Open AccessPredicting Solar Flares Using a Novel Deep Convolutional Neural Network
Author(s) -
Xuebao Li,
Y. G. Zheng,
Xinshuo Wang,
Lulu Wang
Publication year - 2020
Publication title -
astrophysical journal/the astrophysical journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.376
H-Index - 489
eISSN - 1538-4357
pISSN - 0004-637X
DOI - 10.3847/1538-4357/ab6d04
Subject(s) - space weather , solar flare , flare , convolutional neural network , physics , artificial neural network , artificial intelligence , binary number , magnetogram , class (philosophy) , machine learning , stability (learning theory) , pattern recognition (psychology) , computer science , astrophysics , meteorology , magnetic flux , arithmetic , mathematics , quantum mechanics , magnetic field
Space weather forecasting is very important, and the prediction of space weather, especially for solar flares, has increasingly attracted research interests with the numerous recent breakthroughs in machine learning. In this study, we propose a novel convolutional neural network (CNN) model to make binary class prediction for both ≥C-class and ≥M-class flares within 24 hr. We collect magnetogram samples of solar active regions (ARs) provided by the Space-weather Helioseismic and Magnetic Imager Active Region Patches (SHARP) data from 2010 May to 2018 September. These samples are used to construct 10 separate data sets. Then, after training, validating, and testing our model, we compare the results of our model with previous studies in several metrics, with a focus on the true skill statistic (TSS). The major results are summarized as follows. (1) We propose a method of shuffle and split cross-validation (CV) based on AR segregation, which is the first attempt to verify the validity and stability of the model in flare prediction. (2) The proposed CNN model achieves a relatively high score of TSS = 0.749 ± 0.079 for ≥M-class prediction, and TSS = 0.679 ± 0.045 for ≥C-class prediction, which is greatly improved compared with previous studies. (3) The model trained on 10 CV data sets is considerably robust and stable in making flare prediction for both ≥C class and ≥M class. Our experimental results indicate that our proposed CNN model is a highly effective method for flare forecasting, with quite excellent prediction performance.