Dr. Christopher Osborne
13:00 27 July 2022
University of Glasgow | School of Physics and Astronomy | Website
Learning to Invert Solar Flares with Invertible Neural Networks.
During a solar flare, it is believed that reconnection takes place in the corona followed by fast energy transport to the chromosphere. The resulting intense heating strongly disturbs the chromospheric structure and induces complex radiation hydrodynamic effects. Interpreting the physics of the flaring solar atmosphere is one of the most challenging tasks in solar physics. Here we present a novel deep learning approach, an invertible neural network, to understanding the chromospheric physics of a flaring solar atmosphere via the inversion of observed spectral line profiles. Our network is trained using flare simulations from the 1D radiation hydrodynamics code RADYN and learns a bijective function between the atmospheric parameters and observables, considering information lost between the two. This information is recovered by repeated sampling from a learned latent space. The inverted atmospheres obtained from observations provide physical information on the electron number density, temperature, and bulk velocity flow of the plasma throughout the solar atmosphere. This algorithm can also be adapted for a menagerie of inverse problems providing extremely fast (approximately 10 microsecond) inversion samples.
