[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3165":3,"related-3165":74},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":24,"tags":26,"search_phrases":32,"slug":35,"view_count":36,"doi":37,"paper":38,"created_at":73},3165,"Explainable growth stage classification of cacao (Theobroma cacao L.) leaves and key feature visualization using vision transformer and transfer learning","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffpls.2026.1885906","Accurate and objective plant phenotyping is crucial for optimizing agricultural practices, understanding plant development, and enabling rapid responses to environmental changes. Traditional methods, often relying on visual observation, can be subjective, time-consuming, and may overlook subtle but important differences. This study demonstrates the power of combining digital imaging with deep learning to classify plant material with high accuracy, even when visual differences are minimal. We focused on differentiating between stage D (light green) and stage E (dark green) leaves of cacao ( Theobroma cacao L. ), which are visually very similar in size and overall structure. Using cleared and stained leaves of the SCA 6 genotype to highlight the venation network, we trained a Vision Transformer (ViT) model, a deep learning architecture, on image patches. At the patch level, the model achieved an overall accuracy of 97.03% on an independent test set, with a recall of 96.0% for stage D and 98.3% for stage E. At the whole-leaf level, majority voting correctly classified 14 of 15 independent test leaves (93.3%). Attention maps indicated that image regions containing the midrib and primary lateral veins contributed strongly to classification. These attention maps identify discriminative image regions, but they do not by themselves determine the biological mechanism underlying the signal. The major-vein signal may reflect developmental differences in vein-associated structure, stage-associated differences in Safranin O uptake or optical density, tissue thickness, or a combination of these factors. Because vascular anatomy, lignification, hydraulic conductance, phloem loading, and source–sink status were not directly measured, these mechanisms are treated as hypotheses requiring future anatomical, histochemical, and physiological validation. Thus, this study provides a proof-of-concept for interpretable image-based classification of stage D and stage E leaves within greenhouse-grown SCA 6 cacao. Extension to other cacao genotypes, field-grown plants, independent seasons, staining batches, stress detection, species identification, genotype discrimination, or precision-agriculture deployment will require external validation.","准确、客观的植物表型分析对于优化农业实践、理解植物发育以及快速响应环境变化至关重要。传统方法通常依赖视觉观察，可能具有主观性、耗时，并且可能忽略细微但重要的差异。本研究展示了将数字成像与深度学习相结合，即使在视觉差异极小的情况下，也能以高精度对植物材料进行分类。我们聚焦于区分可可（Theobroma cacao L.）的D期（浅绿色）和E期（深绿色）叶片，这些叶片在大小和整体结构上视觉上非常相似。利用SCA 6基因型的透明染色叶片以突出脉序网络，我们在图像块上训练了Vision Transformer（ViT）模型，一种深度学习架构。在图像块水平上，该模型在独立测试集上达到了97.03%的总体准确率，D期的召回率为96.0%，E期为98.3%。在整叶水平上，多数投票正确分类了15片独立测试叶片中的14片（93.3%）。注意力图表明，包含中脉和初级侧脉的图像区域对分类贡献显著。这些注意力图识别了具有判别力的图像区域，但它们本身并不能确定信号背后的生物学机制。主脉信号可能反映了脉相关结构的发育差异、番红O摄取或光密度的阶段相关差异、组织厚度，或这些因素的组合。由于未直接测量维管解剖结构、木质化、水力导度、韧皮部装载和源–库状态，这些机制被视为假设，需要未来的解剖学、组织化学和生理学验证。因此，本研究为温室种植的SCA 6可可中D期和E期叶片的可解释图像分类提供了概念验证。扩展到其他可可基因型、田间种植植株、独立季节、染色批次、胁迫检测、物种鉴定、基因型区分或精准农业部署将需要外部验证。",null,"Frontiers in Plant Science","2026-09-21T00:00:00Z","论文",10,false,71,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},12,20,17,13,9,1,"方法新颖、数据可靠的可解释作物表型概念验证研究，但属实验室小样本，产业影响有限。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业人工智能","深度学习","可可","作物表型",[33,34],"可可 叶片 生长阶段 分类","Vision Transformer 作物表型","可可叶片生长阶段分类-3165",0,"10.3389\u002Ffpls.2026.1885906",{"doi":37,"openalex_id":39,"authors":40,"venue":10,"cited_by_count":36,"oa_url":6,"card":66,"direction":70,"ingested_from":72},"W7213901640",[41,43,46,48,50,52,55,58,61,63],{"name":42,"orcid":9},"Ezekiel Ahn",{"name":44,"orcid":45},"Eun-Sung Park","https:\u002F\u002Forcid.org\u002F0000-0001-6826-2865",{"name":47,"orcid":9},"Moon S. Kim",{"name":49,"orcid":9},"Hangi Kim",{"name":51,"orcid":9},"Lalit M. Kandpal",{"name":53,"orcid":54},"Sunchung Park","https:\u002F\u002Forcid.org\u002F0000-0002-7398-9476",{"name":56,"orcid":57},"Seunghyun Lim","https:\u002F\u002Forcid.org\u002F0000-0003-3023-4863",{"name":59,"orcid":60},"Lyndel W. Meinhardt","https:\u002F\u002Forcid.org\u002F0000-0001-8299-2629",{"name":62,"orcid":9},"Byoung-Kwan Cho",{"name":64,"orcid":65},"Insuck Baek","https:\u002F\u002Forcid.org\u002F0000-0003-1044-349X",{"tldr":67,"method":68,"finding":69,"direction":70,"opportunity":71},"用ViT和迁移学习对可可叶D、E期进行可解释分类，准确率达97%。","透明染色叶片图像块训练ViT，注意力图可视化关键区域。","模型准确区分D\u002FE期，中脉和主侧脉区域贡献最大。","农业遥感与作物表型","可扩展到多基因型、田间、胁迫检测，并验证脉信号生物学机制。","openalex","2026-09-22T23:30:19.972949Z",{"total":75,"page":22,"page_size":75,"items":76},6,[77,116,137,182,220,250],{"id":78,"title":79,"url":80,"summary":81,"summary_zh":82,"content":9,"source_name":83,"source_url":80,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":84,"score_detail":85,"sources":89,"tags":91,"search_phrases":94,"slug":97,"view_count":36,"doi":98,"paper":99,"created_at":115},3164,"Spatiotemporal Deep Learning for Rice Plant Height Estimation from Multi-Temporal UAV RGB Imagery","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fagriculture16182034","Accurate plant height estimation is important for monitoring crop growth and supporting precision agricultural management. Manual measurements are labor-intensive, while LiDAR-based methods are expensive and require complex processing. UAV photogrammetry provides a lower-cost alternative but remains challenging in flooded rice paddies because of canopy deformation and difficulties in terrain extraction. This study proposes Rice-STNet, a spatiotemporal deep learning framework for end-to-end rice plant height estimation using multi-temporal UAV RGB imagery. Rice-STNet integrates a convolutional neural network for spatial feature extraction, Time2Vec for temporal encoding, and a gated recurrent unit network for modeling temporal dependencies across observation dates. The framework was evaluated using field data collected from rice paddies over two growing seasons. Rice-STNet achieved an R2 of 0.97, a root mean squared error of 1.97 cm, and a mean absolute error of 1.14 cm. It outperformed random forest, support vector regression, a CNN-only baseline, and a UAV photogrammetry-based point-cloud approach. In addition, the framework generated high-resolution plant height maps for field-scale analysis of spatial growth variability. These results underscore the importance of jointly modeling spatial and temporal characteristics for continuously evolving crop traits. The proposed framework offers an accurate, scalable, and non-destructive solution for large-scale crop phenotyping and precision agriculture.","准确的株高估算对于监测作物生长和支持精准农业管理具有重要意义。人工测量劳动强度大，而基于激光雷达（LiDAR）的方法成本高昂且需要复杂的处理。无人机摄影测量提供了一种成本较低的替代方案，但在淹水稻田中仍面临挑战，原因在于冠层变形和地形提取困难。本研究提出了Rice-STNet，一种时空深度学习框架，用于利用多时相无人机RGB影像进行端到端水稻株高估算。Rice-STNet集成了用于空间特征提取的卷积神经网络、用于时间编码的Time2Vec，以及用于建模观测日期之间时间依赖关系的门控循环单元网络。该框架利用两个生长季从稻田采集的田间数据进行了评估。Rice-STNet取得了R²为0.97、均方根误差为1.97 cm、平均绝对误差为1.14 cm的结果。其性能优于随机森林、支持向量回归、仅使用CNN的基线方法以及基于无人机摄影测量的点云方法。此外，该框架生成了高分辨率株高图，用于田块尺度空间生长变异性分析。这些结果凸显了联合建模空间与时间特征对于持续变化的作物性状的重要性。所提出的框架为大规模作物表型分析和精准农业提供了一种准确、可扩展且非破坏性的解决方案。","Agriculture",80,{"impact":86,"substance":87,"depth":86,"authority":20,"freshness":21,"relevant":22,"comment":88},18,22,"提出时空深度学习框架Rice-STNet，用多时相无人机RGB影像实现水稻株高高精度估算，方法新颖、数据跨两个生长季，对作物表型与精准农业有实用价值。",[90],{"name":83,"url":80},[27,28,92,93,31],"水稻","遥感",[95,96],"无人机 RGB 水稻株高","Rice-STNet 水稻表型","无人机RGB水稻株高-3164","10.3390\u002Fagriculture16182034",{"doi":98,"openalex_id":100,"authors":101,"venue":83,"cited_by_count":36,"oa_url":80,"card":110,"direction":70,"ingested_from":72},"W7213887432",[102,105,107],{"name":103,"orcid":104},"Weiguo Wang","https:\u002F\u002Forcid.org\u002F0009-0003-4028-9363",{"name":106,"orcid":9},"Noboru Noguchi",{"name":108,"orcid":109},"Liangliang Yang","https:\u002F\u002Forcid.org\u002F0000-0002-5055-3987",{"tldr":111,"method":112,"finding":113,"direction":70,"opportunity":114},"提出Rice-STNet时空深度学习框架，用多时相无人机RGB影像估算水稻株高。","CNN提取空间特征，Time2Vec编码时间，GRU建模时序依赖，两季稻田数据验","R²达0.97、RMSE 1.97cm，优于随机森林、SVR、纯CNN及点云方法。","可迁移至其他作物与多源遥感融合，探索轻量化模型及实时田间部署。","2026-09-22T23:30:18.545958Z",{"id":117,"title":118,"url":119,"summary":120,"summary_zh":9,"content":121,"source_name":122,"source_url":9,"published_at":123,"category":124,"cover_url":9,"hotness":13,"is_selected":14,"score":125,"score_detail":126,"sources":128,"tags":130,"search_phrases":132,"slug":135,"view_count":36,"doi":9,"paper":9,"created_at":136},3103,"山东省农科院举办人工智能专题舜耕论坛暨培训交流会——浙江大学数字农业农村研究中心主任何勇教授作\"作物表型多源多尺度智能感知技术与装备\"专题报告","http:\u002F\u002Fwww.saas.ac.cn\u002Farticles\u002Fch10717\u002F202609\u002F1c1dbcca-09c4-421f-80dd-09910a603152.shtml","9-16 山东省农业科学院举办人工智能专题舜耕论坛暨培训交流会，落实院党委\"人工智能驱动科技创新智慧引领高质量发展\"专题活动部署，促进人工智能与各学科创新团队重点攻关方向深度耦合。论坛特邀浙江大学数字农业农村研究中心主任何勇教授作专题报告，围绕植物表型采集解析、智慧农业技术装备前沿领域，从细胞\u002F组织器官\u002F表型获取装备三个层级系统阐释作物表型智能感知技术创新实践，介绍该技术在水稻\u002F草莓\u002F茶叶等作物的示范应用。院长李向东要求各创新团队推动人工智能与作物栽培、畜禽育种、病虫害防控、种质资源鉴定、农产品质量安全等领域深度融合。会议设主会场和视频分会场，全院科研人员代表 500 余人参会。","![Image 2](http:\u002F\u002Fwww.saas.ac.cn\u002Ftemplate\u002Fsdnky\u002Fdefault2026\u002Fimages\u002Fnew2026\u002Flogo02.png)\n\n*   [首页](http:\u002F\u002Fwww.saas.ac.cn\u002F)![Image 3](http:\u002F\u002Fwww.saas.ac.cn\u002Ftemplate\u002Fsdnky\u002Fdefault2026\u002Fimages\u002Fnew2026\u002Fxm.png)\n*   [全院概况](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch17267\u002F)![Image 4](http:\u002F\u002Fwww.saas.ac.cn\u002Ftemplate\u002Fsdnky\u002Fdefault2026\u002Fimages\u002Fnew2026\u002Fxm.png)![Image 5](http:\u002F\u002Fwww.saas.ac.cn\u002Ftemplate\u002Fsdnky\u002Fdefault2026\u002Fimages\u002Fnew2026\u002Fch_img01.jpg)  [院情简介](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10890\u002F)[领导班子](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10892\u002F)[组织机构](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10707\u002F)[领导关怀](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10906\u002F)[历史沿革](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16390\u002F)[功勋品种](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10908\u002F)[院所文化](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10894\u002F)[院容院貌](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10904\u002F)   \n*   [新闻中心](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10715\u002F)![Image 6](http:\u002F\u002Fwww.saas.ac.cn\u002Ftemplate\u002Fsdnky\u002Fdefault2026\u002Fimages\u002Fnew2026\u002Fxm.png)![Image 7](http:\u002F\u002Fwww.saas.ac.cn\u002Ftemplate\u002Fsdnky\u002Fdefault2026\u002Fimages\u002Fnew2026\u002Fch_img02.jpg)  [图片新闻](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10910\u002F)[农科要闻](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10717\u002F)[综合新闻](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10719\u002F)[媒体聚焦](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10723\u002F)[公开公示](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10800\u002F)[通知公告](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10798\u002F)   \n*   [科技创新](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10737\u002F)![Image 8](http:\u002F\u002Fwww.saas.ac.cn\u002Ftemplate\u002Fsdnky\u002Fdefault2026\u002Fimages\u002Fnew2026\u002Fxm.png)![Image 9](http:\u002F\u002Fwww.saas.ac.cn\u002Ftemplate\u002Fsdnky\u002Fdefault2026\u002Fimages\u002Fnew2026\u002Fch_img03.jpg)  [科技动态](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10721\u002F)[科技奖励](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10739\u002F)[科研平台](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10745\u002F)[主导品种](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16826\u002F)[主推技术](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16827\u002F)[科技期刊](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16828\u002F)[舜耕论坛](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16829\u002F)[文献资源](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10761\u002F)[查新检索](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10763\u002F)   \n*   [成果转化](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16830\u002F)![Image 10](http:\u002F\u002Fwww.saas.ac.cn\u002Ftemplate\u002Fsdnky\u002Fdefault2026\u002Fimages\u002Fnew2026\u002Fxm.png)![Image 11](http:\u002F\u002Fwww.saas.ac.cn\u002Ftemplate\u002Fsdnky\u002Fdefault2026\u002Fimages\u002Fnew2026\u002Fch_img04.jpg)  [推广服务 (信息发布)](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch14047\u002F)[合作平台](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16832\u002F)[重点成果推介](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16833\u002F)[产业支撑](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16834\u002F)[科普服务](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16835\u002F)   \n*   [人才工作](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16836\u002F)![Image 12](http:\u002F\u002Fwww.saas.ac.cn\u002Ftemplate\u002Fsdnky\u002Fdefault2026\u002Fimages\u002Fnew2026\u002Fxm.png)![Image 13](http:\u002F\u002Fwww.saas.ac.cn\u002Ftemplate\u002Fsdnky\u002Fdefault2026\u002Fimages\u002Fnew2026\u002Fch_img05.jpg)  [人才概况](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16837\u002F)[工作动态](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16839\u002F)[人才队伍](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16840\u002F)[博士后工作站](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16857\u002F)   \n*   [党建之窗](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16858\u002F)![Image 14](http:\u002F\u002Fwww.saas.ac.cn\u002Ftemplate\u002Fsdnky\u002Fdefault2026\u002Fimages\u002Fnew2026\u002Fxm.png)![Image 15](http:\u002F\u002Fwww.saas.ac.cn\u002Ftemplate\u002Fsdnky\u002Fdefault2026\u002Fimages\u002Fnew2026\u002Fch_img06.jpg)  [基层党建](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10725\u002F)[党建要闻](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16859\u002F)[文明创建](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16860\u002F)[星火学社](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16861\u002F)[清廉农科院](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16862\u002F)[党内法规](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16863\u002F)   \n\n![Image 16](http:\u002F\u002Fwww.saas.ac.cn\u002Ftemplate\u002Fsdnky\u002Fdefault2026\u002Fimages\u002Fnew2026\u002Fsearch.png)\n\n[](javascript:;)\n\n[![Image 17](http:\u002F\u002Fwww.saas.ac.cn\u002Ftemplate\u002Fsdnky\u002Fdefault2026\u002Fimages\u002Fnew2026\u002Flogo02.png)](http:\u002F\u002Fwww.saas.ac.cn\u002F)\n\n*   [首页](http:\u002F\u002Fwww.saas.ac.cn\u002F \"首页\") \n*   [全院概况](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch17267\u002F \"全院概况\") [院情简介](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10890\u002F \"院情简介\") [领导班子](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10892\u002F \"领导班子\") [组织机构](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10707\u002F \"组织机构\") [领导关怀](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10906\u002F \"领导关怀\") [历史沿革](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16390\u002F \"历史沿革\") [功勋品种](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10908\u002F \"功勋品种\") [院所文化](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10894\u002F \"院所文化\") [院容院貌](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10904\u002F \"院容院貌\")  \n*   [新闻中心](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10715\u002F \"新闻中心\") [图片新闻](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10910\u002F \"图片新闻\") [农科要闻](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10717\u002F \"农科要闻\") [综合新闻](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10719\u002F \"综合新闻\") [媒体聚焦](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10723\u002F \"媒体聚焦\") [公开公示](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10800\u002F \"公开公示\") [通知公告](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10798\u002F \"通知公告\")  \n*   [科技创新](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10737\u002F \"科技创新\") [科技动态](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10721\u002F \"科技动态\") [科技奖励](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10739\u002F \"科技奖励\") [科研平台](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10745\u002F \"科研平台\") [主导品种](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16826\u002F \"主导品种\") [主推技术](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16827\u002F \"主推技术\") [科技期刊](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16828\u002F \"科技期刊\") [舜耕论坛](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16829\u002F \"舜耕论坛\") [文献资源](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10761\u002F \"文献资源\") [查新检索](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10763\u002F \"查新检索\")  \n*   [成果转化](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16830\u002F \"成果转化\") [推广服务(信息发布)](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch14047\u002F \"推广服务(信息发布)\") [合作平台](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16832\u002F \"合作平台\") [重点成果推介](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16833\u002F \"重点成果推介\") [产业支撑](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16834\u002F \"产业支撑\") [科普服务](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16835\u002F \"科普服务\")  \n*   [人才工作](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16836\u002F \"人才工作\") [人才概况](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16837\u002F \"人才概况\") [工作动态](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16839\u002F \"工作动态\") [人才队伍](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16840\u002F \"人才队伍\") [博士后工作站](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16857\u002F \"博士后工作站\")  \n*   [党建之窗](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16858\u002F \"党建之窗\") [基层党建](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10725\u002F \"基层党建\") [党建要闻](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16859\u002F \"党建要闻\") [文明创建](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16860\u002F \"文明创建\") [星火学社](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16861\u002F \"星火学社\") [清廉农科院](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16862\u002F \"清廉农科院\") [党内法规](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch16863\u002F \"党内法规\")  \n\n![Image 18](http:\u002F\u002Fwww.saas.ac.cn\u002Ftemplate\u002Fsdnky\u002Fdefault2026\u002Fimages\u002Fnew2026\u002Fny_banner02.jpg)\n\nYour browser does not support the HTML5 canvas tag.Your browser does not support the HTML5 canvas tag.Your browser does not support the HTML5 canvas tag.\n\n新闻中心![Image 19](http:\u002F\u002Fwww.saas.ac.cn\u002Ftemplate\u002Fsdnky\u002Fdefault2026\u002Fimages\u002Fnew2026\u002Flm_icon01png)\n\n*   [图片新闻](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10910\u002F)\n*   [农科要闻](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10717\u002F)\n*   [综合新闻](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10719\u002F)\n*   [媒体聚焦](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10723\u002F)\n*   [媒体聚焦(图片)](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch17317\u002F)\n*   [公开公示](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10800\u002F)\n*   [通知公告](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10798\u002F)\n\n![Image 20](http:\u002F\u002Fwww.saas.ac.cn\u002Ftemplate\u002Fsdnky\u002Fdefault2026\u002Fimages\u002Fnew2026\u002Fwgty.png) 您现在的位置： [首页](http:\u002F\u002Fwww.saas.ac.cn\u002F)→ [新闻中心](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10715\u002F)→ [农科要闻](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch10717\u002F)\n\n我院召开人工智能专题舜耕论坛暨培训交流会\n\n 发布日期：2026-09-17 浏览次数： 393 文章来源：科技管理处\n\n[![Image 21](http:\u002F\u002Fwww.saas.ac.cn\u002Fresource\u002Fsdnky\u002Fimage\u002F202609\u002F8bd7e115-1e18-4d4a-ba0a-1ee03e6e0bcem.jpg)](http:\u002F\u002Fwww.saas.ac.cn\u002Fresource\u002Fsdnky\u002Fimage\u002F202609\u002F8bd7e115-1e18-4d4a-ba0a-1ee03e6e0bce.jpg \"8B9A30510.jpg\")\n\n9月16日，我院举办人工智能专题舜耕论坛暨培训交流会。会议落实院党委“人工智能驱动科技创新 智慧引领高质量发展”专题活动部署，促进人工智能与各学科创新团队重点攻关方向深度耦合，激活科研创新内生动力。论坛特邀浙江大学数字农业农村研究中心主任何勇教授作专题报告，院党委副书记、院长李向东主持会议并讲话。\n\n报告题为《作物表型多源多尺度智能感知技术与装备》，围绕植物表型采集解析、智慧农业技术装备前沿领域，从细胞、组织器官、表型获取装备三个层级，系统阐释作物表型智能感知技术创新实践，介绍该技术在水稻、草莓、茶叶等作物的示范应用，解读无人机、作物智慧管理装备关键技术及应用路径，提出农业科技创新要加速人工智能深度融入，以多技术交叉融合助推智慧农业高质量发展，为我院农业人工智能科研布局提供重要参考。\n\n李向东指出，报告紧扣智慧农业发展前沿，兼具理论深度和实践价值，对我院科研迭代升级具有重要指导意义。他强调，要提高政治站位，把握战略导向。深入学习贯彻习近平总书记关于人工智能创新发展的重要指示精神，把智慧农业摆在全院科技创新突出位置，强化机遇意识，开辟农业科研新赛道。要聚焦主责主业，精准靶向攻坚。各创新团队依托现有科研基础，推动人工智能与作物栽培、畜禽育种、病虫害防控、种质资源鉴定、农产品质量安全等领域深度融合，坚持问题导向，紧扣产业瓶颈凝练攻关方向，推动智能技术赋能科研实践。要压实闭环管理，推动落地见效。细化攻关任务清单，强化项目、平台、人才、经费要素保障，健全调度考核机制，将人工智能攻关及成果产出纳入评价体系，力争产出高水平科研成果、实用技术与智能装备，形成可复制推广的农业人工智能应用模式。全院科研人员要以此次论坛为契机，拓宽科研视野，聚力攻关，推动我院智慧农业科技创新再上新台阶。\n\n会议设主会场和视频分会场，院属各单位主要负责人、科研分管负责人，拟组建创新团队首席、副首席及45岁以下青年科研人员代表500余人参加会议。\n\n（撰写：陈英凯 核稿：张文君）\n\n分享\n\n分享到\n\n[微信](http:\u002F\u002Fwww.saas.ac.cn\u002Farticles\u002Fch10717\u002F202609\u002F1c1dbcca-09c4-421f-80dd-09910a603152.shtml \"分享到微信\")\n\n政府机构\n\n[山东省人民政府](http:\u002F\u002Fwww.shandong.gov.cn\u002F \"山东省人民政府\")[山东省农业厅](http:\u002F\u002Fnync.shandong.gov.cn\u002F \"山东省农业厅\")[山东省科技厅](http:\u002F\u002Fkjt.shandong.gov.cn\u002F \"山东省科技厅\")[国家发改委](https:\u002F\u002Fwww.ndrc.gov.cn\u002F \"国家发改委\")[国家农业部](http:\u002F\u002Fwww.moa.gov.cn\u002F \"国家农业部\")[国家科技部](http:\u002F\u002Fwww.most.gov.cn\u002F \"国家科技部\")\n\n国内科研与教学单位\n\n[中国农科院](http:\u002F\u002Fwww.caas.net.cn\u002F \"中国农科院\")[北京市农林科学院](http:\u002F\u002Fwww.baafs.net.cn\u002F \"北京市农林科学院\")[上海市农科院](http:\u002F\u002Fwww.saas.sh.cn\u002F \"上海市农科院\")[天津市农科院](http:\u002F\u002Fwww.taas.ac.cn\u002F \"天津市农科院\")[福建省农科院](http:\u002F\u002Fwww.faas.cn\u002F \"福建省农科院\")[河北省农林科学院](http:\u002F\u002Fwww.hebnky.com\u002F \"河北省农林科学院\")[四川省农科院](http:\u002F\u002Fwww.chinawestagr.com\u002F \"四川省农科院\")[甘肃省农科院](http:\u002F\u002Fwww.gsagr.ac.cn\u002F \"甘肃省农科院\")[吉林省农科院](http:\u002F\u002Fwww.jaas.com.cn\u002F \"吉林省农科院\")[浙江省农科院](http:\u002F\u002Fwww.zaas.ac.cn\u002F \"浙江省农科院\")[湖南省农科院](http:\u002F\u002Fwww.hunaas.cn\u002F \"湖南省农科院\")[贵州省农科院](http:\u002F\u002Faas.guizhou.gov.cn\u002F \"贵州省农科院\")[安徽省农科院](http:\u002F\u002Fwww.ahas.org.cn\u002F \"安徽省农科院\")[山西省农科院](https:\u002F\u002Fwww.sxau.edu.cn\u002F \"山西省农科院\")[辽宁省农科院](http:\u002F\u002Fwww.laas.cn\u002F \"辽宁省农科院\")[云南省农科院](http:\u002F\u002Fwww.yaas.org.cn\u002F \"云南省农科院\")[广东省农科院](http:\u002F\u002Fwww.gdaas.cn\u002F \"广东省农科院\")[广西省农科院](http:\u002F\u002Fwww.gxaas.net\u002F \"广西省农科院\")[河南省农科院](http:\u002F\u002Fwww.hnagri.org.cn\u002F \"河南省农科院\")[江西省农科院](http:\u002F\u002Fjxaas.com\u002F \"江西省农科院\")\n\n国际组织或科研单位\n\n[联合国粮食及农业组织](http:\u002F\u002Fwww.fao.org\u002F \"联合国粮食及农业组织\")[国际玉米小麦改良中心](http:\u002F\u002Fwww.cimmyt.org\u002F \"国际玉米小麦改良中心\")[国际马铃薯中心](http:\u002F\u002Fwww.cipotato.org\u002F \"国际马铃薯中心\")[国际水稻研究所](http:\u002F\u002Firri.org\u002F \"国际水稻研究所\")[国际半干旱地区热带作物研究中心](http:\u002F\u002Fwww.icrisat.org\u002F \"国际半干旱地区热带作物研究中心\")\n\n各市分院\n\n[聊城分院](http:\u002F\u002Fwww.lcsnky.com\u002F \"聊城分院\")[临沂分院](http:\u002F\u002Fnyj.linyi.gov.cn\u002Flysnykxy.htm \"临沂分院\")[滨州分院](http:\u002F\u002Fwww.sdbzasvm.com\u002F \"滨州分院\")[菏泽分院](http:\u002F\u002Fwww.sdhznky.cn\u002F \"菏泽分院\")[德州分院](http:\u002F\u002Fwww.dznky.cn\u002F \"德州分院\")[济宁分院](http:\u002F\u002Fwww.jnnky.com\u002F \"济宁分院\")\n\n新闻媒体\n\n[中央电视台](http:\u002F\u002Fcctv.cntv.cn\u002F \"中央电视台\")[人民网](http:\u002F\u002Fwww.people.com.cn\u002F \"人民网\")[新华网](http:\u002F\u002Fwww.xinhuanet.com\u002F \"新华网\")[科技日报](http:\u002F\u002Fdigitalpaper.stdaily.com\u002F \"科技日报\")[光明日报](http:\u002F\u002Fwww.gmw.cn\u002F \"光明日报\")[农民日报](http:\u002F\u002Fwww.farmer.com.cn\u002Fwlb\u002Fnmrb \"农民日报\")[中国青年报](http:\u002F\u002Fwww.cyol.net\u002F \"中国青年报\")[大众日报](https:\u002F\u002Fwww.dzwww.com\u002F \"大众日报\")[农村大众](http:\u002F\u002Fpaper.dzwww.com\u002Fncdz\u002Fcontent\u002F20120213\u002FPage01NU.htm \"农村大众\")\n\n领导信箱\n\n[书记信箱](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch11447\u002F \" 书记信箱\")[院长信箱](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch11445\u002F \" 院长信箱\")\n\n![Image 22](http:\u002F\u002Fwww.saas.ac.cn\u002Ftemplate\u002Fsdnky\u002Fdefault2026\u002Fimages\u002Fnew2026\u002Fbot_logo02.png)\n\n[![Image 23](http:\u002F\u002Fwww.saas.ac.cn\u002Ftemplate\u002Fsdnky\u002Fdefault2026\u002Fimages\u002Fnew2026\u002Fssdw.png)](http:\u002F\u002Fbszs.conac.cn\u002Fsitename?method=show&id=0B6F776D5D6D5B5FE053012819AC51C1)\n\n主办单位：山东省农业科学院 地址：济南市历城区工业北路23788号\n\n[鲁公网安备：37001399010号](http:\u002F\u002Fwww.beian.gov.cn\u002Fportal\u002FregisterSystemInfo?recordcode=37001399010)[![Image 24](http:\u002F\u002Fwww.saas.ac.cn\u002Ftemplate\u002Fsdnky\u002Fdefault2026\u002Fimages\u002Fnew2026\u002F2009181058165079636.png) 鲁ICP备2022013696号-10](https:\u002F\u002Fbeian.miit.gov.cn\u002F)\n\n邮 编：250100 您是本站第 4208347 位访客\n\n[网站地图](http:\u002F\u002Fwww.saas.ac.cn\u002Fchannels\u002Fch17323\u002F) | [免责声明](javascript: void(0)) | [联系我们](javascript: void(0))\n\n![Image 25](http:\u002F\u002Fwww.saas.ac.cn\u002Fresource\u002Fsdnky01\u002Fimage\u002F202604\u002F3fcb1043-85f2-4dca-958d-b207876c780b.png)\n\n![Image 26](http:\u002F\u002Fwww.saas.ac.cn\u002Fresource\u002Fsdnky01\u002Fimage\u002F202604\u002F219d5bb3-cb2b-4115-a146-fc799b429998.png)","山东省农业科学院","2026-09-16T00:00:00Z","报道",55,{"impact":17,"substance":20,"depth":17,"authority":17,"freshness":75,"relevant":22,"comment":127},"省级农科院举办的AI专题学术交流活动，内容聚焦作物表型智能感知，有一定专业价值但属会议报道，信息增量有限。",[129],{"name":122,"url":119},[27,28,31,131],"学术交流",[133,134],"山东省农科院 舜耕论坛 人工智能","何勇 作物表型 智能感知","山东省农科院舜耕论坛人工智能-3103","2026-09-22T00:05:35.424987Z",{"id":138,"title":139,"url":140,"summary":141,"summary_zh":142,"content":9,"source_name":143,"source_url":140,"published_at":144,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":145,"score_detail":146,"sources":150,"tags":152,"search_phrases":155,"slug":158,"view_count":36,"doi":159,"paper":160,"created_at":181},3067,"Automated detection of visible venation patterns in cowpea leaves under agricultural engineering","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.sasc.2026.200636","Accurate assessment of crop leaf characteristics is important for automated crop phenotyping and precision agriculture. However, manual assessment of leaf characteristics is time-consuming and may be affected by subjective interpretation. This study proposes an RGB-based convolutional neural network (CNN) framework for automated classification of surface-visible venation patterns in cowpea (Vigna unguiculata) leaves. A dataset of 2500 RGB cowpea leaf images, comprising Healthy and Structurally Stressed samples, was used to develop and evaluate the proposed framework. The images were preprocessed using standard image-processing operations and subsequently analyzed using a CNN for binary classification of the two visible-venation categories. Canny edge detection was additionally employed as a supplementary visualization technique to highlight surface-visible venation patterns and support qualitative interpretation; it was not used as the primary classification mechanism. The proposed CNN achieved 95.4% accuracy, 94.8% precision, 95.1% recall, and 95.0% F1-score on the evaluated test dataset. Comparative experiments with conventional feature-based approaches, including GLCM, SIFT, and HOG, showed lower observed classification performance. The results demonstrate the potential of RGB-based deep learning for automated analysis of surface-visible cowpea leaf venation patterns and provide a non-destructive image-based approach for crop phenotyping. The proposed framework can support scalable agricultural image analysis while avoiding claims of direct Surface-visible vein pattern anatomical characterization. The dataset is available at this link: “ https:\u002F\u002Fgithub.com\u002Fvijayachoudharyresearcher\u002FComputer-Vision–Cowpea-Leaves-Internal-Structure “.","准确评估作物叶片特征对于自动化作物表型分析和精准农业具有重要意义。然而，人工评估叶片特征耗时较长，且可能受到主观解释的影响。本研究提出了一种基于RGB的卷积神经网络（CNN）框架，用于对豇豆（Vigna unguiculata）叶片表面可见脉纹模式进行自动分类。研究使用包含健康和结构胁迫样本的2500张RGB豇豆叶片图像数据集来开发和评估所提出的框架。图像经标准图像处理操作预处理后，利用CNN对两个可见脉纹类别进行二分类分析。此外，研究还采用Canny边缘检测作为补充可视化技术，以突出表面可见脉纹模式并支持定性解释；其并未被用作主要分类机制。所提出的CNN在评估测试数据集上取得了95.4%的准确率、94.8%的精确率、95.1%的召回率和95.0%的F1分数。与传统基于特征的方法（包括GLCM、SIFT和HOG）的比较实验显示，其分类性能较低。结果表明，基于RGB的深度学习在自动化分析豇豆叶片表面可见脉纹模式方面具有潜力，并为作物表型分析提供了一种基于图像的非破坏性方法。所提出的框架可支持可扩展的农业图像分析，同时避免声称对表面可见脉纹模式进行直接的解剖学表征。数据集可通过以下链接获取：“https:\u002F\u002Fgithub.com\u002Fvijayachoudharyresearcher\u002FComputer-Vision–Cowpea-Leaves-Internal-Structure”。","Systems and Soft Computing","2026-09-18T00:00:00Z",69,{"impact":17,"substance":18,"depth":147,"authority":20,"freshness":148,"relevant":22,"comment":149},16,8,"基于RGB与CNN的豇豆叶脉自动识别研究，方法清晰、数据规模可观，对作物表型与精准农业有参考价值，但属细分领域技术进展，影响范围有限。",[151],{"name":143,"url":140},[27,28,31,153,154],"图像识别","豇豆",[156,157],"豇豆叶片 叶脉 识别","RGB CNN 作物表型","豇豆叶片叶脉识别-3067","10.1016\u002Fj.sasc.2026.200636",{"doi":159,"openalex_id":161,"authors":162,"venue":143,"cited_by_count":36,"oa_url":140,"card":176,"direction":70,"ingested_from":72},"W7213555214",[163,166,169,171,173],{"name":164,"orcid":165},"Vijaya Choudhary","https:\u002F\u002Forcid.org\u002F0000-0003-3417-1943",{"name":167,"orcid":168},"Paramita Guha","https:\u002F\u002Forcid.org\u002F0000-0001-6696-4812",{"name":170,"orcid":9},"Jai Prakash Mishra",{"name":172,"orcid":9},"Himanshu Sharma",{"name":174,"orcid":175},"Munish Sabharwal","https:\u002F\u002Forcid.org\u002F0000-0002-7338-6982",{"tldr":177,"method":178,"finding":179,"direction":70,"opportunity":180},"用RGB卷积神经网络自动分类豇豆叶片可见脉纹，区分健康与结构胁迫样本。","2500张RGB豇豆叶图像，CNN二分类，Canny边缘检测辅助可视化，对比GL","CNN达95.4%准确率，优于传统特征方法，可实现无损作物表型分析。","可扩展至多作物、多胁迫类型及田间实时检测，并结合多光谱提升脉纹表型解析。","2026-09-21T23:30:18.575016Z",{"id":183,"title":184,"url":185,"summary":186,"summary_zh":187,"content":9,"source_name":188,"source_url":185,"published_at":144,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":189,"score_detail":190,"sources":192,"tags":194,"search_phrases":197,"slug":200,"view_count":36,"doi":201,"paper":202,"created_at":219},2963,"A comprehensive review of deep learning methods for weed classification in precision agriculture","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs44163-026-01916-7","Weeds today are among the factors contributing to low agricultural productivity. As the world’s population continues to grow, there is an urgent need to meet global food demand. Nigeria currently lacks sufficient crop production to feed its growing population, and weeds are among the core contributors to poor agricultural yield. This study conducts a comprehensive review of Deep Learning (DL) approaches to weed classification in precision agriculture, covering literature from 2018 to 2025, was carried out. We employed a mix of quantitative and qualitative methods in the course of this review paper. Our data source is centred on Scopus-indexed papers, published with Sensors, Electronics, and Agriculture in MDPI as well as IEEE, Thomson Reuters, and Springer. The study systematically reviewed and analysed machine learning (ML), DL, and instance segmentation techniques to identify the key technological and environmental barriers, such as data limitations, class imbalance, environmental variability, and model scalability issues that affect the effectiveness and efficiency of these models when deployed in real time. These findings show that while weed management models like the YOLO variants, ResNet, and Vision Transformers achieved high accuracy in training and testing, they are associated with several challenges in their real world-deployment, such as occlusion, small object detection, and environmental adaptability. Overall, this research provides recommended solutions to enhance model robustness, scalability, and efficiency. It further provides a summary of the current state and future directions for AI-driven weed management.","杂草是当前导致农业生产力低下的因素之一。随着世界人口持续增长，满足全球粮食需求已成为迫切任务。尼日利亚目前的作物产量不足以养活其不断增长的人口，而杂草是导致农业产量低下的核心因素之一。本研究对精准农业中基于深度学习（Deep Learning，DL）的杂草分类方法进行了全面综述，涵盖2018年至2025年的文献。在综述过程中，我们采用了定量与定性相结合的方法。数据来源集中于Scopus索引论文，这些论文发表于MDPI旗下的Sensors、Electronics和Agriculture，以及IEEE、Thomson Reuters和Springer。本研究系统综述并分析了机器学习（Machine Learning，ML）、深度学习及实例分割技术，以识别影响这些模型实时部署效果与效率的关键技术和环境障碍，如数据局限性、类别不平衡、环境变异性及模型可扩展性问题。研究结果表明，尽管YOLO系列、ResNet和视觉Transformer（Vision Transformer）等杂草管理模型在训练和测试中达到了较高精度，但在实际部署中仍面临诸多挑战，如遮挡、小目标检测和环境适应性等问题。总体而言，本研究提出了增强模型鲁棒性、可扩展性和效率的推荐解决方案，并进一步总结了人工智能驱动杂草管理的现状与未来方向。","Discover Artificial Intelligence",67,{"impact":17,"substance":86,"depth":147,"authority":20,"freshness":148,"relevant":22,"comment":191},"系统综述2018—2025年深度学习杂草分类方法，指出遮挡、小目标与环境适应性等落地瓶颈，对农业AI研究有参考价值，但属综述类论文、非突破性成果。",[193],{"name":188,"url":185},[27,28,29,195,196],"杂草识别","精准农业",[198,199],"深度学习 杂草分类 精准农业","YOLO 杂草识别 模型部署","深度学习杂草分类精准农业-2963","10.1007\u002Fs44163-026-01916-7",{"doi":201,"openalex_id":203,"authors":204,"venue":188,"cited_by_count":36,"oa_url":185,"card":213,"direction":217,"ingested_from":72},"W7213558223",[205,207,209,211],{"name":206,"orcid":9},"Njoku Camillus Ekene",{"name":208,"orcid":9},"Francis A. Okoye",{"name":210,"orcid":9},"Ebere Uzoka Chidi",{"name":212,"orcid":9},"OGBU MARY NNENNA",{"tldr":214,"method":215,"finding":216,"direction":217,"opportunity":218},"综述2018-2025年深度学习杂草分类方法，分析技术瓶颈并给出改进建议。","混合定量定性法，基于Scopus及MDPI、IEEE等文献，分析ML、DL与实例","YOLO、ResNet、ViT等精度高，但实际部署受遮挡、小目标与环境适应性限制。","农业人工智能与决策模型","可研究轻量化、跨域自适应模型，解决小目标与遮挡下的实时杂草识别难题。","2026-09-19T23:30:56.875661Z",{"id":221,"title":222,"url":223,"summary":224,"summary_zh":225,"content":9,"source_name":226,"source_url":223,"published_at":123,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":145,"score_detail":227,"sources":229,"tags":231,"search_phrases":233,"slug":236,"view_count":22,"doi":237,"paper":238,"created_at":249},2940,"A Hybrid CNN–Transformer–LSTM Deep Learning Framework for Automated Cotton Disease Detection","https:\u002F\u002Fdoi.org\u002F10.53365\u002Fnrfhh.1816","Cotton production is frequently affected by leaf diseases that can reduce plant productivity, deteriorate crop quality, and cause considerable financial losses for farmers. Consequently, rapid and reliable disease identification is an important requirement for precision agriculture and effective crop protection. Conventional image-based approaches predominantly employ CNN architectures for visual classification; however, such methods may have limited capability in learning long-range spatial dependencies and modeling changes associated with disease development over time. To overcome these limitations, this research introduces an integrated hybrid deep learning framework that combines Convolutional Neural Networks (CNNs), Transformer-based self-attention, and Long Short-Term Memory (LSTM) networks for intelligent cotton leaf disease recognition. The proposed framework utilizes a pre-trained EfficientNet network to extract discriminative spatial characteristics from cotton leaf images. The extracted representations are subsequently processed through a multi-head self-attention Transformer module, which enables the network to identify relationships between distant and relevant regions of the leaf. An LSTM component is then incorporated to learn sequential dependencies and provide a foundation for analyzing disease evolution and progression. To improve model reliability and generalization, the network is trained using an appropriately organized cotton leaf image dataset together with image augmentation, transfer learning, and fine-tuning techniques. The experimental evaluation indicates that the proposed CNN–Transformer–LSTM architecture provides improved disease classification performance and more effective feature learning compared with conventional CNN-based models. Performance assessment using classification metrics, confusion matrices, and ROC curves demonstrates strong discrimination among the considered cotton disease categories. The combined learning of local visual characteristics, global contextual information, and sequential dependencies provides a comprehensive framework for automated cotton disease assessment. The proposed approach can serve as a scalable artificial intelligence solution for precision agriculture applications. Its architecture also provides opportunities for future integration with IoT-based crop monitoring systems, environmental data acquisition, and disease progression prediction, supporting early warning systems and intelligent crop health management in smart farming environments.","棉花生产常受叶片病害影响，这些病害会降低植株生产力、恶化作物品质，并给农民造成相当大的经济损失。因此，快速可靠的病害识别是精准农业和有效作物保护的重要需求。传统的基于图像的方法主要采用CNN架构进行视觉分类；然而，此类方法在学习长程空间依赖关系以及建模与病害随时间发展相关的变化方面能力有限。为克服这些局限，本研究提出了一种集成混合深度学习框架，将卷积神经网络（CNN）、基于Transformer的自注意力机制和长短期记忆（LSTM）网络相结合，用于智能棉花叶片病害识别。所提出的框架利用预训练的EfficientNet网络从棉花叶片图像中提取具有判别力的空间特征。提取到的表示随后通过多头自注意力Transformer模块进行处理，使网络能够识别叶片中相距较远且相关区域之间的关系。随后引入LSTM组件以学习序列依赖关系，并为分析病害演变和进展提供基础。为提高模型可靠性和泛化能力，网络使用组织良好的棉花叶片图像数据集进行训练，并结合图像增强、迁移学习和微调技术。实验评估表明，与传统的基于CNN的模型相比，所提出的CNN–Transformer–LSTM架构提供了更好的病害分类性能和更有效的特征学习。使用分类指标、混淆矩阵和ROC曲线进行的性能评估表明，该方法在所考虑的棉花病害类别之间具有较强的判别能力。局部视觉特征、全局上下文信息和序列依赖关系的联合学习为自动化棉花病害评估提供了一个全面的框架。所提出的方法可作为精准农业应用中可扩展的人工智能解决方案。其架构也为未来与基于物联网的作物监测系统、环境数据采集和病害进展预测的集成提供了机会，从而支持预警系统和智能","Natural Resources for Human Health",{"impact":17,"substance":18,"depth":19,"authority":17,"freshness":148,"relevant":22,"comment":228},"提出CNN-Transformer-LSTM混合框架用于棉花叶病识别，方法有创新但属实验室验证阶段，产业影响有限。",[230],{"name":226,"url":223},[27,28,29,196,232],"棉花病害识别",[234,235],"棉花叶病 CNN Transformer LSTM","EfficientNet 棉花病害检测","棉花叶病CNNTransformerLSTM-2940","10.53365\u002Fnrfhh.1816",{"doi":237,"openalex_id":239,"authors":240,"venue":226,"cited_by_count":36,"oa_url":9,"card":243,"direction":248,"ingested_from":72},"W7213544712",[241],{"name":242,"orcid":9},"Prajakta Sunil Gupta",{"tldr":244,"method":245,"finding":246,"direction":217,"opportunity":247},"提出CNN-Transformer-LSTM混合框架，实现棉花叶片病害自动识别。","EfficientNet提取特征，Transformer自注意力与LSTM建模，","混合模型分类性能优于传统CNN，能同时学习局部特征、全局上下文和序列依赖。","可融合IoT环境数据与时间序列，开展病害进展预测和早期预警系统研究。","智慧农业 \u002F 农业物联网","2026-09-19T23:30:19.558449Z",{"id":251,"title":252,"url":253,"summary":254,"summary_zh":255,"content":9,"source_name":256,"source_url":253,"published_at":144,"category":12,"cover_url":9,"hotness":257,"is_selected":14,"score":258,"score_detail":259,"sources":262,"tags":266,"search_phrases":268,"slug":271,"view_count":36,"doi":272,"paper":273,"created_at":283},2934,"A CNN-Based Approach for Leaf Disease Prediction in Smart Agriculture","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22825329","Plants play a crucial role in sustaining life by serving as a primary source of energy and mitigating global warming. However, they are increasingly vulnerable to diseases such as bacterial spot, late blight, and Septoria leaf spot, which significantly impact crop yield and agricultural productivity. Early and accurate detection of these diseases is essential for effective disease management and improved agricultural outcomes. This project aims to develop a deep learning-based approach for detecting plant leaf diseases using Convolutional Neural Networks (CNN). By leveraging benchmark datasets, the proposed CNN model demonstrates superior performance compared to traditional machine learning techniques, achieving an accuracy of 92%, precision of 89%, F1-score of 93%, and recall of 92.47%. The results highlight the effectiveness of CNN in automating disease identification, enabling timely intervention, and promoting sustainable agricultural practices.","植物在维持生命方面发挥着至关重要的作用，既是主要的能量来源，又能缓解全球变暖。然而，植物日益受到细菌性斑点病、晚疫病和壳针孢叶斑病等病害的威胁，严重影响作物产量和农业生产率。早期准确地检测这些病害对于有效防控病害和改善农业成果至关重要。本项目旨在开发一种基于深度学习的方法，利用卷积神经网络（CNN）检测植物叶片病害。通过利用基准数据集，所提出的CNN模型展现出优于传统机器学习技术的性能，达到了92%的准确率、89%的精确率、93%的F1分数和92.47%的召回率。结果表明，CNN在自动化病害识别方面具有显著效果，能够实现及时干预并促进可持续农业实践。","Zenodo (CERN European Organization for Nuclear Research)",25,65,{"impact":17,"substance":86,"depth":260,"authority":17,"freshness":21,"relevant":22,"comment":261},14,"基于CNN的叶片病害识别研究，方法常规、数据集为公开基准，准确率92%属中等水平，对智慧农业植保场景有一定参考价值但缺乏突破性。",[263,264],{"name":256,"url":253},{"name":256,"url":265},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22825330",[27,28,29,267],"植物病害识别",[269,270],"CNN 植物叶片病害 识别","卷积神经网络 作物病害 检测","CNN植物叶片病害识别-2934","10.5281\u002Fzenodo.22825329",{"doi":272,"openalex_id":274,"authors":275,"venue":256,"cited_by_count":36,"oa_url":253,"card":278,"direction":248,"ingested_from":72},"W7213587327",[276],{"name":277,"orcid":9},"B.Yashmal Sai, K.Karthik, K.Neeraj, G. Mahabub Subhani",{"tldr":279,"method":280,"finding":281,"direction":217,"opportunity":282},"用CNN对植物叶片病害进行自动识别，在基准数据集上取得92%准确率。","基于卷积神经网络，使用植物叶片病害基准数据集训练与评估。","CNN优于传统机器学习方法，准确率92%、F1值93%，可支持及时干预。","可探索轻量化CNN在田间移动端实时检测，并结合多病害与早期症状识别。","2026-09-19T23:30:11.855376Z"]