Generating Space-based SDO/HMI-like Solar Magnetograms from Ground-based Hα Images by Deep Learning
Recently, the method of estimating magnetic field through monochromatic images by deep learning has been proposed, demonstrating good morphological similarity but somewhat poor magnetic polarity consistency relative to real observation. In this paper, we propose to estimate magnetic field from H α i...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IOP Publishing
2023-01-01
|
Series: | The Astrophysical Journal Supplement Series |
Subjects: | |
Online Access: | https://doi.org/10.3847/1538-4365/accbb9 |
_version_ | 1797697074661163008 |
---|---|
author | Fei Gao Tie Liu WenQing Sun Long Xu |
author_facet | Fei Gao Tie Liu WenQing Sun Long Xu |
author_sort | Fei Gao |
collection | DOAJ |
description | Recently, the method of estimating magnetic field through monochromatic images by deep learning has been proposed, demonstrating good morphological similarity but somewhat poor magnetic polarity consistency relative to real observation. In this paper, we propose to estimate magnetic field from H α images by using a conditional generative adversarial network (cGAN) as the basic framework. The H α images from the Global Oscillation Network Group are used as the inputs and the line-of-sight magnetograms of the Helioseismic Magnetic Imager (HMI) are used as the targets. First, we train a cGAN model (Model A) with shuffling training data. However, the estimated magnetic polarities are not very consistent with real observations. Second, to improve the accuracy of estimated magnetic polarities, we train a cGAN model (Model B) with the chronological H α and HMI images, which can implicitly exploit the magnetic polarity constraint of time-series observation to generate more accurate magnetic polarities. We compare the generated magnetograms with the target HMI magnetograms to evaluate the two models. It can be observed that Model B has better magnetic polarity consistency than Model A. To quantitatively measure this consistency, we propose a new metric called pixel-to-pixel polarity accuracy (PPA). With respect to PPA, Model B is superior to Model A. This work gives us an insight that the time-series constraint can be implicitly exploited through organizing training data chronologically, and this conclusion also can be applied to other similar tasks related to time-series data. |
first_indexed | 2024-03-12T03:35:05Z |
format | Article |
id | doaj.art-c2bfc8467f3a479d9036195c30093477 |
institution | Directory Open Access Journal |
issn | 0067-0049 |
language | English |
last_indexed | 2024-03-12T03:35:05Z |
publishDate | 2023-01-01 |
publisher | IOP Publishing |
record_format | Article |
series | The Astrophysical Journal Supplement Series |
spelling | doaj.art-c2bfc8467f3a479d9036195c300934772023-09-03T13:19:11ZengIOP PublishingThe Astrophysical Journal Supplement Series0067-00492023-01-0126621910.3847/1538-4365/accbb9Generating Space-based SDO/HMI-like Solar Magnetograms from Ground-based Hα Images by Deep LearningFei Gao0Tie Liu1WenQing Sun2Long Xu3https://orcid.org/0000-0002-9286-2876State Key Laboratory of Space Weather, National Space Science Center, Chinese Academy of Sciences , Beijing 100190, People’s Republic of China lxu@nao.cas.cn; University of Chinese Academy of Sciences , Beijing 100049, People’s Republic of ChinaSchool of Astronomy and Space Science, Nanjing University , Nanjing 210023, People’s Republic of China; Key Laboratory for Modern Astronomy and Astrophysics (Nanjing University) , Ministry of Education, Nanjing 210023, People’s Republic of ChinaState Key Laboratory of Space Weather, National Space Science Center, Chinese Academy of Sciences , Beijing 100190, People’s Republic of China lxu@nao.cas.cn; University of Chinese Academy of Sciences , Beijing 100049, People’s Republic of ChinaState Key Laboratory of Space Weather, National Space Science Center, Chinese Academy of Sciences , Beijing 100190, People’s Republic of China lxu@nao.cas.cn; Peng Cheng National Laboratory , Shenzhen 518000, People’s Republic of ChinaRecently, the method of estimating magnetic field through monochromatic images by deep learning has been proposed, demonstrating good morphological similarity but somewhat poor magnetic polarity consistency relative to real observation. In this paper, we propose to estimate magnetic field from H α images by using a conditional generative adversarial network (cGAN) as the basic framework. The H α images from the Global Oscillation Network Group are used as the inputs and the line-of-sight magnetograms of the Helioseismic Magnetic Imager (HMI) are used as the targets. First, we train a cGAN model (Model A) with shuffling training data. However, the estimated magnetic polarities are not very consistent with real observations. Second, to improve the accuracy of estimated magnetic polarities, we train a cGAN model (Model B) with the chronological H α and HMI images, which can implicitly exploit the magnetic polarity constraint of time-series observation to generate more accurate magnetic polarities. We compare the generated magnetograms with the target HMI magnetograms to evaluate the two models. It can be observed that Model B has better magnetic polarity consistency than Model A. To quantitatively measure this consistency, we propose a new metric called pixel-to-pixel polarity accuracy (PPA). With respect to PPA, Model B is superior to Model A. This work gives us an insight that the time-series constraint can be implicitly exploited through organizing training data chronologically, and this conclusion also can be applied to other similar tasks related to time-series data.https://doi.org/10.3847/1538-4365/accbb9Solar magnetic fieldsConvolutional neural networks |
spellingShingle | Fei Gao Tie Liu WenQing Sun Long Xu Generating Space-based SDO/HMI-like Solar Magnetograms from Ground-based Hα Images by Deep Learning The Astrophysical Journal Supplement Series Solar magnetic fields Convolutional neural networks |
title | Generating Space-based SDO/HMI-like Solar Magnetograms from Ground-based Hα Images by Deep Learning |
title_full | Generating Space-based SDO/HMI-like Solar Magnetograms from Ground-based Hα Images by Deep Learning |
title_fullStr | Generating Space-based SDO/HMI-like Solar Magnetograms from Ground-based Hα Images by Deep Learning |
title_full_unstemmed | Generating Space-based SDO/HMI-like Solar Magnetograms from Ground-based Hα Images by Deep Learning |
title_short | Generating Space-based SDO/HMI-like Solar Magnetograms from Ground-based Hα Images by Deep Learning |
title_sort | generating space based sdo hmi like solar magnetograms from ground based hα images by deep learning |
topic | Solar magnetic fields Convolutional neural networks |
url | https://doi.org/10.3847/1538-4365/accbb9 |
work_keys_str_mv | AT feigao generatingspacebasedsdohmilikesolarmagnetogramsfromgroundbasedhaimagesbydeeplearning AT tieliu generatingspacebasedsdohmilikesolarmagnetogramsfromgroundbasedhaimagesbydeeplearning AT wenqingsun generatingspacebasedsdohmilikesolarmagnetogramsfromgroundbasedhaimagesbydeeplearning AT longxu generatingspacebasedsdohmilikesolarmagnetogramsfromgroundbasedhaimagesbydeeplearning |