Forecasting Solar Flares Using Magnetogram-based Predictors and Machine Learning

TL;DR

This paper develops a machine learning-based method using magnetogram data to forecast solar flares within a 24-hour window, achieving high accuracy and skill scores, which can improve space weather prediction.

Contribution

It introduces a novel set of thirteen predictors from magnetogram data and compares multiple ML techniques, identifying random forests as the most effective for solar flare prediction.

Findings

Random forests achieved the highest prediction accuracy.

The method predicts >M1 flares with 93% accuracy and >C1 flares with 84% accuracy.

Support vector machines and multi-layer perceptrons also performed well.

Abstract

We propose a forecasting approach for solar flares based on data from Solar Cycle 24, taken by the Helioseismic and Magnetic Imager (HMI) on board the Solar Dynamics Observatory (SDO) mission. In particular, we use the Space-weather HMI Active Region Patches (SHARP) product that facilitates cut-out magnetograms of solar active regions (AR) in the Sun in near-real-time (NRT), taken over a five-year interval (2012 - 2016). Our approach utilizes a set of thirteen predictors, which are not included in the SHARP metadata, extracted from line-of-sight and vector photospheric magnetograms. We exploit several Machine Learning (ML) and Conventional Statistics techniques to predict flares of peak magnitude >M1 and >C1, within a 24 h forecast window. The ML methods used are multi-layer perceptrons (MLP), support vector machines (SVM) and random forests (RF). We conclude that random forests could be the prediction technique of choice for our sample, with the second best method being multi-layer perceptrons, subject to an entropy objective function. A Monte Carlo simulation showed that the best performing method gives accuracy ACC=0.93(0.00), true skill statistic TSS=0.74(0.02) and Heidke skill score HSS=0.49(0.01) for >M1 flare prediction with probability threshold 15% and ACC=0.84(0.00), TSS=0.60(0.01) and HSS=0.59(0.01) for >C1 flare prediction with probability threshold 35%.