Testing and Validating Two Morphological Flare Predictors by Logistic Regression Machine Learning

TL;DR

This study evaluates two morphological parameters as predictors for solar flares using logistic regression, demonstrating their combined effectiveness with at least 70% prediction probability a day in advance.

Contribution

It introduces and validates a machine learning approach using two morphological parameters to predict solar flares with high accuracy.

Findings

Combined parameters improve flare prediction accuracy.

Prediction probability reaches at least 70% one day before flares.

Parameters serve as good complementary predictors.

Abstract

Whilst the most dynamic solar active regions (ARs) are known to flare frequently, predicting the occurrence of individual flares and their magnitude, is very much a developing field with strong potentials for machine learning applications. The present work is based on a method which is developed to define numerical measures of the mixed states of ARs with opposite polarities. The method yields compelling evidence for the assumed connection between the level of mixed states of a given AR and the level of the solar eruptive probability of this AR by employing two morphological parameters: (i) the separation parameter $S_{l-f}$ and (ii) the sum of the horizontal magnetic gradient $G_{S}$. In this work, we study the efficiency of $S_{l-f}$ and $G_{S}$ as flare predictors on a representative sample of ARs, based on the SOHO/MDI-Debrecen Data (SDD) and the SDO/HMI - Debrecen Data (HMIDD) sunspot catalogues. In particular, we investigate about 1000 ARs in order to test and validate the joint prediction capabilities of the two morphological parameters by applying the logistic regression machine learning method. Here, we confirm that the two parameters with their threshold values are, when applied together, good complementary predictors. Furthermore, the prediction probability of these predictor parameters is given at least 70\% a day before.