Precipitation Nowcasting Based on Radar Echo Images via Multiscale Spatiotemporal LSTM
文献类型：期刊论文
| 作者 | Wang, Yueting1,2; Yao, Ling1,3; Jiang, Hou1; Liu, Tang1; Lu, Yuxiang1; Zhou, Chenghu1 |
| 刊名 | IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
 |
| 出版日期 | 2025 |
| 卷号 | 63页码:5105614 |
| 关键词 | Spatiotemporal phenomena Precipitation Radar Long short term memory Predictive models Radar imaging Forecasting Extrapolation Feature extraction Convolution Deep learning (DL) long short-term memory (LSTM) multiscale spatiotemporal ((MST)-T-2) feature precipitation nowcasting radar echo extrapolation |
| ISSN号 | 0196-2892 |
| DOI | 10.1109/TGRS.2025.3584824 |
| 产权排序 | 1 |
| 文献子类 | Article |
| 英文摘要 | Accurate precipitation nowcasting up to 2 h in advance is crucial for weather-sensitive decision-making, such as flood disaster warnings. Although deep learning-based radar echo extrapolation methods show advantages, they still face challenges, particularly in predicting local spatial variations and mitigating performance degradation with increasing prediction time horizon. This study proposes a new multiscale spatiotemporal (MS2T)-long short-term memory (LSTM) model to enhance precipitation nowcasting capabilities by fusing multiscale spatial features through parallel convolutional structures and improving spatiotemporal (ST) reasoning through stacked LSTMs. Notably, a multiscale spatiotemporal feature gate is introduced into the LSTM unit to transmit multiscale spatiotemporal features of radar echo image sequences, mitigating the issue of time-dependent performance degradation. The loss function for model optimization is carefully selected via a series of comparative experiments. The experiments show that MS2T-LSTM outperforms benchmark models in predicting precipitation events with different intensities. Specifically, in comparison to predictive recurrent neural network (PredRNN++), the $F1$ score, critical success index, Heidke skill score, and probability of detection (POD) for low-intensity precipitation threshold (5 mm/h) improved by 2.3%, 3.5%, 13%, and 10.6%. This study demonstrates the effectiveness of integrating multiscale spatiotemporal features to enhance precipitation forecasting, providing valuable insights for spatiotemporal prediction modeling and optimization. |
| URL标识 | 查看原文 |
| WOS研究方向 | Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology |
| 语种 | 英语 |
| WOS记录号 | WOS:001530269200020 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/215427]  |
| 专题 | 资源与环境信息系统国家重点实验室_外文论文 |
| 通讯作者 | Yao, Ling |
| 作者单位 | 1.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China; 2.Univ Chinese Acad Sci, Coll Resources & Environm, Beijing 101408, Peoples R China; 3.Jiangsu Ctr Collaborat Innovat Geog Informat Resou, Nanjing 210023, Peoples R China |
| 推荐引用方式 GB/T 7714 | Wang, Yueting,Yao, Ling,Jiang, Hou,et al. Precipitation Nowcasting Based on Radar Echo Images via Multiscale Spatiotemporal LSTM[J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,2025,63:5105614. |
| APA | Wang, Yueting,Yao, Ling,Jiang, Hou,Liu, Tang,Lu, Yuxiang,&Zhou, Chenghu.(2025).Precipitation Nowcasting Based on Radar Echo Images via Multiscale Spatiotemporal LSTM.IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING,63,5105614. |
| MLA | Wang, Yueting,et al."Precipitation Nowcasting Based on Radar Echo Images via Multiscale Spatiotemporal LSTM".IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 63(2025):5105614. |
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。