[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-183":3,"related-183":73},{"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":30,"secondary_topics":36,"classification":37,"search_phrases":67,"slug":70,"view_count":71,"doi":8,"paper":8,"created_at":72},183,"一株橡胶草的百年突围","http:\u002F\u002Fm.ce.cn\u002Fbwzg\u002F202608\u002Ft20260803_3123436.shtml","新疆科研团队建成橡胶草天然橡胶中试提取线并产出合格产品，打通从种质资源到工业化提胶的关键环节。橡胶草适宜在天山河谷盐碱荒滩生长，为我国天然橡胶多元化供给和盐碱地特色利用提供了产业化探索。",null,"从“草”到“胶”的实质性突破，徐麟团队构建起集“种质保护—良种选育—规模种植—工业提胶—副产品深加工”于一体的全自主产业链体系。团队还创新提出“主产品提胶+副产品高值化利用”的协同开发模式——橡胶草根部除富含天然橡胶外，还含有20%的菊糖，可发酵生产乙醇、制作保健品，残渣还能作饲料或有机肥，实现全株“吃干榨净”。\n\n“经过这几年研发，我们已经围绕橡胶草开发出了一些精深加工产品，包括凉茶、保健功能饮品等。”张龑说。\n\n2015年，我国成立了蒲公英橡胶产业技术创新战略联盟，以北京化工大学为盟主单位，联合中国热带农业科学院橡胶研究所、新疆农科院等机构，构建了“人才科技支撑+基础理论研究+规模化种植”的协同创新格局。目前，徐麟团队的橡胶草课题组已形成8个博士、16人的科研队伍，涵盖种质资源创新、新品种选育、栽培技术集成、副产品开发和天然橡胶提取的全链条科研能力。\n\n2024年进入橡胶草课题组的博士阿依加马力·克然木，目前主要的研究方向是野生橡胶草的生态保护以及橡胶草的栽培技术。“目前橡胶草的种质资源还相对匮乏，遗传改良刚刚起步，还有很长的路要走。”阿依加马力·克然木说，未来我们需要在不同气候生态区，围绕播种量、种植方式、水肥措施、杂草防除、收获贮存等方面，对不同类型橡胶草的生长发育规律与物质积累分配进行深入研究。“只有摸清野生橡胶草的遗传、繁衍、进化规律，才能用来指导育种以及未来的规模化栽培。”\n\n从1931年科学家在天山发现第一株橡胶草，到今年新疆科研团队成功实现工业化提胶，这株小草走过了近一个世纪的漫长旅程。“中试成功是万里长征第一步。从实验室到产业化，还有很长的路要走。”徐麟说，下一步，首先要加快品种选育，尽快推出自主品种，填补国内空白；其次要进一步深化基础研究，包括盐碱地栽培机理、橡胶草驯化机理、叶片与根部开发的机理等；最后要尽快熟化栽培技术和副产品开发技术，真正进入市场，取得经济效益。\n\n草虽微末，亦可担大任。徐麟常对团队成员说，现在的研究是在填补国内空白，一旦国家面临天然橡胶供应瓶颈，这项技术就至关重要。“对我们而言，最大的制约是成本和政策支持。”徐麟坦言，希望未来获得更多政策支持和产业关注，帮助团队进一步熟化技术，让橡胶草的大规模种植和研发更可持续。（经济日报记者 耿丹丹）","中国经济网","2026-08-03T00:00:00Z","报道",10,true,75,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},25,20,18,12,0,1,"报道橡胶草工业化提胶突破，涉及农业科技与产业链，影响深远，但日期为未来，时效性不符。",[25],{"name":10,"url":6},[27,28,29],"农业科技成果转化","特色农业","盐碱地利用",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},"H2","soil","土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",[],{"status":38,"locked":39,"version":40,"method":41,"evidence":42},"classified",false,"2026-10-22.2","rules",{"candidates":43,"agricultural_evidence":14},[44,50,57,62],{"code":31,"score":45,"supported":14,"title":46,"abstract":47,"tags":49},4,[],[48],"盐碱地",[29],{"code":51,"score":52,"supported":14,"title":53,"abstract":54,"tags":56},"F1",3,[],[55],"种质资源",[],{"code":58,"score":22,"supported":39,"title":59,"abstract":60,"tags":61},"G1",[],[],[27],{"code":63,"score":22,"supported":39,"title":64,"abstract":65,"tags":66},"G4",[],[],[28],[68,69],"农业科技成果转化 盐碱地利用 特色农业","农业科技成果转化 盐碱地利用","农业科技成果转化盐碱地利用特色农业-183",15,"2026-08-02T23:54:40.226501Z",{"total":74,"page":22,"page_size":74,"items":75},6,[76,128,188,242,314,398],{"id":77,"title":78,"url":79,"summary":80,"summary_zh":8,"content":81,"source_name":82,"source_url":8,"published_at":83,"category":12,"cover_url":8,"hotness":13,"is_selected":39,"score":84,"score_detail":85,"sources":90,"tags":92,"primary_topic":97,"secondary_topics":103,"classification":105,"search_phrases":123,"slug":126,"view_count":21,"doi":8,"paper":8,"created_at":127},5045,"山东农科院联合育种团队选育耐盐碱耐密植大豆新品种 在河口盐碱地亩产近300公斤","https:\u002F\u002Fwww.toutiao.com\u002Farticle\u002F7694921927810564648","山东省重点研发计划(农业良种工程)\"耐盐碱耐密植大豆新品种选育\"项目在河口区完成田间现场测产。该项目由渤海圣丰种业牵头,联合山东农业大学、青岛农业大学、山东省农业科学院作物研究所、德州市农业科学院组建跨单位育种团队。在土壤含盐量3‰~5‰的盐碱大豆试验基地,8个参试品系群体密度突破2万株\u002F亩,青农豆密2308亩产297.86公斤、德豆10号289.60公斤。","**爱东营讯** 近日，山东省重点研发计划（农业良种工程）“耐盐碱耐密植大豆新品种选育”项目在河口区完成田间现场测产评估。该项目由渤海圣丰种业科技有限公司牵头实施，联合山东农业大学、青岛农业大学、山东省农业科学院作物研究所、德州市农业科学院组建跨单位育种创新团队，由多名正高级大豆育种专家，对自主选育的8个大豆新品种（系）开展田间产量鉴定。\n\n在土壤含盐量3‰—5‰的河口盐碱大豆试验示范基地，系统评价各参试品系在盐碱胁迫环境下的农艺性状、群体结构与产能潜力。经理论测产核算，全部参试品系群体密度突破2万株\u002F亩，部分品系单株平均粒数超70粒。其中，青农豆密2308综合抗逆与产量性能最优，亩株数达21470.85株，理论亩产297.86公斤；德豆10号表现突出，亩株数20557.20株，理论亩产289.60公斤；其他多个品系也均表现优异。专家组现场研判，本次参试的多个大豆新品系实现耐盐、耐密、高产性状协同聚合。\n\n本次田间测产验收，标志着该省级农业良种攻关项目取得关键性阶段性突破。这批筛选创制的耐盐碱、耐密植、高产稳产大豆新品种（系），可为全省乃至全国盐碱耕地大豆产能提升提供核心种质支撑，对降低我国大豆对外依存度、筑牢种业种源安全屏障具有重要战略价值。\n\n下一步，河口区将持续做好良种攻关项目全流程技术服务，推动各参与单位深化产学研协同创新，加速优良品系多点试验、示范与产业化推广，推动育种科研成果高效转化为盐碱地农业现实生产力。\n\n（记者 李萍 通讯员 施国军）","东营市新媒体中心 爱东营讯 2026年10月10日","2026-10-10T06:27:00Z",71,{"impact":86,"substance":86,"depth":87,"authority":74,"freshness":88,"relevant":22,"comment":89},22,16,5,"省级良种攻关项目在盐碱地实现耐盐耐密高产协同突破，数据具体、战略价值明确，值得进入每日精选。",[91],{"name":82,"url":79},[29,93,94,95,96],"种业振兴","产学研协同","大豆育种","耐盐碱大豆",{"code":98,"slug":99,"name":100,"path":101,"parent_code":102},"A4","soybean-oilseeds","大豆与油料","\u002Ftopic\u002Ffield-crops\u002Fsoybean-oilseeds","A",[104],{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"status":38,"locked":39,"version":40,"method":41,"evidence":106},{"candidates":107,"agricultural_evidence":14},[108,113,118],{"code":98,"score":20,"supported":14,"title":109,"abstract":111,"tags":112},[110],"大豆",[110],[95],{"code":31,"score":20,"supported":14,"title":114,"abstract":115,"tags":117},[48],[116],"土壤",[29],{"code":51,"score":45,"supported":14,"title":119,"abstract":120,"tags":122},[],[121],"种业",[93],[124,125],"山东农科院 耐盐碱大豆 河口","青农豆密2308 德豆10号 测产","山东农科院耐盐碱大豆河口-5045","2026-10-16T00:13:11.498967Z",{"id":129,"title":130,"url":131,"summary":132,"summary_zh":8,"content":133,"source_name":134,"source_url":8,"published_at":135,"category":12,"cover_url":8,"hotness":13,"is_selected":39,"score":136,"score_detail":137,"sources":142,"tags":144,"primary_topic":148,"secondary_topics":149,"classification":150,"search_phrases":183,"slug":186,"view_count":45,"doi":8,"paper":8,"created_at":187},4944,"山东农科院联合多家机构发布植物抗逆AI智能体与盐稻芯1号育种芯片","http:\u002F\u002Fgzylhyzx.com\u002Fdetail.html?newsId=58110969","盐碱地综合利用国家技术创新中心联合中国农业科学院深圳农业基因组研究所、崖州湾国家实验室、山东省农业科学院湿地农业与生态研究所,发布全球首个植物抗逆AI智能体与国内首个耐盐水稻11K液相育种芯片(盐稻芯1号)。植物抗逆AI智能体聚焦盐碱、干旱、高温、低温四大非生物逆境,以水稻等6个物种为研究核心,整合全球逆境文献与多源科研数据。盐稻芯1号以耐盐多组学证据定向选择位点,较全基因组重测序成本仅为其三分之一。","### 两大科研成果重磅发布！盐碱地综合利用国家技术创新中心解锁抗逆育种智能新范式\n\n2026-10-15 04:44:38\n\n**大众网记者 唐梦琳 东营报道**\n\n9月19日，盐碱地综合利用国家技术创新中心（以下简称国家盐碱地中心）在总部举办新闻发布会，正式发布全球首个植物抗逆AI智能体与国内首个耐盐水稻11K液相育种芯片（盐稻芯1号）两项重大科研成果。发布会由中心综合事业部部长石东毅主持，中心副主任杨长军、耐盐碱植物微生物基因挖掘创新团队首席专家商连光发布。会上，杨长军介绍了成果开发背景与意义，商连光发布两项最新研究成果，并回答记者提问。\n\n![Image 1](https:\u002F\u002Fdzngimage.dzwww.com\u002F2026\u002F09\u002F19\u002F792a00e9232c00fdcf438be95889fed0.png)\n\n据介绍，两项成果由国家盐碱地中心联合中国农业科学院深圳农业基因组研究所、崖州湾国家实验室、山东省农业科学院湿地农业与生态研究所共同研发，以人工智能与分子育种技术深度融合，破解作物抗逆选育难题，为盐碱地综合利用、种业振兴和国家粮食安全注入强劲科技动能。\n\n植物抗逆AI智能体聚焦盐碱、干旱、高温、低温四大非生物逆境，以水稻等6个物种为研究核心，整合全球逆境文献与多源科研数据，依托6个AI 智能体分工完成资料检索、数据分析、交叉复核、综合研判，能够持续迭代学习科研成果，实现从单一胁迫研究向多逆境耦合研究范式升级。植物抗逆AI智能体可智能挖掘抗逆关键基因、显著压缩分子育种研发周期，作物抗逆上研究性能优于通用科研大模型，并将面向全球科研用户开放共享。\n\n与通用芯片按基因组位置均匀布点不同，耐盐水稻11K液相育种芯片（盐稻芯1号）以耐盐多组学证据定向选择位点，改变了耐盐水稻从生育期表型鉴定向苗期基因型选择的育种变革模式。相较全基因组重测序，该芯片成本仅为其三分之一，核心耐盐表型上，预测精度较同类芯片明显提升，育种科研人员可在苗期完成大规模群体耐盐筛选，为解决水稻耐盐研究中生育期和土地条件制约等问题提供了新的途径。\n\n两项成果取得了五个主要显著进展：一是推动研究范式由单一胁迫走向多逆境耦合；二是育种模式由经验筛选转向数据驱动精准选育；三是科研组织由分散探索升级为 AI 智能协同研究；四是芯片标记由全基因组铺点升级为多组学定向锚定；五是利用芯片将育种选择由大田表型鉴定前移至苗期基因型筛选。\n\n下一步，国家盐碱地中心将持续迭代升级植物抗逆AI智能体，丰富多物种、多场景科研数据集，优化算法模型；打通基础研究到育种应用链条，加速抗逆基因挖掘、种质创制和新品种选育；搭建全球逆境科研协同创新网络，深化与FAO、INSAS等国际组织交流合作，汇聚各方科研力量，联合破解植物逆境响应、气候适应性育种、边际土地高效利用等重大科学问题。\n\n发布会现场还介绍了国家盐碱地中心平台建设、人才集聚、科研攻关、成果转化等方面最新建设成效。\n\n  \n免责声明：以上数据来源于天眼查等平台，相关内容仅为传递更多信息之目的，不代表本网观点，亦不代表本网站赞同其观点或证实其内容的真实性。如有侵权请联系0531-85193563。\n本文来源：海报新闻\n\n查看更多","大众网 每日热点 2026 年 9 月 19 日(10 月 15 日活跃)","2026-09-19T00:00:00Z",84,{"impact":138,"substance":139,"depth":19,"authority":140,"freshness":45,"relevant":22,"comment":141},26,23,13,"国家级盐碱地创新中心发布全球首个植物抗逆AI智能体与国内首个耐盐水稻液相育种芯片，属种业与农业AI交叉领域的重大突破，信息增量足、信源权威，虽发布已近一月但成果价值仍具精选意义。",[143],{"name":134,"url":131},[145,29,93,146,147],"农业人工智能","育种芯片","耐盐水稻",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":39,"version":40,"method":41,"evidence":151},{"candidates":152,"agricultural_evidence":14},[153,157,163,169,173,178],{"code":31,"score":45,"supported":14,"title":154,"abstract":155,"tags":156},[],[48],[29],{"code":158,"score":52,"supported":14,"title":159,"abstract":160,"tags":162},"A1",[],[161],"水稻",[],{"code":164,"score":52,"supported":14,"title":165,"abstract":166,"tags":168},"H7",[],[167],"干旱",[],{"code":51,"score":22,"supported":39,"title":170,"abstract":171,"tags":172},[],[],[93],{"code":174,"score":22,"supported":39,"title":175,"abstract":176,"tags":177},"F2",[],[],[146],{"code":179,"score":22,"supported":39,"title":180,"abstract":181,"tags":182},"I2",[],[],[145],[184,185],"盐稻芯1号 育种芯片","植物抗逆AI智能体 盐碱地","盐稻芯1号育种芯片-4944","2026-10-15T00:06:02.373275Z",{"id":189,"title":190,"url":191,"summary":192,"summary_zh":8,"content":193,"source_name":194,"source_url":8,"published_at":195,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":196,"score_detail":197,"sources":201,"tags":203,"primary_topic":204,"secondary_topics":207,"classification":209,"search_phrases":237,"slug":240,"view_count":45,"doi":8,"paper":8,"created_at":241},2982,"盐碱地综合利用国家技术创新中心发布全球首个植物抗逆AI智能体与国内首个耐盐水稻11K液相育种芯片（盐稻芯1号）","https:\u002F\u002Fwww.toutiao.com\u002Farticle\u002F7687098876901212710","国家盐碱地中心9-19在总部举办新闻发布会发布两项重大科研成果：全球首个植物抗逆AI智能体聚焦盐碱、干旱、高温、低温四大非生物逆境以水稻等6个物种为研究核心，依托6个AI智能体分工完成资料检索、数据分析、交叉复核、综合研判；国内首个耐盐水稻11K液相育种芯片（盐稻芯1号）以耐盐多组学证据定向选择位点改变耐盐水稻从生育期表型鉴定向苗期基因型选择的育种变革模式，成本仅全基因组重测序三分之一。两项成果由国家盐碱地中心联合中国农业科学院深圳农业基因组研究所、崖州湾国家实验室、山东省农业科学院湿地农业与生态研究所共同研发。","## 两大科研成果重磅发布！盐碱地综合利用国家技术创新中心解锁抗逆育种智能新范式\n\n2026-09-19 12:29·[大众网东营](https:\u002F\u002Fwww.toutiao.com\u002Fc\u002Fuser\u002Ftoken\u002FMS4wLjABAAAAWwTcI7rcmoH8YQLif34dXgBEonxq4KbS8is4cb7jJBY\u002F?source=tuwen_detail)\n\n**大众网记者 唐梦琳 东营报道**\n\n9月19日，盐碱地综合利用国家技术创新中心（以下简称国家盐碱地中心）在总部举办新闻发布会，正式发布全球首个植物抗逆AI智能体与国内首个耐盐水稻11K液相育种芯片（盐稻芯1号）两项重大科研成果。发布会由中心综合事业部部长石东毅主持，中心副主任杨长军、耐盐碱植物微生物基因挖掘创新团队首席专家商连光发布。会上，杨长军介绍了成果开发背景与意义，商连光发布两项最新研究成果，并回答记者提问。\n\n![Image 1](https:\u002F\u002Fp3-sign.toutiaoimg.com\u002Ftos-cn-i-axegupay5k\u002F12aca97dece34ce8b4144483f96daca7~tplv-tt-origin-web:gif.jpeg?_iz=58558&from=article.pc_detail&lk3s=953192f4&x-expires=1790467387&x-signature=MUmUvD%2B1WCDEzZ59gn8Ck46C%2F6U%3D)\n据介绍，两项成果由国家盐碱地中心联合中国农业科学院深圳农业基因组研究所、崖州湾国家实验室、山东省农业科学院湿地农业与生态研究所共同研发，以人工智能与分子育种技术深度融合，破解作物抗逆选育难题，为盐碱地综合利用、种业振兴和国家粮食安全注入强劲科技动能。\n\n植物抗逆AI智能体聚焦盐碱、干旱、高温、低温四大非生物逆境，以水稻等6个物种为研究核心，整合全球逆境文献与多源科研数据，依托6个AI 智能体分工完成资料检索、数据分析、交叉复核、综合研判，能够持续迭代学习科研成果，实现从单一胁迫研究向多逆境耦合研究范式升级。植物抗逆AI智能体可智能挖掘抗逆关键基因、显著压缩分子育种研发周期，作物抗逆上研究性能优于通用科研大模型，并将面向全球科研用户开放共享。\n\n与通用芯片按基因组位置均匀布点不同，耐盐水稻11K液相育种芯片（盐稻芯1号）以耐盐多组学证据定向选择位点，改变了耐盐水稻从生育期表型鉴定向苗期基因型选择的育种变革模式。相较全基因组重测序，该芯片成本仅为其三分之一，核心耐盐表型上，预测精度较同类芯片明显提升，育种科研人员可在苗期完成大规模群体耐盐筛选，为解决水稻耐盐研究中生育期和土地条件制约等问题提供了新的途径。\n\n两项成果取得了五个主要显著进展：一是推动研究范式由单一胁迫走向多逆境耦合；二是育种模式由经验筛选转向数据驱动精准选育；三是科研组织由分散探索升级为 AI 智能协同研究；四是芯片标记由全基因组铺点升级为多组学定向锚定；五是利用芯片将育种选择由大田表型鉴定前移至苗期基因型筛选。\n\n下一步，国家盐碱地中心将持续迭代升级植物抗逆AI智能体，丰富多物种、多场景科研数据集，优化算法模型；打通基础研究到育种应用链条，加速抗逆基因挖掘、种质创制和新品种选育；搭建全球逆境科研协同创新网络，深化与FAO、INSAS等国际组织交流合作，汇聚各方科研力量，联合破解植物逆境响应、气候适应性育种、边际土地高效利用等重大科学问题。\n\n发布会现场还介绍了国家盐碱地中心平台建设、人才集聚、科研攻关、成果转化等方面最新建设成效。","大众网·今日头条","2026-09-19T04:29:00Z",92,{"impact":198,"substance":199,"depth":19,"authority":140,"freshness":13,"relevant":22,"comment":200},27,24,"国家级科研机构发布全球首个植物抗逆AI智能体与国内首个耐盐水稻育种芯片，属种业与农业AI领域重大突破，信息增量与时效性俱佳，值得进入每日精选。",[202],{"name":194,"url":191},[145,29,93,146,147],{"code":158,"slug":205,"name":161,"path":206,"parent_code":102},"rice","\u002Ftopic\u002Ffield-crops\u002Frice",[208],{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"status":38,"locked":39,"version":40,"method":41,"evidence":210},{"candidates":211,"agricultural_evidence":14},[212,216,221,225,229,233],{"code":31,"score":20,"supported":14,"title":213,"abstract":214,"tags":215},[48],[48],[29],{"code":158,"score":217,"supported":14,"title":218,"abstract":219,"tags":220},11,[161],[161],[],{"code":164,"score":52,"supported":14,"title":222,"abstract":223,"tags":224},[],[167],[],{"code":51,"score":22,"supported":39,"title":226,"abstract":227,"tags":228},[],[],[93],{"code":174,"score":22,"supported":39,"title":230,"abstract":231,"tags":232},[],[],[146],{"code":179,"score":22,"supported":39,"title":234,"abstract":235,"tags":236},[],[],[145],[238,239],"盐碱地国家技术创新中心 植物抗逆AI智能体","耐盐水稻 盐稻芯1号 液相育种芯片","盐碱地国家技术创新中心植物抗逆AI智能体-2982","2026-09-20T00:03:02.715667Z",{"id":243,"title":244,"url":245,"summary":246,"summary_zh":247,"content":8,"source_name":248,"source_url":245,"published_at":249,"category":250,"cover_url":8,"hotness":13,"is_selected":39,"score":251,"score_detail":252,"sources":257,"tags":259,"primary_topic":264,"secondary_topics":265,"classification":271,"search_phrases":292,"slug":295,"view_count":21,"doi":296,"paper":297,"created_at":313},5583,"Active-Labeling Evaluation for Computer Agriculture Nematode-Cyst Detection Under Sparse Soil-Sample Ground Truth: An Artificial Intelligence Annotation-Efficiency Bound","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23544145","Active learning promises to reduce the annotation burden of training nematode-cyst detection models for precision agriculture, but the size of that reduction is not known when ground truth comes from sparse soil samples rather than exhaustive visual inspection. the present analysis derives an annotation-efficiency bound for pool-based active learning under sparse soil-sample ground truth. The detection task is formalised as a two-stage process in which a classifier selects candidate cysts from soil imagery and a laboratory assay confirms a small labelled subset. Under a declared variance structure with between-cluster standard deviation 6.0, residual standard deviation 4.5 and intraclass correlation 0.64, the bound is evaluated across a design grid of 8, 16, 24 and 32 clusters and effect sizes of 3, 5 and 8 percentage points, with 2000 replications per cell. The annotation-efficiency gain is bounded by the ratio of label noise to cluster-level variance, and that 52 clusters are required to detect a 5-percentage-point improvement at 80% power. The bound provides a design rule for allocating annotation effort between active selection and confirmatory soil sampling.","主动学习有望减轻精准农业中训练线虫囊检测模型所需的标注负担，但当真实标签来自稀疏土壤样本而非详尽的视觉检查时，这种负担减轻的幅度尚不清楚。本分析推导了在稀疏土壤样本真实标签下基于池的主动学习的标注效率界限。检测任务被形式化为两阶段过程：分类器从土壤图像中筛选候选线虫囊，实验室检测确认一个小的已标注子集。在设定的方差结构下——组间标准差为6.0、残差标准差为4.5、组内相关系数为0.64——该界限在8、16、24和32个簇的设计网格以及3、5和8个百分点的效应量下进行评估，每个单元格重复2000次。标注效率增益受标签噪声与簇级方差之比的约束，并且在80%检验功效下检测5个百分点的改进需要52个簇。该界限为在主动选择与验证性土壤采样之间分配标注工作量提供了设计规则。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-21T00:00:00Z","论文",64,{"impact":253,"substance":18,"depth":254,"authority":255,"freshness":13,"relevant":22,"comment":256},8,17,9,"该研究给出稀疏土壤样本下主动学习标注效率的理论边界与聚类设计规则，方法新颖、结论具体，但属细分方法学研究，产业影响有限，适合作为专业精选而非头条。",[258],{"name":248,"url":245},[260,145,261,262,263],"智慧农业","主动学习","线虫检测","土壤采样",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[266],{"code":179,"slug":267,"name":268,"path":269,"parent_code":270},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":38,"locked":39,"version":40,"method":41,"evidence":272},{"candidates":273,"agricultural_evidence":14},[274,279,284],{"code":31,"score":275,"supported":14,"title":276,"abstract":277,"tags":278},14,[32],[116,32],[],{"code":179,"score":255,"supported":14,"title":280,"abstract":282,"tags":283},[281],"artificial intelligence",[],[145],{"code":285,"score":286,"supported":14,"title":287,"abstract":288,"tags":291},"I1",7,[],[289,290],"精准农业","precision agriculture",[260],[293,294],"线虫孢囊 检测 主动学习","稀疏土壤样本 标注效率","线虫孢囊检测主动学习-5583","10.5281\u002Fzenodo.23544145",{"doi":296,"openalex_id":298,"authors":299,"venue":248,"cited_by_count":21,"oa_url":245,"card":306,"direction":310,"ingested_from":312},"W7223082195",[300,302,304],{"name":301,"orcid":8},"Amine Ben Salah",{"name":303,"orcid":8},"Ines Trabelsi",{"name":305,"orcid":8},"Mohamed Aziz Khelifi",{"tldr":307,"method":308,"finding":309,"direction":310,"opportunity":311},"推导稀疏土壤样本真值下主动学习标注效率的理论上界。","基于方差结构与设计网格的统计模拟，2000次重复。","标注效率增益受标签噪声与簇间方差之比限制，检测5个百分点提升需52簇。","农业人工智能与决策模型","可将该上界推广到其他稀疏真值农业检测任务，并探索主动选择与确认采样的最优分配策略。","openalex","2026-10-22T11:20:58.901747Z",{"id":315,"title":316,"url":317,"summary":318,"summary_zh":319,"content":8,"source_name":320,"source_url":317,"published_at":321,"category":250,"cover_url":8,"hotness":13,"is_selected":39,"score":322,"score_detail":323,"sources":325,"tags":327,"primary_topic":333,"secondary_topics":334,"classification":335,"search_phrases":359,"slug":362,"view_count":21,"doi":363,"paper":364,"created_at":397},5576,"Land cover change and soil salinization in Mozambique: A counterfactual analysis over two decades (2001−2022)","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.catena.2026.110691","Soil salinization is a major issue that constrains the sustainable development of agriculture in arid, semi-arid, and coastal lowland areas. It is of great importance for regional land management and climate adaptation to clarify the influence of land cover change on soil salinization. This study aims to quantitatively assess the contribution of land cover change to soil salinization in Mozambique, where both rapid land cover transformation and salinization issues are evident. Firstly, we integrated soil profile electrical conductivity (EC) data, Landsat time-series remote sensing imagery, TerraClimate meteorological data, and the 30 m resolution land cover data, to construct a remote sensing-based EC inversion model for Mozambique. Secondly, we applied a spatially and environmentally constrained counterfactual matching method to quantitatively identify the contributions of different land cover changes on soil salinization trends. Our results reveal that: (1) the spatial distribution of soil salinization in Mozambique exhibits distinct a clear association with proximity to water bodies, with high EC areas primarily concentrated around Lake Malawi in the north and in the coastal regions of Greater Maputo in the south. (2) 26.98% of Mozambique's territory showed a trend of intensifying soil salinization, while 10.88% exhibited a decreasing trend. Areas with intensifying trends are primarily concentrated in the central alluvial plains, localized agricultural development zones, and coastal lowlands. (3) Urbanization was significantly associated with an increasing salinization trend after false discovery rate correction, suggesting that the expansion of impervious surfaces, changes in drainage patterns, and soil compaction may exacerbate localized salt accumulation. Agricultural expansion showed a negative trend difference, consistent with the potential influence of crop cover, tillage, and wet-season leaching, although this association was not significant after false discovery rate correction. The effects of ecological restoration and other factors were not statistically significant. In addition to elucidating the heterogeneous impacts of land cover changes in Mozambique on soil salinization trends, this study also provides methodological guidance and a scientific basis for monitoring\u002Fmanaging soil salinity risks in other coastal lowlands.","土壤盐渍化是制约干旱、半干旱及沿海低地地区农业可持续发展的主要问题。阐明土地覆盖变化对土壤盐渍化的影响，对区域土地管理和气候适应具有重要意义。本研究旨在定量评估土地覆盖变化对莫桑比克土壤盐渍化的贡献，该国土地覆盖转型迅速且盐渍化问题突出。首先，我们整合了土壤剖面电导率（EC）数据、Landsat时间序列遥感影像、TerraClimate气象数据以及30 m分辨率土地覆盖数据，构建了基于遥感的莫桑比克EC反演模型。其次，我们采用空间与环境约束的反事实匹配方法，定量识别不同土地覆盖变化对土壤盐渍化趋势的贡献。研究结果表明：（1）莫桑比克土壤盐渍化的空间分布与水体邻近性呈现明显的关联，高EC区域主要集中于北部的马拉维湖周边以及南部大马普托沿海地区。（2）莫桑比克26.98%的国土面积呈现土壤盐渍化加剧趋势，而10.88%呈现减轻趋势。加剧趋势区域主要集中于中部冲积平原、局部农业开发区及沿海低地。（3）经错误发现率校正后，城市化与盐渍化加剧趋势显著相关，表明不透水面扩张、排水格局改变及土壤压实可能加剧局部盐分累积。农业扩张呈现负向趋势差异，与作物覆盖、耕作及湿季淋洗的潜在影响一致，但该关联经错误发现率校正后不显著。生态恢复及其他因素的影响在统计上不显著。本研究不仅阐明了莫桑比克土地覆盖变化对土壤盐渍化趋势的异质性影响，还为其他沿海低地土壤盐渍化风险的监测与管理提供了方法学指导和科学依据。","CATENA","2026-10-20T00:00:00Z",79,{"impact":87,"substance":86,"depth":19,"authority":275,"freshness":255,"relevant":22,"comment":324},"该研究基于遥感与反事实匹配方法，定量评估土地覆盖变化对盐渍化的贡献，方法新颖、结论可靠，对沿海低地盐渍化监测具有参考价值，但属境外区域研究，国内政策与产业影响有限。",[326],{"name":320,"url":317},[328,329,330,331,332],"遥感监测","莫桑比克","土壤盐渍化","土地覆盖变化","盐分反演",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":39,"version":40,"method":41,"evidence":336},{"candidates":337,"agricultural_evidence":14},[338,342,349,354],{"code":31,"score":275,"supported":14,"title":339,"abstract":340,"tags":341},[32],[116,32],[],{"code":343,"score":286,"supported":14,"title":344,"abstract":345,"tags":348},"I3",[],[346,347],"遥感","remote sensing",[328],{"code":164,"score":74,"supported":14,"title":350,"abstract":351,"tags":353},[],[352,167],"气候适应",[],{"code":355,"score":22,"supported":39,"title":356,"abstract":357,"tags":358},"H6",[],[],[331],[360,361],"莫桑比克 土壤盐渍化 遥感","土地覆盖变化 盐渍化 反事实分析","莫桑比克土壤盐渍化遥感-5576","10.1016\u002Fj.catena.2026.110691",{"doi":363,"openalex_id":365,"authors":366,"venue":320,"cited_by_count":21,"oa_url":317,"card":391,"direction":395,"ingested_from":312},"W7223069171",[367,369,371,373,376,378,381,384,386,388],{"name":368,"orcid":8},"Yue Li",{"name":370,"orcid":8},"Mengfei Shi",{"name":372,"orcid":8},"Fei Zhang",{"name":374,"orcid":375},"Brian Alan Johnson","https:\u002F\u002Forcid.org\u002F0000-0003-1911-3585",{"name":377,"orcid":8},"Gowhar Meraj",{"name":379,"orcid":380},"Jaime Carlos Macuácua","https:\u002F\u002Forcid.org\u002F0000-0002-4822-6098",{"name":382,"orcid":383},"Pankaj Kumar","https:\u002F\u002Forcid.org\u002F0000-0002-5264-3951",{"name":385,"orcid":8},"Yuanfang Chai",{"name":387,"orcid":8},"Hongtao Xu",{"name":389,"orcid":390},"Xu Ma","https:\u002F\u002Forcid.org\u002F0000-0003-0644-7498",{"tldr":392,"method":393,"finding":394,"direction":395,"opportunity":396},"量化莫桑比克2001-2022年土地覆盖变化对土壤盐渍化的贡献。","融合EC剖面、Landsat时序与气候数据反演EC，并用空间环境约束的反事实匹配","26.98%区域盐渍化加剧；城市化显著关联盐渍化上升，农业扩张关联不显著。","农业遥感与作物表型","可将反事实匹配框架迁移至其他滨海低地，并引入作物类型与灌溉制度细化农业扩张的盐渍化效应。","2026-10-22T11:20:42.713789Z",{"id":399,"title":400,"url":401,"summary":402,"summary_zh":403,"content":8,"source_name":404,"source_url":401,"published_at":249,"category":250,"cover_url":8,"hotness":13,"is_selected":39,"score":405,"score_detail":406,"sources":409,"tags":411,"primary_topic":415,"secondary_topics":420,"classification":423,"search_phrases":456,"slug":459,"view_count":21,"doi":460,"paper":461,"created_at":479},5558,"Estimation of Soil Water Content in Winter Wheat Field at Jointing Stage Using Multi-Source Features and Machine Learning","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fagronomy16202071","Accurate and timely monitoring of soil water content (SWC) plays an essential supporting role in crop irrigation management and smart agricultural practice. Remote sensing technology provides rapid and convenient approaches to large-scale farmland SWC estimation or inversion. However, existing mechanistic modeling methods are limited by parameter localization and land surface heterogeneity, while machine learning data-driven methods lack quite good physical interpretability. To address deficiencies in single data-driven methods and single vegetation microwave scattering models, and explore the estimation effect of different feature variables in machine learning. This study proposes an innovative estimation model that integrates machine learning strategies and multi-source features, including spectral indices and features derived from the classic water cloud model (WCM). The novelty of the proposed model lies in balancing physical interpretability and data-driven accuracy, namely extracting relevant soil backscattering parameters through WCM, which are then used as input features in the machine learning. A combination of field-measured data and unmanned aerial vehicle (UAV) multi-source remote sensing data, including multispectral and synthetic aperture radar (SAR) data, was acquired synchronously at the jointing stage of winter wheat. Through extracting variables such as the SAR microwave backscattering coefficient and the optical vegetation index, and conducting feature screening and parameter sensitivity analysis, we optimized the input variable sets of models based on back-propagation (BP) neural network, support vector regression (SVR) and random forest (RF) algorithms. The study results showed that the established estimation model had excellent estimation performance, especially for the RF algorithm, with the highest R2 of 0.855, lowest MAE of 0.0212 cm3\u002Fcm3, and lowest RMSE of 0.0253 cm3\u002Fcm3. It was also shown that different feature input schemes have obvious effects on SWC estimation performance. On the whole, RF had the best estimation accuracy, followed by SVR and then BPNN. This study demonstrated that models integrating multi-source remote sensing data and machine learning could enhance SWC estimation ability for winter wheat fields, and could also serve as a promising approach for SWC monitoring in winter wheat fields in the North China Plain.","准确、及时地监测土壤含水量（SWC）对作物灌溉管理和智慧农业实践具有重要的支撑作用。遥感技术为大规模农田土壤含水量估算或反演提供了快速便捷的手段。然而，现有机理建模方法受参数本地化和地表异质性限制，机器学习数据驱动方法则缺乏良好的物理解释性。针对单一数据驱动方法和单一植被微波散射模型的不足，并探究不同特征变量在机器学习中的估算效果，本研究提出了一种融合机器学习策略与多源特征的创新估算模型，所采用特征包括光谱指数和经典水云模型（WCM）衍生的特征。该模型的新颖性在于平衡物理解释性与数据驱动精度，即通过WCM提取相关土壤后向散射参数，再将其作为机器学习的输入特征。研究在冬小麦拔节期同步获取了田间实测数据与无人机（UAV）多源遥感数据，包括多光谱和合成孔径雷达（SAR）数据。通过提取SAR微波后向散射系数和光学植被指数等变量，并进行特征筛选和参数敏感性分析，优化了基于反向传播（BP）神经网络、支持向量回归（SVR）和随机森林（RF）算法的模型输入变量集。研究结果表明，所建立的估算模型具有优良的估算性能，尤其是RF算法，最高R²为0.855，最低MAE为0.0212 cm³\u002Fcm³，最低RMSE为0.0253 cm³\u002Fcm³。研究还表明，不同特征输入方案对土壤含水量估算性能有明显影响。总体而言，RF估算精度最佳，SVR次之，BPNN再次之。本研究证明，融合多源遥感数据与机器学习的模型能够提升冬小麦田土壤含水量估算能力，也可为华北平原冬小麦田土壤含水量监测提供一种有前景的方法。","Agronomy",77,{"impact":87,"substance":407,"depth":254,"authority":140,"freshness":13,"relevant":22,"comment":408},21,"该研究融合多源遥感与机器学习估算冬小麦拔节期土壤含水量，方法有创新、结论可靠，对智慧灌溉有参考价值，但属细分领域论文，影响范围有限。",[410],{"name":404,"url":401},[260,412,328,413,414],"机器学习","土壤墒情","冬小麦",{"code":416,"slug":417,"name":418,"path":419,"parent_code":102},"A2","wheat","小麦","\u002Ftopic\u002Ffield-crops\u002Fwheat",[421,422],{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"code":179,"slug":267,"name":268,"path":269,"parent_code":270},{"status":38,"locked":39,"version":40,"method":41,"evidence":424},{"candidates":425,"agricultural_evidence":14},[426,431,435,440,445,452],{"code":416,"score":138,"supported":14,"title":427,"abstract":429,"tags":430},[428,417],"winter wheat",[418,428,417],[414],{"code":31,"score":71,"supported":14,"title":432,"abstract":433,"tags":434},[32],[116,32],[413],{"code":179,"score":71,"supported":14,"title":436,"abstract":438,"tags":439},[437],"machine learning",[412,437],[412],{"code":343,"score":13,"supported":14,"title":441,"abstract":442,"tags":444},[],[346,347,443],"multispectral",[328],{"code":446,"score":74,"supported":14,"title":447,"abstract":448,"tags":451},"H3",[],[449,450],"灌溉","irrigation",[],{"code":285,"score":45,"supported":14,"title":453,"abstract":454,"tags":455},[],[260],[260],[457,458],"冬小麦 土壤含水量 遥感","多源遥感 机器学习 墒情","冬小麦土壤含水量遥感-5558","10.3390\u002Fagronomy16202071",{"doi":460,"openalex_id":462,"authors":463,"venue":404,"cited_by_count":21,"oa_url":401,"card":473,"direction":478,"ingested_from":312},"W7223156204",[464,467,469,471],{"name":465,"orcid":466},"Mingliang Jiang","https:\u002F\u002Forcid.org\u002F0000-0002-6486-6087",{"name":468,"orcid":8},"Yi Zhang",{"name":470,"orcid":8},"WEI Lei",{"name":472,"orcid":8},"Chengcai Zhang",{"tldr":474,"method":475,"finding":476,"direction":395,"opportunity":477},"融合WCM物理特征与多源遥感，用机器学习估算冬小麦拔节期土壤含水量。","无人机多光谱与SAR数据，WCM参数+光谱指数，BP\u002FSVR\u002FRF建模。","RF最优，R²达0.855，RMSE为0.0253 cm³\u002Fcm³，特征方案影响显著。","可探索物理约束与深度学习耦合，并迁移至多生育期、多作物及不同土壤质地验证。","智慧农业 \u002F 农业物联网","2026-10-22T11:20:18.887301Z"]