[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-137":3,"related-137":67},{"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":21,"tags":23,"primary_topic":29,"secondary_topics":35,"classification":36,"search_phrases":61,"slug":64,"view_count":65,"doi":8,"paper":8,"created_at":66},137,"甘蓝种质创新团队在甘蓝盐热复合胁迫响应机制研究中取得新进展——江苏省农科院蔬菜所","https:\u002F\u002Fwww.jaas.ac.cn\u002Fxwdt\u002Fkyjz\u002F202607\u002Ft20260727_1170304.html","全球气候变暖导致高温与土壤盐渍化等非生物胁迫频发叠加,严重威胁甘蓝等喜凉蔬菜作物的产量与品质。江苏省农业科学院蔬菜所甘蓝种质创新团队在盐热复合胁迫响应机制研究中取得新进展,相关研究将为甘蓝抗逆育种提供重要的基因资源与理论基础,助力选育适应气候变化的新品种。",null,"江苏省农业科学院 2026-07-27","2026-07-27T00:00:00Z","报道",10,false,54,{"impact":16,"substance":16,"depth":17,"authority":12,"freshness":18,"relevant":19,"comment":20},15,12,2,1,"省级农科院在甘蓝抗逆育种方面的研究进展，属于农业科技细分领域，有一定信息增量，但时效性较差。",[22],{"name":9,"url":6},[24,25,26,27,28],"种质创新","江苏省农科院","甘蓝","盐热胁迫","抗逆育种",{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},"B1","vegetables","蔬菜","\u002Ftopic\u002Fhorticulture\u002Fvegetables","B",[],{"status":37,"locked":13,"version":38,"method":39,"evidence":40},"classified","2026-10-22.2","rules",{"candidates":41,"agricultural_evidence":44},[42,48,55],{"code":30,"score":43,"supported":44,"title":45,"abstract":46,"tags":47},23,true,[32,26],[32,26],[26],{"code":49,"score":50,"supported":44,"title":51,"abstract":52,"tags":54},"H2",3,[],[53],"土壤",[],{"code":56,"score":50,"supported":44,"title":57,"abstract":58,"tags":60},"H7",[],[59],"气候变化",[],[62,63],"江苏省农科院 抗逆育种 盐热胁迫 种质创新","江苏省农科院 抗逆育种","江苏省农科院抗逆育种盐热胁迫种质创新-137",6,"2026-08-01T06:01:54.218487Z",{"total":65,"page":19,"page_size":65,"items":68},[69,116,172,216,276,331],{"id":70,"title":71,"url":72,"summary":73,"summary_zh":8,"content":74,"source_name":75,"source_url":8,"published_at":76,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":77,"score_detail":78,"sources":83,"tags":85,"primary_topic":90,"secondary_topics":91,"classification":92,"search_phrases":111,"slug":114,"view_count":50,"doi":8,"paper":8,"created_at":115},283,"江苏省农科院甘蓝种质创新团队在Plant Stress发表甘蓝盐热复合胁迫响应机制研究——首次揭示硫代葡萄糖苷合成途径核心调控枢纽作用","https:\u002F\u002Fwiki.antpedia.com\u002F%E6%B1%9F%E8%8B%8F%E7%9C%81%E5%86%9C%E4%B8%9A%E7%A7%91%E5%AD%A6%E9%99%A2%E8%94%AC%E8%8F%9C%E6%89%80%E7%94%98%E8%93%9D%E7%A7%8D%E8%B4%A8%E5%88%9B%E6%96%B0%E5%9B%A2%E9%98%9F%E5%9C%A8%E7%94%98%E8%93%9D%E7%9B%90%E7%83%AD%E5%A4%8D%E5%90%88%E8%83%81%E8%BF%AB%E5%93%8D%E5%BA%94%E6%9C%BA%E5%88%B6%E7%A0%94%E7%A9%B6%E4%B8%AD%E5%8F%96%E5%BE%97%E6%96%B0%E8%BF%9B%E5%B1%95-3657556-news","江苏省农业科学院蔬菜所甘蓝种质创新团队以耐盐热性状差异显著的甘蓝种质为材料,设置对照、高温、盐胁迫及盐热复合胁迫四组处理,整合表型观测、生理指标测定、转录组与代谢组学分析,系统解析了甘蓝应对复合胁迫的适应策略,相关研究成果近日发表于国际著名期刊Plant Stress(Q1,IF=8.1)。研究发现,复合胁迫触发了甘蓝在形态、生理、转录和代谢层面的协同重编程,其中盐胁迫是主导驱动因子;光合参数与防御酶活性等生理指标的变化,与相关基因表达及关键代谢物积累高度关联。尤为重要的是,研究首次揭示硫代葡萄糖苷生物合成途径在甘蓝盐热复合胁迫响应中发挥核心调控枢纽作用,推测其通过协同调控活性氧稳态和渗透平衡来增强胁迫耐受性。该途径中CYP79B2-1、BCAT4和ST5a-2等关键基因在复合胁迫下呈现基因型特异性表达模式,为解析甘蓝复合胁迫适应的分子基础提供了新视角。本研究不仅为解析甘蓝复杂胁迫适应机制建立了分子框架,也为多胁迫耐受性甘蓝品种分子育种提供了关键候选基因资源,获得江苏省种业振兴揭榜挂帅项目[JBGS(2021)015]和国家重点研发计划(2023YFD1201501)资助。","江苏省农业科学院蔬菜所甘蓝种质创新团队在甘蓝盐热复合胁迫响应机制研究中取得新进展\n\n发布时间：2026-08-04 16:43 原文链接： 江苏省农业科学院蔬菜所甘蓝种质创新团队在甘蓝盐热复合胁迫响应机制研究中取得新进展\n\n全球气候变暖导致高温与土壤盐渍化等非生物胁迫频发叠加，严重威胁甘蓝等喜凉蔬菜作物的产量与品质。然而，甘蓝协同响应盐热复合胁迫的调控机制尚不明确，成为制约多胁迫耐受性品种分子育种的关键瓶颈。\n\n针对这一关键问题，蔬菜所甘蓝种质创新团队以耐盐热性状差异显著的甘蓝种质为材料，设置对照、高温、盐胁迫及盐热复合胁迫四组处理，整合表型观测、生理指标测定、转录组与代谢组学分析，系统解析了甘蓝应对复合胁迫的适应策略。相关研究成果近日发表于国际著名期刊Plant Stress（Q1，IF=8.1）。\n\n研究发现，复合胁迫触发了甘蓝在形态、生理、转录和代谢层面的协同重编程，其中盐胁迫是主导驱动因子。光合参数与防御酶活性等生理指标的变化，与相关基因表达及关键代谢物积累高度关联。尤为重要的是，研究首次揭示硫代葡萄糖苷生物合成途径在甘蓝盐热复合胁迫响应中发挥核心调控枢纽作用，推测其通过协同调控活性氧稳态和渗透平衡来增强胁迫耐受性。该途径中CYP79B2-1、BCAT4和ST5a-2等关键基因在复合胁迫下呈现基因型特异性表达模式，为解析甘蓝复合胁迫适应的分子基础提供了新视角。本研究揭示的途径特异性和基因型特异性的调控功能，不仅为解析甘蓝复杂胁迫适应机制建立了分子框架，也为多胁迫耐受性甘蓝品种分子育种提供了关键候选基因资源。\n\n该研究获得江苏省种业振兴揭榜挂帅项目[JBGS（2021）015]和国家重点研发计划（2023YFD1201501）的资助。","江苏省农业科学院 2026-08-04","2026-08-04T00:00:00Z",77,{"impact":79,"substance":80,"depth":79,"authority":17,"freshness":81,"relevant":19,"comment":82},18,22,7,"省级农科院在Q1期刊发表甘蓝盐热复合胁迫机制研究，首次揭示硫代葡萄糖苷合成途径核心调控作用，具有较高科研价值，但属细分领域进展，影响范围有限。",[84],{"name":75,"url":72},[25,26,86,87,88,89],"盐热复合胁迫","硫代葡萄糖苷","Plant Stress","蔬菜所",{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},[],{"status":37,"locked":13,"version":38,"method":39,"evidence":93},{"candidates":94,"agricultural_evidence":44},[95,99,105],{"code":30,"score":16,"supported":44,"title":96,"abstract":97,"tags":98},[26],[32,26],[26],{"code":100,"score":50,"supported":44,"title":101,"abstract":102,"tags":104},"F1",[],[103],"种业",[],{"code":106,"score":50,"supported":44,"title":107,"abstract":108,"tags":110},"F2",[],[109],"分子育种",[],[112,113],"江苏省农科院 盐热复合胁迫 硫代葡萄糖苷 蔬菜所","江苏省农科院 盐热复合胁迫","江苏省农科院盐热复合胁迫硫代葡萄糖苷蔬菜所-283","2026-08-07T23:57:49.936510Z",{"id":117,"title":118,"url":119,"summary":120,"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":121,"score_detail":122,"sources":125,"tags":127,"primary_topic":131,"secondary_topics":132,"classification":144,"search_phrases":167,"slug":170,"view_count":123,"doi":8,"paper":8,"created_at":171},212,"江苏农科院早醒1号与早醒4号西瓜品种成果转化——分别以30万元转让南京金色种业","https:\u002F\u002Fjaas.ac.cn\u002Fznbmxwlsml\u002Fcgzhc\u002Fart\u002F2026\u002Fart_df878dc5f0774920b39bb323556e17fe.html","江苏省农业科学院果树研究所选育的早醒1号和早醒4号两个西瓜品种,根据促进科技成果转化法规定进行转化价格公示,分别以30万元转让南京金色种业科技有限公司,公示截止日期至2026年8月11日。",42,{"impact":123,"substance":17,"depth":123,"authority":17,"freshness":18,"relevant":19,"comment":124},8,"省级农科院西瓜品种成果转化公示，属农业科技细分进展，信息具体但时效性较低。",[126],{"name":9,"url":119},[128,25,129,130],"成果转化","西瓜品种","果树所",{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},[133,139],{"code":134,"slug":135,"name":136,"path":137,"parent_code":138},"G1","extension-transfer","农技推广与成果转化","\u002Ftopic\u002Frural-services\u002Fextension-transfer","G",{"code":100,"slug":140,"name":141,"path":142,"parent_code":143},"seed-industry","种业与品种管理","\u002Ftopic\u002Finputs-equipment\u002Fseed-industry","F",{"status":37,"locked":13,"version":38,"method":39,"evidence":145},{"candidates":146,"agricultural_evidence":44},[147,151,157,161],{"code":134,"score":17,"supported":44,"title":148,"abstract":149,"tags":150},[128],[128],[128],{"code":30,"score":152,"supported":44,"title":153,"abstract":155,"tags":156},11,[154],"西瓜",[154],[],{"code":100,"score":152,"supported":44,"title":158,"abstract":159,"tags":160},[103],[103],[],{"code":162,"score":50,"supported":44,"title":163,"abstract":164,"tags":166},"B2",[],[165],"果树",[],[168,169],"江苏省农科院 成果转化 西瓜品种 果树所","江苏省农科院 成果转化","江苏省农科院成果转化西瓜品种果树所-212","2026-08-04T23:54:46.505111Z",{"id":173,"title":174,"url":175,"summary":176,"summary_zh":8,"content":177,"source_name":178,"source_url":8,"published_at":179,"category":180,"cover_url":8,"hotness":12,"is_selected":13,"score":181,"score_detail":182,"sources":186,"tags":188,"primary_topic":192,"secondary_topics":193,"classification":194,"search_phrases":209,"slug":212,"view_count":213,"doi":214,"paper":8,"created_at":215},145,"基于改进YOLOv10和LAMP通道剪枝的串番茄成熟度检测算法研发","https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045","赵丽成、卢鑫羽、吴茜、任妮、周玲莉、程雅雯、胡安琦、戚超(江苏省农业科学院农业信息研究所\u002F淮阴工学院)提出基于改进YOLOv10的轻量级串番茄成熟度目标检测模型LampCT-YOLO:在主干网络引入SegNeXt注意力机制,基于梯度的全局通道重要性方法LAMP通道剪枝显著压缩模型体积和计算复杂度。LampCT-YOLO对红熟早\u002F中\u002F晚期mAP分别达84.6%\u002F89.5%\u002F88.4%,应用LAMP通道剪枝后参数量和计算量分别减少63.07%和50.06%,推理速度提升23.1%;部署至自主研发的果蔬巡检机器人在边缘设备NVIDIA Jetson AGX Orin上达到9.1帧\u002Fs推理速度。","欢迎您访问《智慧农业（中英文）》官方网站！[English](https:\u002F\u002Fwww.smartag.net.cn\u002FEN\u002F2096-8094\u002Fhome.shtml)\n\n[![Image 1](https:\u002F\u002Fwww.smartag.net.cn\u002Fimages\u002F2096-8094\u002Fimages\u002Fbanner.png)](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F2096-8094\u002Fhome.shtml)\n\n[![Image 2](https:\u002F\u002Fwww.smartag.net.cn\u002Fimages\u002F2096-8094\u002Fimages\u002Fbanner_mobile.png)](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F2096-8094\u002Fhome.shtml)\n\n[![Image 3](https:\u002F\u002Fwww.smartag.net.cn\u002Fimages\u002F2096-8094\u002Fimages\u002Fyyzkj.png)](https:\u002F\u002Fpano.bookan.com.cn\u002F?id=60704&cid=352)\n\nToggle navigation[智慧农业](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045)\n\n*   [网站首页](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F2096-8094\u002Fhome.shtml)\n*   [期刊介绍](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002Fcolumn\u002Fcolumn133.shtml)\n*   [编委会](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002Fcolumn\u002Fcolumn153.shtml)\n*   [投稿指南](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002Fcolumn\u002Fcolumn135.shtml)\n*   [期刊服务](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002Fcolumn\u002Fcolumn124.shtml)\n*   [下载中心](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002Fcolumn\u002Fcolumn126.shtml)\n*   [联系我们](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002Fcolumn\u002Fcolumn127.shtml)\n\n[Smart Agriculture](https:\u002F\u002Fwww.smartag.net.cn\u002F) ›› [2026](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002Farticle\u002FshowTenYearVolumnDetail.do?nian=2026), [Vol. 8](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002Farticle\u002FshowTenYearVolumnDetail.do?nian=2026) ›› [Issue (2)](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002Fvolumn\u002Fvolumn_838.shtml): 133-146.doi: [10.12133\u002Fj.smartag.SA202507045](https:\u002F\u002Fdoi.org\u002F10.12133\u002Fj.smartag.SA202507045)\n\n• 信息处理与决策 •[上一篇](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002Fabstract\u002Fabstract22683.shtml)\n\n### 基于改进YOLOv10和LAMP通道剪枝的串番茄成熟度检测算法研发\n\n赵丽成 1,2, 卢鑫羽 2, 吴茜 2, 任妮 2, 周玲莉 2, 程雅雯 2, 胡安琦 2, 戚超 2([![Image 4](https:\u002F\u002Fwww.smartag.net.cn\u002Fimages\u002Femail.png)](mailto:chaoqi@jaas.ac.cn))\n\n1.   1. 淮阴工学院化学工程学院，江苏 淮安 223003，中国\n\n2. 江苏省农业科学院农业信息研究所，江苏 南京 210014，中国\n\n*   `收稿日期:`2025-07-30 `出版日期:`2026-03-30 \n*   `基金项目:`国家自然科学基金(32201664); 江苏省农业科技自主创新资金（CX（24）1021）(CX(24)1021); 农机研发制造推广应用一体化试点专项(JSYTH08) \n*   `作者简介:`赵丽成，硕士研究生，研究方向为作物表型算法。E-mail：[zhao_orange@163.com](mailto:zhao_orange@163.com) \n*   `通信作者:`戚 超，博士，助理研究员，研究方向为图像处理与机器视觉。E-mail：[chaoqi@jaas.ac.cn](mailto:chaoqi@jaas.ac.cn) \n\n### An Improved YOLOv10-Based Tomato Ripeness Detection Algorithm with LAMP Channel Pruning\n\nZHAO Licheng 1,2, LU Xinyu 2, WU Qian 2, REN Ni 2, ZHOU Lingli 2, CHENG Yawen 2, HU Anqi 2, QI Chao 2([![Image 5](https:\u002F\u002Fwww.smartag.net.cn\u002Fimages\u002Femail.png)](mailto:chaoqi@jaas.ac.cn))\n\n1.   1. School of Chemical Engineering, Huaiyin Institute of Technology, Huai'an 223003, China\n\n2. Institute of Agricultural Information, Jiangsu Academy of Agricultural Sciences, Nanjing 210014, China\n\n*   `Received:`2025-07-30 `Online:`2026-03-30 \n*   `Foundation items:`National Natural Science Foundation of China(32201664); Jiangsu Provincial Agricultural Science and Technology Independent Innovation Fund(CX(24)1021); Special Pilot Program for the Integrated R&D, Manufacturing, Promotion and Application of Agricultural Machinery(JSYTH08) \n*   `About author:`biography:ZHAO Licheng, E-mail: [zhao_orange@163.com](mailto:zhao_orange@163.com) \n*   `Corresponding author:`QI Chao, E-mail: [chaoqi@jaas.ac.cn](mailto:chaoqi@jaas.ac.cn) \n\n## [在线阅读 33](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#)\n\n## [知网下载](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045)\n\n## [本地下载 63](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#1)\n\n[_![Image 6](https:\u002F\u002Fwww.smartag.net.cn\u002Fimages\u002Fknowledge\\_map1.png)_ ## 可视化 0](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002Flexeme\u002FshowArticleByLexeme.do?articleID=22641)\n\n#### [摘要\u002FAbstract](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045)\n\n**摘要：**\n\n**【目的\u002F意义】** 由于串番茄果实密集重叠、温室光照复杂多变及果实颜色连续渐变等因素，检测模型在对成熟度进行精准快速识别时面临挑战。因此，提出了一种基于改进YOLOv10（You Only Look Once version 10）的轻量级串番茄成熟度目标检测模型LampCT-YOLO （Cluster Tomato YOLO with Layer-wise Adaptive Mask Pruning），以提高检测精度、推理速度和鲁棒性。 **【方法】** 以YOLOv10为基线模型，在主干网络引入SegNeXt（Segmentation Next）注意力机制，通过自适应调整注意力权重，增强模型对3类不同成熟度串番茄关键区域（如边界、颜色深浅）的特征提取能力；在训练完成的模型基础上，通过基于梯度的全局通道重要性方法LAMP（Layer-wise Adaptive Mask Pruning）通道剪枝，显著压缩模型体积和计算复杂度，同时有效保持模型对串番茄3分类成熟度的高检测性能。 **【结果和讨论】** 在NVIDIA A100显卡环境下，LampCT-YOLO模型对串番茄红熟早期、中期、晚期的平均精度均值（Mean Average Precision, mAP）分别为84.6%、89.5%、88.4%，相比YOLOv10分别提升了5.5、7.7和0.9个百分点，对串番茄3个成熟度类别的mAP 50 为87.6%，相比YOLOv10提升了4.7个百分点。应用LAMP通道剪枝技术后，模型的参数量和计算量分别减少63.07%和50.06%，推理速度提升23.1%。部署至自主研发的果蔬巡检机器人后，在边缘设备NVIDIA Jetson AGX Orin上达到9.1帧\u002Fs的推理速度，实现了检测精度与实时性的有效平衡。 **【结论】** 研究结果可为基于巡检机器人的串番茄成熟度精准快速识别提供坚实的技术支撑。\n\n**关键词:**[串番茄,](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#)[成熟度检测,](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#)[注意力机制,](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#)[通道剪枝,](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#)[果蔬巡检机器人,](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#)[YOLOv10](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#)\n\n**Abstract:**\n\n**[Objective]** As a major crop in protected horticulture, cluster tomatoes grow in clusters with dense overlapping fruits. In greenhouse environments, light conditions are complex and variable, and the fruit color transitions continuously from green to red across different ripening stages, showing continuous gradation characteristics. These factors result in the low efficiency and strong subjectivity of traditional manual recognition methods. Meanwhile, deep learning-based detection models often suffer from decreased detection accuracy, large localization errors, and slow inference speed when facing complex backgrounds and color interference, making it difficult to meet the dual requirements of real-time performance and high precision in practical applications. Therefore, to meet the practical application requirements of high accuracy, high real-time performance, and strong robustness for cluster tomato ripeness detection, this paper proposes a lightweight target detection model for cluster tomato ripeness, namely LampCT-YOLO (Cluster Tomato YOLO with LAMP pruning), which is based on improved YOLOv10. Through structural optimization and lightweight transformation of the baseline model, the detection accuracy, inference speed, and robustness are effectively improved, providing a novel technical solution for cluster tomato ripeness detection. **[Methods]** Taking YOLOv10 as the baseline model, first, the issue of insufficient feature extraction capability in complex scenarios was addressed by introducing the SegNeXt attention mechanism into the backbone network. By adaptively adjusting attention weights and calculating the correlation matrix between different feature channels, the mechanism automatically identified color channels strongly associated with the three ripeness levels of cluster tomatoes and assigned them higher attention weights, while suppressing feature responses from irrelevant background channels such as greenhouse frames, soil, and irrigation pipes. To achieve lightweight deployment of the model and meet the real-time detection requirements of edge devices, a gradient-based global channel importance method—LAMP channel pruning technology—was introduced after model training. The core principle of this technology was to evaluate the contribution of each channel to the model's detection performance by calculating the gradient magnitude of channels in each network layer, thereby eliminating redundant channels. This significantly reduced the model size and computational complexity while effectively maintaining the model's high detection performance for the three-category ripeness classification of cluster tomatoes. **[Results and Discussions]** Experiments showed that under the environment of NVIDIA A100 graphics card, for 240 cluster tomato images in the test set, the LampCT-YOLO model exhibited excellent detection performance. The mean average precision at 50 intersection over union (mAP50) for the early ripe, mid-ripe, and late ripe stages of cluster tomatoes was 84.6%, 89.5%, and 88.4%, respectively, which represented increases of 5.5, 7.7, and 0.9 percentage points compared with YOLOv10. The average mAP50 for the three ripeness categories of cluster tomatoes reached 87.6%, a 4.7 percentage points improvement over YOLOv10, demonstrating outstanding performance in both detection accuracy and stability. In addition, the model was found to maintain high recognition accuracy when facing variations in light intensity, fruit occlusion ratio, and background complexity, indicating good robustness and environmental adaptability. Regarding the lightweight effect, after applying the LAMP channel pruning technology, the number of model parameters and computational complexity were reduced by 63.07% and 50.06%, respectively, while the inference speed was improved by 23.1%. This effectively met the requirements of edge computing devices for real-time detection and low power consumption, alleviating the trade-off between model accuracy and inference speed. To verify the practical application value of the LampCT-YOLO model, the model was deployed on a self-developed fruit and vegetable inspection robot, which conducted field tests on 456 clusters of tomatoes in a real greenhouse environment. The results showed that the inspection robot successfully identified 78, 61, and 248 clusters of early ripe, mid-ripe, and late ripe cluster tomatoes, respectively, with detection accuracies of 84.8%, 87.1%, and 84.4%, and an average accuracy of 85.4%. Meanwhile, there were 5, 7, and 10 false detections, as well as 9, 2, and 36 missed detections for the early ripe, mid-ripe, and late ripe stages respectively, which to a certain extent reflected the practical application potential of the model. **[Conclusions]** The optimized LampCT-YOLO model not only significantly improves the recognition accuracy of cluster tomatoes at different ripening stages but also greatly reduces the model complexity, successfully achieving efficient deployment in resource-constrained scenarios. This model effectively balances the dual requirements of detection accuracy and real-time performance for inspection robots, and further constructs a reusable technical framework for the ripeness detection of protected horticultural fruits and vegetables. It provides strong support for the transformation of protected agriculture from labor-intensive to technology-intensive, and injects key innovative impetus into the large-scale and diversified implementation of smart agriculture.\n\n**Key words:**[cluster tomato,](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#)[ripeness detection,](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#)[attention mechanism,](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#)[channel pruning,](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#)[fruit and vegetable inspection robot,](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#)[YOLOv10](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#)\n\n**中图分类号:**\n\n*   [TP391.41](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#)\n\n*   [S641.2](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#)\n\n*   [S626](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#)\n\n#### 引用本文\n\n赵丽成, 卢鑫羽, 吴茜, 任妮, 周玲莉, 程雅雯, 胡安琦, 戚超. 基于改进YOLOv10和LAMP通道剪枝的串番茄成熟度检测算法研发[J]. 智慧农业(中英文), 2026, 8(2): 133-146.\n\nZHAO Licheng, LU Xinyu, WU Qian, REN Ni, ZHOU Lingli, CHENG Yawen, HU Anqi, QI Chao. An Improved YOLOv10-Based Tomato Ripeness Detection Algorithm with LAMP Channel Pruning[J]. Smart Agriculture, 2026, 8(2): 133-146.\n\n#### 使用本文\n\n**[[收藏文章](javascript:;)](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#) \u002F[推荐](javascript:void(null))**\n**导出引用管理器**[EndNote](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002Farticle\u002FgetTxtFile.do?fileType=EndNote&id=22641)|[Ris](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002Farticle\u002FgetTxtFile.do?fileType=Ris&id=22641)|[BibTeX](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002Farticle\u002FgetTxtFile.do?fileType=BibTeX&id=22641)\n\n**链接本文:**[https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045)\n\n[https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002FY2026\u002FV8\u002FI2\u002F133](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002FY2026\u002FV8\u002FI2\u002F133)\n\n#### [图\u002F表 18](javascript:;)\n\n[![Image 7](https:\u002F\u002Fwww.smartag.net.cn\u002Ffileup\u002F2096-8094\u002FFIGURE\u002F2026-8-2\u002FImages\u002F2096-8094-2026-8-2-133\u002Fthumbnail\u002F43D49185-E927-4387-B4EB-F464B099DD26-F001.jpg)](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#figureClass13721)\n\n**图1**\n\n移动巡检机器人现场图\n\n![Image 8](https:\u002F\u002Fwww.smartag.net.cn\u002Ffileup\u002F2096-8094\u002FFIGURE\u002F2026-8-2\u002FImages\u002F2096-8094-2026-8-2-133\u002F43D49185-E927-4387-B4EB-F464B099DD26-F001.jpg)\n\n 图1 \n\n[![Image 9](https:\u002F\u002Fwww.smartag.net.cn\u002Ffileup\u002F2096-8094\u002FFIGURE\u002F2026-8-2\u002FImages\u002F2096-8094-2026-8-2-133\u002Fthumbnail\u002F43D49185-E927-4387-B4EB-F464B099DD26-F002.jpg)](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#figureClass13722)\n\n**图2**\n\n串番茄不同成熟度示例图\n\n![Image 10](https:\u002F\u002Fwww.smartag.net.cn\u002Ffileup\u002F2096-8094\u002FFIGURE\u002F2026-8-2\u002FImages\u002F2096-8094-2026-8-2-133\u002F43D49185-E927-4387-B4EB-F464B099DD26-F002.jpg)\n\n 图2 \n\n[![Image 11](https:\u002F\u002Fwww.smartag.net.cn\u002Fimages\u002Ftable-icon.gif)](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#inline_content13723)\n\n**表1**\n\n串番茄三类成熟度标注样本数量\n\n| 成熟时期 | 训练集 | 验证集 | 测试集 | 总计（占比\u002F%） |\n| :---: | :---: | :---: | :---: | :---: |\n| 红熟早期 | 93 | 841 | 148 | 1 082（32.07） |\n| 红熟中期 | 104 | 934 | 166 | 1 204（35.07） |\n| 红熟晚期 | 107 | 831 | 149 | 1 087（32.86） |\n\n 表1 \n\n[![Image 12](https:\u002F\u002Fwww.smartag.net.cn\u002Ffileup\u002F2096-8094\u002FFIGURE\u002F2026-8-2\u002FImages\u002F2096-8094-2026-8-2-133\u002Fthumbnail\u002F43D49185-E927-4387-B4EB-F464B099DD26-F003.jpg)](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#figureClass13724)\n\n**图3**\n\n串番茄图像数据增强示例图\n\n![Image 13](https:\u002F\u002Fwww.smartag.net.cn\u002Ffileup\u002F2096-8094\u002FFIGURE\u002F2026-8-2\u002FImages\u002F2096-8094-2026-8-2-133\u002F43D49185-E927-4387-B4EB-F464B099DD26-F003.jpg)\n\n 图3 \n\n[![Image 14](https:\u002F\u002Fwww.smartag.net.cn\u002Ffileup\u002F2096-8094\u002FFIGURE\u002F2026-8-2\u002FImages\u002F2096-8094-2026-8-2-133\u002Fthumbnail\u002F43D49185-E927-4387-B4EB-F464B099DD26-F004.jpg)](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#figureClass13725)\n\n**图4**\n\nLampCT-YOLO模型结构图\n\n![Image 15](https:\u002F\u002Fwww.smartag.net.cn\u002Ffileup\u002F2096-8094\u002FFIGURE\u002F2026-8-2\u002FImages\u002F2096-8094-2026-8-2-133\u002F43D49185-E927-4387-B4EB-F464B099DD26-F004.jpg)\n\n 图4 \n\n[![Image 16](https:\u002F\u002Fwww.smartag.net.cn\u002Ffileup\u002F2096-8094\u002FFIGURE\u002F2026-8-2\u002FImages\u002F2096-8094-2026-8-2-133\u002Fthumbnail\u002F43D49185-E927-4387-B4EB-F464B099DD26-F005.jpg)](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#figureClass13726)\n\n**图5**\n\nSegNeXt注意力机制网络结构图\n\n![Image 17](https:\u002F\u002Fwww.smartag.net.cn\u002Ffileup\u002F2096-8094\u002FFIGURE\u002F2026-8-2\u002FImages\u002F2096-8094-2026-8-2-133\u002F43D49185-E927-4387-B4EB-F464B099DD26-F005.jpg)\n\n 图5 \n\n[![Image 18](https:\u002F\u002Fwww.smartag.net.cn\u002Ffileup\u002F2096-8094\u002FFIGURE\u002F2026-8-2\u002FImages\u002F2096-8094-2026-8-2-133\u002Fthumbnail\u002F43D49185-E927-4387-B4EB-F464B099DD26-F006.jpg)](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#figureClass13727)\n\n**图6**\n\nLAMP通道剪枝示意图\n\n![Image 19](https:\u002F\u002Fwww.smartag.net.cn\u002Ffileup\u002F2096-8094\u002FFIGURE\u002F2026-8-2\u002FImages\u002F2096-8094-2026-8-2-133\u002F43D49185-E927-4387-B4EB-F464B099DD26-F006.jpg)\n\n 图6 \n\n[![Image 20](https:\u002F\u002Fwww.smartag.net.cn\u002Fimages\u002Ftable-icon.gif)](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#inline_content13728)\n\n**表2**\n\n串番茄成熟度检测的SegNeXt注意力机制消融试验\n\n| 模型 | 红熟早期\u002F% | 红熟中期\u002F% | 红熟晚期\u002F% | mAP 50\u002F% | FPS\u002F（帧\u002Fs） | 计算量\u002FGFLOPs | 参数量\u002FMB | 权重文件大小\u002FMB |\n| :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |\n| YOLOv10 | 79.1 | 81.8 | 87.5 | 82.8 | 37.37 | 106.700 | 45.811 | 107.7 |\n| YOLOv10+SegNeXt | 84.6（+5.5） | 89.5（+7.7） | 88.4（+0.9） | 87.5（+4.7） | 35.8（-1.57） | 228.765 | 53.522 | 107.6（-0.1） |\n\n 表2 \n\n[![Image 21](https:\u002F\u002Fwww.smartag.net.cn\u002Fimages\u002Ftable-icon.gif)](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#inline_content13729)\n\n**表3**\n\nLamp模型剪枝消融试验\n\n| 模型 | 红熟早期\u002F% | 红熟中期\u002F% | 红熟晚期\u002F% | mAP 50\u002F% | FPS\u002F（帧\u002Fs） | 计算量\u002FGFLOPs | 参数量\u002FMB | 权重文件大小\u002FMB |\n| :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |\n| YOLOv10+SegNeXt | 84.6 | 89.5 | 88.4 | 87.5 | 35.8 | 228.7 | 53.5 | 107.6 |\n| YOLOv10+SegNeXt +DWConv | 75.4 （-9.2） | 75.0 （-14.5） | 82.2 （-6.2） | 77.5 （-10.0） | 37.7 （+1.9） | 115.2 （-113.5） | 21.1 （-32.4） | 52.2 （-55.5） |\n| YOLOv10+SegNeXt +Lamp | 81.4 （-3.2） | 84.3 （-5.2） | 91.9 （+3.5） | 85.9 （-1.6） | 66.9 （+23.1） | 114.2 （-114.5） | 19.7 （-33.7） | 40.0 （-67.7） |\n\n 表3 \n\n[![Image 22](https:\u002F\u002Fwww.smartag.net.cn\u002Ffileup\u002F2096-8094\u002FFIGURE\u002F2026-8-2\u002FImages\u002F2096-8094-2026-8-2-133\u002Fthumbnail\u002F43D49185-E927-4387-B4EB-F464B099DD26-F007.jpg)](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#figureClass13730)\n\n**图7**\n\nLampCT-YOLO模型优化前后注意力可视化对比\n\n![Image 23](https:\u002F\u002Fwww.smartag.net.cn\u002Ffileup\u002F2096-8094\u002FFIGURE\u002F2026-8-2\u002FImages\u002F2096-8094-2026-8-2-133\u002F43D49185-E927-4387-B4EB-F464B099DD26-F007.jpg)\n\n 图7 \n\n[![Image 24](https:\u002F\u002Fwww.smartag.net.cn\u002Ffileup\u002F2096-8094\u002FFIGURE\u002F2026-8-2\u002FImages\u002F2096-8094-2026-8-2-133\u002Fthumbnail\u002F43D49185-E927-4387-B4EB-F464B099DD26-F008.jpg)](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#figureClass13731)\n\n**图8**\n\nLampCT-YOLO模型各层剪枝前后参数对比图\n\n![Image 25](https:\u002F\u002Fwww.smartag.net.cn\u002Ffileup\u002F2096-8094\u002FFIGURE\u002F2026-8-2\u002FImages\u002F2096-8094-2026-8-2-133\u002F43D49185-E927-4387-B4EB-F464B099DD26-F008.jpg)\n\n 图8 \n\n[![Image 26](https:\u002F\u002Fwww.smartag.net.cn\u002Ffileup\u002F2096-8094\u002FFIGURE\u002F2026-8-2\u002FImages\u002F2096-8094-2026-8-2-133\u002Fthumbnail\u002F43D49185-E927-4387-B4EB-F464B099DD26-F009.jpg)](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#figureClass13732)\n\n**图9**\n\nLampCT-YOLO模型置信区间与分布小提琴图\n\n![Image 27](https:\u002F\u002Fwww.smartag.net.cn\u002Ffileup\u002F2096-8094\u002FFIGURE\u002F2026-8-2\u002FImages\u002F2096-8094-2026-8-2-133\u002F43D49185-E927-4387-B4EB-F464B099DD26-F009.jpg)\n\n 图9 \n\n[![Image 28](https:\u002F\u002Fwww.smartag.net.cn\u002Fimages\u002Ftable-icon.gif)](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#inline_content13733)\n\n**表4**\n\n增加注意力机制后模型与主流目标检测模型对比试验\n\n| 模型名称 | mAP 50\u002F% | FPS\u002F（帧\u002Fs） | 计算量\u002FGFLOPs | 模型参数量\u002FMB | 权重文件大小\u002FMB |\n| :---: | :---: | :---: | :---: | :---: | :---: |\n| SSD | 77.3 | 43.22 | 37.8 | 21.472 | 91.6 |\n| Faster RCNN | 80.7 | 15.75 | 177.3 | 115.684 | 108.3 |\n| YOLOv7 | 76.0 | 48.25 | 51.6 | 36.490 | 71.3 |\n| YOLO8n | 84.5 | 39.89 | 8.1 | 3.006 | 6.3 |\n| YOLO8s | 84.0 | 43.82 | 28.4 | 11.127 | 22.5 |\n| YOLO8m | 82.5 | 45.41 | 78.7 | 25.841 | 52.0 |\n| YOLO8l | 83.6 | 39.91 | 164.8 | 43.609 | 87.7 |\n| YOLO8x | 82.4 | 37.54 | 257.4 | 68.126 | 136.7 |\n| YOLOv10n | 82.8 | 43.57 | 6.0 | 2.207 | 5.6 |\n| YOLOv10s | 81.9 | 44.49 | 21.4 | 7.219 | 16.5 |\n| YOLOv10m | 82.5 | 44.57 | 58.9 | 15.315 | 33.5 |\n| YOLOv10l | 82.6 | 37.37 | 228.7 | 53.522 | 107.7 |\n| YOLOv10x | 79.0 | 41.60 | 160.0 | 29.399 | 130.4 |\n| YOLOv11n | 85.9 | 43.99 | 6.3 | 2.583 | 5.5 |\n| YOLOv11s | 85.3 | 43.12 | 21.3 | 9.414 | 19.2 |\n| YOLOv11m | 85.3 | 37.89 | 67.7 | 20.032 | 40.5 |\n| YOLOv11l | 85.9 | 37.15 | 194.4 | 56.830 | 114.4 |\n| YOLOv11x | 84.0 | 37.21 | 194.4 | 58.362 | 114.4 |\n| YOLOv12n | 84.1 | 39.71 | 5.8 | 2.509 | 11.2 |\n| YOLOv12s | 82.0 | 40.57 | 19.3 | 9.074 | 18.6 |\n| YOLOv12m | 84.6 | 41.98 | 59.5 | 17.579 | 39.7 |\n| YOLOv12l | 79.9 | 36.23 | 82.1 | 26.396 | 53.7 |\n| YOLOv12x | 81.3 | 33.39 | 184.1 | 59.248 | 119.5 |\n| YOLOv10 l + SegNeXt | 87.5 | 66.20 | 114.2 | 19.765 | 40.0 |\n\n 表4 \n\n[![Image 29](https:\u002F\u002Fwww.smartag.net.cn\u002Fimages\u002Ftable-icon.gif)](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#inline_content13734)\n\n**表5**\n\nYOLOv10不同规模模型在SegNeXt与Lamp模块作用下的检测性能分析\n\n| 模型名称 | mAP 50\u002F% | FPS\u002F（帧\u002Fs） | 计算量\u002FGFLOPs | 模型参数量\u002FMB | 权重文件大小\u002FMB |\n| :---: | :---: | :---: | :---: | :---: | :---: |\n| YOLOv10n | 82.8 | 43.57 | 6.000 | 2.207 | 5.6 |\n| YOLOv10n+ SegNeXt | 85.5 | 41.50 | 8.600 | 2.450 | 6.3 |\n| YOLOv10n+ SegNeXt+Lamp | 84.8 | 51.20 | 6.500 | 2.000 | 5.1 |\n| YOLOv10l | 82.6 | 37.37 | 106.700 | 45.811 | 107.7 |\n| YOLOv10 l + SegNeXt | 87.5 | 35.80 | 228.765 | 53.522 | 107.6 |\n| YOLOv10l+ SegNeXt+Lamp | 85.9 | 66.90 | 114.252 | 19.765 | 40.0 |\n\n 表5 \n\n[![Image 30](https:\u002F\u002Fwww.smartag.net.cn\u002Ffileup\u002F2096-8094\u002FFIGURE\u002F2026-8-2\u002FImages\u002F2096-8094-2026-8-2-133\u002Fthumbnail\u002F43D49185-E927-4387-B4EB-F464B099DD26-F010.jpg)](https:\u002F\u002Fwww.smartag.net.cn\u002FCN\u002F10.12133\u002Fj.smartag.SA202507045#f","智慧农业(中英文) 2026 8(2): 133-146","2026-07-29T00:00:00Z","论文",70,{"impact":16,"substance":183,"depth":79,"authority":184,"freshness":50,"relevant":19,"comment":185},20,14,"核心期刊论文，提出改进YOLOv10的轻量级番茄成熟度检测模型，方法新颖，数据详实，但时效性较低。",[187],{"name":178,"url":175},[25,189,190,191],"YOLOv10","LAMP通道剪枝","串番茄",{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},[],{"status":37,"locked":13,"version":38,"method":39,"evidence":195},{"candidates":196,"agricultural_evidence":44},[197,202],{"code":30,"score":152,"supported":44,"title":198,"abstract":200,"tags":201},[199],"番茄",[199],[],{"code":203,"score":65,"supported":44,"title":204,"abstract":205,"tags":208},"I2",[],[206,207],"目标检测","YOLO",[],[210,211],"江苏省农科院 LAMP通道剪枝 串番茄 YOLOv10","江苏省农科院 LAMP通道剪枝","江苏省农科院LAMP通道剪枝串番茄YOLOv10-145",16,"10.12133\u002Fj.smartag.sa202507045","2026-08-01T06:01:55.404775Z",{"id":217,"title":218,"url":219,"summary":220,"summary_zh":221,"content":8,"source_name":222,"source_url":219,"published_at":223,"category":180,"cover_url":8,"hotness":12,"is_selected":13,"score":224,"score_detail":225,"sources":228,"tags":230,"primary_topic":236,"secondary_topics":237,"classification":238,"search_phrases":256,"slug":259,"view_count":260,"doi":261,"paper":262,"created_at":275},5565,"A Unified Survival-Based Energy Framework Linking Plant Color, Stress, and Productivity","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23540961","Plant coloration, expressed through leaf greenness, floral pigmentation, and fruit color intensity, reflects the integrated outcome of pigment biosynthesis, optical absorption, metabolic regulation, and energy–mass exchange with the environment. While the biochemical pathways governing the synthesis and degradation of major pigment classes—including chlorophylls, carotenoids, and anthocyanins—are well established, existing models largely interpret color expression as a localized biochemical phenomenon. Such approaches do not explicitly account for whole-plant energy balance, transpiration-driven losses, or thermodynamic constraints, limiting their ability to explain widely observed patterns of color saturation, stress-induced fading, and species-specific stability across environmental gradients. Here we develop a unified framework for plant color generation and stability that treats pigmentation as a survival-limited energetic process embedded within the broader dynamics of absorption, transport, metabolism, and entropy production. Central to the framework is a dimensionless energy survival factor, Ψ=AE\u002FTE+ε where AE represents absorbed and retained energetic and elemental resources relevant to pigment formation, TE denotes transpiration-linked, metabolic, and environmental dissipation losses, and ε captures irreducible entropy-producing degradation inherent to non-equilibrium biological systems. By construction, 0\u003CΨ\u003C1, ensuring full compliance with the second law of thermodynamics. When combined with pigment-specific optical absorption coefficients and physiological limitation functions, the framework yields a physically interpretable description of both pigment concentration and color stability. Empirical ranges for absorbed photosynthetically active radiation (≈45–70%), excitation survival (≈85–95%), and respiratory and transpiration losses (≈30–60% of assimilated resources) naturally constrain Ψ, predicting observed limits on sustained pigment accumulation without invoking biochemical inefficiency or ad hoc correction factors. The analysis demonstrates that increased light availability or enhanced biosynthetic capacity alone does not intensify coloration unless absorbed resources survive transport and loss processes. Stress-induced chlorosis, transient anthocyanin accumulation, and saturation of greenness under high irradiance emerge as direct consequences of reduced energy survival rather than impaired pigment synthesis. By explicitly separating survival from synthesis, the framework reconciles molecular-scale pigment biochemistry with whole-plant and ecosystem-scale color dynamics. This survival-based formulation provides a unified physical basis for interpreting plant color variation across species and environments and offers a scalable foundation for crop stress diagnostics, remote-sensing interpretation, and comparative plant phenotyping. More broadly, it extends survival-limited energy principles to visible plant traits, advancing plant science beyond isolated biochemical descriptions toward a systems-level understanding of how energy governs phenotypic expression.","植物色泽通过叶片绿色度、花色苷着色和果实颜色强度体现，反映了色素生物合成、光学吸收、代谢调控以及与环境的能量-物质交换的综合结果。尽管主要色素类别——包括叶绿素、类胡萝卜素和花青素——的合成与降解生化途径已较为明确，但现有模型大多将颜色表达解释为局部生化现象。此类方法未明确考虑整株植物能量平衡、蒸腾驱动的损耗或热力学约束，限制了其解释广泛观察到的颜色饱和度、胁迫诱导褪色以及跨环境梯度的物种特异性稳定性等模式的能力。本文构建了一个统一的植物颜色生成与稳定性框架，将色素沉着视为一种受生存限制的能量过程，并将其嵌入吸收、运输、代谢和熵产生的更广泛动力学之中。该框架的核心是一个无量纲能量生存因子Ψ=AE\u002FTE+ε，其中AE代表与色素形成相关的被吸收并保留的能量和元素资源，TE表示与蒸腾相关的、代谢的和环境的耗散损失，ε则捕捉非平衡生物系统固有的不可约熵产生降解。根据构建方式，0\u003CΨ\u003C1，确保完全符合热力学第二定律。当与色素特异性光学吸收系数和生理限制函数相结合时，该框架可对色素浓度和颜色稳定性给出具有物理可解释性的描述。吸收性光合有效辐射（约45–70%）、激发能存活率（约85–95%）以及呼吸和蒸腾损失（约占同化资源的30–60%）的经验范围自然约束了Ψ，从而预测出所观察到的持续色素积累限度，而无需引入生化低效性或特设校正因子。分析表明，仅增加光照可用性或增强生物合成能力并不会加深颜色，除非被吸收的资源能够在运输和损失过程中存活下来。胁迫诱导的黄化、瞬时花青素积累以及高辐照下绿色度饱和，均表现为能量生存率降低而非色素合成受损的直接后果。通过明确分离生存","Zenodo (CERN European Organization for Nuclear Research)","2026-10-21T00:00:00Z",79,{"impact":79,"substance":80,"depth":79,"authority":17,"freshness":226,"relevant":19,"comment":227},9,"提出以能量生存因子统一解释植物颜色与胁迫的物理框架，方法新颖且对遥感解译和作物诊断有潜在价值，但属预印本理论模型，尚缺田间验证。",[229],{"name":222,"url":219},[231,232,233,234,235],"智慧农业","遥感监测","植物表型","作物胁迫诊断","能量平衡",{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},[],{"status":37,"locked":13,"version":38,"method":39,"evidence":239},{"candidates":240,"agricultural_evidence":44},[241,246,251],{"code":30,"score":50,"supported":44,"title":242,"abstract":243,"tags":245},[],[244],"萝卜",[],{"code":247,"score":19,"supported":13,"title":248,"abstract":249,"tags":250},"I1",[],[],[231],{"code":252,"score":19,"supported":13,"title":253,"abstract":254,"tags":255},"I3",[],[],[232],[257,258],"植物颜色 能量生存因子","作物胁迫 遥感诊断","植物颜色能量生存因子-5565",0,"10.5281\u002Fzenodo.23540961",{"doi":261,"openalex_id":263,"authors":264,"venue":222,"cited_by_count":260,"oa_url":219,"card":268,"direction":272,"ingested_from":274},"W7223098474",[265],{"name":266,"orcid":267},"Mokhdum Azam Mashrafi","https:\u002F\u002Forcid.org\u002F0009-0002-1801-1130",{"tldr":269,"method":270,"finding":271,"direction":272,"opportunity":273},"提出基于生存的能量框架，用能量存活因子解释植物颜色生成与稳定性。","构建无量纲能量存活因子Ψ=AE\u002F(TE+ε)，结合色素吸收系数与生理限制函数。","颜色深浅取决于吸收资源经运输损耗后的存活率，而非单纯合成能力。","农业遥感与作物表型","可将Ψ因子与冠层光谱\u002F表型遥感结合，发展胁迫早期诊断与生产力预测模型。","openalex","2026-10-22T11:20:31.195819Z",{"id":277,"title":278,"url":279,"summary":280,"summary_zh":8,"content":8,"source_name":281,"source_url":8,"published_at":223,"category":180,"cover_url":8,"hotness":12,"is_selected":13,"score":77,"score_detail":282,"sources":287,"tags":289,"primary_topic":294,"secondary_topics":299,"classification":301,"search_phrases":317,"slug":320,"view_count":260,"doi":8,"paper":321,"created_at":330},5536,"日光温室番茄全生育期环境特征解析与智能调控决策支持方法","https:\u002F\u002Fpaper.sciencenet.cn\u002Fhtmlpaper\u002F2026\u002F10\u002F20261021145441802156759.shtm","研究解析日光温室番茄全生育期环境特征，发现该类温室气候缓冲能力较强、有效积温与番茄生理需求呈双峰匹配，但相对增益指标揭示单位时间热量供给失衡、深冬热量不足以及光能结构性不足、湿度调控昼夜失衡等问题。作者建议构建温度—光照—湿度耦合的智能闭环控制系统。","Agriculture 2026-10-21",{"impact":213,"substance":283,"depth":284,"authority":285,"freshness":12,"relevant":19,"comment":286},21,17,13,"论文解析日光温室番茄全生育期环境特征并提出温光湿耦合智能调控方案，结论有新意，对设施农业信息化有参考价值。",[288],{"name":281,"url":279},[231,290,291,292,293],"设施农业","环境调控","温室番茄","智能决策",{"code":295,"slug":296,"name":297,"path":298,"parent_code":34},"B7","protected-horticulture","设施园艺与植物工厂","\u002Ftopic\u002Fhorticulture\u002Fprotected-horticulture",[300],{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},{"status":37,"locked":13,"version":38,"method":39,"evidence":302},{"candidates":303,"agricultural_evidence":44},[304,309,313],{"code":295,"score":285,"supported":44,"title":305,"abstract":307,"tags":308},[306],"温室",[306],[292,291],{"code":30,"score":152,"supported":44,"title":310,"abstract":311,"tags":312},[199],[199],[],{"code":247,"score":19,"supported":13,"title":314,"abstract":315,"tags":316},[],[],[231],[318,319],"日光温室 番茄 环境调控","温室番茄 智能闭环控制","日光温室番茄环境调控-5536",{"doi":8,"openalex_id":8,"authors":322,"venue":8,"cited_by_count":260,"oa_url":8,"card":323,"direction":327,"ingested_from":329},[],{"tldr":324,"method":325,"finding":326,"direction":327,"opportunity":328},"解析日光温室番茄全生育期环境特征并提出智能调控决策支持方法。","基于全生育期环境监测数据，分析积温匹配与相对增益指标。","温室缓冲力强但深冬热量不足、光能结构性不足、湿度昼夜失衡。","智慧农业 \u002F 农业物联网","可研发温度—光照—湿度耦合的智能闭环控制算法，并验证其对番茄产量与能耗的协同优化效果。","agent","2026-10-22T00:07:10.129353Z",{"id":332,"title":333,"url":334,"summary":335,"summary_zh":8,"content":8,"source_name":336,"source_url":8,"published_at":337,"category":180,"cover_url":8,"hotness":12,"is_selected":13,"score":338,"score_detail":339,"sources":342,"tags":344,"primary_topic":350,"secondary_topics":351,"classification":352,"search_phrases":374,"slug":377,"view_count":260,"doi":8,"paper":378,"created_at":386},5533,"基于低成本遥操作机械臂模仿学习的草莓果柄定点采摘","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.22765","该研究构建视觉运动模仿学习流程，统一感知、运动规划与接触操作，从人工遥操作演示训练基于ResNet-50骨干的动作分块Transformer策略，并在Jetson AGX Orin边缘平台以15赫兹自主部署。策略在130条演示、十万梯度步内损失由2.84降至0.091，数据集与模型权重已开源。预印本，已被IROS农业机器人研讨会接收。","arXiv 预印本 2026-10-16","2026-10-16T00:00:00Z",68,{"impact":213,"substance":283,"depth":79,"authority":226,"freshness":340,"relevant":19,"comment":341},4,"方法新颖、数据与开源材料扎实，但属预印本且已过一周，适合作为细分技术进展收录而非头条精选。",[343],{"name":336,"url":334},[345,346,347,348,349],"农业人工智能","农业机器人","边缘计算","模仿学习","草莓采摘",{"code":30,"slug":31,"name":32,"path":33,"parent_code":34},[],{"status":37,"locked":13,"version":38,"method":39,"evidence":353},{"candidates":354,"agricultural_evidence":44},[355,360,365,369],{"code":30,"score":123,"supported":44,"title":356,"abstract":358,"tags":359},[357],"草莓",[],[],{"code":361,"score":340,"supported":44,"title":362,"abstract":363,"tags":364},"F6",[],[346],[346],{"code":203,"score":19,"supported":13,"title":366,"abstract":367,"tags":368},[],[],[345],{"code":370,"score":19,"supported":13,"title":371,"abstract":372,"tags":373},"I5",[],[],[347],[375,376],"草莓果柄 定点采摘 机械臂","Jetson AGX Orin 采摘 模仿学习","草莓果柄定点采摘机械臂-5533",{"doi":8,"openalex_id":8,"authors":379,"venue":8,"cited_by_count":260,"oa_url":8,"card":380,"direction":384,"ingested_from":329},[],{"tldr":381,"method":382,"finding":383,"direction":384,"opportunity":385},"用低成本遥操作机械臂采集演示，模仿学习实现草莓果柄定点采摘。","ResNet-50骨干的动作分块Transformer策略，Jetson边缘部署","130条演示训练后损失降至0.091，策略可15赫兹自主采摘。","农业人工智能与决策模型","可探索小样本跨品种泛化与失败恢复，降低演示采集成本。","2026-10-22T00:07:09.891422Z"]