A Deep Learning Framework for Predicting Solar EUV Irradiance During Significant Flares

2026-07-21

AI Summary

This study addresses the challenge of accurately forecasting 6.5 nm extreme ultraviolet (EUV) irradiance over the next three days during intense solar flares. To this end, we propose FlareEUV, a lightweight attention-based deep learning model that, for the first time, incorporates a multimodal attention mechanism into EUV prediction. Leveraging full-disk, multi-channel images from the Atmospheric Imaging Assembly (AIA) and Helioseismic and Magnetic Imager (HMI) aboard NASA’s Solar Dynamics Observatory (SDO), FlareEUV end-to-end models the complex relationship between photospheric magnetic activity and coronal radiative response. Evaluated on 33 major flare events from 2011 to 2014, the model significantly outperforms existing baseline methods, achieving high-accuracy short-term EUV irradiance forecasts.

Abstract

We present FlareEUV, a multimodal deep learning framework for predicting daily extreme ultraviolet (EUV) irradiance at 6.5 nm over three consecutive days during significant solar flares, using multi-instrument observations from NASA's Solar Dynamics Observatory (SDO). We consider 33 significant flares in the period between 2011 and 2014 in Solar Cycle 24. The SDO observations include 13 co-aligned full-disk images, comprising eight AIA EUV/UV and five HMI magnetic/continuum products. FlareEUV learns the relationship between magnetic structure and coronal emission from the raw imaging data using a lightweight attention-based architecture. Our experimental results demonstrate the good performance of FlareEUV in short-term EUV irradiance forecasting during the significant flares and its superiority over baseline methods.

Problem

• solar flares
• EUV irradiance
• forecasting
• extreme ultraviolet
• solar activity

Innovation

• multimodal deep learning
• solar EUV irradiance prediction
• attention-based architecture
• solar flare forecasting
• SDO multi-instrument data