Predicting Associations between Solar Flares and Coronal Mass Ejections Using SDO/HMI Magnetograms and a Hybrid Neural Network

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Jialiang, Yurchyshyn, Vasyl, Wang, Jason T. L., Wang, Haimin, Georgoulis, Manolis K., He, Wen, Abduallah, Yasser, Farooki, Hameedullah A., Xu, Yan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914464896385024
author Li, Jialiang
Yurchyshyn, Vasyl
Wang, Jason T. L.
Wang, Haimin
Georgoulis, Manolis K.
He, Wen
Abduallah, Yasser
Farooki, Hameedullah A.
Xu, Yan
author_facet Li, Jialiang
Yurchyshyn, Vasyl
Wang, Jason T. L.
Wang, Haimin
Georgoulis, Manolis K.
He, Wen
Abduallah, Yasser
Farooki, Hameedullah A.
Xu, Yan
contents Solar eruptions, including flares and coronal mass ejections (CMEs), have a significant impact on Earth. Some flares are associated with CMEs, and some flares are not. The association between flares and CMEs is not always obvious. In this study, we propose a new deep learning method, specifically a hybrid neural network (HNN) that combines a vision transformer with long short-term memory, to predict associations between flares and CMEs. HNN finds spatio-temporal patterns in the time series of line-of-sight magnetograms of solar active regions (ARs) collected by the Helioseismic and Magnetic Imager on board the Solar Dynamics Observatory and uses the patterns to predict whether a flare projected to occur within the next 24 hours will be eruptive (i.e., CME-associated) or confined (i.e., not CME-associated). Our experimental results demonstrate the good performance of the HNN method. Furthermore, the results show that magnetic flux cancellation in polarity inversion line regions may well play a role in triggering flare-associated CMEs, a finding consistent with literature.
format Preprint
id arxiv_https___arxiv_org_abs_2604_10016
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Predicting Associations between Solar Flares and Coronal Mass Ejections Using SDO/HMI Magnetograms and a Hybrid Neural Network
Li, Jialiang
Yurchyshyn, Vasyl
Wang, Jason T. L.
Wang, Haimin
Georgoulis, Manolis K.
He, Wen
Abduallah, Yasser
Farooki, Hameedullah A.
Xu, Yan
Solar and Stellar Astrophysics
Machine Learning
Solar eruptions, including flares and coronal mass ejections (CMEs), have a significant impact on Earth. Some flares are associated with CMEs, and some flares are not. The association between flares and CMEs is not always obvious. In this study, we propose a new deep learning method, specifically a hybrid neural network (HNN) that combines a vision transformer with long short-term memory, to predict associations between flares and CMEs. HNN finds spatio-temporal patterns in the time series of line-of-sight magnetograms of solar active regions (ARs) collected by the Helioseismic and Magnetic Imager on board the Solar Dynamics Observatory and uses the patterns to predict whether a flare projected to occur within the next 24 hours will be eruptive (i.e., CME-associated) or confined (i.e., not CME-associated). Our experimental results demonstrate the good performance of the HNN method. Furthermore, the results show that magnetic flux cancellation in polarity inversion line regions may well play a role in triggering flare-associated CMEs, a finding consistent with literature.
title Predicting Associations between Solar Flares and Coronal Mass Ejections Using SDO/HMI Magnetograms and a Hybrid Neural Network
topic Solar and Stellar Astrophysics
Machine Learning
url https://arxiv.org/abs/2604.10016