[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-662":3,"related-662":68},{"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":31,"secondary_topics":37,"classification":38,"search_phrases":62,"slug":65,"view_count":66,"doi":8,"paper":8,"created_at":67},662,"山东省农科院葡萄研究院选育锦蜜葡萄新品种 通过农业农村部登记纳入2026山东主导品种","https:\u002F\u002Fdzrb.dzng.com\u002Fvideos\u002F0\u002FNEWS3602505MCPFVAXRGDUGH","山东省早熟葡萄新品种锦蜜现场观摩会在泰安市举行,8月2日至8月12日期间合作社、家庭农场、种植大户及企业陆续到山东省农科院金牛山实验示范基地现场观摩。锦蜜是山东省葡萄研究院葡萄遗传育种与栽培团队在山东省科技厅农业良种工程项目支持下培育的早熟葡萄新品种,2025年初获农业农村部非主要农作物新品种登记证书。早熟色艳、香味浓郁、高产稳产、管理省工是突出优势,2026年山东省农业主导品种中唯一的葡萄品种。",null,"[](https:\u002F\u002Fdzrb.dzng.com\u002F)[推荐](https:\u002F\u002Fdzrb.dzng.com\u002F)[山东](https:\u002F\u002Fdzrb.dzng.com\u002Fhome\u002F407\u002F0)[热点](https:\u002F\u002Fdzrb.dzng.com\u002Fhome\u002F429\u002F0)[齐鲁制造](https:\u002F\u002Fdzrb.dzng.com\u002Fhome\u002F1161\u002F0)[山东](https:\u002F\u002Fdzrb.dzng.com\u002Fhome\u002F407\u002F0)[短剧](https:\u002F\u002Fdzrb.dzng.com\u002Fhome\u002F1294\u002F0)[直播](https:\u002F\u002Fdzrb.dzng.com\u002Fhome\u002F217\u002F0)[数字强省](https:\u002F\u002Fdzrb.dzng.com\u002Fhome\u002F1286\u002F0)[帮办](https:\u002F\u002Fdzrb.dzng.com\u002Fhome\u002F1176\u002F0)[观点](https:\u002F\u002Fdzrb.dzng.com\u002Fhome\u002F497\u002F0)[文化](https:\u002F\u002Fdzrb.dzng.com\u002Fhome\u002F428\u002F0)[V-IP](https:\u002F\u002Fdzrb.dzng.com\u002Fhome\u002F1188\u002F0)[国资](https:\u002F\u002Fdzrb.dzng.com\u002Fhome\u002F439\u002F0)[开放山东](https:\u002F\u002Fdzrb.dzng.com\u002Fhome\u002F1160\u002F0)[财经](https:\u002F\u002Fdzrb.dzng.com\u002Fhome\u002F454\u002F0)[交通](https:\u002F\u002Fdzrb.dzng.com\u002Fhome\u002F461\u002F0)[健康](https:\u002F\u002Fdzrb.dzng.com\u002Fhome\u002F377\u002F0)[文旅](https:\u002F\u002Fdzrb.dzng.com\u002Fhome\u002F468\u002F0)[教育](https:\u002F\u002Fdzrb.dzng.com\u002Fhome\u002F1338\u002F0)[监管](https:\u002F\u002Fdzrb.dzng.com\u002Fhome\u002F475\u002F0)[智库](https:\u002F\u002Fdzrb.dzng.com\u002Fhome\u002F650\u002F0)[政法](https:\u002F\u002Fdzrb.dzng.com\u002Fhome\u002F629\u002F0)[党建](https:\u002F\u002Fdzrb.dzng.com\u002Fhome\u002F373\u002F0)[民生](https:\u002F\u002Fdzrb.dzng.com\u002Fhome\u002F1340\u002F0)[果然视频](https:\u002F\u002Fdzrb.dzng.com\u002Fhome\u002F1339\u002F0)[青未了](https:\u002F\u002Fdzrb.dzng.com\u002Fhome\u002F366\u002F0)[灵境](https:\u002F\u002Fdzrb.dzng.com\u002Fhome\u002F1293\u002F0)[深度](https:\u002F\u002Fdzrb.dzng.com\u002Fhome\u002F1335\u002F0)[创意](https:\u002F\u002Fdzrb.dzng.com\u002Fhome\u002F1337\u002F0)[观察](https:\u002F\u002Fdzrb.dzng.com\u002Fhome\u002F1336\u002F0)[科技](https:\u002F\u002Fdzrb.dzng.com\u002Fhome\u002F421\u002F0)\n\n 大众新闻APP\n\n![Image 1](https:\u002F\u002Fimage.dzplus.dzng.com\u002F2025\u002F07\u002F15\u002F1752550874tg98qmb4twoimage.png?)微信扫码 扫码下载客户端\n\n[大众日报](https:\u002F\u002Fpaper.dzwww.com\u002Fdzrb)[农村大众](https:\u002F\u002Fpaper.dzwww.com\u002Fncdz\u002Findex.html)[齐鲁晚报](https:\u002F\u002Fepaper.qlwb.com.cn\u002F)[半岛都市报](https:\u002F\u002Fbddsb.bandao.cn\u002Fpc\u002Fbddsb\u002F)[鲁中晨报](http:\u002F\u002Fepaper.lzcb.com\u002F)[经济导报](http:\u002F\u002Fjjdb.sdenews.com\u002F)[山东法制报](https:\u002F\u002Fpaper.dzwww.com\u002Fsdfzb\u002Findex.html)[黄三角早报](https:\u002F\u002Fhsjzb.qlwb.com.cn\u002F)[青岛西海岸报](https:\u002F\u002Fepaper.xihaiannews.com\u002F)\n\n# 早熟色艳、香味浓郁！省工且不易掉粒的葡萄新品种“锦蜜”来了\n\n大众新闻·农村大众 08-12 原创\n\n[Video 2](https:\u002F\u002Fvideo.dzplus.dzng.com\u002F2026\u002F08\u002F12\u002F17865039002pkdei8m8hcvideo_1080p_1_889194.mp4)\n\n![Image 2](https:\u002F\u002Fimage.dzplus.dzng.com\u002F2026\u002F08\u002F12\u002F1786503995b5mv6df4xjo.png)\n\n8月2日至8月12日，山东省早熟葡萄新品种“锦蜜”现场观摩会在泰安市举行。来自全国各地的合作社、家庭农场、种植大户及企业陆续来到山东省农科院金牛山实验示范基地，现场观摩这一被专家称为“具有里程碑意义”的早熟葡萄新品种。\n\n“锦蜜”是山东省葡萄研究院葡萄遗传育种与栽培团队在山东省科技厅农业良种工程项目支持下培育而成的早熟葡萄新品种。2025年初，“锦蜜”拿到了农业农村部非主要农作物新品种登记证书。早熟色艳、香味浓郁、高产稳产、管理省工是“锦蜜”的突出优势。\n\n6月29日，山东省农业农村厅、山东省科学技术厅、山东省畜牧兽医局联合发布2026年山东省农业主导品种，总共50个。其中，早熟葡萄新品种“锦蜜”赫然在列，这是今年山东省农业主导品种中的唯一一个葡萄品种。\n\n（大众新闻·农村大众记者 刘真真）\n\n热门评论 我要评论 \n\n![Image 3](blob:http:\u002F\u002Flocalhost\u002F680f90c7e0c561831a17c4a3b4ef2b69)微信扫码 扫码下载客户端\n\n1\n\n![Image 4](blob:http:\u002F\u002Flocalhost\u002F680f90c7e0c561831a17c4a3b4ef2b69)微信扫码 立即点赞\n\n![Image 5](blob:http:\u002F\u002Flocalhost\u002F680f90c7e0c561831a17c4a3b4ef2b69)微信扫码 立即评论\n\n![Image 6](blob:http:\u002F\u002Flocalhost\u002F680f90c7e0c561831a17c4a3b4ef2b69)微信扫码 立即收藏\n\n![Image 7](blob:http:\u002F\u002Flocalhost\u002F680f90c7e0c561831a17c4a3b4ef2b69)微信扫码 立即分享\n\n[1 果然视频·看天下|伊朗：不要拿海峡开玩笑，会打断侵略者的腿](https:\u002F\u002Fdzrb.dzng.com\u002Fvideos\u002F0\u002FNEWS3613142MTCINEGMDWXDX)[2 果然视频|出行遭遇大雨，这些消防安全事项请注意](https:\u002F\u002Fdzrb.dzng.com\u002Fvideos\u002F0\u002FNEWS3613016SAOOZRQUDZCZA)[3 果然视频·看天下|“林肯”号航母水兵拍视频狂吐槽：疯了吧！](https:\u002F\u002Fdzrb.dzng.com\u002Fvideos\u002F0\u002FNEWS3613069EZCADQQOBOEYW)[4 果然视频|水木年华助阵，潍坊市“村BA”篮球联赛火热举办](https:\u002F\u002Fdzrb.dzng.com\u002Fvideos\u002F0\u002FNEWS3613376QDEHPAMHRGMTL)[5 果然视频·看天下|以部长“疯了”：每晚都应清除加沙数十人](https:\u002F\u002Fdzrb.dzng.com\u002Fvideos\u002F0\u002FNEWS3613067NOZZXXNBCKSAX)[6 果然视频|如果真的遇到火灾，该如何正确拨打119？](https:\u002F\u002Fdzrb.dzng.com\u002Fvideos\u002F0\u002FNEWS3612907RVNKMLHRAFSYI)[7 果然视频|中国男篮不敌新西兰，以1胜2负结束佛山热身赛之旅](https:\u002F\u002Fdzrb.dzng.com\u002Fvideos\u002F0\u002FNEWS3613635IQMVTBXWSTDAQ)[8 纪录片丨“蔬”写四十年之一棚兴](https:\u002F\u002Fdzrb.dzng.com\u002Fvideos\u002F0\u002FNEWS3612889GCHBRTZUUEHAD)[9 果然视频|壹点公益2026暑期夏令营走进数字济南体验馆](https:\u002F\u002Fdzrb.dzng.com\u002Fvideos\u002F0\u002FNEWS3613626OTCUNUKVLKKZW)\n\n融媒矩阵（媒体）\n\n[大众日报人民号](https:\u002F\u002Fwap.peopleapp.com\u002Frmh\u002F7881)[大众日报北京号](https:\u002F\u002Fmobile.bjd.com.cn\u002F#\u002Fpages\u002Fbjh\u002Fspecial?info=1&uuid=6232c6b7e4b0a7e96c5859d1)[大众日报潮鸣号](https:\u002F\u002Ftidenews.com.cn\u002Fnative\u002Fuser_page.html?id=63feb6ed79e9af000141f691)[大众日报南方号](https:\u002F\u002Fstatic.nfapp.southcn.com\u002Fnfh\u002FshareNFNum\u002Findex.html?nfhId=33790)\n\n融媒矩阵（商业）\n\n[大众日报抖音号](https:\u002F\u002Fv.douyin.com\u002Fi2J8pFVf\u002F%200@9.com)[大众日报头条号](https:\u002F\u002Fprofile.zjurl.cn\u002Frogue\u002Fugc\u002Fprofile\u002F?active_tab=dongtai&app_name=news_article&device_id=65&media_id=1598246319660046&request_source=1&share_token=5c28b11e-cd2e-454e-859a-443ccf27dc71&tt_from=copy_link&user_id=3340580883&utm_campaign=client_share&utm_medium=toutiao_android&utm_source=copy_link&version_code=961&version_name=90601)[大众日报企鹅号](https:\u002F\u002Fview.inews.qq.com\u002Fu\u002F8QMd3HxY64IUvDnZ?chlid=_qqnews_custom_search_all)[大众日报百家号](https:\u002F\u002Fmq.mbd.baidu.com\u002Fr\u002F1gX5pQ6Vlsc?f=cp&u=a221255631243b77)\n\n[大众日报一点号](https:\u002F\u002Fwww.yidianzixun.com\u002Fchannel\u002Fm1020119?s=13&appid=yidian&ver=7.0.7.0&utk=zocp53pz)[大众日报网易号](https:\u002F\u002Fc.m.163.com\u002Fnews\u002Fsub\u002FT1526373341687.html?spss=newsapp&spsnuid=&spsdevid=MGMyYmZlZWY2NzYwOGY2Zl84ZjA2NmM4ODVkMzRfdml2b19WMTgyNEE%253D&spsvid=OGYwNjZjODg1ZDM0YjUyMjdiYjJhOWIyYjNmYTcyYWYyNDNiZTRlMzMyYzM3ZGY1ZGJiZDQ2OTE1M2I3OGQzYw%253D%253D&spsshare=default&spsts=1714296476804&spstoken=KGhAyb%2B3pPS4WM%2FalHfZNnEDofPHvtgCFsevCX%2BVHM1lML3vK5IIMoZD9%2FDbd1fabQ8n42RV2o1y%2BTBNLybXBw%3D%3D)\n\n[大众日报 微信 ![Image 8](https:\u002F\u002Fimage.dzplus.dzng.com\u002F2024\u002F04\u002F18\u002F1713422420ot72poqm39iimage.png)微信扫码 关注微信公众号](https:\u002F\u002Fdzrb.dzng.com\u002Fvideos\u002F0\u002FNEWS3602505MCPFVAXRGDUGH)[果然视频 抖音 ![Image 9](https:\u002F\u002Fimage.dzplus.dzng.com\u002F2024\u002F04\u002F18\u002F1713422420fglbbvp2eriimage.png)抖音扫码 关注抖音号](https:\u002F\u002Fdzrb.dzng.com\u002Fvideos\u002F0\u002FNEWS3602505MCPFVAXRGDUGH)[海报新闻 抖音 ![Image 10](https:\u002F\u002Fimage.dzplus.dzng.com\u002F2024\u002F04\u002F18\u002F171342242007t2njx4i1n8image.png)抖音扫码 关注抖音号](https:\u002F\u002Fdzrb.dzng.com\u002Fvideos\u002F0\u002FNEWS3602505MCPFVAXRGDUGH)[齐鲁晚报 微博 ![Image 11](https:\u002F\u002Fimage.dzplus.dzng.com\u002F2024\u002F04\u002F18\u002F1713422420tjfabmrwhsfimage.png)微信扫码 关注微博号](https:\u002F\u002Fdzrb.dzng.com\u002Fvideos\u002F0\u002FNEWS3602505MCPFVAXRGDUGH)[半岛都市报 微博 ![Image 12](https:\u002F\u002Fimage.dzplus.dzng.com\u002F2024\u002F04\u002F18\u002F17134224205ii632993ayimage.png)微信扫码 关注微博号](https:\u002F\u002Fdzrb.dzng.com\u002Fvideos\u002F0\u002FNEWS3602505MCPFVAXRGDUGH)[齐鲁壹点 学习强国 ![Image 13](https:\u002F\u002Fimage.dzplus.dzng.com\u002F2024\u002F04\u002F18\u002F17134224205ermw4jgt77image.png)微信扫码 关注学习强国](https:\u002F\u002Fdzrb.dzng.com\u002Fvideos\u002F0\u002FNEWS3602505MCPFVAXRGDUGH)\n\n[鲁ICP备11011784号-3](https:\u002F\u002Fbeian.miit.gov.cn\u002F#\u002FIntegrated\u002Findex)鲁公网安备 37010202001823号 大众报业集团 版权所有(C)All Rights Reserved 2026\n\n[](https:\u002F\u002Fss.knet.cn\u002Fverifyseal.dll?sn=e230824370100855450wpz4609&pa=0.4414261436616874)[](https:\u002F\u002Fcyberpolice.mps.gov.cn\u002F#\u002F)[](https:\u002F\u002Fwww.12377.cn\u002F)[](https:\u002F\u002Fwww.12377.cn\u002Fnode_548446.htm)[](https:\u002F\u002Fwww.shdf.gov.cn\u002Fshdf\u002Fchannels\u002F740.html)[](http:\u002F\u002Fggfw.cnipa.gov.cn:8010\u002FPatentCMS_Center\u002F)\n\n[顶部](https:\u002F\u002Fdzrb.dzng.com\u002Fvideos\u002F0\u002FNEWS3602505MCPFVAXRGDUGH)","大众日报农村大众记者 刘真真 2026-08-12","2026-08-17T00:00:00Z","报道",10,false,72,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},22,20,14,11,5,1,"报道山东省农科院选育的葡萄新品种‘锦蜜’通过登记并纳入省级主导品种，具有省级产业影响，信息具体，来源为省级官媒，但时效性稍差。",[25],{"name":10,"url":6},[27,28,29,30],"山东省农科院","主导品种","葡萄","锦蜜",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},"B2","fruit","果树","\u002Ftopic\u002Fhorticulture\u002Ffruit","B",[],{"status":39,"locked":14,"version":40,"method":41,"evidence":42},"classified","2026-10-22.2","rules",{"candidates":43,"agricultural_evidence":46},[44,50,57],{"code":32,"score":45,"supported":46,"title":47,"abstract":48,"tags":49},12,true,[29],[29],[29],{"code":51,"score":52,"supported":46,"title":53,"abstract":54,"tags":56},"G2",3,[],[55],"家庭农场",[],{"code":58,"score":22,"supported":14,"title":59,"abstract":60,"tags":61},"F1",[],[],[28],[63,64],"山东省农科院 主导品种 葡萄 锦蜜","山东省农科院 主导品种","山东省农科院主导品种葡萄锦蜜-662",6,"2026-08-17T23:54:54.685442Z",{"total":66,"page":22,"page_size":66,"items":69},[70,117,184,263,336,377],{"id":71,"title":72,"url":73,"summary":74,"summary_zh":8,"content":75,"source_name":76,"source_url":8,"published_at":77,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":78,"score_detail":79,"sources":84,"tags":86,"primary_topic":91,"secondary_topics":92,"classification":93,"search_phrases":111,"slug":114,"view_count":115,"doi":8,"paper":8,"created_at":116},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":80,"substance":81,"depth":82,"authority":82,"freshness":66,"relevant":22,"comment":83},16,17,13,"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。",[85],{"name":76,"url":73},[87,88,29,89,90],"智慧农业","智能农机","栽培技术","国际交流",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":14,"version":40,"method":41,"evidence":94},{"candidates":95,"agricultural_evidence":46},[96,100,106],{"code":32,"score":45,"supported":46,"title":97,"abstract":98,"tags":99},[29],[29],[29],{"code":101,"score":102,"supported":46,"title":103,"abstract":104,"tags":105},"I1",4,[],[87],[87],{"code":107,"score":22,"supported":14,"title":108,"abstract":109,"tags":110},"F5",[],[],[88],[112,113],"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":118,"title":119,"url":120,"summary":121,"summary_zh":122,"content":8,"source_name":123,"source_url":120,"published_at":124,"category":125,"cover_url":8,"hotness":13,"is_selected":14,"score":126,"score_detail":127,"sources":132,"tags":134,"primary_topic":138,"secondary_topics":139,"classification":140,"search_phrases":159,"slug":162,"view_count":52,"doi":163,"paper":164,"created_at":183},3255,"Grape yield estimation using on-the-fly MIMO millimeter-wave radar at operational field speed: A variety-dependent proof of concept","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112395","Accurate pre-harvest grape yield estimation is a critical challenge in precision viticulture, yet current optical approaches (RGB cameras, LiDAR) are fundamentally limited by foliage occlusion and sensitivity to ambient lighting conditions. This paper presents a ground-based grape yield estimation system using a dual 77 GHz Multiple-Input Multiple-Output (MIMO) Frequency-Modulated Continuous-Wave (FM-CW) radar mounted on a rover operating at an average speed of 1.0 m\u002Fs (3.7 km\u002Fh), matching practical vineyard tractor speeds. Unlike prior radar-based studies conducted in static or slow-moving setups, the proposed pipeline achieves continuous 3D reconstruction of vinerows through digital beamforming in the elevation plane, combined with an IMU-fused Kalman filter for point cloud stabilization on irregular terrain. An experimental campaign was conducted on 136 km of scanned vinerows across seven grape varieties and three phenological growth stages (BBCH 75–89) in a commercial vineyard in Gascony, France. Statistical features extracted from 3D radar echo level images are used to train a Support Vector Regressor (SVR) evaluated in cross-validation. The primary out-of-sample result is a cross-validation Mean Absolute Error (CV MAE) of 31.2% on the full multi-variety dataset without any defoliation, achieved against certified wine-vat bulk weights as the ground truth reference. This figure should be contextualized against the ∼ 24–25% discrepancy observed between portable field weighing plates and vat-certified weights across the same dataset, and against manual pre-harvest estimation errors routinely exceeding 30% in viticultural practice. A sensitivity analysis over physical parameters reveals that grape variety is the dominant −and limiting- source of performance heterogeneity: CV MAE ranges from 7% for Tannat to 69% for Baco, demonstrating that a single global model is insufficient for multi-variety deployment and that variety-specific calibration is a necessary condition for operational use. These results are best understood as an architectural proof of concept: the primary contribution is the demonstration that MIMO digital beamforming removes the speed bottleneck of prior mechanically-scanned radar systems, enabling gapless 3D vinerow reconstruction at practical field speeds. The yield estimation results provide a first quantitative characterization of the system’s sensing capability and its variety-dependent limitations and establish a baseline for future variety-specific model development.","准确的采前葡萄产量估测是精准葡萄栽培中的一项关键挑战，然而当前的光学方法（RGB相机、LiDAR）从根本上受到冠层遮挡和对环境光照条件敏感性的限制。本文提出了一种地基葡萄产量估测系统，采用双77 GHz多输入多输出（MIMO）调频连续波（FM-CW）雷达，搭载于以平均速度1.0 m\u002Fs（3.7 km\u002Fh）行驶的移动平台上，与实际葡萄园拖拉机作业速度相匹配。与先前在静态或慢速移动装置中进行的雷达研究不同，所提出的处理流程通过仰角平面上的数字波束成形实现葡萄行连续三维重建，并结合IMU融合卡尔曼滤波器在不规则地形上实现点云稳定。在法国加斯科尼的一个商业葡萄园中，对七个葡萄品种和三个物候生长期（BBCH 75–89）的136 km扫描葡萄行进行了实验。从三维雷达回波强度图像中提取的统计特征用于训练支持向量回归器（SVR），并通过交叉验证进行评估。主要样本外结果为：在完整多品种数据集上、未进行任何去叶处理的情况下，交叉验证平均绝对误差（CV MAE）为31.2%，以认证酒罐散装重量作为地面真值参考。该数值应结合以下背景加以理解：在同一数据集上，便携式田间称重板与酒罐认证重量之间观察到约24–25%的差异，而葡萄栽培实践中人工采前估测误差通常超过30%。对物理参数的敏感性分析表明，葡萄品种是性能异质性的主要——也是限制性——来源：CV MAE从Tannat的7%到Baco的69%不等，表明单一全局模型不足以支持多品种部署，品种特异性校准是实际应用的必要条件。这些结果最好被理解为一种架构层面的概念验证：主要贡献在于证明了MIMO数字波束成形消除了先前机械扫描雷达系统的速度瓶颈，从而能够在实际田间速度下实现无间隙三维葡萄行重建。产量估测结果首次定量表征了该系统的感知能力及其品种依赖性局限，并为未来","Computers and Electronics in Agriculture","2026-09-23T00:00:00Z","论文",84,{"impact":128,"substance":129,"depth":130,"authority":19,"freshness":13,"relevant":22,"comment":131},18,23,19,"首次在实用田间车速下用MIMO毫米波雷达实现葡萄产量预估，136公里商业园数据与品种依赖性结论具参考价值。",[133],{"name":123,"url":120},[87,135,29,136,137],"精准农业","产量预估","毫米波雷达",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":14,"version":40,"method":41,"evidence":141},{"candidates":142,"agricultural_evidence":46},[143,149,154],{"code":32,"score":144,"supported":46,"title":145,"abstract":147,"tags":148},15,[146],"grape",[29,146],[29],{"code":107,"score":52,"supported":46,"title":150,"abstract":151,"tags":153},[],[152],"tractor",[],{"code":101,"score":155,"supported":14,"title":156,"abstract":157,"tags":158},2,[],[],[87,135],[160,161],"MIMO 毫米波雷达 葡萄 产量预估","葡萄园 雷达 三维重建","MIMO毫米波雷达葡萄产量预估-3255","10.1016\u002Fj.compag.2026.112395",{"doi":163,"openalex_id":165,"authors":166,"venue":123,"cited_by_count":115,"oa_url":120,"card":176,"direction":180,"ingested_from":182},"W7214043753",[167,170,173],{"name":168,"orcid":169},"Etienne Dedic","https:\u002F\u002Forcid.org\u002F0000-0002-1414-019X",{"name":171,"orcid":172},"Dominique Henry","https:\u002F\u002Forcid.org\u002F0000-0002-6016-140X",{"name":174,"orcid":175},"H. Aubert","https:\u002F\u002Forcid.org\u002F0000-0002-6113-0648",{"tldr":177,"method":178,"finding":179,"direction":180,"opportunity":181},"用双77GHz MIMO雷达在1m\u002Fs车速下重建葡萄藤行并估算产量，验证品种依赖性。","双77GHz MIMO FMCW雷达、数字波束成形、IMU卡尔曼滤波、SVR，1","全品种交叉验证MAE为31.2%，但品种间差异大（Tannat 7%至Baco 69%），需按品种校","农业遥感与作物表型","可研究品种自适应建模与迁移学习，解决多品种部署时单一模型失效问题，并融合光学与雷达数据。","openalex","2026-09-23T23:30:01.516727Z",{"id":185,"title":186,"url":187,"summary":188,"summary_zh":189,"content":8,"source_name":190,"source_url":187,"published_at":191,"category":125,"cover_url":8,"hotness":13,"is_selected":14,"score":192,"score_detail":193,"sources":196,"tags":198,"primary_topic":202,"secondary_topics":203,"classification":210,"search_phrases":241,"slug":244,"view_count":155,"doi":245,"paper":246,"created_at":262},2874,"Laboratory Evaluation of Multispectral Grape Quality Grade Prediction with Compensation for Controlled Illumination Variation","https:\u002F\u002Fdoi.org\u002F10.1088\u002F2631-8695\u002Faea952","Abstract Accurate fruit quality assessment is important for selective harvesting in agricultural robotics, where multispectral sensing provides a non-destructive approach but remains sen- sitive to variability in illumination conditions. This study presents a controlled laboratory evaluation conducted in a dark box under halogen illumination with fixed sensor and sam- ple geometry, in which illumination variation was simulated by adjusting lamp intensity. Prediction models for visually assigned grape quality grades were first established under fixed illumination using an AS7265x multispectral sensor with 18 channels from 410 to 940 nm, covering the visible and part of the near-infrared range. Spectral data were prepro- cessed using standard normal variate transformation, standardization, variable importance in projection feature selection, and mixup interpolation. Three machine learning meth- ods, partial least squares regression, support vector regression, and random forest, were evaluated with nested cross-validation, out-of-fold prediction, and 2000-iteration bootstrap resampling. Support vector regression achieved the best performance, with R² = 0.9084 [95% CI: 0.851–0.945], RMSE = 0.3352, and MAE = 0.2374. To address illumination vari- ability, three compensation methods, direct standardization, extended multiplicative scatter correction, and a polynomial per-band fitting method, were implemented and compared across five lamp intensity levels from 20% to 100% of rated power. The three methods and the uncompensated condition reached similar mean accuracy across the five levels, with the exception of extended multiplicative scatter correction, which was lower at every level. Di- rect standardization reduced the spread of the five predictions obtained for the same berry by about 31% relative to no compensation, and gave the highest grade-level accuracy of the four conditions. These results provide laboratory feasibility evidence that direct standard- ization can improve the consistency of grade prediction across controlled illumination levels, and establish a basis for further validation under natural field illumination toward future robotic harvesting applications.","摘要 准确的水果品质评估对于农业机器人中的选择性采收至关重要，其中多光谱传感提供了一种非破坏性方法，但仍对光照条件的变化较为敏感。本研究提出了一种在暗箱中、卤素灯照明下、传感器与样品几何构型固定的受控实验室评估方法，通过调节灯强度来模拟光照变化。首先在固定光照条件下，使用AS7265x多光谱传感器（具有410至940 nm范围内的18个通道，覆盖可见光及部分近红外波段）建立了视觉 assigned 葡萄品质等级的预测模型。光谱数据采用标准正态变量变换、标准化、投影变量重要性特征选择以及mixup插值进行预处理。采用嵌套交叉验证、折外预测和2000次迭代自助重采样，对偏最小二乘回归、支持向量回归和随机森林三种机器学习方法进行了评估。支持向量回归取得了最佳性能，R² = 0.9084 [95% CI: 0.851–0.945]，RMSE = 0.3352，MAE = 0.2374。为解决光照变化问题，实施了直接标准化、扩展多元散射校正和逐波段多项式拟合三种补偿方法，并在额定功率20%至100%的五个灯强度水平下进行了比较。三种方法及未补偿条件在五个水平下达到了相似的平均准确率，但扩展多元散射校正除外，其在每个水平下均较低。与未补偿相比，直接标准化使同一浆果五次预测结果的离散度降低了约31%，并在四种条件中给出了最高的等级准确率。这些结果为直接标准化能够提高受控光照水平下等级预测的一致性提供了实验室可行性证据，并为未来机器人采收应用中在自然田间光照下进一步验证奠定了基础。","Engineering Research Express","2026-09-17T00:00:00Z",66,{"impact":194,"substance":18,"depth":81,"authority":82,"freshness":194,"relevant":22,"comment":195},8,"实验室条件下多光谱葡萄品质分级与光照补偿研究，方法扎实、结论可靠，但属实验室可行性验证，产业影响有限。",[197],{"name":190,"url":187},[87,199,29,200,201],"农业人工智能","多光谱检测","水果品质分级",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[204],{"code":205,"slug":206,"name":207,"path":208,"parent_code":209},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",{"status":39,"locked":14,"version":40,"method":41,"evidence":211},{"candidates":212,"agricultural_evidence":46},[213,217,222,230,237],{"code":32,"score":144,"supported":46,"title":214,"abstract":215,"tags":216},[146],[29,146],[29],{"code":205,"score":20,"supported":46,"title":218,"abstract":220,"tags":221},[219],"multispectral",[219],[],{"code":223,"score":224,"supported":46,"title":225,"abstract":226,"tags":229},"I2",7,[],[227,228],"机器学习","machine learning",[199],{"code":231,"score":66,"supported":46,"title":232,"abstract":233,"tags":236},"F6",[],[234,235],"农业机器人","robotic harvesting",[],{"code":101,"score":22,"supported":14,"title":238,"abstract":239,"tags":240},[],[],[87],[242,243],"多光谱 葡萄 品质分级","AS7265x 多光谱传感器","多光谱葡萄品质分级-2874","10.1088\u002F2631-8695\u002Faea952",{"doi":245,"openalex_id":247,"authors":248,"venue":190,"cited_by_count":115,"oa_url":187,"card":256,"direction":261,"ingested_from":182},"W7213509882",[249,251,253],{"name":250,"orcid":8},"Guodong Xiu",{"name":252,"orcid":8},"Sára Strakošová",{"name":254,"orcid":255},"Ikuo Mizuuchi","https:\u002F\u002Forcid.org\u002F0000-0003-4657-2613",{"tldr":257,"method":258,"finding":259,"direction":180,"opportunity":260},"在暗箱中评估多光谱葡萄品质分级预测，并比较三种光照补偿方法。","AS7265x多光谱传感器、SNV与VIP预处理、SVR\u002FRF建模、直接标准化等","SVR预测最佳（R²=0.9084）；直接标准化使同果预测离散度降低约31%。","可延伸至自然田间光照下的验证，并融合机器人采摘的实时多光谱分级系统。","农业人工智能与决策模型","2026-09-18T23:30:52.790038Z",{"id":264,"title":265,"url":266,"summary":267,"summary_zh":268,"content":8,"source_name":269,"source_url":266,"published_at":270,"category":125,"cover_url":8,"hotness":13,"is_selected":14,"score":271,"score_detail":272,"sources":275,"tags":277,"primary_topic":282,"secondary_topics":283,"classification":284,"search_phrases":296,"slug":299,"view_count":52,"doi":300,"paper":301,"created_at":335},2630,"Effects of microwave heating on concentration properties and quality attributes of blueberry–grape blended pulp","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffsufs.2026.1920261","Blended blueberry–grape pulp (BBGP) was concentrated using microwave heating concentration (MHC) to evaluate the effects of microwave intensity (2–6 W\u002Fg), blueberry-to-grape mass ratio (1:1–1:7), citric acid addition (0.2%–0.4%), and granulated sugar addition (10%–15%) on temperature, moisture content, anthocyanin retention ratio, soluble solids content, and sensory quality. Microwave intensity and blueberry-to-grape mass ratio each exhibited a biphasic effect on anthocyanin retention and sensory scores, with optimal levels around 4 W\u002Fg and 1:3 mass ratio, whereas soluble solids content remained unaffected by variations in these parameters or citric acid concentration. Citric acid addition enhanced anthocyanin stability but impaired palatability at excessive levels, while granulated sugar addition did not significantly influence anthocyanin retention yet effectively modulated soluble solids and sweet-sour balance, with 12.5% yielding the highest sensory performance. The recommended processing parameters for MHC of BBGP are 4–6 W\u002Fg, 1:3 blueberry-to-grape mass ratio, 0.3% citric acid, and 12.5% granulated sugar. These findings provide practical guidance for optimizing MHC processes to produce high-quality blended fruit concentrates such as BBGP.","采用微波加热浓缩（MHC）对蓝莓-葡萄混合果浆（BBGP）进行浓缩，以评估微波强度（2–6 W\u002Fg）、蓝莓与葡萄质量比（1:1–1:7）、柠檬酸添加量（0.2%–0.4%）和砂糖添加量（10%–15%）对温度、水分含量、花青素保留率、可溶性固形物含量和感官品质的影响。微波强度和蓝莓与葡萄质量比均对花青素保留率和感官评分表现出双相效应，最佳水平分别约为4 W\u002Fg和质量比1:3，而可溶性固形物含量不受这些参数或柠檬酸浓度变化的影响。添加柠檬酸增强了花青素稳定性，但过量会损害适口性；添加砂糖对花青素保留率无显著影响，但能有效调节可溶性固形物和酸甜平衡，其中12.5%的添加量获得最佳感官表现。BBGP微波加热浓缩的推荐工艺参数为：微波强度4–6 W\u002Fg、蓝莓与葡萄质量比1:3、柠檬酸0.3%、砂糖12.5%。这些发现为优化微波加热浓缩工艺以生产BBGP等高品质混合果汁浓缩液提供了实践指导。","Frontiers in Sustainable Food Systems","2026-09-15T00:00:00Z",63,{"impact":194,"substance":128,"depth":144,"authority":82,"freshness":273,"relevant":22,"comment":274},9,"蓝莓葡萄复合果浆微波浓缩工艺优化的实证研究，给出可落地的参数组合，对果蔬加工与品质保持有参考价值，但属细分领域技术论文，公共影响有限。",[276],{"name":269,"url":266},[278,279,29,280,281],"农产品加工","花青素","蓝莓","微波浓缩",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":14,"version":40,"method":41,"evidence":285},{"candidates":286,"agricultural_evidence":46},[287,291],{"code":32,"score":80,"supported":46,"title":288,"abstract":289,"tags":290},[146],[29,146],[29,280],{"code":292,"score":22,"supported":14,"title":293,"abstract":294,"tags":295},"E1",[],[],[278],[297,298],"农产品加工 微波浓缩 花青素 葡萄","农产品加工 微波浓缩","农产品加工微波浓缩花青素葡萄-2630","10.3389\u002Ffsufs.2026.1920261",{"doi":300,"openalex_id":302,"authors":303,"venue":269,"cited_by_count":115,"oa_url":266,"card":329,"direction":333,"ingested_from":182},"W7213252471",[304,306,308,311,313,315,317,319,321,323,325,327],{"name":305,"orcid":8},"Xinglong Zhao",{"name":307,"orcid":8},"A. Wangze",{"name":309,"orcid":310},"Yuhan Zhang","https:\u002F\u002Forcid.org\u002F0009-0009-0505-6322",{"name":312,"orcid":8},"Chunhao Kan",{"name":314,"orcid":8},"Yuedong Wang",{"name":316,"orcid":8},"Chenghai Liu",{"name":318,"orcid":8},"Chai Liu",{"name":320,"orcid":8},"Wei Zhao",{"name":322,"orcid":8},"Gang Shi",{"name":324,"orcid":8},"Chao Ma",{"name":326,"orcid":8},"Li Xi",{"name":328,"orcid":8},"Jie Jiang",{"tldr":330,"method":331,"finding":332,"direction":333,"opportunity":334},"研究微波加热浓缩蓝莓-葡萄混合果浆的工艺参数对品质的影响。","微波加热浓缩，考察微波强度、配比、柠檬酸和糖添加量。","最佳工艺为4-6 W\u002Fg、1:3配比、0.3%柠檬酸、12.5%糖，花青素保留和感官最佳。","其他","可探索微波浓缩中花青素降解动力学与在线监测，结合智能控制优化品质。","2026-09-16T23:30:07.980146Z",{"id":337,"title":338,"url":339,"summary":340,"summary_zh":8,"content":8,"source_name":341,"source_url":8,"published_at":342,"category":125,"cover_url":8,"hotness":13,"is_selected":14,"score":192,"score_detail":343,"sources":345,"tags":347,"primary_topic":351,"secondary_topics":352,"classification":353,"search_phrases":364,"slug":367,"view_count":52,"doi":8,"paper":368,"created_at":376},2396,"[预印本]Multi-Task Learning for Sparsely-Labeled Time Series: A Case Study on Cold-Hardiness Modeling","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.09062","arXiv 2609.09062（2026-09-10）。研究针对葡萄抗寒性的时间序列过程建模问题（数据有限且标签时序稀疏），提出基于RNN的多任务学习方法。实验证明某些MTL架构优于单任务学习和现有科学模型，并在相关萌芽期预测任务上展现良好潜力。","arXiv | 2026-09-10","2026-09-10T00:00:00Z",{"impact":45,"substance":128,"depth":80,"authority":45,"freshness":194,"relevant":22,"comment":344},"预印本提出RNN多任务学习用于葡萄抗寒性稀疏标签时序建模，方法新颖但尚属早期研究，产业影响有限，可作为农业AI前沿动态收录。",[346],{"name":341,"url":339},[199,348,29,349,350],"预印本","抗寒育种","时间序列",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":14,"version":40,"method":41,"evidence":354},{"candidates":355,"agricultural_evidence":46},[356,360],{"code":32,"score":102,"supported":46,"title":357,"abstract":358,"tags":359},[],[29],[29],{"code":223,"score":22,"supported":14,"title":361,"abstract":362,"tags":363},[],[],[199],[365,366],"农业人工智能 抗寒育种 时间序列 预印本","农业人工智能 抗寒育种","农业人工智能抗寒育种时间序列预印本-2396",{"doi":8,"openalex_id":8,"authors":369,"venue":8,"cited_by_count":115,"oa_url":8,"card":370,"direction":261,"ingested_from":375},[],{"tldr":371,"method":372,"finding":373,"direction":261,"opportunity":374},"提出RNN多任务学习方法，用于标签稀疏的葡萄抗寒时间序列建模。","基于RNN的多任务学习，处理有限且时序稀疏的标签数据。","部分MTL架构优于单任务学习和现有科学模型，并利于萌芽期预测。","可探索多任务学习在更多稀疏标签农业时序场景（如病虫害、物候）中的迁移与泛化。","agent","2026-09-14T00:06:33.014967Z",{"id":378,"title":379,"url":380,"summary":381,"summary_zh":382,"content":8,"source_name":123,"source_url":380,"published_at":383,"category":125,"cover_url":8,"hotness":13,"is_selected":14,"score":384,"score_detail":385,"sources":387,"tags":389,"primary_topic":391,"secondary_topics":392,"classification":398,"search_phrases":419,"slug":422,"view_count":52,"doi":423,"paper":424,"created_at":449},1278,"ERG-Mask: An edge–region collaborative instance segmentation model for greenhouse table-grape clusters","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112369","ERG-Mask: An edge–region collaborative instance segmentation model for greenhouse table-grape clusters。Computers and Electronics in Agriculture","ERG-Mask：面向温室鲜食葡萄果串的边缘-区域协同实例分割模型。《Computers and Electronics in Agriculture》","2026-08-31T00:00:00Z",62,{"impact":45,"substance":128,"depth":80,"authority":19,"freshness":155,"relevant":22,"comment":386},"针对温室葡萄簇的实例分割新方法，发表于核心期刊，技术有创新性，但影响范围限于细分领域，时效性较低。",[388],{"name":123,"url":380},[87,199,390,29],"设施农业",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[393],{"code":394,"slug":395,"name":396,"path":397,"parent_code":36},"B7","protected-horticulture","设施园艺与植物工厂","\u002Ftopic\u002Fhorticulture\u002Fprotected-horticulture",{"status":39,"locked":14,"version":40,"method":41,"evidence":399},{"candidates":400,"agricultural_evidence":46},[401,405,411,415],{"code":32,"score":144,"supported":46,"title":402,"abstract":403,"tags":404},[146],[29,146],[29],{"code":394,"score":19,"supported":46,"title":406,"abstract":408,"tags":410},[407],"greenhouse",[409,407],"温室",[],{"code":101,"score":22,"supported":14,"title":412,"abstract":413,"tags":414},[],[],[87],{"code":223,"score":22,"supported":14,"title":416,"abstract":417,"tags":418},[],[],[199],[420,421],"农业人工智能 智慧农业 设施农业 葡萄","农业人工智能 智慧农业","农业人工智能智慧农业设施农业葡萄-1278","10.1016\u002Fj.compag.2026.112369",{"doi":423,"openalex_id":425,"authors":426,"venue":123,"cited_by_count":115,"oa_url":8,"card":444,"direction":261,"ingested_from":182},"W7204777248",[427,430,433,436,438,441],{"name":428,"orcid":429},"Zhengtong Ning","https:\u002F\u002Forcid.org\u002F0000-0002-9218-6425",{"name":431,"orcid":432},"Jian Li","https:\u002F\u002Forcid.org\u002F0000-0002-4187-317X",{"name":434,"orcid":435},"Haidong Li","https:\u002F\u002Forcid.org\u002F0000-0002-6634-9593",{"name":437,"orcid":8},"Liangkuan Zhu",{"name":439,"orcid":440},"Qingjie Wang","https:\u002F\u002Forcid.org\u002F0009-0001-9038-7821",{"name":442,"orcid":443},"Yi Wang","https:\u002F\u002Forcid.org\u002F0000-0002-0192-3195",{"tldr":445,"method":446,"finding":447,"direction":261,"opportunity":448},"提出ERG-Mask模型，用于温室鲜食葡萄串的实例分割，提升边缘与区域协同精度。","结合边缘与区域信息的协同实例分割模型，基于深度学习。","ERG-Mask在葡萄串分割上优于现有方法，精度更高。","可探索该模型在复杂遮挡、不同光照下的鲁棒性，或扩展至其他簇状果实（如番茄、蓝莓）的检测。","2026-09-01T23:30:01.626379Z"]