arrow
Return

Multiclass solar flare forecasting models with different deep learning algorithms

delete2023-03-22
delete13
delete
OA
AI
Y
Yanfang Zheng
X
Xuebao Li *
S
Shuainan Yan
黄旭升 (Xusheng Huang)
H
Hengrui Lou
Z
Zhe Li
DOI:10.1093/mnras/stad839delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
We develop a Hybrid Bidirectional Long and Short-Term Memory based on attention mechanism (HBiLSTM-Attention) model and a BiLSTM-Attention model for multiclass flare forecasting within 24 h. We construct a new data base containing 10 separate data sets with magnetogram images and magnetic field parameters. Based on the same data base, for the first time we compare the multiclass forecasting performance of our proposed HBiLSTM-Attention model, BiLSTM-Attention model, and three other deep-learning models based on Convolutional Neural Network (CNN-based) from two aspects of categorical performance with the true skill statistic (TSS) and probabilistic performance with the Brier skill score (BSS). The major results are as follows. (1) The TSS values of our proposed model are 0.692 +/- 0.042, 0.475 +/- 0.038, 0.642 +/- 0.043, 0.754 +/- 0.062, 0.692 +/- 0.042, and 0.708 +/- 0.052 for No-flare, C, M, X, >= C, and >= M class, respectively, which are better than those of the BiLSTM-Attention model, and much better than those of the three other CNN-based models. (2) Our proposed model achieves the scores of BSS = 0.498 +/- 0.061, 0.202 +/- 0.037, 0.209 +/- 0.050, -0.271 +/- 0.180, 0.498 +/- 0.061, 0.268 +/- 0.056 for No-flare, C, M, X, >= C, and >= M class, respectively, outperforming the other four models in every class except for X class. (3) To our knowledge, HBiLSTM-Attention is the first multiclass flare forecasting model based on magnetic field parameters and deep learning, and achieves promising prediction performance. Moreover, this is the first attempt to investigate the reliability of probabilistic prediction for multiclass flares.
Keywords:
methods: data analysis
techniques: image processing
Sun: activity
Sun: flares
Sun: magnetic fields

Journal

Monthly Notices of the Royal Astronomical Society cover
Monthly Notices of the Royal Astronomical Society
IF:
4.8
Papers:
7.0W
Citations:
25.0W

Organization

J
jiangsu university of science & technology
Scholars:
9.0K
Papers: 6.9K
Citations: 9
Cited Papers

Cited Papers

“Worse than I anticipated” or “This isn’t so bad”?: The impact of affective forecasting accuracy on self-reported task performance
err2020-07-13
err0
errOAAI
errSeth Kaplan; Carolyn Winslow; Lydia Craig; Xue Lei; Carol Wong; Jill Bradley-Geist; Martin Biskup; Gregory Ruark
errShare
errSave
errShare
errSave
Predicting Solar Flares Using a Long Short-term Memory Network
err2019-06-03
err109
errOAAI
errLiu, Hao; Liu, Chang; Wang, Jason T. L.; Wang, Haimin
errShare
errSave
TOWARD RELIABLE BENCHMARKING OF SOLAR FLARE FORECASTING METHODS
err2012-02-24
err210
errOAAI
errBloomfield, D. Shaun; Higgins, Paul A.; McAteer, R. T. James; Gallagher, Peter T.
errShare
errSave
Fine-grained Solar Flare Forecasting Based on the Hybrid Convolutional Neural Networks*
err2021-12-03
err17
errOAAI
errDeng, Zheng; Wang, Feng; Deng, Hui; Tan, Lei; Deng, Linhua; Feng, Song
errShare
errSave
errShare
errSave
researcher View more