Solar Atmosphere Inversion

An ML model for inverse solar physics, trained on terabyte-scale simulation data from the Daniel K. Inouye Solar Telescope (DKIST). Solves the inverse simulation problem by recovering atmospheric parameters from observed Stokes profiles.

The system monitors the sim-to-real gap and is optimized for deployment in the telescope's operational workflow. Part of the SPIn4D project published in The Astrophysical Journal (2024).