Neural network predicts solar flares by pinpointing active regions
ARENA: Active Region attENtion Aggregation for interpretable solar flare prediction
Computer Vision and Pattern RecognitionMachine Learning
Summary
Solar flares can disrupt communications on Earth, but predicting them is hard. The authors created a neural network that looks at different parts of the Sun and figures out which area is most likely to cause a flare. This method learns from general flare information without needing exact details about where flares start. Their approach predicts flares with accuracy similar to current methods and helps explain which solar region caused the prediction.
What this means in practice
- •For space weather forecasters: Identify which solar active region is most likely to cause a flare using this attention-based flare prediction method for more interpretable alerts.
- •For telecommunications infrastructure teams: Improve preparedness for solar flare disruptions by integrating interpretable flare prediction signals that highlight key solar regions.
Authors
Luis Bauer, Annalena Kofler, Andrés Asensio Ramos, Aparna Venkataramanasastry, Valentín Martínez Pillet, Bernhard Schölkopf
Abstract
Predicting solar flares is a challenging space-weather forecasting problem with potentially significant impacts on Earth's upper atmosphere, including disruptions to radio communications. We propose Active Region attENtion Aggregation (ARENA), a neural network architecture that predicts solar flares from a variable number of active-region cutouts while learning to identify the region most relevant to the prediction. ARENA is trained using multiple-instance learning under weak supervision, requiring only a flare/no-flare label for the observation and no labels specifying the flare origin. The learned attention mechanism therefore provides a means of localizing the active region driving the prediction without explicit origin annotations. ARENA achieves a heidke skill score of 0.45 which is comparable to other flare prediction approaches. These results demonstrate that active-region-based aggregation can provide an efficient and interpretable approach to solar flare prediction. The code is available at https://github.com/LuisBauer22/ARENA.