AI RESEARCH
Learning Neural Operator Surrogates for the Black Hole Accretion Code
arXiv CS.LG
•
ArXi:2604.25985v1 Announce Type: cross General-relativistic magnetohydrodynamic (GR-MHD) simulations are essential for studying black hole accretion, relativistic jets, and magnetic reconnection, yet their computational cost severely limits systematic parameter exploration. We investigate neural operator surrogates for two astrophysically relevant simulation scenarios produced by the Black Hole Accretion Code (\texttt