# Machine learning reveals systematic accumulation of electric current in lead-up to solar flares

## TL;DR

This study uses machine learning to analyze magnetic field data, revealing that active regions build up electric currents and magnetic stresses days before solar flares, improving understanding and prediction of these space-weather events.

## Contribution

The paper demonstrates that machine learning can identify precursors like electric current accumulation and magnetic stress intensification in active regions before solar flares, offering new physical insights.

## Key findings

- Active regions persist in flare-productive states for days.
- Pre-flare build-up of electric currents indicates twisted magnetic fields.
- Magnetic stresses intensify days before flare events.

## Abstract

Solar flares - bursts of high-energy radiation responsible for severe space-weather effects - are a consequence of the occasional destabilization of magnetic fields rooted in active regions (ARs). The complexity of AR evolution is a barrier to a comprehensive understanding of flaring processes and accurate prediction. Though machine learning (ML) has been used to improve flare predictions, the potential for revealing precursors and associated physics has been underexploited. Here, we train ML algorithms to classify between vector-magnetic-field observations from flaring ARs, producing at least one M-/X-class flare, and non-flaring ARs. Analysis of magnetic-field observations accurately classified by the machine presents statistical evidence for (1) ARs persisting in flare-productive states --- characterized by AR area --- for days, before and after M- and X-class flare events, (2) systematic pre-flare build-up of free energy in the form of electric currents, suggesting that associated subsurface magnetic field is twisted, (3) intensification of Maxwell stresses in the corona above newly emerging ARs, days before first flares. These results provide new insights into flare physics and improving flare forecasting.