[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2106":3,"related-2106":75},{"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":22,"tags":24,"primary_topic":30,"secondary_topics":36,"classification":37,"search_phrases":69,"slug":72,"view_count":73,"doi":8,"paper":8,"created_at":74},2106,"中国农业大学马韫韬教授到上海农科院作\"AI与植物表型\"专题学术报告 推动智慧农业多学科交叉","https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fjcdt\u002Fcontent_56742","9月2日下午上海农科院信息所举办\"AI时代的智慧农业与植物表型\"专题学术报告会,特邀中国农业大学教授、博士生导师、作物表型三维仿真首席科学家马韫韬作专题学术报告。马韫韬重点介绍了棉花育种表型研究进展,基于DINO视觉大模型实现棉铃精准分割与最佳集中收获期量化,首创无人机交叉环绕飞行三维重建技术,为棉花机采化育种、产量预测与基因挖掘提供高效技术手段。",null,"尊敬的用户，您好！\n\n网站不支持您所使用的浏览器版本（可能会出现网页变形等问题）。为了更好地展示页面效果，请您使用以下浏览器（点击图标会跳转到相关浏览器的官方网站下载页面）。\n\n*   [![Image 3: Chrome](https:\u002F\u002Fwww.saas.sh.cn\u002Fcontent\u002F_common\u002Fbase\u002Fimg\u002Ficon-browser\u002Fbr-chrome.png)Chrome](https:\u002F\u002Fwww.google.cn\u002Fchrome\u002F)\n*   [![Image 4: Firefox](https:\u002F\u002Fwww.saas.sh.cn\u002Fcontent\u002F_common\u002Fbase\u002Fimg\u002Ficon-browser\u002Fbr-firefox.png)Firefox](https:\u002F\u002Fwww.firefox.com\u002F)\n*   [![Image 5: edge](https:\u002F\u002Fwww.saas.sh.cn\u002Fcontent\u002F_common\u002Fbase\u002Fimg\u002Ficon-browser\u002Fbr-edge.png)新Edge](https:\u002F\u002Fwww.microsoft.com\u002Fzh-cn\u002Fedge)\n*   [![Image 6: 360极速浏览器](https:\u002F\u002Fwww.saas.sh.cn\u002Fcontent\u002F_common\u002Fbase\u002Fimg\u002Ficon-browser\u002Fbr-360.png)360极速浏览器](https:\u002F\u002Fbrowser.360.cn\u002Fee\u002F)\n*   [![Image 7: QQ浏览器](https:\u002F\u002Fwww.saas.sh.cn\u002Fcontent\u002F_common\u002Fbase\u002Fimg\u002Ficon-browser\u002Fbr-qq.png)QQ浏览器](https:\u002F\u002Fbrowser.qq.com\u002F)\n\n[关闭提示](javascript:closeUpdateBrowserTips();)\n\n# [![Image 8](https:\u002F\u002Fwww.saas.sh.cn\u002Fcontent\u002Fmain\u002Fbase\u002Fimg\u002Flogo.png)](https:\u002F\u002Fwww.saas.sh.cn\u002F)\n\n[全站群](javascript:void(0) \"全站群\")\n*   全站群\n*   上海市农业科学院\n*   英文版\n*   作物所\n*   林果所\n*   园艺所\n*   食用菌\n*   畜牧所\n*   生态所\n*   信息所\n*   生物所\n*   质标所\n*   服务中心\n*   庄行试验站\n*   科立特\n*   信息化办公室\n*   新品种测试中心\n*   国家家禽中心\n*   上海杂草\n*   食用菌学会\n*   百信\n*   瑞丰\n\n热门搜索：\n\n×\n#### 搜索过于频繁，请输入验证码\n\n[确定](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fjcdt\u002Fcontent_56742)\n\n[English](http:\u002F\u002Fen.saas.sh.cn\u002F)\n\n*   ### [网站首页](https:\u002F\u002Fwww.saas.sh.cn\u002F)\n\n*   ### [院情概况](https:\u002F\u002Fwww.saas.sh.cn\u002Fyqgk \"院情概况\")\n\n    *   ### [院长致辞](https:\u002F\u002Fwww.saas.sh.cn\u002Fyqgk\u002Fyzzc \"院长致辞\")\n\n    *   ### [院容院貌](https:\u002F\u002Fwww.saas.sh.cn\u002Fyqgk\u002Fyrym \"院容院貌\")\n\n*   ### [机构设置](https:\u002F\u002Fwww.saas.sh.cn\u002Fjgsz358 \"机构设置\")\n\n    *   ### [现任领导](https:\u002F\u002Fwww.saas.sh.cn\u002Fjgsz\u002Fxrld \"现任领导\")\n\n    *   ### [院属单位](https:\u002F\u002Fwww.saas.sh.cn\u002Fjgsz\u002Fysdw \"院属单位\")\n\n    *   ### [机关处室](https:\u002F\u002Fwww.saas.sh.cn\u002Fjgsz\u002Fjgcs\u002Fdzbgsxcczystw \"机关处室\")\n\n*   ### [科学研究](https:\u002F\u002Fwww.saas.sh.cn\u002Fkxyj \"科学研究\")\n\n    *   ### [创新平台](https:\u002F\u002Fwww.saas.sh.cn\u002Fkxyj\u002Fcxpt \"创新平台\")\n\n    *   ### [重点学科](https:\u002F\u002Fwww.saas.sh.cn\u002Fkxyj\u002Fzdxk \"重点学科\")\n\n    *   ### [科研诚信](https:\u002F\u002Fwww.saas.sh.cn\u002Fkxyj\u002Fkycx \"科研诚信\")\n\n*   ### [人才队伍](https:\u002F\u002Fwww.saas.sh.cn\u002Frcdw \"人才队伍\")\n\n    *   ### [专家风采](https:\u002F\u002Fwww.saas.sh.cn\u002Frcdw\u002Fzjfcsz \"专家风采\")\n\n    *   ### [联合培养平台](https:\u002F\u002Fwww.saas.sh.cn\u002Frcdw\u002Fpypty \"联合培养平台\")\n\n    *   ### [人才工作动态](https:\u002F\u002Fwww.saas.sh.cn\u002Frcdw\u002Frcgzdt \"人才工作动态\")\n\n    *   ### [人才培养](https:\u002F\u002Fwww.saas.sh.cn\u002Frcdw\u002Frcpy \"人才培养\")\n\n    *   ### [院优秀青年](https:\u002F\u002Fwww.saas.sh.cn\u002Frcdw\u002Fydwjyxqn \"院优秀青年\")\n\n    *   ### [学习型团队](https:\u002F\u002Fwww.saas.sh.cn\u002Frcdw\u002Fxxxtdss \"学习型团队\")\n\n    *   ### [博士后之家](javascript:openexternallink('aHR0cHMlM2ElMmYlMmZ3d3cuc2Fhcy5zaC5jbiUyZnh3englMmZ6dHpsJTJmcG9zdGRvY3M=') \"博士后之家\")\n\n*   ### [合作交流](https:\u002F\u002Fwww.saas.sh.cn\u002Fhzjl \"合作交流\")\n\n    *   ### [国际合作](https:\u002F\u002Fwww.saas.sh.cn\u002Fhzjl\u002Fgjhz \"国际合作\")\n\n    *   ### [国内合作](https:\u002F\u002Fwww.saas.sh.cn\u002Fhzjl\u002Fgnhz \"国内合作\")\n\n*   ### [成果转化](https:\u002F\u002Fwww.saas.sh.cn\u002Fzhhfw \"成果转化\")\n\n    *   ### [成果动态](https:\u002F\u002Fwww.saas.sh.cn\u002Fzhhfw\u002Fcyfwss \"成果动态\")\n\n    *   ### [产业服务](https:\u002F\u002Fwww.saas.sh.cn\u002Fzhhfw\u002Fkfdts \"产业服务\")\n\n    *   ### [拟转化成果](https:\u002F\u002Fwww.saas.sh.cn\u002Fzhhfw\u002Fnzhcg \"拟转化成果\")\n\n    *   ### [院属企业](https:\u002F\u002Fwww.saas.sh.cn\u002Fzhhfw\u002Fysqyss \"院属企业\")\n\n*   ### [文明创建](https:\u002F\u002Fwww.saas.sh.cn\u002Fdjwh \"文明创建\")\n\n    *   ### [全国文明单位创建](https:\u002F\u002Fwww.saas.sh.cn\u002Fdjwh\u002Fwmcj \"全国文明单位创建\")\n\n    *   ### [先进典型](https:\u002F\u002Fwww.saas.sh.cn\u002Fdjwh\u002Fxjdx \"先进典型\")\n\n    *   ### [最靓农科人](https:\u002F\u002Fwww.saas.sh.cn\u002Fdjwh\u002Fzlnkr \"最靓农科人\")\n\n    *   ### [最美农科人](https:\u002F\u002Fwww.saas.sh.cn\u002Fdjwh\u002Fzmnkr \"最美农科人\")\n\n    *   ### [团建动态](https:\u002F\u002Fwww.saas.sh.cn\u002Fdjwh\u002Ftjdt \"团建动态\")\n\n    *   ### [党风廉政](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fztzl\u002Fjjjc \"党风廉政\")\n\n    *   ### [工会园地](https:\u002F\u002Fwww.saas.sh.cn\u002Fdjwh\u002Fghyd \"工会园地\")\n\n    *   ### [老干部之家](https:\u002F\u002Fwww.saas.sh.cn\u002Fdjwh\u002Flgbzj \"老干部之家\")\n\n    *   ### [经验交流](https:\u002F\u002Fwww.saas.sh.cn\u002Fdjwh\u002Fjyjl \"经验交流\")\n\n    *   ### [文化园地](https:\u002F\u002Fwww.saas.sh.cn\u002Fdjwh\u002Fwhyd \"文化园地\")\n\n*   ### [管理服务](https:\u002F\u002Fwww.saas.sh.cn\u002Fglfw \"管理服务\")\n\n    *   ### [行政后勤](https:\u002F\u002Fwww.saas.sh.cn\u002Fglfw\u002Fxzhq \"行政后勤\")\n\n    *   ### [信息化服务](https:\u002F\u002Fwww.saas.sh.cn\u002Fglfw\u002Fwlfw \"信息化服务\")\n\n_您的位置：_[首页](https:\u002F\u002Fwww.saas.sh.cn\u002F)>[新闻中心](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx \"新闻中心\")>[基层动态](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fjcdt \"基层动态\")>详细内容\n\n## 中国农业大学马韫韬教授来我院作“AI与植物表型”专题学术报告\n\n来源：农业科技信息研究所 作者：钱婷婷 发布时间：2026-09-07 14:30:33 浏览次数：77 次【字体：[小](javascript:;)[大](javascript:;)】\n\n9月2日下午，信息所举办“AI时代的智慧农业与植物表型”专题学术报告会，特邀中国农业大学教授、博士生导师、作物表型三维仿真首席科学家马韫韬作专题学术报告。所长施建春主持会议，信息所、园艺所、生态所、质标所科技人员和学生共同参加交流学习。\n\n报告会上，马韫韬结合团队近几年的研究积累，围绕人工智能时代智慧农业与植物表型技术的前沿趋势和最新研究进展作了系统分享。在设施温室方面，团队利用三维仿真模型、微气候仿真方法开展了基于流体力学的温室骨架设计和安全性分析，优化后的温室结构进一步提升了环境调控能力；针对设施内遥感手段缺乏的问题，自主研制RGB、多光谱、热红外多元传感器装备，结合人工智能与视觉大模型实现作物株高、叶面积等表型指标的自动提取与动态监测。\n\n在大田育种表型方面，马韫韬重点介绍了棉花育种表型研究进展。团队开展了基于视觉大模型的棉花单株多性状表型提取与稳定性分析方法；建立基于DINO视觉大模型的棉花集中吐絮特征筛选与采收决策技术体系，实现棉铃精准分割与最佳集中收获期量化；首创无人机交叉环绕飞行三维重建技术，为棉花机采化育种、产量预测与基因挖掘提供了高效技术手段。\n\n交流环节，与会人员围绕温室环境仿真、多模态数据融合、单株表型提取、无人机低空航线设计、三维点云与AI训练等话题与马韫韬展开深入探讨。马韫韬结合计算机与农学交叉背景，就学科交叉融合和研究生培养分享了宝贵经验。\n\n本次报告会是信息所“智慧农业与高通量表型技术前沿”系列学术报告活动之一。报告内容前沿务实，进一步开阔了科研人员的学术视野，促进了人工智能、作物表型、农业信息技术等多学科交叉融合，为推进我院智慧农业科技创新和成果转化注入了新动能。\n\n![Image 9: 5f39e0ad07e8461bb2d0dac0a5ddad26.jpg](https:\u002F\u002Fwww.saas.sh.cn\u002Fupload\u002Fmain\u002Fcontentmanage\u002Farticle\u002Fimage\u002F2026\u002F09\u002F07\u002F5f39e0ad07e8461bb2d0dac0a5ddad26.jpg)\n\n![Image 10: 2ac47dc0f9d84003a2d0ee86b6c82076.jpg](https:\u002F\u002Fwww.saas.sh.cn\u002Fupload\u002Fmain\u002Fcontentmanage\u002Farticle\u002Fimage\u002F2026\u002F09\u002F07\u002F2ac47dc0f9d84003a2d0ee86b6c82076.jpg)\n\n### 相关内容\n\n分享到：\n\n[](http:\u002F\u002Fsns.qzone.qq.com\u002Fcgi-bin\u002Fqzshare\u002Fcgi_qzshare_onekey?url=https%3A%2F%2Fwww.saas.sh.cn%2Fxwzx%2Fjcdt%2Fcontent_56742&title=%E4%B8%AD%E5%9B%BD%E5%86%9C%E4%B8%9A%E5%A4%A7%E5%AD%A6%E9%A9%AC%E9%9F%AB%E9%9F%AC%E6%95%99%E6%8E%88%E6%9D%A5%E6%88%91%E9%99%A2%E4%BD%9C%E2%80%9CAI%E4%B8%8E%E6%A4%8D%E7%89%A9%E8%A1%A8%E5%9E%8B%E2%80%9D%E4%B8%93%E9%A2%98%E5%AD%A6%E6%9C%AF%E6%8A%A5%E5%91%8A&desc=9%E6%9C%882%E6%97%A5%E4%B8%8B%E5%8D%88%EF%BC%8C%E4%BF%A1%E6%81%AF%E6%89%80%E4%B8%BE%E5%8A%9E%E2%80%9CAI%E6%97%B6%E4%BB%A3%E7%9A%84%E6%99%BA%E6%85%A7%E5%86%9C%E4%B8%9A%E4%B8%8E%E6%A4%8D%E7%89%A9%E8%A1%A8%E5%9E%8B%E2%80%9D%E4%B8%93%E9%A2%98%E5%AD%A6%E6%9C%AF%E6%8A%A5%E5%91%8A%E4%BC%9A%EF%BC%8C%E7%89%B9%E9%82%80%E4%B8%AD%E5%9B%BD%E5%86%9C%E4%B8%9A%E5%A4%A7%E5%AD%A6%E6%95%99%E6%8E%88%E3%80%81%E5%8D%9A%E5%A3%AB%E7%94%9F%E5%AF%BC%E5%B8%88%E3%80%81%E4%BD%9C%E7%89%A9%E8%A1%A8%E5%9E%8B%E4%B8%89%E7%BB%B4%E4%BB%BF%E7%9C%9F%E9%A6%96%E5%B8%AD%E7%A7%91%E5%AD%A6%E5%AE%B6%E9%A9%AC%E9%9F%AB%E9%9F%AC%E4%BD%9C%E4%B8%93%E9%A2%98%E5%AD%A6%E6%9C%AF%E6%8A%A5%E5%91%8A%E3%80%82%E6%89%80%E9%95%BF%E6%96%BD%E5%BB%BA%E6%98%A5%E4%B8%BB%E6%8C%81%E4%BC%9A%E8%AE%AE%EF%BC%8C%E4%BF%A1%E6%81%AF%E6%89%80%E3%80%81%E5%9B%AD%E8%89%BA%E6%89%80%E3%80%81%E7%94%9F%E6%80%81%E6%89%80%E3%80%81%E8%B4%A8%E6%A0%87%E6%89%80%E7%A7%91%E6%8A%80%E4%BA%BA%E5%91%98%E5%92%8C%E5%AD%A6%E7%94%9F%E5%85%B1%E5%90%8C%E5%8F%82%E5%8A%A0%E4%BA%A4%E6%B5%81%E5%AD%A6%E4%B9%A0%E3%80%82%E6%8A%A5%E5%91%8A%E4%BC%9A%E4%B8%8A%EF%BC%8C%E9%A9%AC%E9%9F%AB%E9%9F%AC%E7%BB%93%E5%90%88%E5%9B%A2%E9%98%9F%E8%BF%91%E5%87%A0%E5%B9%B4%E7%9A%84%E7%A0%94%E7%A9%B6%E7%A7%AF%E7%B4%AF%EF%BC%8C%E5%9B%B4%E7%BB%95%E4%BA%BA%E5%B7%A5%E6%99%BA%E8%83%BD%E6%97%B6%E4%BB%A3%E6%99%BA%E6%85%A7%E5%86%9C%E4%B8%9A%E4%B8%8E%E6%A4%8D%E7%89%A9%E8%A1%A8%E5%9E%8B%E6%8A%80%E6%9C%AF%E7%9A%84%E5%89%8D%E6%B2%BF%E8%B6%8B%E5%8A%BF%E5%92%8C%E6%9C%80%E6%96%B0%E7%A0%94%E7%A9%B6%E8%BF%9B%E5%B1%95%E4%BD%9C%E4%BA%86%E7%B3%BB%E7%BB%9F%E5%88%86%E4%BA%AB%E3%80%82%E5%9C%A8%E8%AE%BE%E6%96%BD%E6%B8%A9%E5%AE%A4%E6%96%B9%E9%9D%A2%EF%BC%8C%E5%9B%A2%E9%98%9F%E5%88%A9%E7%94%A8%E4%B8%89%E7%BB%B4%E4%BB%BF%E7%9C%9F%E6%A8%A1%E5%9E%8B%E3%80%81%E5%BE%AE%E6%B0%94%E5%80%99%E4%BB%BF%E7%9C%9F%E6%96%B9%E6%B3%95%E5%BC%80%E5%B1%95%E4%BA%86%E5%9F%BA%E4%BA%8E%E6%B5%81%E4%BD%93%E5%8A%9B%E5%AD%A6%E7%9A%84%E6%B8%A9%E5%AE%A4%E9%AA%A8%E6%9E%B6%E8%AE%BE%E8%AE%A1%E5%92%8C%E5%AE%89%E5%85%A8%E6%80%A7%E5%88%86%E6%9E%90%EF%BC%8C%E4%BC%98%E5%8C%96%E5%90%8E%E7%9A%84%E6%B8%A9%E5%AE%A4%E7%BB%93%E6%9E%84%E8%BF%9B%E4%B8%80%E6%AD%A5%E6%8F%90%E5%8D%87%E4%BA%86%E7%8E%AF%E5%A2%83%E8%B0%83%E6%8E%A7%E8%83%BD%E5%8A%9B%EF%BC%9B%E9%92%88%E5%AF%B9%E8%AE%BE%E6%96%BD%E5%86%85%E9%81%A5%E6%84%9F%E6%89%8B%E6%AE%B5%E7%BC%BA%E4%B9%8F%E7%9A%84%E9%97%AE%E9%A2%98%EF%BC%8C%E8%87%AA%E4%B8%BB%E7%A0%94%E5%88%B6RGB%E3%80%81%E5%A4%9A%E5%85%89%E8%B0%B1%E3%80%81%E7%83%AD%E7%BA%A2%E5%A4%96%E5%A4%9A%E5%85%83%E4%BC%A0%E6%84%9F%E5%99%A8%E8%A3%85%E5%A4%87%EF%BC%8C%E7%BB%93%E5%90%88%E4%BA%BA%E5%B7%A5%E6%99%BA%E8%83%BD%E4%B8%8E%E8%A7%86%E8%A7%89%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%AE%9E%E7%8E%B0%E4%BD%9C%E2%80%A6%E2%80%A6&summary=9%E6%9C%882%E6%97%A5%E4%B8%8B%E5%8D%88%EF%BC%8C%E4%BF%A1%E6%81%AF%E6%89%80%E4%B8%BE%E5%8A%9E%E2%80%9CAI%E6%97%B6%E4%BB%A3%E7%9A%84%E6%99%BA%E6%85%A7%E5%86%9C%E4%B8%9A%E4%B8%8E%E6%A4%8D%E7%89%A9%E8%A1%A8%E5%9E%8B%E2%80%9D%E4%B8%93%E9%A2%98%E5%AD%A6%E6%9C%AF%E6%8A%A5%E5%91%8A%E4%BC%9A%EF%BC%8C%E7%89%B9%E9%82%80%E4%B8%AD%E5%9B%BD%E5%86%9C%E4%B8%9A%E5%A4%A7%E5%AD%A6%E6%95%99%E6%8E%88%E3%80%81%E5%8D%9A%E5%A3%AB%E7%94%9F%E5%AF%BC%E5%B8%88%E3%80%81%E4%BD%9C%E7%89%A9%E8%A1%A8%E5%9E%8B%E4%B8%89%E7%BB%B4%E4%BB%BF%E7%9C%9F%E9%A6%96%E5%B8%AD%E7%A7%91%E5%AD%A6%E5%AE%B6%E9%A9%AC%E9%9F%AB%E9%9F%AC%E4%BD%9C%E4%B8%93%E9%A2%98%E5%AD%A6%E6%9C%AF%E6%8A%A5%E5%91%8A%E3%80%82%E6%89%80%E9%95%BF%E6%96%BD%E5%BB%BA%E6%98%A5%E4%B8%BB%E6%8C%81%E4%BC%9A%E8%AE%AE%EF%BC%8C%E4%BF%A1%E6%81%AF%E6%89%80%E3%80%81%E5%9B%AD%E8%89%BA%E6%89%80%E3%80%81%E7%94%9F%E6%80%81%E6%89%80%E3%80%81%E8%B4%A8%E6%A0%87%E6%89%80%E7%A7%91%E6%8A%80%E4%BA%BA%E5%91%98%E5%92%8C%E5%AD%A6%E7%94%9F%E5%85%B1%E5%90%8C%E5%8F%82%E5%8A%A0%E4%BA%A4%E6%B5%81%E5%AD%A6%E4%B9%A0%E3%80%82%E6%8A%A5%E5%91%8A%E4%BC%9A%E4%B8%8A%EF%BC%8C%E9%A9%AC%E9%9F%AB%E9%9F%AC%E7%BB%93%E5%90%88%E5%9B%A2%E9%98%9F%E8%BF%91%E5%87%A0%E5%B9%B4%E7%9A%84%E7%A0%94%E7%A9%B6%E7%A7%AF%E7%B4%AF%EF%BC%8C%E5%9B%B4%E7%BB%95%E4%BA%BA%E5%B7%A5%E6%99%BA%E8%83%BD%E6%97%B6%E4%BB%A3%E6%99%BA%E6%85%A7%E5%86%9C%E4%B8%9A%E4%B8%8E%E6%A4%8D%E7%89%A9%E8%A1%A8%E5%9E%8B%E6%8A%80%E6%9C%AF%E7%9A%84%E5%89%8D%E6%B2%BF%E8%B6%8B%E5%8A%BF%E5%92%8C%E6%9C%80%E6%96%B0%E7%A0%94%E7%A9%B6%E8%BF%9B%E5%B1%95%E4%BD%9C%E4%BA%86%E7%B3%BB%E7%BB%9F%E5%88%86%E4%BA%AB%E3%80%82%E5%9C%A8%E8%AE%BE%E6%96%BD%E6%B8%A9%E5%AE%A4%E6%96%B9%E9%9D%A2%EF%BC%8C%E5%9B%A2%E9%98%9F%E5%88%A9%E7%94%A8%E4%B8%89%E7%BB%B4%E4%BB%BF%E7%9C%9F%E6%A8%A1%E5%9E%8B%E3%80%81%E5%BE%AE%E6%B0%94%E5%80%99%E4%BB%BF%E7%9C%9F%E6%96%B9%E6%B3%95%E5%BC%80%E5%B1%95%E4%BA%86%E5%9F%BA%E4%BA%8E%E6%B5%81%E4%BD%93%E5%8A%9B%E5%AD%A6%E7%9A%84%E6%B8%A9%E5%AE%A4%E9%AA%A8%E6%9E%B6%E8%AE%BE%E8%AE%A1%E5%92%8C%E5%AE%89%E5%85%A8%E6%80%A7%E5%88%86%E6%9E%90%EF%BC%8C%E4%BC%98%E5%8C%96%E5%90%8E%E7%9A%84%E6%B8%A9%E5%AE%A4%E7%BB%93%E6%9E%84%E8%BF%9B%E4%B8%80%E6%AD%A5%E6%8F%90%E5%8D%87%E4%BA%86%E7%8E%AF%E5%A2%83%E8%B0%83%E6%8E%A7%E8%83%BD%E5%8A%9B%EF%BC%9B%E9%92%88%E5%AF%B9%E8%AE%BE%E6%96%BD%E5%86%85%E9%81%A5%E6%84%9F%E6%89%8B%E6%AE%B5%E7%BC%BA%E4%B9%8F%E7%9A%84%E9%97%AE%E9%A2%98%EF%BC%8C%E8%87%AA%E4%B8%BB%E7%A0%94%E5%88%B6RGB%E3%80%81%E5%A4%9A%E5%85%89%E8%B0%B1%E3%80%81%E7%83%AD%E7%BA%A2%E5%A4%96%E5%A4%9A%E5%85%83%E4%BC%A0%E6%84%9F%E5%99%A8%E8%A3%85%E5%A4%87%EF%BC%8C%E7%BB%93%E5%90%88%E4%BA%BA%E5%B7%A5%E6%99%BA%E8%83%BD%E4%B8%8E%E8%A7%86%E8%A7%89%E5%A4%A7%E6%A8%A1%E5%9E%8B%E5%AE%9E%E7%8E%B0%E4%BD%9C%E2%80%A6%E2%80%A6&site=%E4%B8%8A%E6%B5%B7%E5%B8%82%E5%86%9C%E4%B8%9A%E7%A7%91%E5%AD%A6%E9%99%A2&pics=https%3A%2F%2Fwww.saas.sh.cn%2Fupload%2Fmain%2Fcontentmanage%2Farticle%2Fimage%2F2026%2F09%2F07%2F5f39e0ad07e8461bb2d0dac0a5ddad26.jpg)[](javascript:;)[](https:\u002F\u002Fservice.weibo.com\u002Fshare\u002Fshare.php?url=https%3A%2F%2Fwww.saas.sh.cn%2Fxwzx%2Fjcdt%2Fcontent_56742&title=%E4%B8%AD%E5%9B%BD%E5%86%9C%E4%B8%9A%E5%A4%A7%E5%AD%A6%E9%A9%AC%E9%9F%AB%E9%9F%AC%E6%95%99%E6%8E%88%E6%9D%A5%E6%88%91%E9%99%A2%E4%BD%9C%E2%80%9CAI%E4%B8%8E%E6%A4%8D%E7%89%A9%E8%A1%A8%E5%9E%8B%E2%80%9D%E4%B8%93%E9%A2%98%E5%AD%A6%E6%9C%AF%E6%8A%A5%E5%91%8A&pic=https%3A%2F%2Fwww.saas.sh.cn%2Fupload%2Fmain%2Fcontentmanage%2Farticle%2Fimage%2F2026%2F09%2F07%2F5f39e0ad07e8461bb2d0dac0a5ddad26.jpg&appkey=)\n\n[【打印正文】](javascript:;)\n\n*   [![Image 11](https:\u002F\u002Fwww.saas.sh.cn\u002Fcontent\u002Fmain\u002Fbase\u002Fimg\u002Fkslk-04.png?v=eDZQirORLxEnKVrSTe4ycpQjtVfsGLt2I05u1csl8Ok) 电子院报](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fdzybss)\n*   [![Image 12](https:\u002F\u002Fwww.saas.sh.cn\u002Fcontent\u002Fmain\u002Fbase\u002Fimg\u002Fkslk-05.png?v=B-yuuuYvw0Ljo2XSKd3rcReyR4ZfgE326IAL9vrXvTc) 智慧平台](http:\u002F\u002Fi.saas.sh.cn\u002F)\n*   [![Image 13](https:\u002F\u002Fwww.saas.sh.cn\u002Fcontent\u002Fmain\u002Fbase\u002Fimg\u002Fkslk-06.png?v=LCj-Defw13FW2oavEQIAQSq_uCOJRGtgOdYOO4UDRjg) 电子邮箱](http:\u002F\u002Fmail.saas.sh.cn\u002F)\n\n![Image 14](https:\u002F\u002Fwww.saas.sh.cn\u002Fcontent\u002Fmain\u002Fbase\u002Fimg\u002Flogo.png?v=TMOFOIMYr2UoDy7RaN3A1pkcKB9P9_5QoSKm5kY5DlI)\n\n版权所有：上海市农业科学院\n\n网络支持：上海市农业科学院信息化办公室\n\nCopyright © saas.sh.cn. All Rights Reserved\n\n![Image 15](https:\u002F\u002Fwww.saas.sh.cn\u002Fcontent\u002Fmain\u002Fbase\u002Fimg\u002Fga.png?v=ogWDyBgF_mT3-iEIUc4pdUr50l_WqloyJalVdSlgJRM)公安备案号 31012002002003[沪ICP备19007860号-1](http:\u002F\u002Fbeian.miit.gov.cn\u002F)\n\n*   ### 奉浦院区地址\n\n上海市奉贤区金齐路1000号\n\n邮编：201403\n\n电话：021-62208660\n\n*   ### 华漕院区地址\n\n上海市闵行区北翟路2901号\n\n邮编：201106\n\n电话：021-62208660\n\n*   ### 庄行综合试验站地址\n\n上海市奉贤区叶庄公路888号\n\n邮编：201415\n\n电话：021-57460562\n\n*   [手机版](javascript:;)![Image 16: Scan me!](blob:http:\u002F\u002Flocalhost\u002Fc142eb17a42117c70e4750f992ea3c81) \n*   [微信](javascript:;)![Image 17](https:\u002F\u002Fwww.saas.sh.cn\u002Fcontent\u002Fmain\u002Fbase\u002Fimg\u002Fweixin.png?v=HKoimZHLNyFmdkdZYldK3E1DoeqlI-HlaAsXgpJQHFM)\n\nx\n\n#### 微信扫一扫：分享\n\n![Image 18: Scan me!](blob:http:\u002F\u002Flocalhost\u002Fe48aab16a67dfb567438680511ed5263)\n\n微信里点“发现”，扫一下\n\n二维码便可将本文分享至朋友圈。\n\n×\n### 用户登录\n\n 未注册的手机号在初次登录时会自动注册。 \n\n登 录\n\n*   账号密码登录\n*   手机免密登录\n*   微信登录\n\n成功登录后，保持登录状态\n\n[忘记密码？](https:\u002F\u002Fwww.saas.sh.cn\u002FUser\u002Fforgotpassword)\n\n![Image 19](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fjcdt\u002Fcontent_56742)\n\n加载中...\n\n刷新\n\n切换至语音验证码\n\n[Audio 15](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fjcdt\u002Fcontent_56742)播放语音验证码\n\n刷新\n\n返回文字点选验证\n\n![Image 20](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fjcdt\u002Fcontent_56742)\n\n加载中...\n\n刷新\n\n切换至语音验证码\n\n[Audio 16](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fjcdt\u002Fcontent_56742)播放语音验证码\n\n刷新\n\n返回文字点选验证\n\n![Image 21](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fjcdt\u002Fcontent_56742)\n\n加载中...\n\n刷新\n\n切换至语音验证码\n\n[Audio 17](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fjcdt\u002Fcontent_56742)播放语音验证码\n\n刷新\n\n返回文字点选验证\n\n![Image 22](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fjcdt\u002Fcontent_56742)\n\n加载中...\n\n刷新\n\n切换至语音验证码\n\n[Audio 18](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fjcdt\u002Fcontent_56742)播放语音验证码\n\n刷新\n\n返回文字点选验证\n\n![Image 23](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fjcdt\u002Fcontent_56742)\n\n加载中...\n\n刷新\n\n切换至语音验证码\n\n[Audio 19](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fjcdt\u002Fcontent_56742)播放语音验证码\n\n刷新\n\n返回文字点选验证\n\n![Image 24](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fjcdt\u002Fcontent_56742)\n\n加载中...\n\n刷新\n\n切换至语音验证码\n\n[Audio 20](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fjcdt\u002Fcontent_56742)播放语音验证码\n\n刷新\n\n返回文字点选验证\n\n![Image 25](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fjcdt\u002Fcontent_56742)\n\n加载中...\n\n刷新\n\n切换至语音验证码\n\n[Audio 21](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fjcdt\u002Fcontent_56742)播放语音验证码\n\n刷新\n\n返回文字点选验证\n\n![Image 26](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fjcdt\u002Fcontent_56742)\n\n加载中...\n\n刷新\n\n切换至语音验证码\n\n[Audio 22](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fjcdt\u002Fcontent_56742)播放语音验证码\n\n刷新\n\n返回文字点选验证\n\n![Image 27](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fjcdt\u002Fcontent_56742)\n\n加载中...\n\n刷新\n\n切换至语音验证码\n\n[Audio 23](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fjcdt\u002Fcontent_56742)播放语音验证码\n\n刷新\n\n返回文字点选验证\n\n![Image 28](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fjcdt\u002Fcontent_56742)\n\n加载中...\n\n刷新\n\n切换至语音验证码\n\n[Audio 24](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fjcdt\u002Fcontent_56742)播放语音验证码\n\n刷新\n\n返回文字点选验证\n\n![Image 29](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fjcdt\u002Fcontent_56742)\n\n加载中...\n\n刷新\n\n切换至语音验证码\n\n[Audio 25](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fjcdt\u002Fcontent_56742)播放语音验证码\n\n刷新\n\n返回文字点选验证\n\n![Image 30](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fjcdt\u002Fcontent_56742)\n\n加载中...\n\n刷新\n\n切换至语音验证码\n\n[Audio 26](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fjcdt\u002Fcontent_56742)播放语音验证码\n\n刷新\n\n返回文字点选验证\n\n![Image 31](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fjcdt\u002Fcontent_56742)\n\n加载中...\n\n刷新\n\n切换至语音验证码\n\n[Audio 27](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fjcdt\u002Fcontent_56742)播放语音验证码\n\n刷新\n\n返回文字点选验证\n\n![Image 32](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fjcdt\u002Fcontent_56742)\n\n加载中...\n\n刷新\n\n切换至语音验证码\n\n[Audio 28](https:\u002F\u002Fwww.saas.sh.cn\u002Fxwzx\u002Fjcdt\u002Fcontent_56742)播放语音验证码\n\n刷新\n\n返回文字点选验证","上海市农业科学院","2026-09-02T00:00:00Z","报道",10,false,43,{"impact":17,"substance":13,"depth":18,"authority":13,"freshness":19,"relevant":20,"comment":21},8,9,6,1,"省级农科院举办的AI与植物表型学术报告，属细分领域学术交流动态，有交叉学科价值但公共影响有限，时效性一般。",[23],{"name":10,"url":6},[25,26,27,28,29],"智慧农业","农业人工智能","学术交流","植物表型","棉花育种",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":38,"locked":14,"version":39,"method":40,"evidence":41},"classified","2026-10-22.2","rules",{"candidates":42,"agricultural_evidence":46},[43,50,56,63],{"code":44,"score":45,"supported":46,"title":47,"abstract":48,"tags":49},"I1",12,true,[25],[25],[25],{"code":31,"score":51,"supported":46,"title":52,"abstract":53,"tags":55},4,[],[54],"大模型",[26],{"code":57,"score":58,"supported":46,"title":59,"abstract":60,"tags":62},"A6",3,[],[61],"棉花",[],{"code":64,"score":58,"supported":46,"title":65,"abstract":66,"tags":68},"I3",[],[67],"作物表型",[],[70,71],"农业人工智能 学术交流 智慧农业 棉花育种","农业人工智能 学术交流","农业人工智能学术交流智慧农业棉花育种-2106",2,"2026-09-11T00:04:21.627848Z",{"total":19,"page":20,"page_size":19,"items":76},[77,149,205,272,336,398],{"id":78,"title":79,"url":80,"summary":81,"summary_zh":82,"content":8,"source_name":83,"source_url":80,"published_at":84,"category":85,"cover_url":8,"hotness":13,"is_selected":14,"score":86,"score_detail":87,"sources":92,"tags":94,"primary_topic":97,"secondary_topics":98,"classification":99,"search_phrases":112,"slug":115,"view_count":116,"doi":117,"paper":118,"created_at":148},5562,"pxGPT: A schema-constrained multimodal LLM framework for plant phenotyping","https:\u002F\u002Fdoi.org\u002F10.1093\u002Fbioinformatics\u002Fbtag781","Abstract Summary Deep learning can scale image-based plant phenotyping but typically targets predefined traits, whereas manual phenotypic description is more flexible but difficult to scale. We present Phenotype eXplorer Generative Plant Traits (pxGPT), a Python framework that converts multi-view plant images into structured phenotype records. The workflow combines free-text description, dataset-specific schema generation with human review, and schema-constrained information extraction. We evaluated the extraction stage on three Brassica datasets using 78,973 annotations from ten annotators who had no access to pxGPT predictions. For 38-45 qualitative traits per dataset, pxGPT-human agreement ranged from 0.572 to 0.712, compared with 0.620 to 0.739 agreement among human annotators. All 32,736 required trait fields were present; 93 values were empty, and no qualitative descriptor violations were recorded. For selected morphological structures, pooled false-positive rates were 0.5-8.0%, while sensitivity varied across structure types in one mature-plant dataset (37.5-100%). The curated schemas were applied unchanged with two commercial models and one locally hosted open-weight model, with differences in mean accuracy of 0.03 or less. In the evaluated Brassica datasets, these results support schema-guided extraction of visible plant traits without separate model training for each trait. Human-guided schema development offers a path to extend pxGPT to other crops and imaging conditions, with accuracy requiring validation in each new setting. Availability and Implementation The software is available at https:\u002F\u002Fgithub.com\u002FYaoChengLab\u002Fpxgpt and an archival version of the source code is available on Zenodo (https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22931745). Curated schemas used in this study, annotation guides, phenotype records and human annotations are available at https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22907554. Supplementary information Supplementary data are available at Bioinformatics online.","摘要 深度学习能够扩展基于图像的植物表型分析，但通常针对预定义性状，而人工表型描述更为灵活却难以规模化。我们提出Phenotype eXplorer Generative Plant Traits（pxGPT），一个将多视角植物图像转换为结构化表型记录的Python框架。该工作流程结合了自由文本描述、数据集特定模式生成与人工审核，以及模式约束的信息提取。我们在三个芸薹属（Brassica）数据集上评估了提取阶段，使用了来自十名标注者的78,973条标注，这些标注者无法获取pxGPT的预测结果。对于每个数据集38-45个定性性状，pxGPT与人工标注者之间的一致性范围为0.572至0.712，而人工标注者之间的一致性为0.620至0.739。所有32,736个所需性状字段均已存在；93个值为空，未记录到定性描述符违规。对于选定的形态结构，合并假阳性率为0.5-8.0%，而在一个成熟植株数据集中，灵敏度因结构类型而异（37.5-100%）。经整理的模式在未作修改的情况下应用于两个商业模型和一个本地部署的开放权重模型，平均准确率差异不超过0.03。在所评估的芸薹属数据集中，这些结果支持在无需为每个性状单独训练模型的情况下，对可见植物性状进行模式引导的提取。人工引导的模式开发为将pxGPT扩展至其他作物和成像条件提供了途径，其准确性需在每个新设置中加以验证。可用性与实现 该软件可在https:\u002F\u002Fgithub.com\u002FYaoChengLab\u002Fpxgpt获取，源代码的存档版本可在Zenodo（https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22931745）获取。本研究中使用的经整理模式、标注指南、表型记录和人工标注可在https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22907554获取。补充信息 补充数据可在Bioinformatics在线获取。","Bioinformatics","2026-10-20T00:00:00Z","论文",81,{"impact":88,"substance":89,"depth":88,"authority":90,"freshness":18,"relevant":20,"comment":91},18,22,14,"提出基于模式约束的多模态大模型植物表型提取框架，在近8万条标注上验证，方法新颖、数据规模可观，对智慧育种与表型自动化有参考价值。",[93],{"name":83,"url":80},[25,26,28,95,96],"多模态大模型","芸薹属",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":14,"version":39,"method":40,"evidence":100},{"candidates":101,"agricultural_evidence":46},[102,108],{"code":31,"score":17,"supported":46,"title":103,"abstract":104,"tags":107},[],[105,106],"深度学习","deep learning",[26,95],{"code":44,"score":20,"supported":14,"title":109,"abstract":110,"tags":111},[],[],[25],[113,114],"pxGPT 植物表型","Brassica 表型 多模态大模型","pxGPT植物表型-5562",0,"10.1093\u002Fbioinformatics\u002Fbtag781",{"doi":117,"openalex_id":119,"authors":120,"venue":83,"cited_by_count":116,"oa_url":139,"card":140,"direction":146,"ingested_from":147},"W7223127960",[121,124,126,129,132,135,137],{"name":122,"orcid":123},"Po‐Xing Zheng","https:\u002F\u002Forcid.org\u002F0000-0001-5827-5865",{"name":125,"orcid":8},"Jheng-Yan Ou",{"name":127,"orcid":128},"Yu-Lin Wu","https:\u002F\u002Forcid.org\u002F0009-0003-8596-9047",{"name":130,"orcid":131},"Ruei-Shiuan Wang","https:\u002F\u002Forcid.org\u002F0009-0007-5159-1129",{"name":133,"orcid":134},"WU Ting-li","https:\u002F\u002Forcid.org\u002F0000-0001-7996-5515",{"name":136,"orcid":8},"Te-Chang Hsu",{"name":138,"orcid":8},"Yao-Cheng Lin","https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Fadvance-article-pdf\u002Fdoi\u002F10.1093\u002Fbioinformatics\u002Fbtag781\u002F72201337\u002Fbtag781.pdf",{"tldr":141,"method":142,"finding":143,"direction":144,"opportunity":145},"提出pxGPT框架，用多模态大模型将多视角植物图像转为结构化表型记录。","结合自由文本描述、人工审核的模式生成与模式约束信息抽取，在三个芸薹属数据集上评估","pxGPT与人工标注一致性0.572-0.712，接近人工间一致性，且无需逐性状训练模型。","农业遥感与作物表型","可探索将模式引导抽取迁移至更多作物与复杂成像条件，并研究自动化模式生成以降低人工审核成本。","智慧农业 \u002F 农业物联网","openalex","2026-10-22T11:20:22.173561Z",{"id":150,"title":151,"url":152,"summary":153,"summary_zh":154,"content":8,"source_name":155,"source_url":152,"published_at":156,"category":85,"cover_url":8,"hotness":13,"is_selected":14,"score":86,"score_detail":157,"sources":160,"tags":162,"primary_topic":165,"secondary_topics":166,"classification":167,"search_phrases":189,"slug":192,"view_count":116,"doi":193,"paper":194,"created_at":204},5315,"PLANT-GPK v4.0: Multi-Stage Plant Phenotyping with Time-Discovery and Harvest Prediction","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23461121","This paper presents a comprehensive extension to the PLANT-GPK framework, demonstrating its robust capability to analyze plants across entirely different developmental stages from single images. By formulating an inverse problem that simultaneously optimizes physiological parameters and the hidden time dimension (t), the model successfully discovered the exact age of two distinct wheat samples: a vegetative (green) stage and a senescent (golden) stage. The framework bridges computer vision, spatial heterogeneity analysis, and ODE-based physics to provide a complete digital twin capable of forecasting the exact day of harvest regardless of the plant's current state.","本文对PLANT-GPK框架进行了全面扩展，展示了其仅凭单张图像即可分析处于完全不同发育阶段植物的稳健能力。通过构建一个同时优化生理参数与隐藏时间维度（t）的反问题，该模型成功推断出两个不同小麦样本的精确年龄：一个处于营养期（绿色阶段），另一个处于衰老期（金色阶段）。该框架融合了计算机视觉、空间异质性分析以及基于常微分方程（ODE）的物理建模，提供了一个完整的数字孪生，无论植物当前处于何种状态，均能预测确切的收获日期。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-19T00:00:00Z",{"impact":88,"substance":89,"depth":88,"authority":158,"freshness":13,"relevant":20,"comment":159},13,"该研究提出从单张图像反演植物生育阶段与收获日的数字孪生框架，方法新颖且具产业应用潜力，值得进入每日精选。",[161],{"name":155,"url":152},[25,26,163,28,164],"数字孪生","收获预测",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":14,"version":39,"method":40,"evidence":168},{"candidates":169,"agricultural_evidence":46},[170,175,182],{"code":44,"score":17,"supported":46,"title":171,"abstract":172,"tags":174},[],[163,173],"digital twin",[163,25],{"code":31,"score":176,"supported":46,"title":177,"abstract":178,"tags":181},7,[],[179,180],"计算机视觉","computer vision",[26],{"code":183,"score":19,"supported":46,"title":184,"abstract":185,"tags":188},"A2",[],[186,187],"小麦","wheat",[],[190,191],"PLANT-GPK 植物表型","小麦 收获期 预测","PLANT-GPK植物表型-5315","10.5281\u002Fzenodo.23461121",{"doi":193,"openalex_id":195,"authors":196,"venue":155,"cited_by_count":116,"oa_url":152,"card":199,"direction":144,"ingested_from":147},"W7222875391",[197],{"name":198,"orcid":8},"MOHAMMED TAHAR SAIM",{"tldr":200,"method":201,"finding":202,"direction":144,"opportunity":203},"扩展PLANT-GPK框架，从单张图像反演植物生理参数与隐藏时间维度，实现跨生育期表型分析与收获期预","基于ODE物理模型与逆问题优化，联合估计生理参数和隐藏时间t，用两个不同生育期小","模型能准确发现两个不同生育期小麦样本的精确年龄，并预测确切收获日期。","可将单图时间反演扩展到多作物多生育期，结合时序遥感构建大尺度数字孪生与收获期预报。","2026-10-19T23:30:19.267920Z",{"id":206,"title":207,"url":208,"summary":209,"summary_zh":210,"content":8,"source_name":211,"source_url":208,"published_at":212,"category":85,"cover_url":8,"hotness":13,"is_selected":14,"score":86,"score_detail":213,"sources":215,"tags":217,"primary_topic":220,"secondary_topics":221,"classification":222,"search_phrases":234,"slug":237,"view_count":51,"doi":238,"paper":239,"created_at":271},2783,"Toward scalable organ-level 3D plant segmentation: A systematic and quantitative review through the lens of the data-algorithm-computing triangle","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.isprsjprs.2026.09.003","The precise characterization of plant morphology provides valuable insights into plant-environment interactions and genetic evolution. A key technology for extracting this information is 3D segmentation, which delineates individual plant organs from complex point clouds. Despite significant progress in general 3D computer vision domains, the adoption of 3D segmentation for plant phenotyping remains limited by three major challenges: (i) the scarcity of large-scale annotated datasets, (ii) technical difficulties in adapting advanced deep neural networks to plant point clouds, and (iii) the lack of standardized benchmarks and evaluation protocols tailored to plant science. This review systematically addresses these barriers by: (i) providing an overview of existing 3D plant datasets in the context of general 3D segmentation domains, (ii) systematically summarizing deep learning-based methods for point cloud semantic and instance segmentation, (iii) introducing Plant Segmentation Studio (PSS), an open-source framework for reproducible benchmarking, and (iv) conducting extensive quantitative experiments to evaluate representative networks and sim-to-real learning strategies. Our findings highlight the efficacy of sparse-convolution and serialization-based backbones, as well as transformer-based instance segmentation networks, while also emphasizing the complementary role of modeling-based and augmentation-based synthetic data generation for sim-to-real learning in reducing annotation demands. Overall, this study bridges the gap between algorithmic advances and practical deployment, providing immediate tools for researchers and a roadmap for developing data-efficient and generalizable deep learning solutions in 3D plant phenotyping. Data and code are available at: https:\u002F\u002Fgithub.com\u002Fperrydoremi\u002FPlantSegStudio .","植物形态的精确表征为理解植物-环境相互作用和遗传演化提供了宝贵见解。提取此类信息的一项关键技术是三维分割，它能够从复杂点云中勾勒出植物各器官。尽管通用三维计算机视觉领域已取得显著进展，三维分割在植物表型分析中的应用仍受限于三大挑战：(i) 大规模标注数据集的稀缺，(ii) 将先进深度神经网络适配于植物点云的技术困难，以及(iii) 缺乏面向植物科学量身定制的标准化基准与评估协议。本综述通过以下方式系统性地应对这些障碍：(i) 在通用三维分割领域的背景下概述现有三维植物数据集，(ii) 系统总结基于深度学习的点云语义与实例分割方法，(iii) 介绍植物分割工作室（Plant Segmentation Studio, PSS）——一个用于可重复基准测试的开源框架，以及(iv) 开展大量定量实验以评估代表性网络和仿真到现实（sim-to-real）学习策略。我们的研究结果凸显了稀疏卷积与基于序列化的主干网络以及基于Transformer的实例分割网络的有效性，同时强调了基于建模和基于增强的合成数据生成在仿真到现实学习中对降低标注需求的互补作用。总体而言，本研究弥合了算法进展与实际部署之间的差距，为研究人员提供了即时可用的工具，并为在三维植物表型分析中开发数据高效且具有泛化能力的深度学习解决方案提供了路线图。数据与代码见：https:\u002F\u002Fgithub.com\u002Fperrydoremi\u002FPlantSegStudio 。","ISPRS Journal of Photogrammetry and Remote Sensing","2026-09-16T00:00:00Z",{"impact":88,"substance":89,"depth":88,"authority":90,"freshness":18,"relevant":20,"comment":214},"ISPRS顶刊综述，系统梳理器官级3D植物分割的数据-算法-算力瓶颈，并开源Plant Segmentation Studio基准框架，对作物表型与智慧育种有直接工具价值。",[216],{"name":211,"url":208},[25,26,218,28,219],"开源工具","三维点云",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":14,"version":39,"method":40,"evidence":223},{"candidates":224,"agricultural_evidence":46},[225,230],{"code":31,"score":226,"supported":46,"title":227,"abstract":228,"tags":229},11,[],[105,179,106,180],[219,26],{"code":44,"score":20,"supported":14,"title":231,"abstract":232,"tags":233},[],[],[25],[235,236],"农业人工智能 三维点云 开源工具 智慧农业","农业人工智能 三维点云","农业人工智能三维点云开源工具智慧农业-2783","10.1016\u002Fj.isprsjprs.2026.09.003",{"doi":238,"openalex_id":240,"authors":241,"venue":211,"cited_by_count":116,"oa_url":208,"card":266,"direction":144,"ingested_from":147},"W7213280479",[242,244,246,248,251,254,256,258,260,263],{"name":243,"orcid":8},"Ruiming Du",{"name":245,"orcid":8},"Guangxun Zhai",{"name":247,"orcid":8},"Tian Qiu",{"name":249,"orcid":250},"Shichao Jin","https:\u002F\u002Forcid.org\u002F0000-0003-1150-336X",{"name":252,"orcid":253},"Dawei Li","https:\u002F\u002Forcid.org\u002F0000-0002-9702-8848",{"name":255,"orcid":8},"Zhihong Ma",{"name":257,"orcid":8},"Yongliang Qiao",{"name":259,"orcid":8},"Junfeng Gao",{"name":261,"orcid":262},"Haiyan Cen","https:\u002F\u002Forcid.org\u002F0000-0003-0266-2123",{"name":264,"orcid":265},"Yu Jiang","https:\u002F\u002Forcid.org\u002F0000-0003-4495-3033",{"tldr":267,"method":268,"finding":269,"direction":144,"opportunity":270},"系统综述植物器官级3D分割，提出数据-算法-算力三角框架并开源基准平台PSS。","综述3D植物数据集与深度学习分割方法，构建PSS开源基准并做定量实验。","稀疏卷积与序列化骨干及Transformer实例分割有效，合成数据可降低标注需求。","可探索数据高效、跨物种泛化的3D植物分割模型与标准化评测协议。","2026-09-17T23:30:30.425366Z",{"id":273,"title":274,"url":275,"summary":276,"summary_zh":277,"content":8,"source_name":278,"source_url":275,"published_at":212,"category":85,"cover_url":8,"hotness":13,"is_selected":14,"score":279,"score_detail":280,"sources":283,"tags":285,"primary_topic":287,"secondary_topics":288,"classification":289,"search_phrases":305,"slug":308,"view_count":73,"doi":309,"paper":310,"created_at":335},2742,"LeafTrackNet: A deep learning framework for robust leaf tracking in top-down plant phenotyping","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112417","LeafTrackNet: A deep learning framework for robust leaf tracking in top-down plant phenotyping。Computers and Electronics in Agriculture","LeafTrackNet：一种用于自上而下植物表型分析中稳健叶片追踪的深度学习框架。","Computers and Electronics in Agriculture",70,{"impact":45,"substance":88,"depth":281,"authority":90,"freshness":18,"relevant":20,"comment":282},17,"核心期刊发表的叶片追踪深度学习框架，方法有创新但属细分技术进展，产业影响有限，可作为农业AI主题聚合素材。",[284],{"name":278,"url":275},[25,26,105,286,28],"作物监测",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[],{"status":38,"locked":14,"version":39,"method":40,"evidence":290},{"candidates":291,"agricultural_evidence":46},[292,297,301],{"code":31,"score":293,"supported":46,"title":294,"abstract":295,"tags":296},16,[106],[105,106],[26,105],{"code":44,"score":20,"supported":14,"title":298,"abstract":299,"tags":300},[],[],[25],{"code":64,"score":20,"supported":14,"title":302,"abstract":303,"tags":304},[],[],[286],[306,307],"农业人工智能 作物监测 智慧农业 植物表型","农业人工智能 作物监测","农业人工智能作物监测智慧农业植物表型-2742","10.1016\u002Fj.compag.2026.112417",{"doi":309,"openalex_id":311,"authors":312,"venue":278,"cited_by_count":116,"oa_url":275,"card":330,"direction":144,"ingested_from":147},"W7213430727",[313,316,319,321,323,325,328],{"name":314,"orcid":315},"Shanghua Liu","https:\u002F\u002Forcid.org\u002F0009-0009-9855-9040",{"name":317,"orcid":318},"Majharulislam Babor","https:\u002F\u002Forcid.org\u002F0000-0002-5440-7573",{"name":320,"orcid":8},"Christoph Verduyn",{"name":322,"orcid":8},"Breght Vandenberghe",{"name":324,"orcid":8},"Bruno Betoni Parodi",{"name":326,"orcid":327},"Cornelia Weltzien","https:\u002F\u002Forcid.org\u002F0000-0002-2951-3614",{"name":329,"orcid":8},"Marina M. -C. Höhne",{"tldr":331,"method":332,"finding":333,"direction":144,"opportunity":334},"提出LeafTrackNet深度学习框架，实现俯视植物表型中稳健的叶片追踪。","基于深度学习的叶片追踪框架，用于俯视植物表型图像序列。","该框架能稳健追踪叶片，提升植物表型分析的自动化与准确性。","可探索多物种、遮挡与生长形变下的长期叶片追踪及三维表型融合。","2026-09-17T23:30:01.562015Z",{"id":337,"title":338,"url":339,"summary":340,"summary_zh":341,"content":8,"source_name":155,"source_url":339,"published_at":342,"category":85,"cover_url":8,"hotness":13,"is_selected":14,"score":343,"score_detail":344,"sources":347,"tags":349,"primary_topic":353,"secondary_topics":359,"classification":361,"search_phrases":377,"slug":380,"view_count":116,"doi":381,"paper":382,"created_at":397},5592,"Evaluation of Concept-Rank Collapse Audits for Computer Vision Agriculture Disease Classifiers Under Low-Label Regimes: An Interpretability Capacity Bound for Smallholder Fungicide Selectivity","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23545193","Concept-based interpretability methods for plant-disease classifiers are typically evaluated by whether their concept activations correlate with human-annotated labels, but this criterion is silent on a prior question: whether the classifier's internal representation retains enough concept-rank structure for any audit to be informative. the present analysis formalises that prior question as an interpretability capacity bound. A classifier is modelled as a concept-rank operator whose singular values govern how much concept-level signal survives the projection from pixel space to class logits, and a collapse audit is defined as the ratio of retained concept-rank energy to total concept energy. Under a low-label regime, where concept annotations are scarce and the audit must be estimated from few labelled examples, the bound predicts that audit reliability degrades as a function of the concept-rank spectrum and the label budget. The analysis is a theoretical and methodological contribution: it derives the bound, states the conditions under which a collapse audit is identifiable, and characterises the operating characteristics of the audit as a decision procedure under a declared variance structure (between-cluster SD = 6.0, residual SD = 4.5, intraclass correlation = 0.64). Power was estimated across 2000 design cells for cluster counts of 8, 16, 24 and 32 and effect sizes of 3, 5 and 8 percentage points; 52 clusters were required for 5 percentage points at 80% power. The bound reframes concept audits as capacity tests rather than fidelity tests, with consequences for how smallholder fungicide-selectivity decisions should be supported by interpretable disease classifiers.","面向植物病害分类器的基于概念的可解释性方法，通常以其概念激活是否与人工标注标签相关作为评价标准，但该标准对一个更先前的问题保持沉默：分类器的内部表征是否保留了足够的概念秩结构，从而使任何审计具有信息量。本分析将该先前问题形式化为一个可解释性容量上界。分类器被建模为概念秩算子，其奇异值支配着从像素空间到类别logits的投影中概念级信号得以保留的程度，并将坍缩审计定义为保留的概念秩能量与总概念能量之比。在低标签情形下，概念标注稀缺且审计必须由少量标注样本估计，该上界预测审计可靠性会随概念秩谱和标签预算的函数而退化。本分析是一项理论和方法论贡献：推导出该上界，陈述坍缩审计可识别的条件，并在声明的方差结构（簇间SD = 6.0，残差SD = 4.5，组内相关系数 = 0.64）下刻画审计作为决策程序的操作特征。在2000个设计单元中，针对簇数为8、16、24和32以及效应量为3、5和8个百分点的情形估计了功效；在80%功效下达到5个百分点需要52个簇。该上界将概念审计重新框定为容量检验而非保真度检验，并对可解释病害分类器应如何支持小农杀菌剂选择性决策具有启示意义。","2026-10-21T00:00:00Z",69,{"impact":17,"substance":345,"depth":88,"authority":45,"freshness":13,"relevant":20,"comment":346},21,"理论方法论文，提出可解释性容量上界并给出审计功效分析，对智慧农业病害识别可信度有参考价值，但属小众方法学研究、缺乏田间实证，暂不宜进入每日精选。",[348],{"name":155,"url":339},[25,26,350,351,352],"小农户","植物病害识别","可解释性",{"code":354,"slug":355,"name":356,"path":357,"parent_code":358},"G2","farm-services","社会化服务与规模经营","\u002Ftopic\u002Frural-services\u002Ffarm-services","G",[360],{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"status":38,"locked":14,"version":39,"method":40,"evidence":362},{"candidates":363,"agricultural_evidence":46},[364,369,373],{"code":354,"score":45,"supported":46,"title":365,"abstract":367,"tags":368},[366],"smallholder",[366],[350],{"code":31,"score":13,"supported":46,"title":370,"abstract":371,"tags":372},[180],[],[26,351],{"code":44,"score":20,"supported":14,"title":374,"abstract":375,"tags":376},[],[],[25],[378,379],"农业人工智能 植物病害识别 可解释性 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可解释性智慧农业-5592","10.5281\u002Fzenodo.23545193",{"doi":381,"openalex_id":383,"authors":384,"venue":155,"cited_by_count":116,"oa_url":339,"card":391,"direction":395,"ingested_from":147},"W7223137323",[385,387,389],{"name":386,"orcid":8},"Akshay Ramgoolam",{"name":388,"orcid":8},"Priya Bundhoo Appadoo",{"name":390,"orcid":8},"Jean-Noël LEspérance",{"tldr":392,"method":393,"finding":394,"direction":395,"opportunity":396},"提出可解释性容量上界，评估低标签下概念秩崩溃审计的可靠性。","将分类器建模为概念秩算子，推导容量上界并做2000格功效模拟。","审计可靠性随概念秩谱与标签预算下降；5个百分点效应需52个聚类达80%功效。","农业人工智能与决策模型","可将容量上界用于小农户杀菌剂选择性决策的可解释模型审计与标签预算设计。","2026-10-22T11:21:10.425290Z",{"id":399,"title":400,"url":401,"summary":402,"summary_zh":403,"content":8,"source_name":155,"source_url":401,"published_at":342,"category":85,"cover_url":8,"hotness":13,"is_selected":14,"score":343,"score_detail":404,"sources":406,"tags":408,"primary_topic":412,"secondary_topics":418,"classification":420,"search_phrases":446,"slug":449,"view_count":116,"doi":450,"paper":451,"created_at":463},5591,"Hierarchical Conformal Risk Control for Artificial Intelligence Agriculture Irrigation Scheduling Under Unmodeled Infiltration: A Computer Safety-Guarantee Evaluation","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23543665","Irrigation scheduling algorithms that rely on soil-moisture forecasts are vulnerable to unmodeled infiltration, the process by which water bypasses the root zone through preferential pathways that resistance-based soil models cannot represent. The framework is evaluated through a replication-based design study that characterises the operating characteristics of the before-after-control-impact estimator used to audit scheduler performance, under a declared variance structure with between-cluster standard deviation 6.0, residual standard deviation 4.5 and intraclass correlation 0.64. Power was estimated across 2000 design cells spanning cluster counts of 8, 16, 24 and 32 and effect sizes of 3, 5 and 8 percentage points. The analysis indicates that 54 clusters are required to detect a 5-percentage-point effect at 80% power, and that the minimum detectable effect declines steeply as cluster count rises from 8 to 32. The contribution is a formal safety guarantee for irrigation decision support that remains valid when the infiltration model is wrong, together with an audit design that makes the guarantee empirically checkable.","依赖土壤湿度预报的灌溉调度算法容易受到未建模入渗的影响，即水分通过优先路径绕过根区的过程，而基于阻力的土壤模型无法表征这一过程。该框架通过一项基于重复的设计研究进行评估，该研究刻画了用于审计调度器性能的前后对照影响估计量的运行特性，其所依据的声明方差结构为：组间标准差6.0、残差标准差4.5、组内相关系数0.64。功效估计覆盖2000个设计单元，涵盖聚类数8、16、24和32以及效应量3、5和8个百分点。分析表明，在80%功效下检测5个百分点效应需要54个聚类，且最小可检测效应随聚类数从8增至32而急剧下降。本文的贡献在于为灌溉决策支持提供了一种正式的安全保证，该保证在入渗模型错误时仍然有效，同时提出了一种使该保证可经实证检验的审计设计。",{"impact":17,"substance":89,"depth":88,"authority":45,"freshness":18,"relevant":20,"comment":405},"该研究提出在入渗模型失配条件下仍有效的灌溉决策安全保证框架，并给出可审计的试验设计，方法新颖、结论可靠，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。",[407],{"name":155,"url":401},[25,26,409,410,411],"灌溉决策","安全保证","试验设计",{"code":413,"slug":414,"name":415,"path":416,"parent_code":417},"H3","irrigation","水资源与灌溉","\u002Ftopic\u002Fenvironment\u002Firrigation","H",[419],{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"status":38,"locked":14,"version":39,"method":40,"evidence":421},{"candidates":422,"agricultural_evidence":46},[423,429,435,442],{"code":413,"score":424,"supported":46,"title":425,"abstract":426,"tags":428},15,[414],[427,414],"灌溉",[409],{"code":31,"score":45,"supported":46,"title":430,"abstract":432,"tags":434},[431],"artificial intelligence",[433],"decision support",[26],{"code":436,"score":19,"supported":46,"title":437,"abstract":438,"tags":441},"H2",[],[439,440],"土壤","soil",[],{"code":44,"score":20,"supported":14,"title":443,"abstract":444,"tags":445},[],[],[25],[447,448],"灌溉调度 安全保证","农业人工智能 安全保证 智慧农业 灌溉决策","灌溉调度安全保证-5591","10.5281\u002Fzenodo.23543665",{"doi":450,"openalex_id":452,"authors":453,"venue":155,"cited_by_count":116,"oa_url":401,"card":458,"direction":395,"ingested_from":147},"W7223131205",[454,456],{"name":455,"orcid":8},"Nassima Benkhelifa",{"name":457,"orcid":8},"Yacine Aït Ahmed",{"tldr":459,"method":460,"finding":461,"direction":395,"opportunity":462},"提出分层保形风险控制，为未建模入渗下的灌溉调度提供安全保证。","分层保形风险控制与基于重复设计的BACI审计，2000个设计单元功效分析。","检测5个百分点效应需54个集群，最小可检测效应随集群数增加陡降。","可将保形风险控制扩展到其他未建模扰动下的农业决策安全保证与审计设计。","2026-10-22T11:21:10.283561Z"]