AI to aid prediction of solar flares
doi:10.1038/nindia.2019.68 Published online 28 May 2019
Using a computer-aided technique, astrophysicists have identified unique patterns in the Sun’s active regions, magnetic regions known to generate strong magnetic fields1. Such magnetic regions occasionally produce solar flares that emit harmful radiation, including significant X-ray radiation.
Deciphering the patterns in the magnetic regions will improve the understanding and prediction of flares, which pose threats to astronauts and satellite-based telecommunications on Earth.
Observational studies had provided clues about the physical processes that lead to flares. These studies, however, lacked data on definite flare precursors needed to reliably predict flares.
Scientists from the Tata Institute of Fundamental Research (TIFR) in Mumbai, India, New York University Abu Dhabi in United Arab Emirates and Stanford University in the United States trained a machine to distinguish flare-producing magnetic regions from the non-flaring ones by using magnetic region properties.
The machine successfully classified 75 per cent of the magnetic field observations that are separated in time from flares by at least 72 hours.
The researchers, led by Duttaraj B. Dhuri, detected features that depend on electric currents and magnetic forces in the magnetic regions. They also identified a systematic increase in electric currents and magnetic forces in these regions days prior to flares.
Such a backdrop reveals that the magnetic regions remain in a flare-ready state for several days before and after flares. Flare precursors identified in this research could be used to design a robust system to forecast an imminent flare-producing solar storm, allowing us to take evasive action, says Dhuri.
1. Dhuri, D. B. et al. Machine learning reveals systematic accumulation of electric current in lead-up to solar flares. Proc. Natl. Acad. Sci. Unit. States. Am. (2019) doi: 10.1073/pnas.1820244116