Implementation paradigm for supervised flare forecasting studies: a deep learning application with video data

TL;DR

This paper introduces a robust data set generation paradigm for solar flare forecasting and applies it to a novel deep neural network approach that classifies videos of magnetograms without feature extraction.

Contribution

It proposes a new data set creation method ensuring independence and balance, and demonstrates its use with a deep neural network for video-based flare prediction.

Findings

First application of deep neural networks to video magnetogram data for flare forecasting

Provides a balanced, independent data set for fair performance comparison

Achieves promising results without feature extraction from magnetograms

Abstract

Solar flare forecasting can be realized by means of the analysis of magnetic data through artificial intelligence techniques. The aim is to predict whether a magnetic active region (AR) will originate solar flares above a certain class within a certain amount of time. A crucial issue is concerned with the way the adopted machine learning method is implemented, since forecasting results strongly depend on the criterion with which training, validation, and test sets are populated. In this paper we propose a general paradigm to generate these sets in such a way that they are independent from each other and internally well-balanced in terms of AR flaring effectiveness. This set generation process provides a ground for comparison for the performance assessment of machine learning algorithms. Finally, we use this implementation paradigm in the case of a deep neural network, which takes as input videos of magnetograms recorded by the Helioseismic and Magnetic Imager on-board the Solar Dynamics Observatory (SDO/HMI). To our knowledge, this is the first time that the solar flare forecasting problem is addressed by means of a deep neural network for video classification, which does not require any a priori extraction of features from the HMI magnetograms.