Solar Flare Predictive Features Derived from Polarity Inversion Line Masks in Active Regions Using an Unsupervised Machine Learning Algorithm

doi:10.3847/1538-4357/ab7b6c

NSSC OpenIR

	Solar Flare Predictive Features Derived from Polarity Inversion Line Masks in Active Regions Using an Unsupervised Machine Learning Algorithm
Alternative Title	WOS:000525489700001
	Wang, Jingling 1; Zhang, Yuhang 2; Webber, Shea A. Hess ; Liu, Siqing 1,4; Meng, Xuejie 1; Wang, Tieyan 5
Source Publication	ASTROPHYSICAL JOURNAL
	2020
Volume	892 Issue:2 Pages:140
DOI	10.3847/1538-4357/ab7b6c
ISSN	0004-637X
Language	英语
Keyword	Solar flares Space weather Classification Solar active regions MAGNETIC-FIELD PROPERTIES PRODUCTIVITY NONPOTENTIALITY
Abstract	The properties of the polarity inversion line (PIL) in solar active regions (ARs) are strongly correlated to flare occurrences. The PIL mask, enclosing the PIL areas, has shown significant potential for improving machine-learning-based flare prediction models. In this study, an unsupervised machine-learning algorithm, Kernel Principle Component Analysis (KPCA), is adopted to directly derive features from the PIL mask and difference PIL mask, and use those features to classify ARs into two categories-non-strong flaring ARs and strong-flaring (M-class and above flares) ARs-for time-in-advance from one hour to 72 hr at a 1 hr cadence. The two best features are selected from the KPCA results to develop random-forest classifiers for predicting flares, and the models are then evaluated and compared to similar models based on the R value and difference R value. The results show that the features derived from the PIL masks by KPCA are effective in predicting flare occurrence, with overall better Fisher ranking scores and similar predictive statistics as the R value characteristics.
Indexed By	SCI
Citation statistics
Document Type	期刊论文
Identifier	http://ir.nssc.ac.cn/handle/122/7620
Collection	中国科学院国家空间科学中心
Affiliation	1.Chinese Acad Sci, Natl Space Sci Ctr, Beijing, Peoples R China 2.Chinese Acad Sci, Key Lab Sci & Technol Environm Space Situat Aware, Beijing, Peoples R China 3.Xidian Univ, Sch Comp Sci & Technol, Xian 710126, Peoples R China 4.Stanford Univ, WW Hansen Expt Phys Lab, Stanford, CA 94305 USA 5.Univ Chinese Acad Sci, Beijing, Peoples R China 6.Rutherford Appleton Lab, RAL Space, Harwell Oxford, Didcot OX11 0QX, Oxon, England
Recommended Citation GB/T 7714	Wang, Jingling,Zhang, Yuhang,Webber, Shea A. Hess,et al. Solar Flare Predictive Features Derived from Polarity Inversion Line Masks in Active Regions Using an Unsupervised Machine Learning Algorithm[J]. ASTROPHYSICAL JOURNAL,2020,892(2):140.
APA	Wang, Jingling,Zhang, Yuhang,Webber, Shea A. Hess,Liu, Siqing,Meng, Xuejie,&Wang, Tieyan.(2020).Solar Flare Predictive Features Derived from Polarity Inversion Line Masks in Active Regions Using an Unsupervised Machine Learning Algorithm.ASTROPHYSICAL JOURNAL,892(2),140.
MLA	Wang, Jingling,et al."Solar Flare Predictive Features Derived from Polarity Inversion Line Masks in Active Regions Using an Unsupervised Machine Learning Algorithm".ASTROPHYSICAL JOURNAL 892.2(2020):140.

Files in This Item:
There are no files associated with this item.

If you have any objections to this item, please fill out the form below and the administrator will contact you as soon as possible.
Content:
Email：	*
Institution:
Verification Code:	Refresh

Any comments and suggestions are welcomed.
Title:	*
Content:
Email：	*
Verification Code:	Refresh

中国科学院国家空间科学中心机构知识库