[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-1631":3,"related-1631":83},{"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,"primary_topic":9,"secondary_topics":31,"classification":32,"search_phrases":51,"slug":54,"view_count":55,"doi":56,"paper":57,"created_at":82},1631,"A dynamic multi-scale feature fusion and hierarchical attention network for leaf segmentation","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs10791-026-10494-2","Abstract Accurate leaf instance segmentation is fundamental to quantifying morphological and structural traits in image-based plant phenotyping. However, substantial variations in leaf scale, shape, and orientation, together with dense overlap and occlusion, often lead to ambiguous instance boundaries. In addition, repeated downsampling and feature reconstruction can progressively erode fine structural details, hindering contour preservation and the separation of adjacent leaves. To address these interrelated challenges, we propose DMSHA-Net, a dynamic multi-scale feature fusion and hierarchical attention network for leaf instance segmentation. Its direction-aware Multi-Scale Feature Aggregation (MSFA) encoder captures complementary horizontal and vertical contextual information across multiple receptive-field scales, thereby improving the representation of diverse leaf morphologies. The Dense Feature Aggregation (DFA) decoder selectively integrates deep semantic and shallow structural features through stage-specific attention mechanisms, where self-attention at coarse resolutions models long-range dependencies, whereas lightweight channel recalibration at high resolutions refines local structures and boundaries. The Learnable Feature Fusion (LFF) module subsequently integrates multi-level semantic and boundary features using normalized learned weights. DMSHA-Net achieves Best Dice (BD) scores of 93.17%, 85.12%, and 90.91% on KOMATSUNA, MSU-PID, and the CVPPP-A1 subset, respectively, with corresponding foreground–background Dice (FBD) scores of 98.19%, 91.02%, and 98.24%. These results indicate that DMSHA-Net achieves competitive segmentation performance across the three datasets, particularly in scenarios involving pronounced scale variation and dense leaf overlap.","准确的叶片实例分割是基于图像植物表型分析中量化形态与结构特征的基础。然而，叶片在尺度、形状和方向上的显著差异，加之密集重叠和遮挡，常导致实例边界模糊不清。此外，重复的下采样和特征重建会逐步侵蚀细微的结构细节，妨碍轮廓保持及相邻叶片的分离。为应对这些相互关联的挑战，我们提出了DMSHA-Net，一种用于叶片实例分割的动态多尺度特征融合与层次注意力网络。其方向感知的多尺度特征聚合（MSFA）编码器在多个感受野尺度上捕获互补的水平和垂直上下文信息，从而增强对不同叶片形态的表征能力。密集特征聚合（DFA）解码器通过阶段特定的注意力机制选择性地整合深层语义特征与浅层结构特征，其中在粗分辨率下的自注意力建模长距离依赖关系，而在高分辨率下的轻量级通道重校准则细化局部结构和边界。可学习特征融合（LFF）模块随后利用归一化的学习权重整合多层次语义与边界特征。DMSHA-Net在KOMATSUNA、MSU-PID和CVPPP-A1子集上分别取得了93.17%、85.12%和90.91%的最佳Dice（BD）分数，相应的前景-背景Dice（FBD）分数分别为98.19%、91.02%和98.24%。这些结果表明，DMSHA-Net在三个数据集上均实现了具有竞争力的分割性能，尤其在涉及显著尺度变化和密集叶片重叠的场景中表现突出。",null,"Discover Computing","2026-09-03T00:00:00Z","论文",10,false,74,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},15,22,18,12,7,1,"提出DMSHA-Net网络，在多个植物叶片分割数据集上取得领先性能，对农业表型分析有实质推进。",[25],{"name":10,"url":6},[27,28,29,30],"智慧农业","农业人工智能","植物表型","图像分割",[],{"status":33,"locked":14,"version":34,"method":35,"evidence":36},"unclassified","2026-10-22.2","rules",{"candidates":37,"agricultural_evidence":49,"reason":50},[38,44],{"code":39,"score":40,"supported":14,"title":41,"abstract":42,"tags":43},"I2",2,[],[],[28,30],{"code":45,"score":22,"supported":14,"title":46,"abstract":47,"tags":48},"I1",[],[],[27],true,"缺少足够的主题证据",[52,53],"农业人工智能 图像分割 智慧农业 植物表型","农业人工智能 图像分割","农业人工智能图像分割智慧农业植物表型-1631",3,"10.1007\u002Fs10791-026-10494-2",{"doi":56,"openalex_id":58,"authors":59,"venue":10,"cited_by_count":74,"oa_url":6,"card":75,"direction":79,"ingested_from":81},"W7207602965",[60,63,65,67,70,72],{"name":61,"orcid":62},"Fei Liu","https:\u002F\u002Forcid.org\u002F0000-0002-6148-3697",{"name":64,"orcid":9},"Yingjie Fan",{"name":66,"orcid":9},"Mingtao Zhou",{"name":68,"orcid":69},"Huabing Liu","https:\u002F\u002Forcid.org\u002F0000-0003-1312-3926",{"name":71,"orcid":9},"Shuya Chen",{"name":73,"orcid":9},"Bin Wen",0,{"tldr":76,"method":77,"finding":78,"direction":79,"opportunity":80},"提出动态多尺度特征融合与层级注意力网络，用于叶片实例分割，提升精度。","使用方向感知多尺度特征聚合编码器、密集特征聚合解码器及可学习特征融合模块。","在三个数据集上取得最佳Dice分数，尤其在尺度变化和密集重叠场景表现优异。","农业遥感与作物表型","可探索将DMSHA-Net应用于更多作物类型或复杂田间环境，或结合轻量化设计用于实时表型分析。","openalex","2026-09-04T23:30:26.243015Z",{"total":84,"page":22,"page_size":84,"items":85},6,[86,159,230,284,328,371],{"id":87,"title":88,"url":89,"summary":90,"summary_zh":91,"content":9,"source_name":92,"source_url":89,"published_at":93,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":94,"score_detail":95,"sources":99,"tags":101,"primary_topic":103,"secondary_topics":109,"classification":110,"search_phrases":127,"slug":130,"view_count":131,"doi":132,"paper":133,"created_at":158},2316,"Vision Transformers Enable Advanced Plant Phenotyping in Controlled Environments","https:\u002F\u002Fdoi.org\u002F10.64898\u002F2026.09.04.748299","Reliable plant segmentation in high-throughput phenotyping must transfer across species and imaging conditions without repeated model tuning or extensive reannotation. We compare three segmentation strategies using images from Oak Ridge National Laboratory's Advanced Plant Phenotyping Laboratory: (i) fixed color-based thresholding, (ii) supervised U-Nets trained from scratch, and (iii) pretrained vision transformers fine-tuned for binary segmentation. Models were evaluated on a held-out test set and a generalization set that comprised unseen species. On the held-out test set, thresholding, the best U-Net, and the best vision transformer achieved mean Dice scores of 58.3, 96.6, and 97.3, respectively. On the generalization set, the corresponding Dice scores were 56.5, 86.2, and 95.7. Thresholding remained effective on some datasets but failed when plant appearance changed. Supervised U-Net training resolved within-distribution errors but failed to generalize to novel species and backgrounds. Pretrained vision transformers consistently produced high-accuracy segmentations across the evaluated species, views, soil backgrounds, and tray types. These results benchmark the practical progression from fixed rules to task-specific supervision and pretrained visual representations for controlled-environment plant phenotyping.","在高通量表型分析中，可靠的植物分割必须能够在不同物种和成像条件之间迁移，而无需重复调整模型或进行大量重新标注。我们利用橡树岭国家实验室先进植物表型实验室的图像，比较了三种分割策略：（i）基于颜色的固定阈值法，（ii）从零开始训练的有监督U-Net，以及（iii）针对二值分割进行微调的预训练视觉Transformer。模型在留出测试集和包含未见物种的泛化集上进行了评估。在留出测试集上，阈值法、最佳U-Net和最佳视觉Transformer的平均Dice分数分别为58.3、96.6和97.3。在泛化集上，相应的Dice分数分别为56.5、86.2和95.7。阈值法在某些数据集上仍然有效，但当植物外观发生变化时则失效。有监督U-Net训练解决了分布内误差，但未能泛化到新物种和背景。预训练视觉Transformer在所评估的物种、视角、土壤背景和托盘类型上始终产生高精度分割。这些结果基准了受控环境植物表型分析中从固定规则到任务特定监督再到预训练视觉表示的实际进展。","bioRxiv (Cold Spring Harbor Laboratory)","2026-09-10T00:00:00Z",79,{"impact":19,"substance":18,"depth":19,"authority":96,"freshness":97,"relevant":22,"comment":98},13,8,"预训练视觉Transformer在跨物种植物分割上显著优于U-Net与阈值法，为受控环境高通量表型提供可复用基准，方法新颖、数据扎实，值得入选。",[100],{"name":92,"url":89},[27,28,102,29,30],"高通量表型",{"code":104,"slug":105,"name":106,"path":107,"parent_code":108},"H2","soil","土壤健康与改良","\u002Ftopic\u002Fenvironment\u002Fsoil","H",[],{"status":111,"locked":14,"version":34,"method":35,"evidence":112},"classified",{"candidates":113,"agricultural_evidence":49},[114,119,123],{"code":104,"score":84,"supported":49,"title":115,"abstract":116,"tags":118},[],[117,105],"土壤",[],{"code":39,"score":40,"supported":14,"title":120,"abstract":121,"tags":122},[],[],[28,30],{"code":45,"score":22,"supported":14,"title":124,"abstract":125,"tags":126},[],[],[27],[128,129],"农业人工智能 高通量表型 图像分割 智慧农业","农业人工智能 高通量表型","农业人工智能高通量表型图像分割智慧农业-2316",4,"10.64898\u002F2026.09.04.748299",{"doi":132,"openalex_id":134,"authors":135,"venue":92,"cited_by_count":74,"oa_url":9,"card":153,"direction":79,"ingested_from":81},"W7212309344",[136,138,141,144,147,150],{"name":137,"orcid":9},"Janou Milligan",{"name":139,"orcid":140},"Anand Seethepalli","https:\u002F\u002Forcid.org\u002F0000-0003-0937-9128",{"name":142,"orcid":143},"Aristeidis Tsaris","https:\u002F\u002Forcid.org\u002F0000-0002-7734-3349",{"name":145,"orcid":146},"Xiao Wang","https:\u002F\u002Forcid.org\u002F0000-0001-6545-1943",{"name":148,"orcid":149},"Larry M. York","https:\u002F\u002Forcid.org\u002F0000-0002-1995-9479",{"name":151,"orcid":152},"John Lagergren","https:\u002F\u002Forcid.org\u002F0000-0002-8092-7433",{"tldr":154,"method":155,"finding":156,"direction":79,"opportunity":157},"比较阈值法、U-Net和预训练ViT在植物分割中的跨物种泛化能力。","使用ORNL表型实验室图像，对比阈值法、U-Net和微调ViT的分割性能。","预训练ViT在未见物种上Dice达95.7，显著优于U-Net的86.2和阈值法的56.5。","可探索预训练ViT在田间复杂场景的跨物种泛化，并降低微调数据需求。","2026-09-13T23:30:21.474320Z",{"id":160,"title":161,"url":162,"summary":163,"summary_zh":164,"content":9,"source_name":165,"source_url":162,"published_at":166,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":167,"score_detail":168,"sources":172,"tags":174,"primary_topic":177,"secondary_topics":182,"classification":183,"search_phrases":196,"slug":199,"view_count":74,"doi":200,"paper":201,"created_at":229},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",81,{"impact":19,"substance":18,"depth":19,"authority":169,"freshness":170,"relevant":22,"comment":171},14,9,"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。",[173],{"name":165,"url":162},[27,28,29,175,176],"多模态大模型","芸薹属",{"code":39,"slug":178,"name":179,"path":180,"parent_code":181},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":111,"locked":14,"version":34,"method":35,"evidence":184},{"candidates":185,"agricultural_evidence":49},[186,192],{"code":39,"score":97,"supported":49,"title":187,"abstract":188,"tags":191},[],[189,190],"深度学习","deep learning",[28,175],{"code":45,"score":22,"supported":14,"title":193,"abstract":194,"tags":195},[],[],[27],[197,198],"pxGPT 植物表型","Brassica 表型 多模态大模型","pxGPT植物表型-5562","10.1093\u002Fbioinformatics\u002Fbtag781",{"doi":200,"openalex_id":202,"authors":203,"venue":165,"cited_by_count":74,"oa_url":222,"card":223,"direction":228,"ingested_from":81},"W7223127960",[204,207,209,212,215,218,220],{"name":205,"orcid":206},"Po‐Xing Zheng","https:\u002F\u002Forcid.org\u002F0000-0001-5827-5865",{"name":208,"orcid":9},"Jheng-Yan Ou",{"name":210,"orcid":211},"Yu-Lin Wu","https:\u002F\u002Forcid.org\u002F0009-0003-8596-9047",{"name":213,"orcid":214},"Ruei-Shiuan Wang","https:\u002F\u002Forcid.org\u002F0009-0007-5159-1129",{"name":216,"orcid":217},"WU Ting-li","https:\u002F\u002Forcid.org\u002F0000-0001-7996-5515",{"name":219,"orcid":9},"Te-Chang Hsu",{"name":221,"orcid":9},"Yao-Cheng Lin","https:\u002F\u002Facademic.oup.com\u002Fbioinformatics\u002Fadvance-article-pdf\u002Fdoi\u002F10.1093\u002Fbioinformatics\u002Fbtag781\u002F72201337\u002Fbtag781.pdf",{"tldr":224,"method":225,"finding":226,"direction":79,"opportunity":227},"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。","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","2026-10-22T11:20:22.173561Z",{"id":231,"title":232,"url":233,"summary":234,"summary_zh":235,"content":9,"source_name":236,"source_url":233,"published_at":237,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":167,"score_detail":238,"sources":240,"tags":242,"primary_topic":9,"secondary_topics":245,"classification":246,"search_phrases":268,"slug":271,"view_count":74,"doi":272,"paper":273,"created_at":283},5317,"PLANT-GPK v4.0: A Unified Time-Discovery Framework for Multi-Stage Plant Phenotyping","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23460911","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 future harvest windows 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，该模型成功发现了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）的物理学，提供了一个完整的数字孪生体，无论植物当前处于何种状态，均能预测未来的收获窗口。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-19T00:00:00Z",{"impact":19,"substance":18,"depth":19,"authority":96,"freshness":13,"relevant":22,"comment":239},"该研究提出统一时间发现框架，可从单幅图像反演植物生育阶段并预测收获窗口，方法新颖且具数字孪生应用潜力，值得进入每日精选。",[241],{"name":236,"url":233},[27,28,243,244,29],"小麦","数字孪生",[],{"status":247,"locked":14,"version":34,"method":35,"evidence":248},"needs_review",{"candidates":249,"agricultural_evidence":49,"reason":267},[250,255,261],{"code":45,"score":97,"supported":49,"title":251,"abstract":252,"tags":254},[],[244,253],"digital twin",[244,27],{"code":256,"score":21,"supported":49,"title":257,"abstract":258,"tags":260},"A2",[],[243,259],"wheat",[243],{"code":39,"score":21,"supported":49,"title":262,"abstract":263,"tags":266},[],[264,265],"计算机视觉","computer vision",[28],"多个产业证据相当，需要确认主归属",[269,270],"PLANT-GPK 植物表型","小麦 数字孪生 生育期","PLANT-GPK植物表型-5317","10.5281\u002Fzenodo.23460911",{"doi":272,"openalex_id":274,"authors":275,"venue":236,"cited_by_count":74,"oa_url":233,"card":278,"direction":79,"ingested_from":81},"W7222895088",[276],{"name":277,"orcid":9},"MOHAMMED TAHAR SAIM",{"tldr":279,"method":280,"finding":281,"direction":79,"opportunity":282},"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，实现跨发育阶段表型分析。","基于ODE物理模型的反问题优化，联合估计生理参数与时间t，用两个小麦样本验证。","模型成功发现营养期与衰老期小麦的精确年龄，可预测收获窗口。","单图跨阶段时间反演可延伸至多作物多生育期数字孪生与收获期预测的通用化研究。","2026-10-19T23:30:19.498798Z",{"id":285,"title":286,"url":287,"summary":288,"summary_zh":289,"content":9,"source_name":236,"source_url":287,"published_at":237,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":94,"score_detail":290,"sources":292,"tags":294,"primary_topic":296,"secondary_topics":300,"classification":301,"search_phrases":314,"slug":316,"view_count":74,"doi":317,"paper":318,"created_at":327},5316,"PLANT-GPK v2.7: Spatial Heterogeneity and Predictive Digital Twin for Plant Phenotyping","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23460273","Traditional image-based plant phenotyping assumes spatial homogeneity, estimating a single set of physiological parameters for the entire plant. This paper introduces a novel extension to the PLANT-GPK framework: Spatial Physiological Heatmaps and Predictive Digital Twins. By dividing the plant image into a 3x3 grid and solving the inverse ODE problem for each spatial patch, we reveal the hidden spatial heterogeneity of resource allocation. Furthermore, the recovered parameters are extrapolated to predict the exact day of harvest using a continuous smooth-physics model, providing a powerful prescriptive tool for precision agriculture.","传统的基于图像的植物表型分析假设空间同质性，即对整个植株估计单一组生理参数。本文提出了对PLANT-GPK框架的一种新颖扩展：空间生理热图与预测性数字孪生。通过将植物图像划分为3×3网格并针对每个空间区块求解逆常微分方程（ODE）问题，我们揭示了资源分配中隐藏的空间异质性。此外，利用连续光滑物理模型对所恢复的参数进行外推，以预测确切的收获日期，为精准农业提供了强有力的规范性工具。",{"impact":19,"substance":18,"depth":19,"authority":20,"freshness":170,"relevant":22,"comment":291},"该论文提出植物表型空间异质性建模与预测性数字孪生方法，方法新颖、结论有实用价值，但属细分领域预印本成果，未达重大突破层级。",[293],{"name":236,"url":287},[27,28,244,295,29],"精准农业",{"code":45,"slug":297,"name":298,"path":299,"parent_code":181},"smart-agriculture","智慧农业总论","\u002Ftopic\u002Fdigital-agriculture\u002Fsmart-agriculture",[],{"status":111,"locked":14,"version":34,"method":35,"evidence":302},{"candidates":303,"agricultural_evidence":49},[304,310],{"code":45,"score":305,"supported":49,"title":306,"abstract":307,"tags":309},20,[253],[295,244,308],"precision agriculture",[244,27,295],{"code":39,"score":22,"supported":14,"title":311,"abstract":312,"tags":313},[],[],[28],[269,315],"空间生理热图 数字孪生","PLANT-GPK植物表型-5316","10.5281\u002Fzenodo.23460273",{"doi":317,"openalex_id":319,"authors":320,"venue":236,"cited_by_count":74,"oa_url":287,"card":322,"direction":79,"ingested_from":81},"W7222885652",[321],{"name":277,"orcid":9},{"tldr":323,"method":324,"finding":325,"direction":79,"opportunity":326},"将植物图像分3x3网格反演ODE参数，构建空间生理热图与预测数字孪生。","基于PLANT-GPK框架，分块求解逆ODE问题，并用连续平滑物理模型外推。","揭示了植物资源分配的空间异质性，可预测精确收获日。","可探索更细粒度网格与多模态表型融合，提升数字孪生预测精度与田间适用性。","2026-10-19T23:30:19.414490Z",{"id":329,"title":330,"url":331,"summary":332,"summary_zh":333,"content":9,"source_name":236,"source_url":331,"published_at":237,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":167,"score_detail":334,"sources":336,"tags":338,"primary_topic":340,"secondary_topics":341,"classification":342,"search_phrases":357,"slug":359,"view_count":74,"doi":360,"paper":361,"created_at":370},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。",{"impact":19,"substance":18,"depth":19,"authority":96,"freshness":13,"relevant":22,"comment":335},"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。",[337],{"name":236,"url":331},[27,28,244,29,339],"收获预测",{"code":39,"slug":178,"name":179,"path":180,"parent_code":181},[],{"status":111,"locked":14,"version":34,"method":35,"evidence":343},{"candidates":344,"agricultural_evidence":49},[345,349,353],{"code":45,"score":97,"supported":49,"title":346,"abstract":347,"tags":348},[],[244,253],[244,27],{"code":39,"score":21,"supported":49,"title":350,"abstract":351,"tags":352},[],[264,265],[28],{"code":256,"score":84,"supported":49,"title":354,"abstract":355,"tags":356},[],[243,259],[],[269,358],"小麦 收获期 预测","PLANT-GPK植物表型-5315","10.5281\u002Fzenodo.23461121",{"doi":360,"openalex_id":362,"authors":363,"venue":236,"cited_by_count":74,"oa_url":331,"card":365,"direction":79,"ingested_from":81},"W7222875391",[364],{"name":277,"orcid":9},{"tldr":366,"method":367,"finding":368,"direction":79,"opportunity":369},"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":372,"title":373,"url":374,"summary":375,"summary_zh":376,"content":9,"source_name":377,"source_url":374,"published_at":378,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":167,"score_detail":379,"sources":381,"tags":383,"primary_topic":386,"secondary_topics":391,"classification":392,"search_phrases":448,"slug":451,"view_count":74,"doi":452,"paper":453,"created_at":509},5314,"A data‐driven image extraction and analysis pipeline for plant phenotyping in controlled environments","https:\u002F\u002Fdoi.org\u002F10.1002\u002Fppj2.70116","Abstract Advances in automation, imaging, and artificial intelligence have enabled large‐scale plant phenotyping, but image analysis remains a critical bottleneck for crop improvement and biological discovery. We developed an integrated multispectral phenotyping framework using imagery from the Texas A&M AgriLife Automated Precision Phenotyping Greenhouse and expanded plant growth and phenotyping (PGP v2) data across maize ( Zea mays L.), cotton ( Gossypium hirsutum ), rice ( Oryza sativa ), and sorghum ( Sorghum bicolor L.). The pipeline integrates pseudo‐red‐green‐blue composite image generation, plant detection and segmentation, image stitching, vegetation‐index analysis, texture analysis, morphological trait extraction, and temporal comparison of image‐derived features to quantify changes in plant structure, spectral reflectance, and texture over time. Among the evaluated segmentation approaches, segment anything model (SAM) v3 provided the highest and most consistent accuracy across diverse crop structures, although it required greater computational time than classical methods. Segment anything model for long sequences (SAM2Long)maintained plant‐instance associations across vertically stacked frames, while scale‐invariant feature transform–based stitching reconstructed plant mosaics when individual plants extended beyond a single field of view. For each plant and imaging date, the pipeline generated an 863‐dimensional feature vector spanning vegetation indices, spectral statistics, texture descriptors, and morphological traits. The framework was evaluated through two case studies: treatment‐level temporal analysis of mutagenized sorghum lines and cold‐stress phenotyping of maize using a separate imaging system. In both studies, the extracted features supported statistical and multivariate analyses of phenotypic variation and enabled separation of plants based on treatment‐ or stress‐related responses. The combined dataset and workflow provide structured, automated, and well‐documented phenotypic analysis across multiple crops, experimental settings, and imaging systems for controlled‐environment plant science and crop improvement.","摘要　自动化、成像和人工智能的进步使得大规模植物表型分析成为可能，但图像分析仍然是作物改良和生物学发现的关键瓶颈。我们利用德克萨斯农工大学农业生命科学自动化精准表型温室（Texas A&M AgriLife Automated Precision Phenotyping Greenhouse）的图像，开发了一个集成多光谱表型分析框架，并扩展了玉米（Zea mays L.）、棉花（Gossypium hirsutum）、水稻（Oryza sativa）和高粱（Sorghum bicolor L.）的植物生长与表型分析（plant growth and phenotyping，PGP v2）数据。该流程整合了伪红绿蓝合成图像生成、植物检测与分割、图像拼接、植被指数分析、纹理分析、形态性状提取以及图像衍生特征的时间比较，以量化植物结构、光谱反射率和纹理随时间的变化。在评估的分割方法中，segment anything model（SAM）v3在不同作物结构下提供了最高且最一致的准确性，尽管其所需计算时间多于经典方法。面向长序列的segment anything model（SAM2Long）在垂直堆叠帧之间维持了植物实例关联，而基于尺度不变特征变换（scale-invariant feature transform）的拼接在单株植物超出单一视野时重建了植物拼接图。对于每株植物和每个成像日期，该流程生成了一个863维特征向量，涵盖植被指数、光谱统计量、纹理描述符和形态性状。该框架通过两个案例研究进行了评估：诱变高粱品系的处理水平时间分析，以及使用独立成像系统对玉米进行的冷胁迫表型分析。在这两项研究中，提取的特征支持了表型变异的统计分析和多变量分析，并能够根据处理或胁迫相关响应区分植物。合并的数据集和工作流程为受控环境植物科学和作物改良提供了跨多种作物、实验设置和成像系统的结构化、自动化且记录完善的表型分析。","The Plant Phenome Journal","2026-10-18T00:00:00Z",{"impact":19,"substance":18,"depth":19,"authority":169,"freshness":170,"relevant":22,"comment":380},"该研究提出一套面向多作物的自动化多光谱表型分析流程，方法新颖、数据规模可观，对智慧育种与受控环境植物科学研究具有较高参考价值。",[382],{"name":377,"url":374},[27,28,30,384,385],"表型组学","多光谱成像",{"code":387,"slug":388,"name":389,"path":390,"parent_code":9},"A","field-crops","大田作物","\u002Ftopic\u002Ffield-crops",[],{"status":393,"locked":14,"version":34,"method":35,"evidence":394},"partial",{"candidates":395,"agricultural_evidence":49,"reason":447},[396,403,410,417,424,431,437,443],{"code":397,"score":84,"supported":49,"title":398,"abstract":399,"tags":402},"A1",[],[400,401],"水稻","rice",[],{"code":404,"score":84,"supported":49,"title":405,"abstract":406,"tags":409},"A3",[],[407,408],"玉米","maize",[],{"code":411,"score":84,"supported":49,"title":412,"abstract":413,"tags":416},"A5",[],[414,415],"高粱","sorghum",[],{"code":418,"score":84,"supported":49,"title":419,"abstract":420,"tags":423},"A6",[],[421,422],"棉花","cotton",[],{"code":425,"score":84,"supported":49,"title":426,"abstract":427,"tags":430},"B7",[],[428,429],"温室","greenhouse",[],{"code":39,"score":432,"supported":49,"title":433,"abstract":434,"tags":436},5,[],[435],"artificial intelligence",[28,30],{"code":438,"score":131,"supported":49,"title":439,"abstract":440,"tags":442},"I3",[],[441],"multispectral",[385],{"code":45,"score":22,"supported":14,"title":444,"abstract":445,"tags":446},[],[],[27],"一级领域明确，二级方向需要细分",[449,450],"Texas A&M 自动化表型温室","玉米 高粱 多光谱表型","TexasAM自动化表型温室-5314","10.1002\u002Fppj2.70116",{"doi":452,"openalex_id":454,"authors":455,"venue":377,"cited_by_count":74,"oa_url":374,"card":504,"direction":79,"ingested_from":81},"W7222893982",[456,458,461,464,467,469,471,474,477,480,483,486,489,492,495,498,500,502],{"name":457,"orcid":9},"Fahimeh Orvati Nia",{"name":459,"orcid":460},"Joshua Peeples","https:\u002F\u002Forcid.org\u002F0000-0001-7861-7789",{"name":462,"orcid":463},"Seth C. Murray","https:\u002F\u002Forcid.org\u002F0000-0002-2960-8226",{"name":465,"orcid":466},"Andrew J. McFarland","https:\u002F\u002Forcid.org\u002F0009-0000-3516-8274",{"name":468,"orcid":9},"Troy Vann",{"name":470,"orcid":9},"Shima Salehi",{"name":472,"orcid":473},"Robert G. Hardin","https:\u002F\u002Forcid.org\u002F0000-0002-0714-8281",{"name":475,"orcid":476},"David D. Baltensperger","https:\u002F\u002Forcid.org\u002F0000-0003-4511-5680",{"name":478,"orcid":479},"Amir M. H. Ibrahim","https:\u002F\u002Forcid.org\u002F0000-0002-0584-753X",{"name":481,"orcid":482},"J. Alex Thomasson","https:\u002F\u002Forcid.org\u002F0000-0002-5557-105X",{"name":484,"orcid":485},"Henry Y. Fadamiro","https:\u002F\u002Forcid.org\u002F0000-0002-4530-9680",{"name":487,"orcid":488},"Nithya K. Subramanian","https:\u002F\u002Forcid.org\u002F0000-0002-1659-7396",{"name":490,"orcid":491},"Suresh D. Pillai","https:\u002F\u002Forcid.org\u002F0000-0002-9766-8765",{"name":493,"orcid":494},"Rebecca Roston","https:\u002F\u002Forcid.org\u002F0000-0002-3063-5002",{"name":496,"orcid":497},"Joslin Ishimwe","https:\u002F\u002Forcid.org\u002F0009-0003-6999-7718",{"name":499,"orcid":9},"Diptadeep Basak",{"name":501,"orcid":9},"Nazar Oladepo",{"name":503,"orcid":9},"Uday Santhosh Raju Vysyaraju",{"tldr":505,"method":506,"finding":507,"direction":79,"opportunity":508},"构建多光谱图像提取分析流程，实现多作物表型自动化量化。","用温室多光谱图像，集成SAM v3分割、SIFT拼接与863维特征提取。","SAM v3分割最准，特征可区分高粱诱变与玉米冷胁迫响应。","可探索轻量化分割模型与跨成像系统迁移，降低计算成本并拓展田间表型。","2026-10-19T23:30:17.276726Z"]