中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 云南天文台
  3. 中国科学院云南天文台
  4. 射电天文研究组
A transformer-based forecasting model for F 10.7 index and its application study on the Chinese Langfang dataset

文献类型：期刊论文

作者Ye, Hongwei5; Zheng, Yanfang5; Li, Xuebao5; Dong L(董亮)1,4; Huang, Wengeng3; Wang, Jing3; Yan, Shuainan2,3; Lou, Hengrui7; Yan, Pengchao5; Zhang, Shunhuang5
刊名ADVANCES IN SPACE RESEARCH
出版日期2024-12-15
卷号74期号:12页码:6309-6324
关键词F 10.7 forecasting Bidirectional gating recurrent unit Transformer
ISSN号0273-1177
DOI10.1016/j.asr.2024.08.024
产权排序第2完成单位
文献子类Article
英文摘要The 10.7 cm solar radio flux (F 10.7) is a key indicator of solar activity. Accurately forecasting of F 10 . 7 is crucial for reducing the impact of solar activity on fields such as radio communication, navigation, and satellite communication. In this work, we present a novel channel-independent patch time series Transformer (PatchTST) for F 10 . 7 forecasting. This is the first time that the PatchTST model is applied to F 10.7 forecasting. We construct the F 10 . 7 dataset, which is measured by the Dominion Radio Astrophysical Observatory (DRAO) in Canada. We compare the performance of PatchTST, N-Beats, BiGRU, and CNN-BiGRU on DRAO data. The root mean squared error (RMSE), mean absolute percentage error (MAPE), and correlation coefficient (R) of our PatchTST model are 4.731, 2.351%, and 0.986, respectively, which outperforms those of the other models when the prediction length is 1 day. Especially in midterm forecasting, the PatchTST model performs much better than those of the other models. We make uncertainty analyses on these models, and the PatchTST model exhibits superior adaptability to model uncertainty compared to the N-Beats, BiGRU, and CNNBiGRU. The PatchTST model shows a 62.9% improvement in mean error (ME) and a 40.5% improvement in standard mean error (STDE) compared to the benchmark data provided by Space Environment Technologies (SET). This work also shows that our PatchTST model generalizes well by applying it to other F 10.7 observational data originating from Long and Short-band Solar Precision Flux Radiotelescope (L&S) in China. (c) 2024 COSPAR. Published by Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.
学科主题天文学 ; 射电与天文学
URL标识查看原文
出版地125 London Wall, London, ENGLAND
资助项目National Natural Science Foundation of China[11703009]; National Natural Science Foundation of China[11803010]; Natural Science Foundation of Jiangsu Province, China[SBK2024023582]; Natural Science Foundation of Jiangsu Province, China[BK20170566]; Natural Science Foundation of Jiangsu Province, China[BK20201199]; National Natural Science Astronomy Joint Fund[U2031133]; Kunming Foreign (International) Cooperation Base Project[GHJD-2021022]; Qing Lan Project
WOS研究方向Engineering ; Astronomy & Astrophysics ; Geology ; Meteorology & Atmospheric Sciences
语种英语
WOS记录号WOS:001407046100001
出版者ELSEVIER SCI LTD
资助机构National Natural Science Foundation of China[11703009, 11803010] ; Natural Science Foundation of Jiangsu Province, China[SBK2024023582, BK20170566, BK20201199] ; National Natural Science Astronomy Joint Fund[U2031133] ; Kunming Foreign (International) Cooperation Base Project[GHJD-2021022] ; Qing Lan Project
版本出版稿
源URL[http://ir.ynao.ac.cn/handle/114a53/28055]  
专题云南天文台_射电天文研究组
作者单位1.Yunnan Sino-Malaysian International Joint Laboratory of HF-VHF Advanced Radio Astronomy Technology, Kunming 650216, China;
2.University of Chinese Academy of Sciences, Beijing 100049, China;
3.National Space Science Center, Chinese Academy of Sciences, Beijing 100190, China;
4.Yunnan Astronomical Observatory, Chinese Academy of Sciences, Kunming 650216, China;
5.School of Computer, Jiangsu University of Science and Technology, Zhenjiang 212100, China;
6.MailBox 5111, Beijing 100094, China
7.School of Software Technology, Zhejiang University, Ningbo 315000, China;
推荐引用方式
GB/T 7714		 Ye, Hongwei,Zheng, Yanfang,Li, Xuebao,et al. A transformer-based forecasting model for F 10.7 index and its application study on the Chinese Langfang dataset[J]. ADVANCES IN SPACE RESEARCH,2024,74(12):6309-6324.
APA Ye, Hongwei.,Zheng, Yanfang.,Li, Xuebao.,董亮.,Huang, Wengeng.,...&Pan, Yexin.(2024).A transformer-based forecasting model for F 10.7 index and its application study on the Chinese Langfang dataset.ADVANCES IN SPACE RESEARCH,74(12),6309-6324.
MLA Ye, Hongwei,et al."A transformer-based forecasting model for F 10.7 index and its application study on the Chinese Langfang dataset".ADVANCES IN SPACE RESEARCH 74.12(2024):6309-6324.

入库方式： OAI收割

来源：云南天文台

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。