Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

FOXES: A Framework For Operational X-ray Emission Synthesis

Griffin T. Goodwin, Jayant Biradar, Alison J. March, Christoph Schirninger, Robert Jarolim, Angelos Vourlidas, Lorien Pratt

TL;DR

FOXES tackles the challenge of localizing and sizing solar flares beyond Earth by leveraging six-channel EUV data to predict the integrated soft X-ray flux recorded by GOES. The method uses a Vision Transformer (ViT) architecture to translate EUV observations into SXR flux, with patch-based processing, multi-channel fusion, and attention-based interpretability. Results show accurate flux predictions across flare classes, with strong alignment to ground truth and spatial attention maps that highlight physically relevant regions, suggesting the approach can extend to far-side solar observations. This work promises richer flare catalogs and improved forecasting, particularly when integrated with ITI-calibrated data from EUV-observing missions off the Sun–Earth line.

Abstract

Understanding solar flares is critical for predicting space weather, as their activity shapes how the Sun influences Earth and its environment. The development of reliable forecasting methodologies of these events depends on robust flare catalogs, but current methods are limited to flare classification using integrated soft X-ray emission that are available only from Earth's perspective. This reduces accuracy in pinpointing the location and strength of farside flares and their connection to geoeffective events. In this work, we introduce a Vision Transformer (ViT)-based approach that translates Extreme Ultraviolet (EUV) observations into soft x-ray flux while also setting the groundwork for estimating flare locations in the future. The model achieves accurate flux predictions across flare classes using quantitative metrics. This paves the way for EUV-based flare detection to be extended beyond Earth's line of sight, which allows for a more comprehensive and complete solar flare catalog.

FOXES: A Framework For Operational X-ray Emission Synthesis

TL;DR

FOXES tackles the challenge of localizing and sizing solar flares beyond Earth by leveraging six-channel EUV data to predict the integrated soft X-ray flux recorded by GOES. The method uses a Vision Transformer (ViT) architecture to translate EUV observations into SXR flux, with patch-based processing, multi-channel fusion, and attention-based interpretability. Results show accurate flux predictions across flare classes, with strong alignment to ground truth and spatial attention maps that highlight physically relevant regions, suggesting the approach can extend to far-side solar observations. This work promises richer flare catalogs and improved forecasting, particularly when integrated with ITI-calibrated data from EUV-observing missions off the Sun–Earth line.

Abstract

Understanding solar flares is critical for predicting space weather, as their activity shapes how the Sun influences Earth and its environment. The development of reliable forecasting methodologies of these events depends on robust flare catalogs, but current methods are limited to flare classification using integrated soft X-ray emission that are available only from Earth's perspective. This reduces accuracy in pinpointing the location and strength of farside flares and their connection to geoeffective events. In this work, we introduce a Vision Transformer (ViT)-based approach that translates Extreme Ultraviolet (EUV) observations into soft x-ray flux while also setting the groundwork for estimating flare locations in the future. The model achieves accurate flux predictions across flare classes using quantitative metrics. This paves the way for EUV-based flare detection to be extended beyond Earth's line of sight, which allows for a more comprehensive and complete solar flare catalog.
Paper Structure (4 sections, 3 figures, 2 tables)

This paper contains 4 sections, 3 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Data
  3. Methodology
  4. Conclusion

Figures (3)

  • Figure 1: Our FOXES architecture, highlighting patch embedding, class token, positional embedding, transformer layers with multi-head self-attention (MHSA), and output head.
  • Figure 2: A 2D histogram comparing our FOXES model performance to the ground truth. A perfect prediction line (dark red) and the mean absolute error (in log-space) of our model at different flare classes (shaded red) is overlaid on top.
  • Figure 3: (Left Panel) An SDO/AIA 131 Å image, with attention-based heat map, provided by FOXES, overlaid in red. (Right Panel) A comparison of our FOXES model to the ground truth for an X-class flare that occurred on August 5th, 2023. The timestamp of the left image is shown by the gray dotted line.