可研究小农户AI采纳的社会心理障碍、数据主权与AI环境影响的量化评估。","2026-09-10T23:30:16.002269Z",{"id":187,"title":188,"url":189,"summary":190,"summary_zh":9,"content":191,"source_name":192,"source_url":9,"published_at":193,"category":62,"cover_url":9,"hotness":13,"is_selected":14,"score":194,"score_detail":195,"sources":199,"tags":201,"search_phrases":203,"slug":205,"view_count":36,"doi":9,"paper":9,"created_at":206},1706,"AI, Drones, Robots Reshape Farming in Heilongjiang, China's Grain Heartland（CGTN 9-3 报道）","https:\u002F\u002Fnews.cgtn.com\u002Fnews\u002F2026-09-03\u002FAI-drones-robots-reshape-farming-in-China-s-grain-heartland-1Q8bEeCDD7a\u002Fp.html","CGTN 报道黑龙江农业数字化转型。在北大荒信息公司，一面墙大小的数字地图追踪约 320 万公顷农田的状况。土壤条件、作物生长和拖拉机运动数据在屏幕上更新。黑龙江省耕种收综合机械化率达 99.28%，已连续 16 年粮食总产量位居全国第一。激光除草机器人在田间作业可清除 95% 以上的杂草，作物损伤低于 0.1%；电动驱动精量播种机比传统机械式播种机减少种子损伤、作业速度快约 50%。\"十五五\"期间黑龙江将发展农业机器人和智能农业装备产业。","Inside Beidahuang Information Company in Harbin, capital of northeast China's Heilongjiang Province, a wall-sized digital map tracks conditions across some 3.2 million hectares of farmland.\n\nData on soil conditions, crop growth and tractor movements update across the screen, while satellite remote sensing, the Internet of Things and AI are being integrated into different stages of farming.\n\nIt is one example of how agriculture is changing in Heilongjiang, China's top grain-producing province.\n\nHeilongjiang has ranked first in the country in total grain output for 16 consecutive years. The comprehensive mechanization rate for plowing, sowing and harvesting has reached 99.28%.\n\nNow, AI, drones, remote sensing and smarter machinery are pushing that highly mechanized system into a more digital phase.\n\n![Image 1: A worker assembles agricultural machinery at Heilongjiang Dewo Technology Development Co., Ltd. in Harbin, Heilongjiang Province, China, September 1, 2026. \u002FVCG](https:\u002F\u002Fnews.cgtn.com\u002Fnews\u002F2026-09-03\u002FAI-drones-robots-reshape-farming-in-China-s-grain-heartland-1Q8bEeCDD7a\u002Fimg\u002F42432a4bc73b42df9e400419652e7664\u002F42432a4bc73b42df9e400419652e7664.jpeg)\n\nA worker assembles agricultural machinery at Heilongjiang Dewo Technology Development Co., Ltd. in Harbin, Heilongjiang Province, China, September 1, 2026. \u002FVCG\n\nA worker assembles agricultural machinery at Heilongjiang Dewo Technology Development Co., Ltd. in Harbin, Heilongjiang Province, China, September 1, 2026. \u002FVCG\n\nFarming by data\n\nWang Hao, deputy general manager of Beidahuang Information Company's market operation center, said a farmer inspecting crops on foot could previously cover only about 200 mu, or roughly 13 hectares, a day.\n\nDrones and remote sensing can now monitor much larger areas and allow crop data across the monitored farmland to be updated every five days, he said.\n\nThe company's AI model for cold-region crops analyzes soil, weather and crop-growth data to generate planting plans and recommendations for variable-rate fertilization, which allows fertilizer use to be adjusted according to conditions in different parts of a field.\n\nBut scaling up agricultural AI remains challenging.\n\nWang said AI models require large amounts of local data and repeated testing because soil, weather and other environmental conditions can vary significantly from place to place.\n\nDigital technology is also being used farther along the production chain.\n\nIn Wuchang, a major rice-producing area in Harbin, robots at Qiaofu Dayuan Agricultural Co., Ltd. stack packaged rice for shipment. QR codes on the products provide information including where the rice was produced and its nutritional content.\n\nSmarter machines\n\nOther technologies are changing the machinery working directly on farmland.\n\nAt a planting base in Heilongjiang, a four-wheel laser-weeding robot moves between crop rows. Multispectral cameras and sensors scan the ground, while algorithms distinguish crops from weeds and direct laser beams at the unwanted plants.\n\nThe system offers a chemical-free alternative to herbicides while reducing reliance on manual weeding.\n\nLi Yongwei, deputy general manager of Harbin Huagong Zhiyun Technology Co., Ltd., said the technology can remove more than 95% of weeds while keeping crop damage below 0.1%. He said it can also cut weeding costs by up to 70% compared with manual labor.\n\nSeeders are becoming more intelligent as well.\n\nElectric-drive precision seeders produced by Heilongjiang Dewo Technology Development Co., Ltd. allow operators to monitor and adjust air pressure and seed spacing in real time through smart terminals.\n\nDu Mujun, the company's chief engineer, said the system can reduce seed damage and operate about 50% faster than conventional mechanical seeders.\n\n![Image 2: The 25th Heilongjiang Agricultural Machinery Exhibition opens in Harbin, Heilongjiang Province, China, March 14, 2026. \u002FVCG](https:\u002F\u002Fnews.cgtn.com\u002Fnews\u002F2026-09-03\u002FAI-drones-robots-reshape-farming-in-China-s-grain-heartland-1Q8bEeCDD7a\u002Fimg\u002F87095d0d3fda456b868a8a85cb0c2682\u002F87095d0d3fda456b868a8a85cb0c2682.jpeg)\n\nThe 25th Heilongjiang Agricultural Machinery Exhibition opens in Harbin, Heilongjiang Province, China, March 14, 2026. \u002FVCG\n\nThe 25th Heilongjiang Agricultural Machinery Exhibition opens in Harbin, Heilongjiang Province, China, March 14, 2026. \u002FVCG\n\nBeyond mechanization\n\nHeilongjiang produced a record 82 million tonnes of grain in 2025, marking its 22nd consecutive bumper harvest. The province also had 676,000 intelligent agricultural machines that year, ranking first nationwide.\n\nDuring the 15th Five-Year Plan period from 2026 to 2030, Heilongjiang plans to develop industries including agricultural robots and intelligent farming equipment.\n\nConstruction began in August on a national pilot base for AI applications in crop planting, aimed at tackling common technical bottlenecks and developing technologies that can be deployed on a larger scale.\n\nThe shift is part of China's broader push for agricultural modernization. National plans call for wider use of technologies including drones, the Internet of Things and robots in agriculture and rural areas.\n\nFor Heilongjiang, where mechanization of plowing, sowing and harvesting is already above 99%, the focus is increasingly shifting from simply mechanizing farm work to making equipment and agricultural decisions more intelligent.\n\nHu Jinyou, a professor at China Agricultural University, said smart agriculture is still being refined, but deeper integration between AI and agriculture is an \"irreversible trend.\"\n\nAs a new generation of better-educated farmers enters the sector, digital management is likely to become increasingly common, he added.\n\n(With input from Xinhua)","CGTN","2026-09-03T00:00:00Z",81,{"impact":196,"substance":65,"depth":66,"authority":20,"freshness":197,"relevant":22,"comment":198},25,7,"报道黑龙江智慧农业综合进展，含AI、激光除草等具体案例，具产业参考价值。",[200],{"name":192,"url":189},[27,28,29,202,168],"黑龙江",[204,77],"农业人工智能 农业机器人 智慧农业 精准农业","农业人工智能农业机器人智慧农业精准农业-1706","2026-09-05T00:04:40.911477Z",{"id":208,"title":209,"url":210,"summary":211,"summary_zh":212,"content":9,"source_name":108,"source_url":210,"published_at":213,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":214,"score_detail":215,"sources":218,"tags":220,"search_phrases":222,"slug":225,"view_count":36,"doi":226,"paper":227,"created_at":246},1279,"Scene-graph-grounded vision–language reasoning to action for autonomous multipurpose agricultural robots","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112347","Scene-graph-grounded vision–language reasoning to action for autonomous multipurpose agricultural robots。Computers and Electronics in Agriculture","面向自主多用途农业机器人的场景图接地视觉-语言推理到行动。计算机与电子在农业中的应用","2026-08-31T00:00:00Z",76,{"impact":65,"substance":163,"depth":17,"authority":91,"freshness":216,"relevant":22,"comment":217},2,"论文提出基于场景图的视觉-语言推理方法，提升农业机器人自主作业能力，方法新颖，数据详实，但发表于2026年8月，时效性较低。",[219],{"name":108,"url":210},[27,28,29,221],"视觉语言模型",[223,224],"农业人工智能 视觉语言模型 农业机器人 智慧农业","农业人工智能 视觉语言模型","农业人工智能视觉语言模型农业机器人智慧农业-1279","10.1016\u002Fj.compag.2026.112347",{"doi":226,"openalex_id":228,"authors":229,"venue":108,"cited_by_count":36,"oa_url":9,"card":241,"direction":150,"ingested_from":49},"W7204843057",[230,233,235,238],{"name":231,"orcid":232},"Yonghyun Park","https:\u002F\u002Forcid.org\u002F0000-0001-6085-5957",{"name":234,"orcid":9},"Changjo Kim",{"name":236,"orcid":237},"Gangmin Kim","https:\u002F\u002Forcid.org\u002F0009-0007-3565-4900",{"name":239,"orcid":240},"Hyoung Il Son","https:\u002F\u002Forcid.org\u002F0000-0002-7249-907X",{"tldr":242,"method":243,"finding":244,"direction":150,"opportunity":245},"提出场景图增强的视觉-语言-行动模型，用于自主多功能农业机器人。","利用场景图、视觉-语言模型和推理到行动机制。","场景图提升农业机器人对复杂场景的理解和任务执行能力。","可探索场景图在农业机器人多任务协同、动态环境适应及人机交互中的进一步应用。","2026-09-01T23:30:01.788088Z"]