Solar flare recurrence prediction & visual recognition.

Abstract

Solar flares are intense outbursts of radiation observable in the photosphere. The radiation flux is measured in W/m2. Solar flares can kill astronauts, disrupt electrical power grids, and interrupt satellite-dependent technologies. They threaten human survival and the efficiency of technology. The reliability of solar flare prediction models is often undermined by the stochastic nature of solar flare occurrence as shown in previous studies. The Geostationary Operational Environmental Satellite (GOES) system classifies solar flares based on their radiation flux. This study investigated how Recurrent Neural Network (RNN) models compare to their ensembles when predicting flares that emit at least 10−6W/m2 of radiation flux, known as ≥C class flares. A Long-Short Term Memory (LSTM) and Simple RNN homogeneous ensemble achieved a similar performance with a tied True Skill Statistic (TSS) score of 70 ± 1.5%. Calibration curves showed that ensembles are more reliable. The balanced accuracies of the Simple RNN Ensemble and LSTM are both 85% with f1-scores of 79% and 77% respectively. Furthermore, this study proposed a framework that shows how objective function reparameterization can be used to improve binary (≥C or <C) categorical predictions of ensemble RNNs under uncertainty in the stochastic solar flare environment. The best-calibrated ensemble (Heterogenous Stacking Ensemble) had a TSS score of 65 ± 1%, balanced accuracy of 83%, and an f1-score of 81%. Almost perfect calibration usually comes with a trade-off on some metrics, e.g., the TSS as seen in other studies. It is a fact that solar flares erupt from magnetically active regions. Visual manifestations of solar flares can be categorized into various morphological classes which are linked with the underlying magnetic field. Moreover, this study demonstrated how ensemble Convolutional Neural Networks (CNNs) can be used to improve visual recognition of solar flares observed at wavelength 1,600◦A. Base learner diversity was used to improve the likelihood of ensemble success. Classification improved from 94% to 99.99 ± 0.01% when compared to the only preceding study that used CNNs. Overall, this study demonstrated how base learners can be set up to improve ensemble performance in the context of solar flare predictions.