[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2274":3,"related-2274":94},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":8,"source_name":9,"source_url":8,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":15,"sources":22,"tags":24,"primary_topic":30,"secondary_topics":36,"classification":43,"search_phrases":78,"slug":81,"view_count":82,"doi":8,"paper":83,"created_at":93},2274,"ArXiv 2609.10469 AgroVisNet:轻量化卷积网络及萝卜-马铃薯-葫芦病害诊断基准","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.10469","提出AgroVisNet紧凑型卷积网络及专家验证基准BD-PlantDX,包含孟加拉国Bogura和Nilphamari地区12类萝卜、土豆、葫芦共12432张田间图像。模型参数仅29万,测试精度99.52%,加权F1 99.52%,部署后量化0.46MB,CPU推理8.40ms\u002F张。",null,"arXiv 2609.10469","2026-09-08T16:00:00Z","论文",10,false,77,{"impact":16,"substance":17,"depth":16,"authority":18,"freshness":19,"relevant":20,"comment":21},18,22,13,6,1,"提出29万参数轻量卷积网络与万余张田间病害基准数据集，量化后仅0.46MB、CPU单张8.4ms，对低成本边缘部署的作物病害诊断有实用参考价值。",[23],{"name":9,"url":6},[25,26,27,28,29],"智慧农业","农业人工智能","边缘计算","植物病害识别","轻量化模型",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},"B1","vegetables","蔬菜","\u002Ftopic\u002Fhorticulture\u002Fvegetables","B",[37],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},"A5","tubers-grains","薯类与杂粮","\u002Ftopic\u002Ffield-crops\u002Ftubers-grains","A",{"status":44,"locked":13,"version":45,"method":46,"evidence":47},"classified","2026-10-22.2","rules",{"candidates":48,"agricultural_evidence":51},[49,56,62,68,73],{"code":31,"score":50,"supported":51,"title":52,"abstract":54,"tags":55},11,true,[53],"萝卜",[53],[],{"code":38,"score":57,"supported":51,"title":58,"abstract":60,"tags":61},8,[59],"马铃薯",[],[],{"code":63,"score":64,"supported":13,"title":65,"abstract":66,"tags":67},"I2",3,[],[],[26,28,29],{"code":69,"score":20,"supported":13,"title":70,"abstract":71,"tags":72},"I1",[],[],[25],{"code":74,"score":20,"supported":13,"title":75,"abstract":76,"tags":77},"I5",[],[],[27],[79,80],"农业人工智能 植物病害识别 轻量化模型 智慧农业","农业人工智能 植物病害识别","农业人工智能植物病害识别轻量化模型智慧农业-2274",2,{"doi":8,"openalex_id":8,"authors":84,"venue":8,"cited_by_count":85,"oa_url":8,"card":86,"direction":90,"ingested_from":92},[],0,{"tldr":87,"method":88,"finding":89,"direction":90,"opportunity":91},"提出轻量卷积网络AgroVisNet及萝卜、马铃薯、葫芦病害诊断基准BD-PlantDX。","构建12432张田间图像基准，设计29万参数紧凑CNN并量化部署。","测试精度99.52%，量化后仅0.46MB，CPU推理8.40ms\u002F张。","农业人工智能与决策模型","可探索跨地区跨作物泛化、田间复杂光照下的轻量模型鲁棒性与边缘部署。","agent","2026-09-13T00:04:05.295687Z",{"total":19,"page":20,"page_size":19,"items":95},[96,154,211,262,332,395],{"id":97,"title":98,"url":99,"summary":100,"summary_zh":8,"content":101,"source_name":102,"source_url":8,"published_at":8,"category":103,"cover_url":8,"hotness":12,"is_selected":13,"score":104,"score_detail":105,"sources":109,"tags":111,"primary_topic":116,"secondary_topics":117,"classification":124,"search_phrases":149,"slug":152,"view_count":85,"doi":8,"paper":8,"created_at":153},5113,"中国农科院蔬菜花卉所揭示假单胞菌通过代谢重编程赋予马铃薯耐盐性新机制","https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fkyhd\u002F0015064067524be58625da97b466f754.htm","中国农业科学院蔬菜花卉研究所马铃薯遗传育种与栽培创新团队联合国内高校,揭示特异假单胞菌通过代谢重编程赋予马铃薯耐盐性的新机制,相关研究成果发表在《npj Biofilms and Microbiomes》上。研究对117份二倍体马铃薯材料开展耐盐评价与根际微生物组分析,发现耐盐马铃薯材料在盐胁迫条件下可富集更多存在互作关联的细菌类群,且假单胞菌丰度显著提高。研究进一步分离得到耐盐促生特异假单胞菌株,该菌株既可促进耐盐马铃薯在盐渍土壤中生长,也可提升盐敏感马铃薯的耐盐能力,初步证实其可激活苯丙烷生物合成等防御相关通路。","[English](https:\u002F\u002Fwww.caas.cn\u002Fen)[邮箱](https:\u002F\u002Fmail.caas.cn\u002F)[数字农科院](https:\u002F\u002Fi.caas.cn\u002F)[](https:\u002F\u002Fcaas.cn\u002Fcms\u002Fweb\u002Fsearch\u002Findex.jsp?siteID=cdb01dceb46e48488945d4465e90f221&aba=)\n\n官方微信 \n\n![Image 2](https:\u002F\u002Fcaas.cn\u002Fimages\u002F2023-01\u002F020ac4d3d8b6451782a8702c72604336.jpg)农科专家在线微信公众号\n\n![Image 3](https:\u002F\u002Fcaas.cn\u002Fimages\u002F2023-01\u002Fbf6579e4651e437db31a22cd2249b319.jpg)中国农科院微信公众号\n\n[![Image 4](https:\u002F\u002Fcaas.cn\u002Fstatic2022\u002Fimages\u002Fmenu_logo.png)](https:\u002F\u002Fcaas.cn\u002Findex.htm)\n\n*   [组织机构](https:\u002F\u002Fcaas.cn\u002Fzzjg\u002Findex.htm)[走进中国农科院](https:\u002F\u002Fcaas.cn\u002Fzzjg\u002Fzjnky\u002Findex.htm)[寄语](https:\u002F\u002Fcaas.cn\u002Fzzjg\u002Fyczc\u002Findex.htm)[院章程](https:\u002F\u002Fcaas.cn\u002Fzzjg\u002Fzgnykxyzc\u002Findex.htm)[院领导](https:\u002F\u002Fcaas.cn\u002Fzzjg\u002Fyld\u002Findex.htm)[历任领导](https:\u002F\u002Fcaas.cn\u002Fzzjg\u002Flrld\u002Findex.htm)[组织架构](https:\u002F\u002Fcaas.cn\u002Fzzjg\u002Fzzjg\u002Findex.htm)[院机关](https:\u002F\u002Fcaas.cn\u002Fzzjg\u002Fyjg\u002Findex.htm)[院属单位](https:\u002F\u002Fcaas.cn\u002Fzzjg\u002Fysdw\u002Findex.htm)[区域创新中心](https:\u002F\u002Fcaas.cn\u002Fzzjg\u002Fqycxzx\u002Findex.htm) \n*   [新闻中心](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Findex.htm)[图片新闻](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Ftpxw\u002Findex.htm)[时政要闻](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fszyw\u002Findex.htm)[农科要闻](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fnkyw\u002Findex.htm)[科研活动](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fkyhd\u002Findex.htm)[三农一线](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fhzdznew\u002Findex.htm)[媒体报道](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fmtxw\u002Findex.htm)[视频农科](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fspnk\u002Findex.htm)[政务新媒体矩阵](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fzwxmtjz\u002Findex.htm) \n*   [科学研究](https:\u002F\u002Fcaas.cn\u002Fkxyj\u002Findex.htm)[重大成果](https:\u002F\u002Fcaas.cn\u002Fkxyj\u002Fzdcgzs\u002Findex.htm)[科研进展](https:\u002F\u002Fcaas.cn\u002Fkxyj\u002Fkyjz\u002Findex.htm)[科技创新](https:\u002F\u002Fcaas.cn\u002Fkxyj\u002Fkjcx\u002Findex.htm)[科技奖励](https:\u002F\u002Fcaas.cn\u002Fkxyj\u002Fkjjl\u002Findex.htm)[农业高端智库](https:\u002F\u002Fcaas.cn\u002Fkxyj\u002Fnygdzk\u002Findex.htm)[中国农科院重大科学发现](https:\u002F\u002Fcaas.cn\u002Fkxyj\u002Fzgnkyzdkxfx\u002Findex.htm)[中国农科院重大产品创制、重大技术突破和重大智库报告](https:\u002F\u002Fcaas.cn\u002Fkxyj\u002Fjstpzkbg\u002Findex.htm)[中国农科院重大科技任务布局](https:\u002F\u002Fcaas.cn\u002Fkxyj\u002Fzgnkyzdkjrwbj\u002Findex.htm)[中国农科院十大科研进展](https:\u002F\u002Fcaas.cn\u002Fkxyj\u002Fzgnkysdkyjz\u002Findex.htm) \n*   [科技支撑](https:\u002F\u002Fcaas.cn\u002Fkjzc\u002Findex.htm)[主推成果](https:\u002F\u002Fcaas.cn\u002Fkjzc\u002Fcgzhfw\u002Findex.htm)[产业专家团](https:\u002F\u002Fcaas.cn\u002Fkjzc\u002Fcyzjt\u002Findex.htm) \n*   [人才教育](https:\u002F\u002Fcaas.cn\u002Frcjy\u002Findex.htm)[人才队伍概况](https:\u002F\u002Fcaas.cn\u002Frcjy\u002Frcgk\u002Findex.htm)[人才工作概述](https:\u002F\u002Fcaas.cn\u002Frcjy\u002Frcgzgs\u002Findex.htm)[专家学者](https:\u002F\u002Fcaas.cn\u002Frcjy\u002Fzjxz\u002Findex.htm)[人才动态](https:\u002F\u002Fcaas.cn\u002Frcjy\u002Frcdtnew\u002Findex.htm)[研究生教育](https:\u002F\u002Fgs.caas.cn\u002F)[中国农科院人才招聘网](https:\u002F\u002Fzhaopin.caas.cn\u002F#\u002F) \n*   [国际合作](https:\u002F\u002Fcaas.cn\u002Fgjhz\u002Findex.htm)[总体概况](https:\u002F\u002Fcaas.cn\u002Fgjhz\u002Fgjhzgk\u002Findex.htm)[合作伙伴](https:\u002F\u002Fcaas.cn\u002Fgjhz\u002Fhzhb\u002Findex.htm)[合作平台](https:\u002F\u002Fcaas.cn\u002Fgjhz\u002Fhzpt\u002Findex.htm)[合作机制](https:\u002F\u002Fcaas.cn\u002Fgjhz\u002Fhzzz\u002Findex.htm)[国际农业科学计划](https:\u002F\u002Fcaas.cn\u002Fgjhz\u002Fgjnykxjh\u002Findex.htm)[中国农科院年报](https:\u002F\u002Fcaas.cn\u002Fgjhz\u002Fzgnkynb\u002Findex.htm) \n*   [平台基地](https:\u002F\u002Fcaas.cn\u002Fptjd\u002Findex.htm)[资源概况](https:\u002F\u002Fcaas.cn\u002Fptjd\u002Fzygk\u002Findex.htm)[平台](https:\u002F\u002Fcaas.cn\u002Fptjd\u002Fptq\u002Findex.htm)[基地](https:\u002F\u002Fcaas.cn\u002Fptjd\u002Fjd\u002Findex.htm) \n*   [信息服务](https:\u002F\u002Fcaas.cn\u002Fxxfw\u002Findex.htm)[资源服务](https:\u002F\u002Fcaas.cn\u002Fxxfw\u002Fzyfw\u002Findex.htm)[数字农科院](https:\u002F\u002Fcaas.cn\u002Fxxfw\u002Fsznky\u002Findex.htm)[农业科研信息化典型案例](https:\u002F\u002Fwww.caas.cn\u002Fzt\u002Fxxhbp_0\u002Fnykyxxhdxa_0\u002Findex.htm) \n*   [党建文化](https:\u002F\u002Fdw.caas.cn\u002F)\n\n![Image 5](https:\u002F\u002Fcaas.cn\u002Fstatic2022\u002Fimages\u002Flogo_s03.png)[](https:\u002F\u002Fcaas.cn\u002Findex.htm)[](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Findex.htm)\n\n[返回门户首页](https:\u002F\u002Fcaas.cn\u002Findex.htm)[数字农科院](https:\u002F\u002Fi.caas.cn\u002F)[邮箱](https:\u002F\u002Fmail.caas.cn\u002F)\n\n官方微信 \n\n![Image 6](https:\u002F\u002Fcaas.cn\u002Fimages\u002F2023-01\u002F020ac4d3d8b6451782a8702c72604336.jpg)农科专家在线微信公众号\n\n![Image 7](https:\u002F\u002Fcaas.cn\u002Fimages\u002F2023-01\u002Fbf6579e4651e437db31a22cd2249b319.jpg)中国农科院微信公众号\n\n[English](https:\u002F\u002Fwww.caas.cn\u002Fen)[](https:\u002F\u002Fcaas.cn\u002Fcms\u002Fweb\u002Fsearch\u002Findex.jsp?siteID=cdb01dceb46e48488945d4465e90f221&aba=)\n\n*    [院网首页](https:\u002F\u002Fcaas.cn\u002Findex.htm) \n*    [图片新闻](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Ftpxw\u002Findex.htm) \n*    [时政要闻](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fszyw\u002Findex.htm) \n*    [农科要闻](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fnkyw\u002Findex.htm) \n*    [科研活动](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fkyhd\u002Findex.htm) \n*    [三农一线](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fhzdznew\u002Findex.htm) \n*    [媒体报道](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fmtxw\u002Findex.htm) \n*    [视频农科](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fspnk\u002Findex.htm) \n*    [政务新媒体矩阵](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fzwxmtjz\u002Findex.htm) \n\n[返回首页](https:\u002F\u002Fcaas.cn\u002Findex.htm)[English](https:\u002F\u002Fwww.caas.cn\u002Fen\u002F)\n\n[首页](https:\u002F\u002Fcaas.cn\u002Findex.htm)-[新闻中心](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Findex.htm)-[科研活动](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fkyhd\u002Findex.htm)\n\n分享到\n\n### 假单胞菌助力马铃薯闯“盐关”\n\n发布时间：2026-10-12 _|_ 来源： 中国农业科学院蔬菜花卉研究所 _|_ 作者：王万兴\n\n字体[小](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fkyhd\u002F0015064067524be58625da97b466f754.htm)[中](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fkyhd\u002F0015064067524be58625da97b466f754.htm)[大](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fkyhd\u002F0015064067524be58625da97b466f754.htm)\n\n近日，中国农业科学院[蔬菜花卉研究所](http:\u002F\u002Fivf.caas.cn\u002F)马铃薯遗传育种与栽培创新团队联合国内高校，揭示特异假单胞菌通过代谢重编程赋予马铃薯耐盐性的新机制，相关研究成果发表在《npj 生物膜和微生物组（npj Biofilms and Microbiomes）》上。\n\n![Image 8: 0032.png](https:\u002F\u002Fcaas.cn\u002Fimages\u002F2026-10\u002F1f1a7181cf1448d38769c151802b1c94.png)\n\n土壤盐渍化严重制约作物生产。马铃薯属于中度盐敏感作物，提升马铃薯耐盐性对挖掘盐渍土地生产潜力、保障粮食安全具有重要意义，但根际微生物参与马铃薯耐盐响应的机制尚不清楚。\n\n该研究对117份二倍体马铃薯材料开展耐盐评价与根际微生物组分析，发现耐盐马铃薯材料在盐胁迫条件下可富集更多存在互作关联的细菌类群，且假单胞菌丰度显著提高。研究进一步分离得到耐盐促生特异假单胞菌株，该菌株既可促进耐盐马铃薯在盐渍土壤中生长，也可提升盐敏感马铃薯的耐盐能力。研究初步证实该菌株可激活苯丙烷生物合成等防御相关通路，增强植株对盐胁迫的抵御响应。该研究为利用微生物组策略改良马铃薯耐盐性状提供了重要理论依据与微生物种质资源。\n\n该研究得到国家重点研发计划、中国农业科学院科技创新工程等项目支持。（通讯员 陈旭）\n\n原文链接：https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41522-026-01150-0\n\n打印本页\n\n关闭本页\n\n[院网信息发布与管理](https:\u002F\u002Fcaas.cn\u002Fywxxfbygl\u002Findex.htm)[最新动态](https:\u002F\u002Fcaas.cn\u002Fywxxfbygl\u002Findex.htm)\n\n*   [［CCTV-2］《正点财经》农业农村部：9月份全国生猪和猪肉价格环比小幅上](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fmtxw\u002Fbf10b20623d0478b9b2615a667a49718.htm)2026-10-12  \n*   [为农机搭载“智能大脑” 农机智能引擎AMES正式发布](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fkyhd\u002F1e301f834f7a499180a3095b26448e72.htm)2026-10-12  \n*   [ARC生物耦合技术赋能大豆绿色增产](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Ftpxw\u002Fc79eb912c78b4b2d817d1a355da288f0.htm)2026-10-12  \n*   [[CCTV-13]《东方时空》时空观察 秋收正忙 厄尔尼诺现象却在增强](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fmtxw\u002F7fdfae83e9724b5182790239e80c07d0.htm)2026-10-11  \n*   [[CGTN]China-Germany Relations: Decade-long hunt for a barley gene: Scientists decipher barley's early maturity mystery](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fmtxw\u002F635bbc5c976c45fc90ffd0f84bbe59bd.htm)2026-10-11  \n*   [全国农业科技工作会议在京召开](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fnkyw\u002F74ccfe933eee44098cd28dd031dcda63.htm)2026-10-11  \n*   [[CCTV-13]《朝闻天下》我国秋粮收获过半 秋冬种陆续展开](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fmtxw\u002Fda1d29bceb9143a798ce27a8882b1170.htm)2026-10-11  \n*   [[CCTV-13]《新闻联播》[在希望的田野上]全国秋粮收获进度过半 秋冬种陆续展开](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fmtxw\u002Ff5dafd42ddbc4ab8a4f4fb33791eacd9.htm)2026-10-10  \n*   [[科技日报]中德基因组学、育种与农业创新研讨会在京召开](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fmtxw\u002F1b22d96aaa2b420cb12b223a8dd4ed7e.htm)2026-10-10  \n*   [[科技日报]产学研用协同创新 赋能农业绿色低碳发展](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fmtxw\u002F505aca77ead042dfa237d6508780009a.htm)2026-10-10  \n\n*   [](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fspnk\u002Findex.htm)[视频农科](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fspnk\u002Findex.htm) \n*   [](https:\u002F\u002Fcaas.cn\u002Ftzgg\u002Findex.htm)[通知公告](https:\u002F\u002Fcaas.cn\u002Ftzgg\u002Findex.htm) \n*   [](https:\u002F\u002Fcaas.cn\u002Findex.htm?mao=special_attention)[特别关注](https:\u002F\u002Fcaas.cn\u002Findex.htm?mao=special_attention) \n*   [](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fzwxmtjz\u002Findex.htm)[政务新媒体矩阵](https:\u002F\u002Fcaas.cn\u002Fxwzx\u002Fzwxmtjz\u002Findex.htm) \n\n*   [![Image 9](https:\u002F\u002Fcaas.cn\u002Fimages\u002F2025-12\u002Feebc10f934d74b978fccd8c654f47577.jpg)](https:\u002F\u002Fcaas.cn\u002Fxxfw\u002Fzyfw\u002Fcqk\u002Findex.htm)\n*   [![Image 10](https:\u002F\u002Fcaas.cn\u002Fimages\u002Fcontent\u002F2022-02\u002Faefa6458187845e9a3aeb18472ae9e7f.jpg)](https:\u002F\u002Fcaas.cn\u002Fxxfw\u002Fzyfw\u002Fcqk\u002Findex.htm)\n*   [![Image 11](https:\u002F\u002Fcaas.cn\u002Fimages\u002F2023-01\u002F5c35b429611f44aa927c9b2698ff91e5.png)](https:\u002F\u002Fcaas.cn\u002Fxxfw\u002Fzyfw\u002Fcqk\u002Findex.htm)\n*   [![Image 12](https:\u002F\u002Fcaas.cn\u002Fimages\u002F2023-01\u002F2ec7c5b598424a0b801fd6fde5956562.png)](https:\u002F\u002Fcaas.cn\u002Fxxfw\u002Fzyfw\u002Fcqk\u002Findex.htm)\n\n*   [网站地图](https:\u002F\u002Fcaas.cn\u002Fwzdt\u002Findex.htm)\n*   [联系我们](https:\u002F\u002Fcaas.cn\u002Flxwm\u002Findex.htm)\n\n[我要捐赠](https:\u002F\u002Fjjh.caas.cn\u002Fjzzn\u002Fjzfs\u002Findex.htm)\n\n主办：中国农业科学院 承办:中国农业科学院农业信息研究所 地址:北京市海淀区中关村南大街12号 邮编:100081\n\nCopyright@中国农业科学院 京ICP备10039560号-5[_![Image 13](https:\u002F\u002Fcaas.cn\u002Fstatic2022\u002Fimages\u002Ficon\\_ba.png)_ 京公网安备11010802048565号](http:\u002F\u002Fwww.beian.gov.cn\u002Fportal\u002FregisterSystemInfo?recordcode=11010802048565)","中国农业科学院蔬菜花卉研究所 2026 年 10 月","报道",82,{"impact":17,"substance":106,"depth":16,"authority":107,"freshness":19,"relevant":20,"comment":108},21,15,"国家级科研机构揭示假单胞菌代谢重编程提升马铃薯耐盐性的新机制，属农业生物技术领域实质突破，具备较高参考价值。",[110],{"name":102,"url":99},[59,112,113,114,115],"微生物组","耐盐碱","农业科技","代谢重编程",{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},[118,119],{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"code":120,"slug":121,"name":122,"path":123,"parent_code":35},"B4","flowers","花卉与观赏植物","\u002Ftopic\u002Fhorticulture\u002Fflowers",{"status":44,"locked":13,"version":45,"method":46,"evidence":125},{"candidates":126,"agricultural_evidence":51},[127,132,136,141],{"code":38,"score":128,"supported":51,"title":129,"abstract":130,"tags":131},12,[59],[59],[59],{"code":31,"score":50,"supported":51,"title":133,"abstract":134,"tags":135},[33],[33],[],{"code":120,"score":50,"supported":51,"title":137,"abstract":139,"tags":140},[138],"花卉",[138],[],{"code":142,"score":143,"supported":51,"title":144,"abstract":145,"tags":148},"H2",7,[],[146,147],"土壤","根际",[113],[150,151],"中国农科院蔬菜花卉所 马铃薯 耐盐","假单胞菌 马铃薯 耐盐机制","中国农科院蔬菜花卉所马铃薯耐盐-5113","2026-10-17T00:13:39.397840Z",{"id":155,"title":156,"url":157,"summary":158,"summary_zh":8,"content":8,"source_name":159,"source_url":8,"published_at":160,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":161,"score_detail":162,"sources":167,"tags":169,"primary_topic":171,"secondary_topics":172,"classification":173,"search_phrases":199,"slug":202,"view_count":64,"doi":8,"paper":203,"created_at":210},5064,"Detection of Potato Plant Leaf Diseases using Convolutional Neural Networks","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.20544","Haimanot Bitew Alemayehu、Simachew Melaku Ayalew、Chilotie Desalew Mengesha、Ayisheshim Almaw Bogale、Anteneh Birhan Yenew、Abrham Tegegne Bogale在arXiv 2026-10-15上传的预印本,面向埃塞俄比亚粮食安全作物马铃薯,提出可部署于边缘设备的轻量卷积神经网络,完成健康、早疫病、晚疫病三类分类。模型在PlantVillage(2,215张图像)训练,测试准确率98.66%;在埃塞俄比亚Banja镇田间独立采集的247张图像测试中准确率为90.28%,体现独立田间验证相较受控基准更接近真实部署条件。模型仅含446,787个可训练参数、约1.70MB,训练周期较VGG16和MobileNetV2更短。【预印本未审稿;仅在埃塞俄比亚一地进行田间验证,跨地区泛化能力未测】","arXiv preprint 2026-10-15","2026-10-15T00:00:00Z",71,{"impact":107,"substance":163,"depth":164,"authority":165,"freshness":12,"relevant":20,"comment":166},20,17,9,"预印本提出仅1.7MB的轻量CNN实现马铃薯早疫病、晚疫病识别，含独立田间验证，方法扎实但尚未审稿、泛化性待验证，属细分领域技术进展。",[168],{"name":159,"url":157},[25,26,59,27,170],"病害识别",{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},[],{"status":44,"locked":13,"version":45,"method":46,"evidence":174},{"candidates":175,"agricultural_evidence":51},[176,181,187,191,195],{"code":38,"score":128,"supported":51,"title":177,"abstract":179,"tags":180},[178],"potato",[59],[59],{"code":182,"score":64,"supported":51,"title":183,"abstract":184,"tags":186},"A8",[],[185],"粮食安全",[],{"code":63,"score":82,"supported":13,"title":188,"abstract":189,"tags":190},[],[],[26,170],{"code":69,"score":20,"supported":13,"title":192,"abstract":193,"tags":194},[],[],[25],{"code":74,"score":20,"supported":13,"title":196,"abstract":197,"tags":198},[],[],[27],[200,201],"埃塞俄比亚 马铃薯 晚疫病 检测","轻量CNN 马铃薯 叶片病害","埃塞俄比亚马铃薯晚疫病检测-5064",{"doi":8,"openalex_id":8,"authors":204,"venue":8,"cited_by_count":85,"oa_url":8,"card":205,"direction":90,"ingested_from":92},[],{"tldr":206,"method":207,"finding":208,"direction":90,"opportunity":209},"提出轻量CNN实现马铃薯早疫病与晚疫病三分类，并在埃塞俄比亚田间验证。","轻量卷积神经网络，PlantVillage 2215张训练，Banja镇247张","测试集准确率98.66%，独立田间测试降至90.28%，模型仅1.70MB。","可研究跨地区\u002F多作物泛化、田间复杂背景鲁棒性及边缘设备实时部署优化。","2026-10-16T00:14:01.369956Z",{"id":212,"title":213,"url":214,"summary":215,"summary_zh":8,"content":216,"source_name":217,"source_url":8,"published_at":218,"category":103,"cover_url":8,"hotness":12,"is_selected":13,"score":219,"score_detail":220,"sources":222,"tags":224,"primary_topic":229,"secondary_topics":230,"classification":233,"search_phrases":258,"slug":260,"view_count":82,"doi":8,"paper":8,"created_at":261},5038,"中国农科院蔬菜花卉所揭示假单胞菌助力马铃薯闯\"盐关\"登《npj Biofilms and Microbiomes》","https:\u002F\u002Fwww.caas.cn\u002Fxwzx\u002Fkyhd\u002F0015064067524be58625da97b466f754.htm","中国农业科学院蔬菜花卉研究所马铃薯遗传育种与栽培创新团队联合国内高校,揭示特异假单胞菌通过代谢重编程赋予马铃薯耐盐性的新机制。团队对117份二倍体马铃薯开展耐盐评价与根际微生物组分析,发现耐盐材料可富集更多互作关联细菌类群,假单胞菌丰度显著提高;分离的特异假单胞菌株可激活苯丙烷生物合成等防御通路,论文发表于《npj Biofilms and Microbiomes》。","近日，中国农业科学院蔬菜花卉研究所马铃薯遗传育种与栽培创新团队联合国内高校，揭示特异假单胞菌通过代谢重编程赋予马铃薯耐盐性的新机制，相关研究成果发表在《npj 生物膜和微生物组（npj Biofilms and Microbiomes）》上。\n\n土壤盐渍化严重制约作物生产。马铃薯属于中度盐敏感作物，提升马铃薯耐盐性对挖掘盐渍土地生产潜力、保障粮食安全具有重要意义，但根际微生物参与马铃薯耐盐响应的机制尚不清楚。\n\n该研究对117份二倍体马铃薯材料开展耐盐评价与根际微生物组分析，发现耐盐马铃薯材料在盐胁迫条件下可富集更多存在互作关联的细菌类群，且假单胞菌丰度显著提高。研究进一步分离得到耐盐促生特异假单胞菌株，该菌株既可促进耐盐马铃薯在盐渍土壤中生长，也可提升盐敏感马铃薯的耐盐能力。研究初步证实该菌株可激活苯丙烷生物合成等防御相关通路，增强植株对盐胁迫的抵御响应。该研究为利用微生物组策略改良马铃薯耐盐性状提供了重要理论依据与微生物种质资源。\n\n该研究得到国家重点研发计划、中国农业科学院科技创新工程等项目支持。（通讯员 陈旭）","中国农业科学院蔬菜花卉研究所 2026年10月12日","2026-10-12T00:00:00Z",83,{"impact":17,"substance":17,"depth":16,"authority":107,"freshness":19,"relevant":20,"comment":221},"国家级科研机构在《npj Biofilms and Microbiomes》发表的马铃薯耐盐微生物机制研究，117份材料评价与特异菌株分离结论扎实，对盐渍地利用与种业创新有参考价值。",[223],{"name":217,"url":214},[59,225,226,227,228],"种业振兴","根际微生物","耐盐育种","假单胞菌",{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},[231,232],{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"code":120,"slug":121,"name":122,"path":123,"parent_code":35},{"status":44,"locked":13,"version":45,"method":46,"evidence":234},{"candidates":235,"agricultural_evidence":51},[236,240,244,248,253],{"code":38,"score":128,"supported":51,"title":237,"abstract":238,"tags":239},[59],[59],[59],{"code":31,"score":50,"supported":51,"title":241,"abstract":242,"tags":243},[33],[33],[],{"code":120,"score":50,"supported":51,"title":245,"abstract":246,"tags":247},[138],[138],[],{"code":142,"score":249,"supported":51,"title":250,"abstract":251,"tags":252},4,[],[147],[226],{"code":254,"score":20,"supported":13,"title":255,"abstract":256,"tags":257},"F1",[],[],[225],[150,259],"假单胞菌 马铃薯 盐渍化","中国农科院蔬菜花卉所马铃薯耐盐-5038","2026-10-16T00:13:11.018756Z",{"id":263,"title":264,"url":265,"summary":266,"summary_zh":267,"content":8,"source_name":268,"source_url":265,"published_at":269,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":270,"score_detail":271,"sources":273,"tags":275,"primary_topic":278,"secondary_topics":279,"classification":280,"search_phrases":307,"slug":310,"view_count":85,"doi":311,"paper":312,"created_at":331},4417,"CuFormer U-Net: a transformer-enhanced multi-task network for cucumber leaf disease detection and segmentation","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffpls.2026.1975030","Cucumber foliar symptoms reduce functional leaf area and complicate greenhouse scouting. This study presents CuFormer U-Net, a Transformer-enhanced multi-task network for three-class image-level classification on the 3,754-image Kaggle benchmark (healthy, powdery mildew, and downy mildew) and binary visible-symptom segmentation on a separate 400-image greenhouse cohort (200 healthy and 200 affected leaves). The greenhouse annotations comprise 2,705 rectangles (1,741 color-abnormality and 964 tissue-damage instances); rectangle-seeded lesion masks were manually refined for the dense-prediction experiments. The reported fixed-split point estimates were 96.7% accuracy, 96.3% macro precision, 95.8% macro recall, and 96.0% macro F1 for classification, and 92.4% mean image-wise Dice, 83.1% macro IoU, 93.2% foreground precision, and 91.7% foreground recall for segmentation. The complete internal-validation ablation configuration reached 93.1% Dice and 87.3% IoU. The available experiment archive does not contain independent-seed reruns, per-image predictions for inferential testing, annotator-level masks, quantitative results for the separate 100-image greenhouse stress-test cohort, or reproducible hardware profiling. Accordingly, all between-model differences are interpreted descriptively, the external cohort is not presented as formal external validation, and robustness and deployment claims have been moderated. CuFormer U-Net provides a technically motivated basis for joint recognition and spatial characterization, but confirmatory multi-run and multi-site evaluation is required. boundary refinement, cucumber leaf disease, multi-task learning, plant disease, precision agriculture, semantic segmentation, vision transformer","黄瓜叶片症状会减少有效叶面积，并增加温室巡查的难度。本研究提出CuFormer U-Net，这是一种经Transformer增强的多任务网络，用于在包含3，754张图像的Kaggle基准数据集上进行三类图像级分类（健康、白粉病和霜霉病），并在一个独立的包含400张图像的温室队列（200张健康叶片和200张受影响叶片）上进行二值可见症状分割。温室标注包含2，705个矩形框（1，741个颜色异常实例和964个组织损伤实例）；用于密集预测实验的矩形框种子病灶掩膜经过人工精修。所报告的固定划分点估计结果为：分类任务准确率96.7%、宏平均精确率96.3%、宏平均召回率95.8%、宏平均F1值96.0%；分割任务平均图像级Dice系数92.4%、宏平均IoU 83.1%、前景精确率93.2%、前景召回率91.7%。完整的内部验证消融配置达到Dice 93.1%和IoU 87.3%。现有实验档案不包含独立随机种子重跑、用于推断性检验的逐图像预测、标注者级别掩膜、针对独立100张图像温室压力测试队列的定量结果，或可复现的硬件性能分析。因此，所有模型间差异均以描述性方式解释，外部队列不作为正式外部验证呈现，稳健性和部署相关主张也已作审慎表述。CuFormer U-Net为联合识别与空间表征提供了具有技术依据的基础，但仍需开展验证性多轮次和多站点评估。边界精修、黄瓜叶部病害、多任务学习、植物病害、精准农业、语义分割、视觉Transformer","Frontiers in Plant Science","2026-10-07T00:00:00Z",73,{"impact":107,"substance":163,"depth":164,"authority":18,"freshness":57,"relevant":20,"comment":272},"方法新颖、数据与指标披露充分且自我限定严谨，但属单作物单场景研究，产业影响有限，适合作为技术类精选。",[274],{"name":268,"url":265},[25,26,28,276,277],"图像分割","黄瓜种植",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":44,"locked":13,"version":45,"method":46,"evidence":281},{"candidates":282,"agricultural_evidence":51},[283,290,296,303],{"code":31,"score":284,"supported":51,"title":285,"abstract":287,"tags":289},14,[286],"cucumber",[288,286],"黄瓜",[],{"code":69,"score":143,"supported":51,"title":291,"abstract":292,"tags":295},[],[293,294],"精准农业","precision agriculture",[25],{"code":297,"score":19,"supported":51,"title":298,"abstract":299,"tags":302},"B7",[],[300,301],"温室","greenhouse",[],{"code":63,"score":64,"supported":13,"title":304,"abstract":305,"tags":306},[],[],[26,276,28],[308,309],"CuFormer U-Net 黄瓜叶部病害","黄瓜 霜霉病 白粉病 识别","CuFormerU-Net黄瓜叶部病害-4417","10.3389\u002Ffpls.2026.1975030",{"doi":311,"openalex_id":313,"authors":314,"venue":268,"cited_by_count":85,"oa_url":322,"card":323,"direction":329,"ingested_from":330},"W7220838309",[315,318,320],{"name":316,"orcid":317},"Batyrkhan Omarov","https:\u002F\u002Forcid.org\u002F0000-0002-8341-7113",{"name":319,"orcid":8},"Sayat Ibrayev",{"name":321,"orcid":8},"Nurbibi Imanbayeva","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fplant-science\u002Farticles\u002F10.3389\u002Ffpls.2026.1975030\u002Fpdf",{"tldr":324,"method":325,"finding":326,"direction":327,"opportunity":328},"提出CuFormer U-Net多任务网络，同时实现黄瓜叶病分类与病斑分割。","Transformer增强U-Net，用Kaggle 3754图分类和400图温","分类准确率96.7%，分割Dice 92.4%，但缺独立重复与外部验证。","农业遥感与作物表型","需多轮多站点验证，并补全外部压力测试与可复现部署评估。","智慧农业 \u002F 农业物联网","openalex","2026-10-08T23:30:09.461430Z",{"id":333,"title":334,"url":335,"summary":336,"summary_zh":8,"content":8,"source_name":337,"source_url":8,"published_at":338,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":339,"score_detail":340,"sources":343,"tags":345,"primary_topic":348,"secondary_topics":349,"classification":350,"search_phrases":383,"slug":386,"view_count":57,"doi":8,"paper":387,"created_at":394},3960,"Groundbreaking AI Robot Picks Tomatoes Autonomously——YOLOv8n-BiFPN-WIoU模型驱动采摘新范式","https:\u002F\u002Fagritechinsights.com\u002Findex.php\u002F2026\u002F10\u002F02\u002Fgroundbreaking-ai-robot-picks-tomatoes-autonomously","山东理工大学孟凡钊团队开发出基于YOLOv8n-BiFPN-WIoU轻量级深度学习模型的温室番茄自主采摘机器人，可在边缘设备NVIDIA Jetson Nano上运行，优化后达21.1 FPS实时运行；定位误差3.5±0.32mm；mAP@0.5达92.4%。系统采用六轴机械臂+双爪末端执行器，针对温室遮挡与光照变化优化，适用于商业化串番茄采收；系统基于开源ROS模块化设计，未来可适配黄瓜、辣椒、草莓等。","Agritech Insights·2026年10月02日（Frontiers in Plant Science）","2026-10-02T00:00:00Z",86,{"impact":17,"substance":341,"depth":16,"authority":18,"freshness":12,"relevant":20,"comment":342},23,"轻量模型+边缘部署的番茄自主采摘机器人，方法新颖、指标扎实，具备细分行业参考价值。",[344],{"name":337,"url":335},[25,26,346,27,347],"农业机器人","番茄采摘",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":44,"locked":13,"version":45,"method":46,"evidence":351},{"candidates":352,"agricultural_evidence":51},[353,360,366,371,375,379],{"code":31,"score":165,"supported":51,"title":354,"abstract":355,"tags":359},[],[356,357,288,358],"番茄","辣椒","草莓",[],{"code":361,"score":249,"supported":51,"title":362,"abstract":363,"tags":365},"F6",[],[364],"采摘机器人",[346],{"code":63,"score":249,"supported":51,"title":367,"abstract":368,"tags":370},[],[369],"深度学习",[26],{"code":297,"score":64,"supported":51,"title":372,"abstract":373,"tags":374},[],[300],[],{"code":69,"score":20,"supported":13,"title":376,"abstract":377,"tags":378},[],[],[25],{"code":74,"score":20,"supported":13,"title":380,"abstract":381,"tags":382},[],[],[27],[384,385],"山东理工大学 番茄采摘机器人","YOLOv8n 温室番茄 采摘","山东理工大学番茄采摘机器人-3960",{"doi":8,"openalex_id":8,"authors":388,"venue":8,"cited_by_count":85,"oa_url":8,"card":389,"direction":329,"ingested_from":92},[],{"tldr":390,"method":391,"finding":392,"direction":329,"opportunity":393},"开发基于YOLOv8n-BiFPN-WIoU的轻量模型，实现温室番茄自主采摘机器人实时运行。","YOLOv8n-BiFPN-WIoU轻量模型，Jetson Nano边缘部署，六","mAP@0.5达92.4%，21.1 FPS实时运行，定位误差3.5±0.32mm，可商业化串番茄采","可延伸至多作物泛化、复杂遮挡与光照鲁棒性提升，以及边缘端模型轻量化与多机协同采摘。","2026-10-02T11:53:16.408068Z",{"id":396,"title":397,"url":398,"summary":399,"summary_zh":400,"content":8,"source_name":401,"source_url":398,"published_at":402,"category":11,"cover_url":8,"hotness":403,"is_selected":13,"score":404,"score_detail":405,"sources":408,"tags":412,"primary_topic":415,"secondary_topics":416,"classification":422,"search_phrases":454,"slug":457,"view_count":64,"doi":458,"paper":459,"created_at":469},3913,"Lightweight Edge-AI Model for Real-Time Sorghum Disease Detection on Resource-Constrained Mobile Devices","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23054218","Lightweight Edge-AI Model for Real-Time Sorghum Disease Detection on Resource-Constrained Mobile Devices presents an efficient artificial intelligence approach for identifying sorghum diseases directly on mobile and edge-computing platforms. The study focuses on developing a lightweight machine learning model capable of performing rapid and accurate disease detection while operating under limited computational resources, memory, and power constraints. Computer vision and deep learning techniques are used to analyse sorghum leaf images and distinguish healthy plants from diseased conditions. Model optimization strategies are considered to reduce computational complexity and improve inference speed without substantially compromising detection performance. The proposed approach supports real-time, on-device disease diagnosis, reducing dependence on cloud connectivity and enabling timely intervention in agricultural environments. The work highlights the potential of Edge AI and mobile computing to make intelligent crop monitoring more accessible, practical, and scalable, particularly for farmers and agricultural users operating in resource-constrained settings.","面向资源受限移动设备的实时高粱病害检测轻量级边缘人工智能模型提出了一种高效的人工智能方法，用于直接在移动和边缘计算平台上识别高粱病害。该研究聚焦于开发一种轻量级机器学习模型，能够在有限的计算资源、内存和功耗约束下进行快速、准确的病害检测。研究采用计算机视觉和深度学习技术分析高粱叶片图像，区分健康植株与患病状态。研究考虑了模型优化策略，以降低计算复杂度并提高推理速度，同时不过度损害检测性能。所提出的方法支持实时、设备端病害诊断，减少了对云连接的依赖，并能够在农业环境中实现及时干预。该工作凸显了边缘人工智能和移动计算在使智能作物监测更加可及、实用和可扩展方面的潜力，特别是对于在资源受限环境中作业的农民和农业用户而言。","Zenodo (CERN European Organization for Nuclear Research)","2026-09-30T00:00:00Z",25,75,{"impact":406,"substance":163,"depth":164,"authority":18,"freshness":165,"relevant":20,"comment":407},16,"面向资源受限移动端的轻量边缘AI高粱病害实时检测研究，方法实用、契合智慧农业场景，但属细分作物技术进展，影响力有限。",[409,410],{"name":401,"url":398},{"name":401,"url":411},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23054219",[25,26,27,413,414],"作物监测","高粱病害",{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},[417],{"code":63,"slug":418,"name":419,"path":420,"parent_code":421},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":44,"locked":13,"version":45,"method":46,"evidence":423},{"candidates":424,"agricultural_evidence":51},[425,431,441,445,449],{"code":38,"score":284,"supported":51,"title":426,"abstract":428,"tags":430},[427],"sorghum",[429,427],"高粱",[],{"code":63,"score":12,"supported":51,"title":432,"abstract":433,"tags":440},[],[369,434,435,436,437,438,439],"机器学习","计算机视觉","machine learning","deep learning","artificial intelligence","computer vision",[26],{"code":74,"score":249,"supported":51,"title":442,"abstract":443,"tags":444},[],[27],[27],{"code":69,"score":20,"supported":13,"title":446,"abstract":447,"tags":448},[],[],[25],{"code":450,"score":20,"supported":13,"title":451,"abstract":452,"tags":453},"I3",[],[],[413],[455,456],"高粱病害 边缘AI 检测","高粱叶片 病害识别 移动端","高粱病害边缘AI检测-3913","10.5281\u002Fzenodo.23054218",{"doi":458,"openalex_id":460,"authors":461,"venue":401,"cited_by_count":85,"oa_url":398,"card":464,"direction":90,"ingested_from":330},"W7214912247",[462],{"name":463,"orcid":8},"Anantjit Publication",{"tldr":465,"method":466,"finding":467,"direction":90,"opportunity":468},"开发轻量级边缘AI模型，在资源受限移动设备上实时检测高粱病害。","计算机视觉与深度学习分析高粱叶片图像，并做模型轻量化优化。","轻量模型可在移动端实时准确识别病害，减少对云连接依赖。","可探索多作物、多病害通用轻量模型及田间复杂光照下的鲁棒性。","2026-10-01T23:30:48.902282Z"]