[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-665":3,"related-665":88},{"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":30,"secondary_topics":36,"classification":43,"search_phrases":82,"slug":85,"view_count":86,"doi":8,"paper":8,"created_at":87},665,"黑龙江天工开悟农业大模型推广至全省114个农场 克豆91高蛋白大豆以3155万元转让","https:\u002F\u002Fwww.hljapp.com\u002Fcontent\u002Fdetail\u002F3928","黑龙江省新质生产力科技成果展在哈尔滨工业大学先进技术研究院开展,71项科创成果集中亮相。哈尔滨华工智耘科技激光除草机器人在黑龙江大豆、玉米、白菜等作物种植基地开展多场景验证,累计应用面积超1000亩,杂草净除率超95%,伤苗率小于0.1%。天工开悟农业大模型将选种、施肥、田间管理、收获等环节纳入数据分析,已推广至全省114个农场。黑龙江省农业科学院克山分院董全中团队历时10年选育的高蛋白大豆新品种克豆91,2025年生产经营权以3155万元转让,刷新国内大豆单品种单次市场化交易纪录。",null,"育秧巡检机器人穿行苗床，“悟空号”无人无缆潜水器探向万米深海，新型材料、数字技术等创新成果依次呈现……近日，黑龙江省新质生产力科技成果展在哈尔滨工业大学先进技术研究院开展，来自全省高校院所、重点企业的71项科创成果集中亮相，一件件“龙江智造”勾勒出科技创新加快转化为现实生产力的清晰轨迹。\n\n 从实验室走向生产线，从技术突破迈向产业应用，在这片黑土地上，创新之“进”，正不断拓展发展之“新”。\n\n 在新时代东北全面振兴的新征程上，黑龙江持续推动科技创新和产业创新深度融合，加快把创新“关键变量”转化为振兴发展“最大增量”。\n\n**向纵深处“进”：传统优势焕发新机**\n\n 夏管时节，黑土地绿意正浓。在黑龙江一处速冻青刀豆种植基地里，四轮激光除草机器人沿垄缓缓前行，多光谱相机和深度传感器持续扫描，算法迅速分辨作物与杂草，激光束随即精准击中杂草生长点。\n\n “过去除草主要靠人工和化学药剂，要么成本高，要么影响作物和土壤。”哈尔滨华工智耘科技有限公司副总经理李涌伟说，激光除草是纯绿色物理除草方式，杂草净除率超过95%，伤苗率小于0.1%，每小时最高可毁伤上百万棵杂草，成本较人工除草最高可下降70%。田间试验显示，激光除草可减少杂草对作物养分争夺，实现作物增产。\n\n 看得准、打得准，一束光成为除草的新工具。目前，该装备已在黑龙江省内大豆、玉米、白菜等作物种植基地开展多场景验证，累计应用面积超过1000亩。核心激光光源、人工智能视觉算法和植物识别模型均由团队自主研发，国产高端激光除草装备正从田间试验走向规模化应用。\n\n 田垄之外，农业大模型正在覆盖更广阔的农场。“天工开悟”农业大模型将选种、施肥、田间管理、收获等环节纳入数据分析，已推广至全省114个农场。气象、土壤、作物长势等信息汇聚起来，让过去更多依靠经验作出的农事判断，开始有了更精准的数据支撑。\n\n 田间管理向“智”而行，种源创新则关乎农业的长远竞争力。黑龙江省农业科学院克山分院董全中团队历时10年选育的高蛋白大豆新品种“克豆91”，2025年生产经营权以3155万元转让，刷新国内大豆单品种单次市场化交易纪录。一个新品种由实验室走向市场，也让科研成果的价值有了可以丈量的产业尺度。\n\n “一台装备改变一种作业方式，一个模型连接多个生产环节，农业科技，就是要让种子更优良，让农事更精准，让粮食更优质。”黑龙江省科学技术厅科技二处处长杨雪说。科技创新加快嵌入耕、种、管、收农业生产全过程，为大面积单产提升注入动力，让“中国饭碗”装进更多优质龙江粮。\n\n 田野之外，科技创新也在重新擦亮龙江制造的招牌。在中国一重生产车间，3000吨级加氢反应器等重大装备接续突破；在哈电集团，超超临界循环流化床锅炉、大型水电机组等不断刷新技术指标。\n\n 曾经以“块头大、分量重”闻名的龙江制造，正把新材料、数字技术和智能制造加快融入设计、加工、检测等环节，推动大国重器向更高端、更智能、更绿色迈进。\n\n 把传统优势转化为发展胜势，新质生产力加快向产业纵深渗透，新技术、新要素正让厚实的龙江家底焕发新的生机。\n\n**向前沿处“进”：新兴赛道塑造新动能**\n\n “老树发新枝”，也要让“新苗长成大树”。当前，黑龙江着眼科技变革和产业演进趋势，以优势资源切入细分赛道，以技术突破牵引产业集聚，新的增长点正由单点萌发走向链式生长。\n\n 向高处攀登，商业航天加速起势。\n\n 走进哈尔滨新区工大卫星智造基地，洁净厂房内，卫星总装、测试和环境试验有序衔接。\n\n 哈尔滨工大卫星技术有限公司成立于2020年。短短数年，企业已完成14次发射任务，将37颗卫星送入太空，涵盖通信、导航、遥感、深空探测等领域，如今，其研发试验总部基地具备年产180颗500公斤量级卫星的能力。\n\n “柔性制造不是把单星研制简单复制，而是通过标准化模块、数字化工艺和流程再造，提高卫星批量生产和稳定交付能力，为低轨星座快速组网提供支撑。”工大卫星总经理助理王群说。\n\n 卫星制造从单星定制走向柔性化、批量化、数字化，带来的不只是产能提升，也在牵动更长的产业链。标准化模块提高生产效率，数字化工艺贯通研制流程，稳定的批量需求则牵引载荷研制、关键零部件、测运控和数据应用等环节加快集聚。以工大卫星为“链主”，黑龙江商业航天产业正由一颗星、一个企业，向一条链、一个产业集群延伸。\n\n 向寒处探索，“冷资源”催生新产业。\n\n 今年2月，在哈尔滨冰雪大世界科技赋能冰雪实验区，一台智能大型冰雕自动化搭建机器人进入测试阶段。自动上料、精准提升、抓取定位、喷淋黏合，重达1吨的冰块被逐层垒起，以毫米级精度完成砌筑。投入应用后，机器人可承担部分高空作业，降低极寒环境下的施工风险。\n\n 与它协同工作的，还有江面采冰、冰块切割、开槽、雕刻和表面打磨等系列装备，过去主要依靠人工和传统机械完成的冰建流程，开始有了成套智能装备的参与，向全流程智能化、标准化迈进。\n\n “冰雪大世界和松花江采冰场就是我们的试验场，低温导航、视觉识别、精密控制等技术攻关在真实环境中反复接受检验、不断迭代。”哈尔滨冰科智能装备有限公司董事长姜文锐说。\n\n 从冰雪消费到冰雪制造，黑龙江漫长的冬季正在释放新的产业价值。文旅端涌动的热度随之向研发制造端传导，“冷资源”不再只是季节性消费场景，也成为新技术、新产品的孵化场。\n\n 向微处进发，机器人技术进入更加精细的产业场景。\n\n 在哈尔滨灵博机器人有限公司的“创造车间”里，几款灵巧手原型机正在反复调试，抓取、提拉、调整姿态，一系列动作流畅完成。\n\n “我们在这样小的空间里集成了15个主动自由度和多类传感器。”哈尔滨灵博机器人有限公司总经理祁乐说，不仅要“抓得住”，还要能够感知接触力度，在与不同物体交互时实时调整动作。\n\n 灵巧背后，是多年技术积累。灵博团队来自哈工大机器人技术与系统全国重点实验室空间机器人团队。面向具身智能兴起的新赛道，曾经服务航天重大工程的灵巧操作、力感知和控制技术，开始进入人形机器人、工业制造等应用场景，打开了一片新的产业空间。\n\n 科教资源孕育技术源头，工业积淀支撑工程转化，特色场景推动产品迭代。黑龙江正在新的产业坐标中重新发现自身优势，并将其转化为新产业、新企业和新动能。\n\n**向产业处“进”：创新成果跑出加速度**\n\n “十五五”规划纲要提出，推动科技创新和产业创新深度融合。对科研资源富集的黑龙江而言，能否让更多成果走出实验室、进入生产线、汇入产业链，是科技优势转化为振兴动能的关键一跃。\n\n 近年来，黑龙江国家级科技创新平台基地由46家增至69家，其中，全国重点实验室由7家增至16家。机器人技术与系统、陆相页岩油等高水平平台相继布局，为基础研究、关键技术攻关和产业升级注入源头活水。\n\n 科技成果从“最初一公里”走到“最后一公里”，是一场基础研究、技术攻关、中试熟化、企业孵化和场景应用的接力。\n\n 针对一些实验室成果“不成熟”、企业“接不住”等难题，黑龙江布局31家概念验证中心，研判技术可行性和市场潜力，帮助成果找准转化方向；建设99家中试熟化平台，着力破解工艺放大、稳定生产和成本控制等工程化难题。目前，相关平台已推动255个项目开展中试熟化，其中135个实现产业化。\n\n 黑龙江推动企业从成果承接者更多走向创新组织者，生产一线出题、高校院所协同解题、市场检验答卷的路径日益清晰。“十四五”期间，全省攻克重点领域关键技术719项，企业牵头项目资金比例由61%提高到71%。\n\n 让企业挑起创新大梁，还需要科研、人才、资本和场景等要素协同支撑。黑龙江围绕大学、大院、大所建设7个创新创业生态圈，集聚科技型企业2512家，推动科研团队、孵化平台、产业资本和应用场景加快对接。实验室里的技术和样机，由此加快完成工程化验证、产品化打磨和市场化检验，进而转化为产品、孵化出企业、带动起产业。\n\n 制度改革也在为成果转化松绑。职务科技成果单列管理、转化类人才职称评价、尽职免责等改革陆续推进，逐步化解科研人员“不敢转、不愿转”的顾虑。2023年以来，黑龙江省累计转化重大科技成果1873项，新增经济效益348.43亿元，成果转化逐步走向有组织、全链条推进。\n\n 创新链上的一棒接着一棒跑，一个个科技创新“点”由此连成产业发展“线”。黑龙江省科学技术厅科技规划处处长孙启华表示，“十五五”期间，黑龙江将做强有组织科研和有组织转化，围绕产业需求优供给，聚焦成果转化提效能，整合创新资源强企业，培育壮大创新人才队伍，加快以科技创新引领产业全面振兴。\n\n 以创新之“进”，促产业之“新”、动能之“新”、发展之“新”。黑土地上，传统产业因科技赋能焕发新机，新兴产业在创新积累中加快起势，更多科技成果从实验室走向生产线、转化为产业竞争力，振兴发展的科技底色愈加鲜明。\n\n（备注：青蛙工业云平台是哈尔滨本地的一家工业互联网平台，致力于助力黑龙江省各地工业企业完成数字化转型，为推动新质生产力的迅猛发展、实现网络协同制造贡献力量，进而帮助企业降本增效，达成共赢局面。\n\n青蛙工业云平台严格把控数字转型方案的质量，结合哈尔滨在数字化转型城市建设、数字化车间打造、软件定制、互联网工业发展、标识解析方案以及数字化转型咨询诊断等方面的产业政策，为黑龙江工业企业的数字化转型升级探索新路径，提供能够快速有效提升产量与增量的解决方案，助力哈尔滨工厂实现转型，推动黑龙江工业振兴。）","黑龙江日报客户端 2026-08-17","2026-08-17T00:00:00Z","报道",10,false,75,{"impact":17,"substance":18,"depth":19,"authority":13,"freshness":20,"relevant":21,"comment":22},22,18,16,9,1,"报道黑龙江农业科技与产业创新融合，涵盖农业大模型、高蛋白大豆转让等亮点，省级官媒，内容详实，但部分内容偏向综合展示。",[24],{"name":10,"url":6},[26,27,28,29],"黑龙江省农科院","激光除草","天工开悟","克豆91",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},"A4","soybean-oilseeds","大豆与油料","\u002Ftopic\u002Ffield-crops\u002Fsoybean-oilseeds","A",[37],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":44,"locked":14,"version":45,"method":46,"evidence":47},"classified","2026-10-22.2","rules",{"candidates":48,"agricultural_evidence":51},[49,56,62,69,76],{"code":31,"score":50,"supported":51,"title":52,"abstract":54,"tags":55},12,true,[53],"大豆",[53],[29],{"code":38,"score":57,"supported":51,"title":58,"abstract":60,"tags":61},11,[59],"大模型",[59],[],{"code":63,"score":64,"supported":51,"title":65,"abstract":66,"tags":68},"F4",4,[],[67],"除草",[27],{"code":70,"score":71,"supported":51,"title":72,"abstract":73,"tags":75},"A3",3,[],[74],"玉米",[],{"code":77,"score":71,"supported":51,"title":78,"abstract":79,"tags":81},"F3",[],[80],"施肥",[],[83,84],"黑龙江省农科院 天工开悟 激光除草 克豆91","黑龙江省农科院 天工开悟","黑龙江省农科院天工开悟激光除草克豆91-665",2,"2026-08-17T23:54:54.777166Z",{"total":89,"page":21,"page_size":89,"items":90},6,[91,174,255,316,400,448],{"id":92,"title":93,"url":94,"summary":95,"summary_zh":96,"content":8,"source_name":97,"source_url":94,"published_at":98,"category":99,"cover_url":8,"hotness":13,"is_selected":14,"score":100,"score_detail":101,"sources":106,"tags":108,"primary_topic":114,"secondary_topics":115,"classification":117,"search_phrases":137,"slug":140,"view_count":86,"doi":141,"paper":142,"created_at":173},3986,"YOLOv8-MST: a lightweight and efficient real-time detection and counting deep learning algorithm for double-grain peanut seeding","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112481","YOLOv8-MST: a lightweight and efficient real-time detection and counting deep learning algorithm for double-grain peanut seeding。Computers and Electronics in Agriculture","YOLOv8-MST：一种用于双粒花生播种的轻量高效实时检测与计数深度学习算法。《计算机与电子农业》","Computers and Electronics in Agriculture","2026-10-01T00:00:00Z","论文",72,{"impact":50,"substance":102,"depth":103,"authority":104,"freshness":20,"relevant":21,"comment":105},20,17,14,"核心期刊发表的轻量化实时检测计数算法，对花生精量播种智能化有实用价值，但属细分技术进展，影响面有限。",[107],{"name":97,"url":94},[109,110,111,112,113],"智慧农业","农业人工智能","目标检测","精准农业","花生播种",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[116],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"status":44,"locked":14,"version":45,"method":46,"evidence":118},{"candidates":119,"agricultural_evidence":51},[120,126,132],{"code":38,"score":19,"supported":51,"title":121,"abstract":123,"tags":125},[122],"deep learning",[124,122],"深度学习",[110,111],{"code":31,"score":104,"supported":51,"title":127,"abstract":129,"tags":131},[128],"peanut",[130,128],"花生",[],{"code":133,"score":86,"supported":14,"title":134,"abstract":135,"tags":136},"I1",[],[],[109,112],[138,139],"YOLOv8-MST 花生播种","双粒花生 实时检测计数","YOLOv8-MST花生播种-3986","10.1016\u002Fj.compag.2026.112481",{"doi":141,"openalex_id":143,"authors":144,"venue":97,"cited_by_count":165,"oa_url":8,"card":166,"direction":170,"ingested_from":172},"W7215133023",[145,148,150,152,154,156,158,160,163],{"name":146,"orcid":147},"Baogang Li","https:\u002F\u002Forcid.org\u002F0000-0002-3430-7508",{"name":149,"orcid":8},"Enxi Liu",{"name":151,"orcid":8},"Yijia Chen",{"name":153,"orcid":8},"Zhipeng Feng",{"name":155,"orcid":8},"Yuhuan Li",{"name":157,"orcid":8},"Zunmin Liu",{"name":159,"orcid":8},"Jingchun Tang",{"name":161,"orcid":162},"Jiang Liu","https:\u002F\u002Forcid.org\u002F0000-0001-6746-9987",{"name":164,"orcid":8},"Fazhan Yang",0,{"tldr":167,"method":168,"finding":169,"direction":170,"opportunity":171},"提出YOLOv8-MST轻量算法，实现双粒花生播种实时检测与计数。","基于YOLOv8改进的轻量深度学习模型，用于花生播种图像检测计数。","YOLOv8-MST在保持高精度的同时实现轻量化实时检测与计数。","农业人工智能与决策模型","可探索轻量模型在多种作物播种质量实时监测中的泛化与边缘部署。","openalex","2026-10-02T23:30:03.835851Z",{"id":175,"title":176,"url":177,"summary":178,"summary_zh":179,"content":8,"source_name":180,"source_url":177,"published_at":181,"category":99,"cover_url":8,"hotness":13,"is_selected":14,"score":182,"score_detail":183,"sources":186,"tags":188,"primary_topic":192,"secondary_topics":193,"classification":195,"search_phrases":220,"slug":223,"view_count":71,"doi":224,"paper":225,"created_at":254},3485,"Detection of Red Crown Rot of Soybean in Illinois Fields Using High-Resolution Satellite Imagery and Machine Learning","https:\u002F\u002Fdoi.org\u002F10.64898\u002F2026.09.22.753594","Red crown rot (RCR), caused by Calonectria ilicicola, is an emerging soybean disease in the U.S. Midwest for which scalable approaches to characterize within-field disease distribution are lacking. This study evaluated high-resolution PlanetScope satellite imagery for mapping RCR-affected soybean canopies across 15 commercial fields in Illinois surveyed during the 2024 and 2025 growing seasons. A total of 2,921 georeferenced canopy plots were classified as asymptomatic or RCR-affected and paired with six multispectral bands and seven vegetation indices. Spectral differences between classes were evaluated using linear mixed-effects models, and seven machine-learning classifiers representing linear, tree-based, neural-network, kernel, and probabilistic approaches were compared using spatially independent leave-one-field-out cross-validation. RCR-affected canopies exhibited increased reflectance in the visible and red-edge regions, reduced near-infrared reflectance, and lower vegetation-index values relative to asymptomatic canopies. All classifiers showed strong discrimination, with ROC-AUC values ranging from 0.963 to 0.982. Regularized logistic regression achieved the highest overall performance, with an accuracy of 0.945, balanced accuracy of 0.945, F1-score of 0.948, and ROC-AUC of 0.982 at the optimized decision threshold. Permutation analysis identified EVI, NDVI, and red reflectance as the most influential predictors across representative model architectures. Satellite-derived probability and classification maps generally corresponded with symptomatic canopy patterns observed in high-resolution UAV imagery, although mixed pixels reduced precision near disease-patch boundaries. These results demonstrate the potential of high-resolution satellite imagery for within-field mapping of RCR-associated canopy symptoms across independent commercial soybean fields.","由冬青丽赤壳菌（Calonectria ilicicola）引起的红冠腐病（RCR）是美国中西部一种新发大豆病害，目前尚缺乏可规模化表征田块内病害分布的方法。本研究评估了高分辨率PlanetScope卫星影像在2024年和2025年生长季对伊利诺伊州15块商业田块中受RCR影响的大豆冠层的制图能力。共有2,921个地理参考冠层样区被分类为无症状或受RCR影响，并与6个多光谱波段和7个植被指数配对。采用线性混合效应模型评估类别间的光谱差异，并通过空间独立的留一田块交叉验证比较了7种机器学习分类器，涵盖线性、基于树、神经网络、核函数和概率方法。与无症状冠层相比，受RCR影响的冠层在可见光和红边区域反射率增加，近红外反射率降低，植被指数值较低。所有分类器均表现出较强的判别能力，ROC-AUC值范围为0.963至0.982。正则化逻辑回归在优化决策阈值下取得了最高的整体性能，准确率为0.945，平衡准确率为0.945，F1分数为0.948，ROC-AUC为0.982。置换分析表明，在代表性模型架构中，EVI、NDVI和红光反射率是最具影响力的预测变量。卫星衍生的概率图和分类图总体上与高分辨率无人机影像中观察到的症状冠层模式一致，尽管混合像元降低了病害斑块边界附近的精度。这些结果证明了高分辨率卫星影像在独立商业大豆田块中对RCR相关冠层症状进行田块内制图的潜力。","bioRxiv (Cold Spring Harbor Laboratory)","2026-09-23T00:00:00Z",76,{"impact":19,"substance":17,"depth":18,"authority":50,"freshness":184,"relevant":21,"comment":185},8,"基于高分辨率卫星影像与机器学习实现大豆红冠腐病田间制图，方法扎实、数据规模可观，对作物病害遥感监测有参考价值。",[187],{"name":180,"url":177},[109,189,53,190,191],"机器学习","遥感监测","病害识别",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[194],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"status":44,"locked":14,"version":45,"method":46,"evidence":196},{"candidates":197,"agricultural_evidence":51},[198,204,210,216],{"code":31,"score":199,"supported":51,"title":200,"abstract":202,"tags":203},15,[201],"soybean",[53,201],[53],{"code":38,"score":205,"supported":51,"title":206,"abstract":208,"tags":209},13,[207],"machine learning",[189],[189,191],{"code":211,"score":64,"supported":51,"title":212,"abstract":213,"tags":215},"I3",[],[214],"multispectral",[190],{"code":133,"score":21,"supported":14,"title":217,"abstract":218,"tags":219},[],[],[109],[221,222],"伊利诺伊 大豆 红冠腐病 卫星遥感","PlanetScope 大豆 病害 机器学习","伊利诺伊大豆红冠腐病卫星遥感-3485","10.64898\u002F2026.09.22.753594",{"doi":224,"openalex_id":226,"authors":227,"venue":180,"cited_by_count":165,"oa_url":247,"card":248,"direction":252,"ingested_from":172},"W7214126630",[228,231,234,236,238,241,244],{"name":229,"orcid":230},"Bruno Daniel Pugliese","https:\u002F\u002Forcid.org\u002F0009-0000-4795-4248",{"name":232,"orcid":233},"Juan Andrés Paredes","https:\u002F\u002Forcid.org\u002F0000-0002-3967-0197",{"name":235,"orcid":8},"Andres Fabian Ruiz",{"name":237,"orcid":8},"Norman Denis Bowman",{"name":239,"orcid":240},"Elhan S. Ersoz","https:\u002F\u002Forcid.org\u002F0000-0001-6930-6946",{"name":242,"orcid":243},"Nicolas Federico Martin","https:\u002F\u002Forcid.org\u002F0000-0002-1587-665X",{"name":245,"orcid":246},"Boris X. Camiletti","https:\u002F\u002Forcid.org\u002F0000-0002-1492-7988","https:\u002F\u002Fwww.biorxiv.org\u002Fcontent\u002Fbiorxiv\u002Fearly\u002F2026\u002F09\u002F23\u002F2026.09.22.753594.full.pdf",{"tldr":249,"method":250,"finding":251,"direction":252,"opportunity":253},"利用高分辨率卫星影像和机器学习在大豆田中检测红冠腐病。","PlanetScope多光谱影像、植被指数与7种机器学习分类器，留一田块交叉验证","各分类器ROC-AUC达0.963-0.982，正则化逻辑回归最优，EVI、NDVI和红波段最重要。","农业遥感与作物表型","可探索多时相卫星影像与无人机融合，提升病害斑块边界混合像元识别精度。","2026-09-25T23:30:22.839600Z",{"id":256,"title":257,"url":258,"summary":259,"summary_zh":8,"content":8,"source_name":260,"source_url":8,"published_at":261,"category":99,"cover_url":8,"hotness":13,"is_selected":14,"score":262,"score_detail":263,"sources":266,"tags":268,"primary_topic":272,"secondary_topics":273,"classification":275,"search_phrases":302,"slug":305,"view_count":71,"doi":306,"paper":307,"created_at":315},2859,"县域大豆产量预测的深度学习方法:利用大规模环境数据——Frontiers in Artificial Intelligence","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fartificial-intelligence\u002Farticles\u002F10.3389\u002Ffrai.2026.1914697\u002Ffull","论文提出了基于深度学习的大规模环境数据县域大豆产量预测方法。利用县级大豆产量数据和环境变量构建预测模型,评估多种深度学习架构(卷积神经网络、循环神经网络、Transformer等)在大豆产量预测中的表现,并与传统统计回归模型进行比较。结果显示,深度学习方法在预测精度和稳定性方面优于传统模型,能够更好地捕捉环境因素与产量之间的非线性关系,为农业政策制定和粮食安全评估提供数据支持。","Frontiers in Artificial Intelligence","2026-09-17T00:00:00Z",77,{"impact":19,"substance":264,"depth":103,"authority":205,"freshness":13,"relevant":21,"comment":265},21,"论文以县级大规模环境数据对比多种深度学习架构与传统回归模型，方法新颖、结论可靠，对农业政策与粮食安全评估有参考价值，值得进入每日精选。",[267],{"name":260,"url":258},[109,110,269,270,271],"粮食安全","大豆产量预测","环境数据",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[274],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"status":44,"locked":14,"version":45,"method":46,"evidence":276},{"candidates":277,"agricultural_evidence":51},[278,283,287,292,298],{"code":38,"score":102,"supported":51,"title":279,"abstract":281,"tags":282},[124,280],"artificial intelligence",[124],[110],{"code":31,"score":57,"supported":51,"title":284,"abstract":285,"tags":286},[53],[53],[],{"code":288,"score":64,"supported":51,"title":289,"abstract":290,"tags":291},"A8",[],[269],[269],{"code":293,"score":71,"supported":51,"title":294,"abstract":295,"tags":297},"J1",[],[296],"农业政策",[],{"code":133,"score":21,"supported":14,"title":299,"abstract":300,"tags":301},[],[],[109],[303,304],"农业人工智能 大豆产量预测 智慧农业 环境数据","农业人工智能 大豆产量预测","农业人工智能大豆产量预测智慧农业环境数据-2859","10.3389\u002Ffrai.2026.1914697\u002Ffull",{"doi":306,"openalex_id":8,"authors":308,"venue":8,"cited_by_count":165,"oa_url":8,"card":309,"direction":170,"ingested_from":314},[],{"tldr":310,"method":311,"finding":312,"direction":170,"opportunity":313},"用深度学习结合大规模环境数据预测县域大豆产量，并对比多种网络架构与传统模型。","县级大豆产量与环境变量数据，采用CNN、RNN、Transformer等深度学习","深度学习在预测精度和稳定性上优于传统统计回归，能更好捕捉非线性关系。","可探索多模态环境数据融合与可解释性，提升跨区域迁移和极端气候下的预测鲁棒性。","agent","2026-09-18T00:03:31.241582Z",{"id":317,"title":318,"url":319,"summary":320,"summary_zh":321,"content":8,"source_name":322,"source_url":319,"published_at":323,"category":99,"cover_url":8,"hotness":13,"is_selected":14,"score":324,"score_detail":325,"sources":327,"tags":329,"primary_topic":333,"secondary_topics":334,"classification":340,"search_phrases":362,"slug":365,"view_count":64,"doi":366,"paper":367,"created_at":399},2320,"Genotype-Aware Prediction of Soybean Seed Composition from Multimodal UAV Imagery of the Standing Crop","https:\u002F\u002Fdoi.org\u002F10.3390\u002Frs18183121","Geospatial artificial intelligence (GeoAI) integrates multimodal remote sensing with deep learning to model complex agricultural systems at scale. Within this framework, accurate and non-destructive prediction of seed composition from in-season standing crops is essential for breeding and precision agriculture. This study developed an end-to-end convolutional neural network (CNN) framework to estimate eight seed traits (protein, oil, sucrose, fiber, starch, ash, complex and simple carbohydrates) from UAV-based multisensor imagery and associated genotype and phenological metadata. A total of 372 soybean samples were collected over two growing seasons (2020–2021) from two fields in Missouri, with UAV flights capturing multispectral (MSI), thermal (THR), and LiDAR (LDR) data at four time points spanning vegetative to reproductive growth stages. CNN models were trained in single- and multi-date configurations, incorporating genotype (GEN) and days after sowing (DAS) as additional features. The highest accuracy was achieved for sucrose (R2 = 0.80), followed by simple carbohydrate (R2 = 0.70) and starch (R2 = 0.55), with notable gains from GEN and DAS. Multi-date models incorporating earlier acquisitions often matched or outperformed later or all-date combinations. Among modalities, MSI provided the most robust estimates, with limited added value from LDR or THR. Unlike feature-based pipelines prone to multicollinearity, this image-to-trait approach enables automated, scalable prediction of soybean seed composition for in-season, field-level assessment.","地理空间人工智能（GeoAI）将多模态遥感与深度学习相结合，以在大尺度上对复杂农业系统进行建模。在该框架下，对当季未收获作物进行准确且无损的种子成分预测，对于育种和精准农业至关重要。本研究开发了一种端到端的卷积神经网络（CNN）框架，利用基于无人机（UAV）的多传感器影像以及相关的基因型和物候元数据，估算八种种子性状（蛋白质、油分、蔗糖、纤维、淀粉、灰分、复杂碳水化合物和简单碳水化合物）。研究在2020—2021两个生长季内，从密苏里州两块田地共采集372份大豆样本，无人机飞行在从营养生长期到生殖生长期的四个时间点获取了多光谱（MSI）、热红外（THR）和激光雷达（LDR）数据。CNN模型以单日期和多日期配置进行训练，并将基因型（GEN）和播种后天数（DAS）作为附加特征纳入。蔗糖的估算精度最高（R² = 0.80），其次为简单碳水化合物（R² = 0.70）和淀粉（R² = 0.55），且GEN和DAS的加入带来了显著提升。纳入早期采集数据的多日期模型往往与后期或全日期组合的表现相当，甚至更优。在各模态中，MSI提供了最稳健的估算结果，而LDR或THR的附加价值有限。与易受多重共线性影响的特征工程流程不同，这种从图像到性状的方法能够实现大豆种子成分的自动化、可扩展预测，用于当季田块尺度的评估。","Remote Sensing","2026-09-11T00:00:00Z",80,{"impact":18,"substance":17,"depth":18,"authority":104,"freshness":184,"relevant":21,"comment":326},"基于多模态无人机影像与基因型信息的大豆籽粒成分无损预测研究，方法新颖、数据扎实，对智慧育种与精准农业有参考价值。",[328],{"name":322,"url":319},[109,330,110,331,332],"无人机","遥感","大豆育种",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[335,336],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"code":211,"slug":337,"name":338,"path":339,"parent_code":42},"remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":44,"locked":14,"version":45,"method":46,"evidence":341},{"candidates":342,"agricultural_evidence":51},[343,347,351,356],{"code":31,"score":199,"supported":51,"title":344,"abstract":345,"tags":346},[201],[53,201],[332],{"code":38,"score":13,"supported":51,"title":348,"abstract":349,"tags":350},[],[124,122,280],[110],{"code":211,"score":13,"supported":51,"title":352,"abstract":353,"tags":355},[],[331,354,214],"remote sensing",[331],{"code":133,"score":357,"supported":51,"title":358,"abstract":359,"tags":361},7,[],[112,360],"precision agriculture",[109],[363,364],"农业人工智能 大豆育种 智慧农业 无人机","农业人工智能 大豆育种","农业人工智能大豆育种智慧农业无人机-2320","10.3390\u002Frs18183121",{"doi":366,"openalex_id":368,"authors":369,"venue":322,"cited_by_count":165,"oa_url":319,"card":394,"direction":252,"ingested_from":172},"W7212223520",[370,373,376,379,382,384,386,389,392],{"name":371,"orcid":372},"Vasit Sagan","https:\u002F\u002Forcid.org\u002F0000-0003-4375-2096",{"name":374,"orcid":375},"Kristen Rhodes","https:\u002F\u002Forcid.org\u002F0000-0002-8469-5043",{"name":377,"orcid":378},"Sourav Bhadra","https:\u002F\u002Forcid.org\u002F0000-0002-5832-4695",{"name":380,"orcid":381},"Haireti Alifu","https:\u002F\u002Forcid.org\u002F0000-0002-7369-6657",{"name":383,"orcid":8},"Aviskar Giri",{"name":385,"orcid":8},"Ashutosh Pawar",{"name":387,"orcid":388},"Bishal Roy","https:\u002F\u002Forcid.org\u002F0000-0001-9912-5505",{"name":390,"orcid":391},"Supria Sarkar","https:\u002F\u002Forcid.org\u002F0000-0001-9467-5786",{"name":393,"orcid":8},"Felix Fritschi",{"tldr":395,"method":396,"finding":397,"direction":252,"opportunity":398},"用无人机多模态影像与基因型数据训练CNN，预测大豆八种种子成分。","372份大豆样本，多光谱\u002F热红外\u002FLiDAR影像加基因型与播后天数，端到端CNN","蔗糖预测最优(R²=0.80)，基因型与播期提升精度，多光谱最稳健。","可探索基因型-表型-环境交互建模，并迁移至其他作物与多时相早期预测。","2026-09-13T23:30:22.776177Z",{"id":401,"title":402,"url":403,"summary":404,"summary_zh":8,"content":405,"source_name":406,"source_url":8,"published_at":407,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":408,"score_detail":409,"sources":412,"tags":414,"primary_topic":418,"secondary_topics":419,"classification":421,"search_phrases":443,"slug":446,"view_count":86,"doi":8,"paper":8,"created_at":447},2100,"安徽农业大学发布大豆垂直大模型\"丰菽\"2.0 构建我国首个大豆全生命周期生成式AI育种平台","https:\u002F\u002Fiapp.rzdgrmt.cn\u002Fshare\u002FYS0zNDktNDQ4OTEwNTQ.html","在第三十二届全国大豆科研生产研讨会上,安徽农业大学大豆智能设计育种创新团队联合中国农业科学院作物科学研究所共同研发的大豆领域垂直大模型\"丰菽\"2.0正式发布。该模型集成豆百科、豆分子、豆文献、豆病害、豆表型、豆育种六大功能模块,汇聚大豆核心种质资源、基因组、表型影像、科研文本等多源数据,构建\"多源验证—智能融合—可信输出\"的知识技术架构。科研人员用手机拍摄大豆叶片即可进行病害诊断与表型特征提取,实现\"随拍随诊\"。","在东港\n\n官方移动发布平台\n\n[](https:\u002F\u002Fiapp.rzdgrmt.cn\u002Fshare\u002FYS0zNDktNDQ4OTEwNTQ.html)\n\n![Image 1](https:\u002F\u002Fiapp.rzdgrmt.cn\u002Fservice2\u002Farticle\u002Farticle-detail-share\u002Fimages\u002Ficon-voice.png)听新闻\n\n[Audio 2](https:\u002F\u002Fstream-spk.iqilu.com\u002F349\u002F2026\u002F09\u002F07\u002F44891054.mp3?1788887065172)\n\n大豆垂直大模型“丰菽”2.0正式发布\n\n00:00\n\n# 大豆垂直大模型“丰菽”2.0正式发布\n\n人民日报\n\n2026-09-07 08:48\n\n记者从安徽农业大学获悉：在第三十二届全国大豆科研生产研讨会上，由该校大豆智能设计育种创新团队联合中国农业科学院作物科学研究所共同研发的大豆领域垂直大模型“丰菽”2.0正式发布。\n\n该模型构建了我国首个面向大豆全生命周期的生成式人工智能育种平台，有望推动大豆育种从依赖经验向数据辅助决策转变，为提升大豆单产提供新的技术路径。\n\n据介绍，“丰菽”2.0集成了豆百科、豆分子、豆文献、豆病害、豆表型、豆育种六大功能模块，汇聚大豆核心种质资源、基因组、表型影像、科研文本等多源数据，构建起“多源验证—智能融合—可信输出”的知识技术架构，面对同一个大豆专业问题，不同模型可分别进行独立分析，再由“丰菽”总结模块结合领域知识、私有数据和专家规则，对回答中的共识、差异及证据完整性进行结构化比对与综合研判，有效降低了单一模型的回答偏差，输出更加清晰可靠的专业结论。\n\n经过优化，科研人员只需用手机拍摄大豆叶片或植株，即可依托大模型进行病害诊断与表型特征提取，实现“随拍随诊”；同时打通了电脑端与移动端的数据壁垒，育种试验记录、分子标记辅助育种数据及候选基因功能分析结果可实现云端实时同步，方便科研团队随时随地开展虚拟组合设计与数据查阅。\n\n目前，“丰菽”2.0可围绕大豆重要农艺性状，辅助开展病害诊断、育种亲本筛选、虚拟组合设计、表型数据解析、分子标记辅助育种和候选基因功能分析等核心场景应用，能够显著提高科研数据处理效率，减少重复性工作，实现优异等位基因智能挖掘和最优亲本组合虚拟设计。\n\n编辑：许艺璇 王倩 费洪涛 王西辉\n\n版权说明\n\n特别声明：本文为“在东港”客户端“海曲号”作者上传并发布，仅代表作者观点。“在东港”客户端仅提供信息发布平台。\n\n[打开“在东港”看评论 ![Image 2](https:\u002F\u002Fiapp.rzdgrmt.cn\u002Fservice2\u002Farticle\u002Farticle-detail-share\u002Fimages\u002Ficon_comment.png) ![Image 3](https:\u002F\u002Fiapp.rzdgrmt.cn\u002Fservice2\u002Farticle\u002Farticle-detail-share\u002Fimages\u002Ficon-coll.png) ![Image 4](https:\u002F\u002Fiapp.rzdgrmt.cn\u002Fservice2\u002Farticle\u002Farticle-detail-share\u002Fimages\u002Ficon_parse.png)](https:\u002F\u002Fiapp.rzdgrmt.cn\u002Fshare\u002FYS0zNDktNDQ4OTEwNTQ.html)\n\n## 相关资讯\n\n### [我国已累计发布8批121个新职业 数字职业、绿色职业均超百个 15小时前 观天下 ![Image 5](https:\u002F\u002Fimg12.litenews.cn\u002F10293\u002Fsucaiku\u002Fcompress\u002F202312\u002F06\u002F073864c224ae461eb225b4dfb984e096.png)](https:\u002F\u002Fiapp.rzdgrmt.cn\u002Fshare\u002FYS0zNDktNDQ5MzYzNjA.html)### [从机器人“教练”到适老化改造设计师，11个新职业23个新工种发布 新需求一冒头 新职业就“破土” 15小时前 观天下 ![Image 6](https:\u002F\u002Fimg12.litenews.cn\u002F10293\u002Fsucaiku\u002Fcompress\u002F202602\u002F10\u002F32831a81a0094f3b89fb9f6d3bc1e1dc.png)](https:\u002F\u002Fiapp.rzdgrmt.cn\u002Fshare\u002FYS0zNDktNDQ5MzYzNTk.html)### [一车一主题、一厢一景致 “鲁甘协作”冠名列车首发 15小时前 观天下 ![Image 7](https:\u002F\u002Fimg12.litenews.cn\u002F10293\u002Fsucaiku\u002Fcompress\u002F202602\u002F10\u002F32831a81a0094f3b89fb9f6d3bc1e1dc.png)](https:\u002F\u002Fiapp.rzdgrmt.cn\u002Fshare\u002FYS0zNDktNDQ5MzYzNTg.html)### [传承弘扬英烈精神 筑牢国家安全屏障”主题活动举办 15小时前 观天下 ![Image 8](https:\u002F\u002Fimg12.litenews.cn\u002F10293\u002Fsucaiku\u002Fcompress\u002F202602\u002F10\u002F32831a81a0094f3b89fb9f6d3bc1e1dc.png)](https:\u002F\u002Fiapp.rzdgrmt.cn\u002Fshare\u002FYS0zNDktNDQ5MzYzNTQ.html)### [潍坊推动医保、医疗、医药数据融合 人均住院费用下降一千八百余元 15小时前 观天下 ![Image 9](https:\u002F\u002Fimg12.litenews.cn\u002F10293\u002Fsucaiku\u002Fcompress\u002F202602\u002F10\u002F32831a81a0094f3b89fb9f6d3bc1e1dc.png)](https:\u002F\u002Fiapp.rzdgrmt.cn\u002Fshare\u002FYS0zNDktNDQ5MzYzNTA.html)### [从被看见到被照亮山东成就141万“筑梦人” 15小时前 观天下 ![Image 10](https:\u002F\u002Fimg12.litenews.cn\u002F10293\u002Fsucaiku\u002Fcompress\u002F202602\u002F10\u002Fef0b650c0ffe4013becd762b6a1dc423.png)](https:\u002F\u002Fiapp.rzdgrmt.cn\u002Fshare\u002FYS0zNDktNDQ5MzYzNDg.html)### [三尺讲台，四季耕耘——“齐鲁最美教师”用行动和青春诠释“何以为师” 15小时前 观天下 ![Image 11](https:\u002F\u002Fimg12.litenews.cn\u002F10293\u002Fsucaiku\u002Fcompress\u002F202602\u002F10\u002F32831a81a0094f3b89fb9f6d3bc1e1dc.png)](https:\u002F\u002Fiapp.rzdgrmt.cn\u002Fshare\u002FYS0zNDktNDQ5MzYzNDY.html)### [前8个月山东“新三样”出口增长27.7% 15小时前 观天下 ![Image 12](https:\u002F\u002Fimg12.litenews.cn\u002F10293\u002Fsucaiku\u002Fcompress\u002F202602\u002F10\u002F32831a81a0094f3b89fb9f6d3bc1e1dc.png)](https:\u002F\u002Fiapp.rzdgrmt.cn\u002Fshare\u002FYS0zNDktNDQ5MzYzMzg.html)### [95家鲁企亮相2026服贸会 15小时前 观天下 ![Image 13](https:\u002F\u002Fimg12.litenews.cn\u002F10293\u002Farticle\u002F202609\u002F10\u002F716cf80314ad43ce8c5ddb33954e11e1.jpg)](https:\u002F\u002Fiapp.rzdgrmt.cn\u002Fshare\u002FYS0zNDktNDQ5MzYzMjE.html)### [与法同行 护航成长 15小时前 观天下 ![Image 14](https:\u002F\u002Fimg12.litenews.cn\u002F10293\u002Farticle\u002F202609\u002F10\u002Fddda5e025d104b92befddaefd6b221de.jpg)](https:\u002F\u002Fiapp.rzdgrmt.cn\u002Fshare\u002FYS0zNDktNDQ5MzYzMTY.html)","在东港\u002F今日头条","2026-09-07T00:00:00Z",86,{"impact":410,"substance":17,"depth":103,"authority":205,"freshness":184,"relevant":21,"comment":411},26,"我国首个大豆全生命周期生成式AI育种平台发布，属种业与农业AI交叉领域的标志性突破，技术路径与功能模块描述具体，值得进入每日精选。",[413],{"name":406,"url":403},[110,415,416,53,417],"种业振兴","智能育种","垂直大模型",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[420],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"status":44,"locked":14,"version":45,"method":46,"evidence":422},{"candidates":423,"agricultural_evidence":51},[424,428,432,438],{"code":31,"score":50,"supported":51,"title":425,"abstract":426,"tags":427},[53],[53],[53],{"code":38,"score":50,"supported":51,"title":429,"abstract":430,"tags":431},[59],[59],[110],{"code":433,"score":64,"supported":51,"title":434,"abstract":435,"tags":437},"F1",[],[436],"种质资源",[415],{"code":439,"score":21,"supported":14,"title":440,"abstract":441,"tags":442},"F2",[],[],[416],[444,445],"农业人工智能 垂直大模型 智能育种 种业振兴","农业人工智能 垂直大模型","农业人工智能垂直大模型智能育种种业振兴-2100","2026-09-11T00:04:21.173241Z",{"id":449,"title":450,"url":451,"summary":452,"summary_zh":8,"content":8,"source_name":453,"source_url":8,"published_at":454,"category":99,"cover_url":8,"hotness":13,"is_selected":14,"score":455,"score_detail":456,"sources":459,"tags":461,"primary_topic":466,"secondary_topics":467,"classification":469,"search_phrases":484,"slug":487,"view_count":86,"doi":8,"paper":488,"created_at":495},1818,"From Orbit to Leaf: A Critical Systematic Review of Artificial Intelligence for Multi-Scale Crop Monitoring and Soybean Leaf Disease Diagnosis（IJAIML 2026, 6(9s), 471-498）","https:\u002F\u002Fwww.svedbergopen.com\u002Findex.php\u002Fijaiml\u002Farticle\u002Fview\u002F1516","依据PRISMA 2020筛选4286篇记录，保留2019—2026年84项主要研究（41项轨道、17项航空、26项近距），以大豆叶病识别为近距测试案例。引入AGRI-CRITIC八维评估标准并综合为Field Readiness Index（FRI）。中位报告准确率93.9%但中位FRI仅37.5\u002F100，仅22.6%研究超过田间就绪阈值60，且报告准确率与评估集大小呈1.9%\u002F十倍样本负相关——小样本乐观的标志。识别七类反复失败模式，发布FIELD-READY十项报告协议与三阶段研究议程。","International Journal of Artificial Intelligence and Machine Learning 2026, 6(9s)","2026-09-05T00:00:00Z",81,{"impact":18,"substance":457,"depth":102,"authority":50,"freshness":357,"relevant":21,"comment":458},24,"系统综述揭示AI作物监测报告准确率与田间实用性差距，提出评估标准与报告协议，对智慧农业落地有重要参考价值。",[460],{"name":453,"url":451},[110,462,463,464,465],"系统综述","作物监测","大豆叶病","田间就绪",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[468],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"status":44,"locked":14,"version":45,"method":46,"evidence":470},{"candidates":471,"agricultural_evidence":51},[472,476,480],{"code":31,"score":57,"supported":51,"title":473,"abstract":474,"tags":475},[201],[53],[],{"code":38,"score":20,"supported":51,"title":477,"abstract":478,"tags":479},[280],[],[110],{"code":211,"score":21,"supported":14,"title":481,"abstract":482,"tags":483},[],[],[463],[485,486],"农业人工智能 作物监测 大豆叶病 田间就绪","农业人工智能 作物监测","农业人工智能作物监测大豆叶病田间就绪-1818",{"doi":8,"openalex_id":8,"authors":489,"venue":8,"cited_by_count":165,"oa_url":8,"card":490,"direction":170,"ingested_from":314},[],{"tldr":491,"method":492,"finding":493,"direction":170,"opportunity":494},"系统综述AI用于多尺度作物监测与大豆叶病诊断，提出FRI评估标准与报告协议。","PRISMA筛选84项研究，提出AGRI-CRITIC八维评估与FRI指数。","报告准确率中位93.9%但FRI仅37.5，小样本导致乐观偏差，仅22.6%达到田间就绪。","可开发考虑样本量与田间条件的模型评估方法，或构建跨尺度数据集以提升实际部署可靠性。","2026-09-07T00:04:41.715297Z"]