Prediction of Solar Flares Using Unique Signatures of Magnetic Field Images

TL;DR

This paper introduces a machine learning approach using Zernike moments of solar magnetic field images to predict large solar flares within 48 hours, achieving high accuracy and low false prediction rates.

Contribution

The study presents a novel application of Zernike moments combined with SVM for solar flare prediction, improving accuracy over previous methods.

Findings

Predicted large flares within 48 hours with high accuracy.

Achieved only 10 false negatives and 21 false positives.

Method can be used alongside existing forecasting techniques.

Abstract

Prediction of solar flares is an important task in solar physics. The occurrence of solar flares is highly dependent on the structure and the topology of solar magnetic fields. A new method for predicting large (M and X class) flares is presented, which uses machine learning methods applied to the Zernike moments of magnetograms observed by the Helioseismic and Magnetic Imager (HMI) onboard the Solar Dynamics Observatory (SDO) for a period of six years from 2 June 2010 to 1 August 2016. Magnetic field images consisting of the radial component of the magnetic field are converted to finite sets of Zernike moments and fed to the Support Vector Machine (SVM) classifier. Zernike moments have the capability to elicit unique features from any 2-D image, which may allow more accurate classification. The results indicate whether an arbitrary active region has the potential to produce at least one large flare. We show that the majority of large flares can be predicted within 48 hours before their occurrence, with only 10 false negatives out of 385 flaring active region magnetograms, and 21 false positives out of 179 non-flaring active region magnetograms. Our method may provide a useful tool for prediction of solar flares which can be employed alongside other forecasting methods.