# Identifying Solar Flare Precursors Using Time Series of SDO/HMI Images and SHARP Parameters

## TL;DR

This paper develops machine learning methods using SDO/HMI image time series to predict solar flares, achieving early prediction capabilities with significant lead time before flare events.

## Contribution

It introduces a data pipeline and deep learning models that effectively utilize magnetogram data for early solar flare prediction, matching performance of existing active region parameters.

## Key findings

- Prediction score increases significantly 20 hours before strong flares.
- Deep learning captures spatial and temporal features effectively.
- Models perform nearly as well as using traditional active region parameters.

## Abstract

We present several methods towards construction of precursors, which show great promise towards early predictions, of solar flare events in this paper. A data pre-processing pipeline is built to extract useful data from multiple sources, Geostationary Operational Environmental Satellites (GOES) and Solar Dynamics Observatory (SDO)/Helioseismic and Magnetic Imager (HMI), to prepare inputs for machine learning algorithms. Two classification models are presented: classification of flares from quiet times for active regions and classification of strong versus weak flare events. We adopt deep learning algorithms to capture both the spatial and temporal information from HMI magnetogram data. Effective feature extraction and feature selection with raw magnetogram data using deep learning and statistical algorithms enable us to train classification models to achieve almost as good performance as using active region parameters provided in HMI/Space-Weather HMI-Active Region Patch (SHARP) data files. Case studies show a significant increase in the prediction score around 20 hours before strong solar flare events.