A deep learning method to estimate magnetic fields in solar active regions from photospheric continuum images
文献类型:期刊论文
作者 | Bai, Xianyong1,2; Liu H(刘辉)3; Deng, Yuanyong1,2; Jiang, Jie4; Guo, Jingjing1,2; Bi Y(毕以)3; Feng, Tao5; Jin ZY(金振宇)3; Cao, Wenda6; Su, Jiangtao1,2 |
刊名 | ASTRONOMY & ASTROPHYSICS |
出版日期 | 2021-08-25 |
卷号 | 652 |
ISSN号 | 0004-6361 |
关键词 | Sun: magnetic fields Sun: photosphere methods: statistical |
DOI | 10.1051/0004-6361/202140374 |
产权排序 | 第3完成单位 |
文献子类 | Article |
英文摘要 | Context. The magnetic field is the underlying cause of solar activities. Spectropolarimetric Stokes inversions have been routinely used to extract the vector magnetic field from observations for about 40 years. In contrast, the photospheric continuum images have an observational history of more than 100 years. Aims. We suggest a new method to quickly estimate the unsigned radial component of the magnetic field, vertical bar B-r vertical bar, and the transverse field, B-t, just from photospheric continuum images (I) using deep convolutional neural networks (CNN). Methods. Two independent models, that is, I versus vertical bar B-r vertical bar and I versus B-t, are trained by the CNN with a residual architecture. A total of 7800 sets of data (I, B-r and B-t) covering 17 active region patches from 2011 to 2015 from the Helioseismic and Magnetic Imager are used to train and validate the models. Results. The CNN models can successfully estimate vertical bar B-r vertical bar as well as B-t maps in sunspot umbra, penumbra, pore, and strong network regions based on the evaluation of four active regions (test datasets). From a series of continuum images, we can also detect the emergence of a transverse magnetic field quantitatively with the trained CNN model. The three-day evolution of the averaged value of the estimated vertical bar B-r vertical bar and B-t from continuum images follows that from Stokes inversions well. Furthermore, our models can reproduce the nonlinear relationships between I and vertical bar B-r vertical bar as well as B-t, explaining why we can estimate these relationships just from continuum images. Conclusions. Our method provides an effective way to quickly estimate vertical bar B-r vertical bar and B-t maps from photospheric continuum images. The method can be applied to the reconstruction of the historical magnetic fields and to future observations for providing the quick look data of the magnetic fields. |
学科主题 | 天文学 ; 太阳与太阳系 ; 计算机科学技术 ; 人工智能 |
URL标识 | 查看原文 |
出版地 | 17, AVE DU HOGGAR, PA COURTABOEUF, BP 112, F-91944 LES ULIS CEDEX A, FRANCE |
资助项目 | US NSFNational Science Foundation (NSF)[AGS1821294] ; [12073077] ; [11873062] ; [11427901] ; [11873023] ; [11873027] ; [11729301] ; [11833010] ; [U2031140] ; [U1731241] ; [XDA15052200] ; [XDA15320302] ; [1916321TS00103201] |
语种 | 英语 |
出版者 | EDP SCIENCES S A |
WOS记录号 | WOS:000688233900007 |
资助机构 | US NSFNational Science Foundation (NSF)[AGS1821294] ; [12073077] ; [11873062] ; [11427901] ; [11873023] ; [11873027] ; [11729301] ; [11833010] ; [U2031140] ; [U1731241] ; [XDA15052200] ; [XDA15320302] ; [1916321TS00103201] |
版本 | 出版稿 |
源URL | [http://ir.ynao.ac.cn/handle/114a53/24549] |
专题 | 天文技术实验室 云南天文台_抚仙湖太阳观测站 |
通讯作者 | Ji KF(季凯帆) |
作者单位 | 1.Key Laboratory of Solar Activity, National Astronomical Observatories, Chinese Academy of Sciences, 20 Datun Road, Beijing 100101, PR China; 2.School of Astronomy and Space Science, University of Chinese Academy of Sciences, No. 19(A) Yuquan Road, Beijing 100049, PR China; 3.Yunnan Observatories, Chinese Academy of Sciences, Kunming, 650011 Yunnan, PR China; 4.School of Space and Environment, Beihang University, Beijing, PR China; 5.College of Computer Science, Sichuan University, Chengdu 610065, PR China; 6.Big Bear Solar Observatory, New Jersey Institute of Technology, Big Bear City, CA 92314-9672, USA |
推荐引用方式 GB/T 7714 | Bai, Xianyong,Liu H,Deng, Yuanyong,et al. A deep learning method to estimate magnetic fields in solar active regions from photospheric continuum images[J]. ASTRONOMY & ASTROPHYSICS,2021,652. |
APA | Bai, Xianyong.,Liu H.,Deng, Yuanyong.,Jiang, Jie.,Guo, Jingjing.,...&Ji KF.(2021).A deep learning method to estimate magnetic fields in solar active regions from photospheric continuum images.ASTRONOMY & ASTROPHYSICS,652. |
MLA | Bai, Xianyong,et al."A deep learning method to estimate magnetic fields in solar active regions from photospheric continuum images".ASTRONOMY & ASTROPHYSICS 652(2021). |
入库方式: OAI收割
来源:云南天文台
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。