[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3528":3,"related-3528":56},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":8,"source_name":9,"source_url":6,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":15,"sources":23,"tags":25,"search_phrases":31,"slug":34,"view_count":35,"doi":36,"paper":37,"created_at":55},3528,"Long-term dynamic root monitoring based on classification fusion and attention mechanism","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.biosystemseng.2026.104602","Long-term dynamic root monitoring based on classification fusion and attention mechanism。Biosystems Engineering",null,"Biosystems Engineering","2026-09-25T00:00:00Z","论文",10,false,67,{"impact":16,"substance":17,"depth":18,"authority":19,"freshness":20,"relevant":21,"comment":22},12,18,16,13,8,1,"核心期刊论文，方法上有分类融合与注意力机制创新，属农业人工智能细分进展，但应用范围有限，未达重大突破层级。",[24],{"name":9,"url":6},[26,27,28,29,30],"智慧农业","农业人工智能","深度学习","作物表型","根系监测",[32,33],"Biosystems Engineering 根系监测","动态根系监测 注意力机制","BiosystemsEngineering根系监测-3528",0,"10.1016\u002Fj.biosystemseng.2026.104602",{"doi":36,"openalex_id":38,"authors":39,"venue":9,"cited_by_count":35,"oa_url":8,"card":8,"direction":8,"ingested_from":54},"W7214313105",[40,42,44,46,48,50,52],{"name":41,"orcid":8},"Yinkai Fu",{"name":43,"orcid":8},"Pengchong Zhang",{"name":45,"orcid":8},"Yue Zhao",{"name":47,"orcid":8},"Qiaoling Han",{"name":49,"orcid":8},"Benye Xi",{"name":51,"orcid":8},"Yandong Zhao",{"name":53,"orcid":8},"Jianhui Lin","openalex","2026-09-26T23:30:06.143382Z",{"total":57,"page":21,"page_size":57,"items":58},6,[59,117,182,223,266,306],{"id":60,"title":61,"url":62,"summary":63,"summary_zh":64,"content":8,"source_name":65,"source_url":62,"published_at":66,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":67,"score_detail":68,"sources":73,"tags":75,"search_phrases":77,"slug":80,"view_count":35,"doi":81,"paper":82,"created_at":116},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。","Frontiers in Plant Science","2026-09-21T00:00:00Z",71,{"impact":16,"substance":69,"depth":70,"authority":19,"freshness":71,"relevant":21,"comment":72},20,17,9,"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。",[74],{"name":65,"url":62},[26,27,28,76,29],"可可",[78,79],"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","10.3389\u002Ffpls.2026.1885906",{"doi":81,"openalex_id":83,"authors":84,"venue":65,"cited_by_count":35,"oa_url":62,"card":110,"direction":114,"ingested_from":54},"W7213901640",[85,87,90,92,94,96,99,102,105,107],{"name":86,"orcid":8},"Ezekiel Ahn",{"name":88,"orcid":89},"Eun-Sung Park","https:\u002F\u002Forcid.org\u002F0000-0001-6826-2865",{"name":91,"orcid":8},"Moon S. Kim",{"name":93,"orcid":8},"Hangi Kim",{"name":95,"orcid":8},"Lalit M. Kandpal",{"name":97,"orcid":98},"Sunchung Park","https:\u002F\u002Forcid.org\u002F0000-0002-7398-9476",{"name":100,"orcid":101},"Seunghyun Lim","https:\u002F\u002Forcid.org\u002F0000-0003-3023-4863",{"name":103,"orcid":104},"Lyndel W. Meinhardt","https:\u002F\u002Forcid.org\u002F0000-0001-8299-2629",{"name":106,"orcid":8},"Byoung-Kwan Cho",{"name":108,"orcid":109},"Insuck Baek","https:\u002F\u002Forcid.org\u002F0000-0003-1044-349X",{"tldr":111,"method":112,"finding":113,"direction":114,"opportunity":115},"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。","2026-09-22T23:30:19.972949Z",{"id":118,"title":119,"url":120,"summary":121,"summary_zh":122,"content":8,"source_name":65,"source_url":120,"published_at":123,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":124,"score_detail":125,"sources":128,"tags":130,"search_phrases":133,"slug":136,"view_count":35,"doi":137,"paper":138,"created_at":181},3490,"Balancing accuracy, completeness, and efficiency for rice 3D reconstruction through CBAM-UNet-based multi-view segmentation and camera configuration optimization","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffpls.2026.1882534","Multi-view 3D reconstruction has been widely applied in plant phenotyping, but the complex canopy structure of rice plants poses significant challenges for reconstruction accuracy, completene7ss, and efficiency. In this study, we developed an optimized workflow for 3D reconstruction of rice using the self-developed Metatlas V1 multi-view imaging platform combined with the COLMAP + OpenMVS pipeline. A CBAM-UNet-based image segmentation model was used to extract plant regions from complex backgrounds, outperforming thresholding, U-Net, and U-Net++, and increasing the number of reconstructed points. Camera configuration optimization was performed by systematically combining equidistant and greedy strategies, resulting in an optimal six-camera setup (#2, #3, #4, #6, #7, and #8, corresponding to −30°, −15°, 0°, +30°, +45°, and +60° relative to the horizontal viewpoint), which provided complementary views of the canopy inner structure and stem base. This configuration reduced the average nearest-neighbor distance to 0.037–0.066 cm across different varieties and growth stages compared with the full 11-camera setup, retained 73–76% of the points, and decreased reconstruction duration by approximately 70–80%. The strong agreement between point-cloud-derived and manually measured plant height and canopy width ( R 2 = 0.989 and 0.946, respectively) supported the accuracy of the point-cloud-derived phenotypic measurements. Overall, integrating image segmentation with camera-configuration optimization offers an accurate and efficient solution for high-throughput 3D phenotyping of rice using Metatlas V1, balancing reconstruction accuracy, point-cloud completeness, and computational efficiency, and may provide a methodological reference for camera-configuration design in other rotational multi-view phenotyping platforms.","多视角三维重建已广泛应用于植物表型分析，但水稻复杂的冠层结构对重建精度、完整性和效率构成了重大挑战。本研究利用自主研发的Metatlas V1多视角成像平台，结合COLMAP + OpenMVS流程，开发了一套优化的水稻三维重建工作流。采用基于CBAM-UNet的图像分割模型从复杂背景中提取植株区域，其性能优于阈值分割、U-Net和U-Net++，并增加了重建点数量。通过系统组合等距策略和贪心策略进行相机配置优化，得到了最优的六相机方案（#2、#3、#4、#6、#7和#8，分别对应相对于水平视角的−30°、−15°、0°、+30°、+45°和+60°），该方案提供了冠层内部结构和茎基部的互补视角。与完整的11相机方案相比，该配置将不同品种和生育期的平均最近邻距离降至0.037–0.066 cm，保留了73–76%的点云，并将重建时间缩短了约70–80%。点云提取的株高和冠幅与人工测量结果高度一致（R²分别为0.989和0.946），验证了点云表型测量的准确性。总体而言，将图像分割与相机配置优化相结合，为利用Metatlas V1进行水稻高通量三维表型分析提供了一种准确高效的解决方案，在重建精度、点云完整性和计算效率之间取得了平衡，并可为其他旋转式多视角表型平台的相机配置设计提供方法学参考。","2026-09-24T00:00:00Z",78,{"impact":18,"substance":126,"depth":17,"authority":19,"freshness":71,"relevant":21,"comment":127},22,"该研究提出结合CBAM-UNet分割与相机配置优化的水稻三维重建流程，方法新颖、数据详实，对高通量作物表型分析有参考价值，但属细分领域进展，时效性高。",[129],{"name":65,"url":120},[26,27,131,29,132],"水稻","三维重建",[134,135],"Metatlas V1 水稻 三维重建","CBAM-UNet 水稻 图像分割","MetatlasV1水稻三维重建-3490","10.3389\u002Ffpls.2026.1882534",{"doi":137,"openalex_id":139,"authors":140,"venue":65,"cited_by_count":35,"oa_url":120,"card":176,"direction":114,"ingested_from":54},"W7214231705",[141,143,146,148,151,153,155,158,161,164,166,168,171,174],{"name":142,"orcid":8},"Haoyang Zhou",{"name":144,"orcid":145},"Rongjie Chen","https:\u002F\u002Forcid.org\u002F0009-0004-8078-2301",{"name":147,"orcid":8},"Hao Wang",{"name":149,"orcid":150},"Minglu Li","https:\u002F\u002Forcid.org\u002F0000-0003-1751-9418",{"name":152,"orcid":8},"Yongkang Teng",{"name":154,"orcid":8},"Shenghao Ye",{"name":156,"orcid":157},"Menglei Wei","https:\u002F\u002Forcid.org\u002F0009-0004-3070-8023",{"name":159,"orcid":160},"Kun Yu","https:\u002F\u002Forcid.org\u002F0000-0002-0190-8702",{"name":162,"orcid":163},"Pingping Fang","https:\u002F\u002Forcid.org\u002F0000-0002-9911-2963",{"name":165,"orcid":8},"Jing Cao",{"name":167,"orcid":8},"Fanglin Zhu",{"name":169,"orcid":170},"Wenyu Zhang","https:\u002F\u002Forcid.org\u002F0000-0003-3322-9736",{"name":172,"orcid":173},"Ting Sun","https:\u002F\u002Forcid.org\u002F0000-0002-9387-4852",{"name":175,"orcid":8},"Min Jiang",{"tldr":177,"method":178,"finding":179,"direction":114,"opportunity":180},"提出CBAM-UNet分割与相机配置优化结合的水稻多视角三维重建流程，兼顾精度、完整性与效率。","Metatlas V1多视角平台、COLMAP+OpenMVS、CBAM-UNe","最优6相机配置将最近邻距离降至0.037–0.066 cm，保留73–76%点云，重建耗时减少约70","可将相机配置优化策略迁移到其他旋转多视角平台，并探索自适应配置与分割模型联合优化。","2026-09-25T23:30:25.303016Z",{"id":183,"title":184,"url":185,"summary":186,"summary_zh":8,"content":8,"source_name":187,"source_url":185,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":188,"score_detail":189,"sources":192,"tags":194,"search_phrases":196,"slug":199,"view_count":35,"doi":200,"paper":201,"created_at":222},3463,"Cotton leaf disease classification using deep learning models for smart agriculture","https:\u002F\u002Fdoi.org\u002F10.1186\u002Fs40066-026-00610-2","Cotton leaf disease classification using deep learning models for smart agriculture。Agriculture & Food Security","Agriculture & Food Security",66,{"impact":16,"substance":18,"depth":190,"authority":19,"freshness":12,"relevant":21,"comment":191},15,"核心期刊论文，方法有一定参考价值，但属细分技术研究，产业影响有限。",[193],{"name":187,"url":185},[26,27,28,195],"棉花病害",[197,198],"棉花叶部病害 深度学习 分类","农业人工智能 智慧农业 棉花病害 深度学习","棉花叶部病害深度学习分类-3463","10.1186\u002Fs40066-026-00610-2",{"doi":200,"openalex_id":202,"authors":203,"venue":187,"cited_by_count":35,"oa_url":185,"card":8,"direction":221,"ingested_from":54},"W7214238516",[204,206,209,212,215,218],{"name":205,"orcid":8},"Hina Kiran Abbas",{"name":207,"orcid":208},"Muhammad Farrukh Shahid","https:\u002F\u002Forcid.org\u002F0009-0004-8787-1868",{"name":210,"orcid":211},"Rehab Bahaaddin Ashari","https:\u002F\u002Forcid.org\u002F0000-0003-1225-7535",{"name":213,"orcid":214},"Arwa Mashat","https:\u002F\u002Forcid.org\u002F0000-0002-0612-6005",{"name":216,"orcid":217},"Tariq Jamil Saifullah Khanzada","https:\u002F\u002Forcid.org\u002F0000-0003-1617-4403",{"name":219,"orcid":220},"M. Hassan Tanveer","https:\u002F\u002Forcid.org\u002F0000-0001-9266-6368","智慧农业 \u002F 农业物联网","2026-09-25T23:30:09.012501Z",{"id":224,"title":225,"url":226,"summary":227,"summary_zh":228,"content":8,"source_name":229,"source_url":226,"published_at":230,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":231,"score_detail":232,"sources":235,"tags":237,"search_phrases":240,"slug":243,"view_count":35,"doi":244,"paper":245,"created_at":265},3277,"Downscaling of SMAP Soil Moisture Based on the Transformer Algorithm in Anhui Province","https:\u002F\u002Fdoi.org\u002F10.3390\u002Frs18193272","Soil moisture (SM) is critical for climate, water, and agriculture, but Soil Moisture Active Passive (SMAP) passive microwave products have coarse resolution, limiting regional applications. This study develops an SM downscaling framework based on Transformer and its variants (PatchTST and iTransformer), integrating multi-source satellite and groundwater data to generate 1 km daily SM products (2015–2022). Compared with Random Forest (RF), Long Short-Term Memory (LSTM), and Convolutional Neural Network–LSTM (CNN-LSTM), Transformer and its variants achieve superior accuracy and generalization. Validated against in situ measurements and SMCI1.0, the Transformer-downscaled SM product achieved the best accuracy with ubRMSE = 0.0372 m3\u002Fm3 and RMSE = 0.0591 m3\u002Fm3. The downscaled SM dataset not only captured finer spatial details but also preserved the spatial patterns and seasonal dynamics of the original SMAP product and showed good responsiveness to precipitation events. Feature importance analysis revealed that, aside from precipitation, the diurnal land surface temperature difference had a greater impact on SM than individual daytime or nighttime land surface temperature, ranking just below vegetation indices and soil texture factors, while groundwater level showed higher importance than elevation and surface temperature. This study confirms the effectiveness of Transformer-based models for SM spatial downscaling, providing a novel framework integrating remote sensing and deep hydrological information to generate accurate 1 km SM products.","土壤水分（SM）对气候、水资源和农业至关重要，但土壤水分主动被动（SMAP）被动微波产品分辨率较粗，限制了区域应用。本研究构建了一个基于Transformer及其变体（PatchTST和iTransformer）的土壤水分降尺度框架，融合多源卫星和地下水数据，生成1 km日尺度土壤水分产品（2015—2022年）。与随机森林（RF）、长短期记忆网络（LSTM）和卷积神经网络—长短期记忆网络（CNN-LSTM）相比，Transformer及其变体取得了更高的精度和泛化能力。利用站点实测数据和SMCI1.0进行验证，Transformer降尺度土壤水分产品精度最优，ubRMSE = 0.0372 m³\u002Fm³，RMSE = 0.0591 m³\u002Fm³。降尺度土壤水分数据集不仅捕捉到了更精细的空间细节，还保留了原始SMAP产品的空间格局和季节动态，并对降水事件表现出良好的响应。特征重要性分析表明，除降水外，昼夜地表温差对土壤水分的影响大于单独的白天或夜间地表温度，其重要性仅次于植被指数和土壤质地因子，而地下水埋深的重要性高于高程和地表温度。本研究证实了基于Transformer的模型在土壤水分空间降尺度中的有效性，为融合遥感和深层水文信息生成准确的1 km土壤水分产品提供了一种新框架。","Remote Sensing","2026-09-22T00:00:00Z",81,{"impact":17,"substance":126,"depth":17,"authority":233,"freshness":71,"relevant":21,"comment":234},14,"基于Transformer的SMAP土壤水分1km降尺度研究，方法新颖、验证充分，对区域农业旱情监测有实用价值。",[236],{"name":229,"url":226},[26,27,28,238,239],"遥感","土壤墒情",[241,242],"SMAP 土壤水分 降尺度","Transformer 土壤水分 安徽","SMAP土壤水分降尺度-3277","10.3390\u002Frs18193272",{"doi":244,"openalex_id":246,"authors":247,"venue":229,"cited_by_count":35,"oa_url":226,"card":260,"direction":114,"ingested_from":54},"W7208807695",[248,250,252,254,256,258],{"name":249,"orcid":8},"Yuyang Fan",{"name":251,"orcid":8},"Jianwei Ma",{"name":253,"orcid":8},"Mengmeng Li",{"name":255,"orcid":8},"Changqing Ke",{"name":257,"orcid":8},"Bin Cheng",{"name":259,"orcid":8},"Zheng Duan",{"tldr":261,"method":262,"finding":263,"direction":114,"opportunity":264},"基于Transformer及变体融合多源卫星与地下水数据，将SMAP土壤湿度降尺度至1km日尺度。","Transformer、PatchTST、iTransformer，融合多源卫星","Transformer降尺度产品精度最优（ubRMSE=0.0372），保留原产品时空格局并响应降水","可探索Transformer降尺度产品在区域干旱监测、灌溉决策及作物估产中的耦合应用。","2026-09-23T23:30:19.132307Z",{"id":267,"title":268,"url":269,"summary":270,"summary_zh":271,"content":8,"source_name":272,"source_url":269,"published_at":230,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":273,"score_detail":274,"sources":276,"tags":278,"search_phrases":281,"slug":284,"view_count":35,"doi":285,"paper":286,"created_at":305},3256,"Leakage-aware, calibrated, and explainable deep learning for robust almond disease classification","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112464","Leakage-aware, calibrated, and explainable deep learning for robust almond disease classification。Computers and Electronics in Agriculture","面向稳健杏仁病害分类的泄漏感知、校准且可解释的深度学习。《农业计算机与电子》","Computers and Electronics in Agriculture",72,{"impact":16,"substance":69,"depth":70,"authority":233,"freshness":71,"relevant":21,"comment":275},"核心期刊论文，方法上有防泄漏、校准与可解释性创新，但作物小众、属细分技术进展，未达每日精选门槛。",[277],{"name":272,"url":269},[26,27,28,279,280],"病害识别","巴旦木",[282,283],"巴旦木 病害 深度学习","农业人工智能 智慧农业 深度学习 病害识别","巴旦木病害深度学习-3256","10.1016\u002Fj.compag.2026.112464",{"doi":285,"openalex_id":287,"authors":288,"venue":272,"cited_by_count":35,"oa_url":269,"card":299,"direction":303,"ingested_from":54},"W7213988471",[289,292,295,297],{"name":290,"orcid":291},"Abebaw Degu Workneh","https:\u002F\u002Forcid.org\u002F0000-0001-7694-1577",{"name":293,"orcid":294},"Badr Elkari","https:\u002F\u002Forcid.org\u002F0000-0002-0893-783X",{"name":296,"orcid":8},"Meryam El Mouhtadi",{"name":298,"orcid":8},"Mohammad Furqan Ali",{"tldr":300,"method":301,"finding":302,"direction":303,"opportunity":304},"提出防泄漏、校准且可解释的深度学习框架，用于稳健的杏仁病害分类。","采用防数据泄漏的深度学习训练、概率校准与可解释性分析。","该框架能提升杏仁病害分类的稳健性、可信度与可解释性。","农业人工智能与决策模型","可探索防泄漏与校准机制在其他作物病害识别中的泛化及田间部署。","2026-09-23T23:30:01.628054Z",{"id":307,"title":308,"url":309,"summary":310,"summary_zh":311,"content":8,"source_name":312,"source_url":309,"published_at":66,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":313,"score_detail":314,"sources":316,"tags":318,"search_phrases":319,"slug":322,"view_count":35,"doi":323,"paper":324,"created_at":340},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":17,"substance":126,"depth":17,"authority":19,"freshness":71,"relevant":21,"comment":315},"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。",[317],{"name":312,"url":309},[26,27,131,238,29],[320,321],"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":323,"openalex_id":325,"authors":326,"venue":312,"cited_by_count":35,"oa_url":309,"card":335,"direction":114,"ingested_from":54},"W7213887432",[327,330,332],{"name":328,"orcid":329},"Weiguo Wang","https:\u002F\u002Forcid.org\u002F0009-0003-4028-9363",{"name":331,"orcid":8},"Noboru Noguchi",{"name":333,"orcid":334},"Liangliang Yang","https:\u002F\u002Forcid.org\u002F0000-0002-5055-3987",{"tldr":336,"method":337,"finding":338,"direction":114,"opportunity":339},"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"]