详细信息
Solar Cycle Prediction Using a Temporal Convolutional Network Deep-learning Model with a One-step Pattern ( SCI-EXPANDED收录)
文献类型:期刊文献
英文题名:Solar Cycle Prediction Using a Temporal Convolutional Network Deep-learning Model with a One-step Pattern
作者:Zhao, Cui[1,2];Liu, Kun[1];Yang, Shangbin[2,3,4];Xia, Jinchao[5];Chen, Jingxia[1];Ren, Jie[1];Liu, Shiyuan[1];He, Fangyuan[1]
第一作者:Zhao, Cui
通讯作者:Yang, SB[1];Yang, SB[2];Yang, SB[3]
机构:[1]Beijing Union Univ, Coll Appl Sci & Technol, Beijing 102200, Peoples R China;[2]State Key Lab Solar Act & Space Weather, Beijing 100190, Peoples R China;[3]Chinese Acad Sci, Natl Astron Observ, 20A Datun Rd, Beijing 100012, Peoples R China;[4]Univ Chinese Acad Sci, Beijing 100049, Peoples R China;[5]Inspur Yunzhou Ind Internet Co Ltd, 1036 Inspur Rd,High Tech Zone, Jinan, Shandong, Peoples R China
第一机构:北京联合大学应用科技学院
通讯机构:[1]corresponding author), State Key Lab Solar Act & Space Weather, Beijing 100190, Peoples R China;[2]corresponding author), Chinese Acad Sci, Natl Astron Observ, 20A Datun Rd, Beijing 100012, Peoples R China;[3]corresponding author), Univ Chinese Acad Sci, Beijing 100049, Peoples R China.
年份:2025
卷号:277
期号:2
外文期刊名:ASTROPHYSICAL JOURNAL SUPPLEMENT SERIES
收录:;Scopus(收录号:2-s2.0-105001240645);WOS:【SCI-EXPANDED(收录号:WOS:001448958600001)】;
基金:The authors would like to thank the anonymous referee for comments and suggestions that improved the quality of the manuscript. The images and data used in this paper are provided by WDC-SILSO, Royal Observatory of Belgium, Brussels, for which we are very grateful. This research is supported by the National Key R&D Program of China Nos. 2022YFF0503800, 2021YFA1600500, and 2022YFF0503001; National Natural Science Foundation of China (grant Nos. 12250005, 12073040, 12273059, 11973056, 12003051, 11573037, 12073041, 11427901, 11572005, and 11611530679); the Strategic Priority Research Program of the China Academy of Sciences (grant Nos. XDB0560000, XDA15052200, XDB09040200, XDA15010700, XDB0560301, and XDA15320102); and by the Chinese Meridian Project (CMP). This work is supported by the Academic Research Projects of Beijing Union University (No. ZK20202204, ZK90202106, ZK90202105), the Research Topic on Digital Education in Beijing of 2023 (No. BDEC2023619047), the general projects of science and technology plan of Beijing Municipal Education Commission (No. KM202111417002), and Beijing Union University Education and Teaching Research and Reform Project (No. JJ2024Y047).
语种:英文
摘要:The human living environment is influenced by intense solar activity that exhibits periodicity and regularity. Although many deep-learning models are currently used for solar cycle prediction, most of them are based on a multistep pattern. In this paper a solar cycle prediction method based on a one-step pattern is proposed with the temporal convolutional network neural network model, in which historical data are input and only one value is predicted at a time. Through an autoregressive strategy, this predicted value is added to the input sequence to generate the next output. This process is iterated until the prediction of multiple future data is achieved. The experiments were performed on the 13 months-smoothed monthly total sunspot number data sourced from WDC-SILSO. The results showed that a one-step pattern fits solar cycles 20 to 25 well. The average fitting errors are mean absolute error = 1.74 and RMSE = 2.34. Finally, the intensity of solar cycle 25 was predicted with a one-step pattern. The peak was predicted to occur in 2024 October with a magnitude of 135.3 and end in 2030 November. By comparing the prediction results with other methods, our method is more reasonable and better than most methods. The codes are available on GitHub (https://github.com/zhaocui1207/solar-cycle-prediction-by-tcn) and Zenodo (doi:10.5281/zenodo.14211884).
参考文献:
正在载入数据...