A Deep Learning Approach to Operational Flare Forecasting

TL;DR

This paper introduces SolarFlareNet, a transformer-based deep learning framework that predicts solar flares within 24-72 hours by modeling magnetic parameters as time series, achieving real-time operational forecasting.

Contribution

The paper presents a novel transformer-based model for solar flare prediction, extending deterministic forecasts to probabilistic calibration, and demonstrates real-time operational capability.

Findings

Effective prediction of gamma-class flares within 24-72 hours.

Model captures temporal dynamics of magnetic parameters.

System operates in near real-time for practical use.

Abstract

Solar flares are explosions on the Sun. They happen when energy stored in magnetic fields around solar active regions (ARs) is suddenly released. In this paper, we present a transformer-based framework, named SolarFlareNet, for predicting whether an AR would produce a gamma-class flare within the next 24 to 72 hours. We consider three gamma classes, namely the >=M5.0 class, the >=M class and the >=C class, and build three transformers separately, each corresponding to a gamma class. Each transformer is used to make predictions of its corresponding gamma-class flares. The crux of our approach is to model data samples in an AR as time series and to use transformers to capture the temporal dynamics of the data samples. Each data sample consists of magnetic parameters taken from Space-weather HMI Active Region Patches (SHARP) and related data products. We survey flare events that occurred from May 2010 to December 2022 using the Geostationary Operational Environmental Satellite X-ray flare catalogs provided by the National Centers for Environmental Information (NCEI), and build a database of flares with identified ARs in the NCEI flare catalogs. This flare database is used to construct labels of the data samples suitable for machine learning. We further extend the deterministic approach to a calibration-based probabilistic forecasting method. The SolarFlareNet system is fully operational and is capable of making near real-time predictions of solar flares on the Web.