Preformer: Simple and Efficient Design for Precipitation Nowcasting With Transformers
文献类型:期刊论文
作者 | Jin, Qizhao2; Zhang, Xinbang2; Xiao, Xinyu2; Wang, Ying1; Xiang, Shiming1; Pan, Chunhong1 |
刊名 | IEEE GEOSCIENCE AND REMOTE SENSING LETTERS |
出版日期 | 2024 |
卷号 | 21页码:5 |
ISSN号 | 1545-598X |
关键词 | Precipitation Transformers Spatiotemporal phenomena Decoding Humidity Correlation Computer architecture Data mining precipitation nowcasting transformer |
DOI | 10.1109/LGRS.2023.3325628 |
通讯作者 | Wang, Ying(ywang@nlpr.ia.ac.cn) |
英文摘要 | The primary objective of precipitation nowcasting is to predict precipitation patterns several hours in advance. Recent studies have emphasized the potential of deep learning methods for this task. To harness the correlations among various meteorological elements, existing frameworks project multiple meteorological elements into a latent space and then utilize convolutional-recurrent networks for future precipitation prediction. Although effective, the escalating model complexity may impede practical applications. This letter develops the Preformer, a streamlined Transformer framework for precipitation nowcasting that efficiently captures global spatiotemporal dependencies among multiple meteorological elements. The Preformer implements an encoder-translator-decoder architecture, where the encoder integrates spatial features of multiple elements, the translator models spatiotemporal dynamics, and the decoder combines spatiotemporal information to forecast future precipitation. Without introducing complex structures or strategies, the Preformer achieves state-of-the-art performance even with the least parameters. |
资助项目 | National Natural Science Foundation of China |
WOS研究方向 | Geochemistry & Geophysics ; Engineering ; Remote Sensing ; Imaging Science & Photographic Technology |
语种 | 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:001136775600033 |
资助机构 | National Natural Science Foundation of China |
源URL | [http://ir.ia.ac.cn/handle/173211/55524] |
专题 | 多模态人工智能系统全国重点实验室 |
通讯作者 | Wang, Ying |
作者单位 | 1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China |
推荐引用方式 GB/T 7714 | Jin, Qizhao,Zhang, Xinbang,Xiao, Xinyu,et al. Preformer: Simple and Efficient Design for Precipitation Nowcasting With Transformers[J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS,2024,21:5. |
APA | Jin, Qizhao,Zhang, Xinbang,Xiao, Xinyu,Wang, Ying,Xiang, Shiming,&Pan, Chunhong.(2024).Preformer: Simple and Efficient Design for Precipitation Nowcasting With Transformers.IEEE GEOSCIENCE AND REMOTE SENSING LETTERS,21,5. |
MLA | Jin, Qizhao,et al."Preformer: Simple and Efficient Design for Precipitation Nowcasting With Transformers".IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 21(2024):5. |
入库方式: OAI收割
来源:自动化研究所
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。