Deep Learning With ERA5 Variables Accurately Simulates Near-Surface Wind Speed Variations Across a Complex Terrain Region
文献类型：期刊论文
| 作者 | Long, Zhiyi1; Zha, Jinlin1; Zhang, Hao2; Chuan, Ting1; Lu, Wenxi3; Yan, Yijun4; Xia, Lei5; Fan, Wenxuan1; Jiang, Huiping6,7; Zhao, Deming8 |
| 刊名 | GEOPHYSICAL RESEARCH LETTERS
 |
| 出版日期 | 2025-06-28 |
| 卷号 | 52期号:12页码:e2025GL116108 |
| 关键词 | wind speed deep learning complex terrain region Tibetan Plateau transformer convolutional neural networks |
| ISSN号 | 0094-8276 |
| DOI | 10.1029/2025GL116108 |
| 产权排序 | 6 |
| 文献子类 | Article |
| 英文摘要 | Reanalysis products and global climate models are the foundation of weather and climate prediction; however, they encounter challenges in capturing the spatiotemporal changes of near-surface wind speed (NSWS) in a topographically complex area. Based on deep learning with ERA5 variables, the changes in NSWS were well captured across the Tibetan Plateau (TP), and the simulated NSWS bias can be reduced by 50.0% when the factor and location self-attentions were considered. The reanalysis products overestimated the probabilities of light air, exceeding 40.0%, and underestimated the probabilities of gentle breeze, reaching 30.0%. Compared to some mainstream reanalysis products, the prediction success rate and threat score of the deep learning model for different wind strength events were improved, and its false alarm ratio and missing alarm ratio were decreased. Meanwhile, the predictive indices showed superior spatial homogeneity. This study offers a valuable reference for improving the NSWS simulation over a complex topography region. |
| URL标识 | 查看原文 |
| WOS关键词 | CHINA ; CIRCULATION ; FRICTION ; INCREASE ; DECLINE ; TRENDS |
| WOS研究方向 | Geology |
| 语种 | 英语 |
| WOS记录号 | WOS:001507225000001 |
| 出版者 | AMER GEOPHYSICAL UNION |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/214525]  |
| 专题 | 区域可持续发展分析与模拟院重点实验室_外文论文 |
| 通讯作者 | Zha, Jinlin |
| 作者单位 | 1.Yunnan Univ, Dept Atmospher Sci, Key Lab Atmospher Environm & Proc Boundary Layer L, Kunming, Peoples R China; 2.Kunming Met Coll, Kunming, Peoples R China; 3.Yuxi Meteorol Bur, Yuxi, Peoples R China; 4.Yunnan Power Grid Co Ltd, Elect Power Res Inst, Kunming, Peoples R China; 5.Yunnan Univ, Dept Geog Informat Sci, Kunming, Peoples R China; 6.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res IGSNRR, Key Lab Reg Sustainable Dev Modeling, Beijing, Peoples R China; 7.Int Res Ctr Big Data Sustainable Dev Goals CBAS, Beijing, Peoples R China; 8.Chinese Acad Sci, Inst Atmospher Phys, Key Lab Reg Climate & Environm Temperate East Asia, Beijing, Peoples R China |
| 推荐引用方式 GB/T 7714 | Long, Zhiyi,Zha, Jinlin,Zhang, Hao,et al. Deep Learning With ERA5 Variables Accurately Simulates Near-Surface Wind Speed Variations Across a Complex Terrain Region[J]. GEOPHYSICAL RESEARCH LETTERS,2025,52(12):e2025GL116108. |
| APA | Long, Zhiyi.,Zha, Jinlin.,Zhang, Hao.,Chuan, Ting.,Lu, Wenxi.,...&Wu, Jian.(2025).Deep Learning With ERA5 Variables Accurately Simulates Near-Surface Wind Speed Variations Across a Complex Terrain Region.GEOPHYSICAL RESEARCH LETTERS,52(12),e2025GL116108. |
| MLA | Long, Zhiyi,et al."Deep Learning With ERA5 Variables Accurately Simulates Near-Surface Wind Speed Variations Across a Complex Terrain Region".GEOPHYSICAL RESEARCH LETTERS 52.12(2025):e2025GL116108. |
入库方式： OAI收割
来源：地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。