Predicting solar flares with machine learning: investigating solar cycle dependence

TL;DR

This study employs LSTM neural networks to predict solar flare classes within 24 hours based on magnetic parameters, revealing the importance of temporal data and year-specific training for accurate forecasting.

Contribution

The paper demonstrates the effectiveness of LSTM networks in solar flare prediction and highlights the impact of training data selection on model performance.

Findings

LSTM models outperform previous single-input models.

Skill scores vary significantly with different training years.

Temporal features improve flare prediction accuracy.

Abstract

A deep learning network, Long-Short Term Memory (LSTM) network, is used in this work to predict whether the maximum flare class an active region (AR) will produce in the next 24 hours is class $\Gamma$. We considered $\Gamma$ are $\ge M$, $\ge C$ and any flare class. The essence of using LSTM, which is a recurrent neural network, is its capability to capture temporal information of the data samples. The input features are time sequences of 20 magnetic parameters from SHARPs - Space-weather HMI Active Region Patches. We analyzed active regions from June 2010 to Dec 2018, using the Geostationary Operational Environmental Satellite (GOES) X-ray flare catalogs and label the data samples with identified ARs in the GOES X-ray flare catalogs. Our results (i) shows consistent skill scores with recently published results using LSTMs and better than the previous work using single time input (eg. DeFN) (ii) The skill scores from the model show essential differences when different years of data was chosen for training and testing.