A novel short-term radio flux trend prediction model based on deep learning

doi:10.1007/s10509-023-04246-7

YNAO OpenIR > 射电天文研究组

	A novel short-term radio flux trend prediction model based on deep learning
	Zheng, Yanfang 1; Ling, Yi 1; Li, Xuebao 1; Qin, Weishu 1; Dong L(董亮)2,3 ; Huang, Xusheng 1; Li, Xuefeng 1; Yan, Pengchao 1; Yan, Shuainan 1; Lou, Hengrui 1; Ye, Hongwei 1
发表期刊	ASTROPHYSICS AND SPACE SCIENCE
	2023-10
卷号	368 期号:10
DOI	10.1007/s10509-023-04246-7
产权排序	第2完成单位
收录类别	SCI
关键词	Sun Solar activity Solar radio flux
摘要	Solar radio flux is an important indicator of solar activity and solar UV burst. Accurate prediction of solar radio flux plays a crucial role in preventing and mitigating the impact of solar activity on human productivity. We propose a novel approach for the first time to predict short-term radio flux trends using a bidirectional long short-term memory (BLSTM) network. This approach aims to address the unique characteristics of temporality and nonlinearity observed in solar radio flux data. Our model takes into account various frequency characteristics that impact radio flux. This allows it to learn temporal patterns within the data, ultimately enabling accurate predictions of radio flux for the next 30 minutes. The proposed method is experimentally applied to the radio flux dataset of the US Radio Solar Telescope Network (RSTN). The results show that, in most frequency bands, the BLSTM model exhibits superior prediction accuracy and greater sensitivity to peak responses compared to the LSTM model, LSTM-Attention (LSTM-A) model, BLSTM-Attention (BLSTM-A) model, and persistence model (PM). Consequently, the BLSTM model is better equipped to accurately forecast changes in radio flux for the next 30 minutes.
资助项目	We would like to thank the anonymous referees for their valuable suggestions and comments, which significantly improved this work. We are grateful to the Australian Space Weather Forecasting Centre for the provision of Solar Radio data.
项目资助者	We would like to thank the anonymous referees for their valuable suggestions and comments, which significantly improved this work. We are grateful to the Australian Space Weather Forecasting Centre for the provision of Solar Radio data.
语种	英语
学科领域	天文学
文章类型	Article
出版者	SPRINGER
出版地	VAN GODEWIJCKSTRAAT 30, 3311 GZ DORDRECHT, NETHERLANDS
ISSN	0004-640X
URL	查看原文
WOS记录号	WOS:001090545300001
WOS研究方向	Astronomy & Astrophysics
WOS类目	Astronomy & Astrophysics
关键词[WOS]	CORONAL ROTATION ; SOLAR ; MULTIFREQUENCY
引用统计
文献类型	期刊论文
版本	出版稿
条目标识符	http://ir.ynao.ac.cn/handle/114a53/26422
专题	射电天文研究组
作者单位	1.School of Automation, Jiangsu University of Science and Technology, Zhenjiang, 212100, Jiangsu, China; 2.Yunnan Astronomical Observatory, Chinese Academy of Sciences, Kunming, 650216, Yunnan, China; 3.Yunnan Sino-Malaysian International Joint Laboratory of HF-VHF Advanced Radio Astronomy Technology, Kunming, 650216, Yunnan, China
推荐引用方式 GB/T 7714	Zheng, Yanfang,Ling, Yi,Li, Xuebao,et al. A novel short-term radio flux trend prediction model based on deep learning[J]. ASTROPHYSICS AND SPACE SCIENCE,2023,368(10).
APA	Zheng, Yanfang.,Ling, Yi.,Li, Xuebao.,Qin, Weishu.,董亮.,...&Ye, Hongwei.(2023).A novel short-term radio flux trend prediction model based on deep learning.ASTROPHYSICS AND SPACE SCIENCE,368(10).
MLA	Zheng, Yanfang,et al."A novel short-term radio flux trend prediction model based on deep learning".ASTROPHYSICS AND SPACE SCIENCE 368.10(2023).

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
A novel short-term r（1385KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览请求全文