The influence of magnetic field parameters and time step on deep learning models of solar flare prediction

doi:10.1007/s10509-024-04314-6

	The influence of magnetic field parameters and time step on deep learning models of solar flare prediction
	Wei, Jinfang 7; Zheng, Yanfang 7; Li, Xuebao 7; Xiang, Changtian 7; Yan, Pengchao 7; Huang, Xusheng 7; Dong L(董亮)3,5; Lou, Hengrui 6; Yan, Shuainan 1,4; Ye, Hongwei 7
刊名	ASTROPHYSICS AND SPACE SCIENCE
	2024-05
卷号	369 期号:5
关键词	Methods: data analysis Techniques: image processing Sun: activity Sun: flares Sun: magnetic fields
ISSN号	0004-640X
DOI	10.1007/s10509-024-04314-6
产权排序	第3完成单位
文献子类	Article
英文摘要	The research on solar flare predicting holds significant practical and scientific value for safeguarding human activities. Current solar flare prediction models have not fully considered important factors such as time step length, nor have they conducted a comparative analysis of the physical features in multiple models or explored the consistency in the importance of features. In this work, based on SHARP data from SDO, we build 9 machine learning-based solar flare prediction models for binary Yes or No class prediction within the next 24 hours, and study the impact of different time steps and other factors on the forecasting performance. The main results are as follows. (1) The predictive performance of eight deep learning models shows an increasing trend as the time step length increases, and the models perform the best at the length of 40. (2) In predicting solar flares of >= C class and >= M class, the True Skill Statistic(TSS) of deep learning models consistently outperforms that of baseline model. For the same model, the TSS for predicting >= M class flares generally exceeds that for predicting >= C class flares. (3) The Brier Skill Score (BSS) of deep learning models significantly surpasses that of baseline model in predicting >= C class flares. However, the BSS scores of the nine models are comparable for predicting >= M class flares. For the same model, the BSS for predicting >= C class flares is generally higher than that for predicting >= M class flares. (4) Through feature importance analysis of multiple models, the common features that consistently rank at the top and bottom are identified.
学科主题	天文学 ; 太阳与太阳系
URL标识	查看原文
出版地	VAN GODEWIJCKSTRAAT 30, 3311 GZ DORDRECHT, NETHERLANDS
资助项目	National Natural Science Foundation of China
WOS研究方向	Astronomy & Astrophysics
语种	英语
出版者	SPRINGER
WOS记录号	WOS:001224090500001
资助机构	National Natural Science Foundation of China
内容类型	期刊论文
版本	出版稿
源URL	[http://ir.ynao.ac.cn/handle/114a53/27194]
专题	云南天文台_射电天文研究组
作者单位	1.University of Chinese Academy of Sciences, Beijing, 100049, China 2.MailBox 5111, Beijing, 100094, China; 3.Yunnan Sino-Malaysian International Joint Laboratory of HF-VHF Advanced Radio Astronomy Technology, Kunming, 650216, Yunnan, China; 4.National Space Science Center, Chinese Academy of Sciences, Beijing, 100190, China; 5.Yunnan Astronomical Observatory, Chinese Academy of Sciences, Kunming, 650216, Yunnan, China; 6.School of Software Technology, Zhejiang University, Ningbo, 315000, Zhejiang, China; 7.School of Computer Science, Jiangsu University of Science and Technology, Zhenjiang, 212100, Jiangsu, China;
推荐引用方式 GB/T 7714	Wei, Jinfang,Zheng, Yanfang,Li, Xuebao,et al. The influence of magnetic field parameters and time step on deep learning models of solar flare prediction[J]. ASTROPHYSICS AND SPACE SCIENCE,2024,369(5).
APA	Wei, Jinfang.,Zheng, Yanfang.,Li, Xuebao.,Xiang, Changtian.,Yan, Pengchao.,...&Wu, Huiwen.(2024).The influence of magnetic field parameters and time step on deep learning models of solar flare prediction.ASTROPHYSICS AND SPACE SCIENCE,369(5).
MLA	Wei, Jinfang,et al."The influence of magnetic field parameters and time step on deep learning models of solar flare prediction".ASTROPHYSICS AND SPACE SCIENCE 369.5(2024).