Using Physics Informed Neural Networks for Supernova Radiative Transfer Simulation
Published in arXiv, 2022
Recommended citation: Chen, X. and Jeffery, D. J. and Zhong, M. and McClenny, L. and Braga-Neto, U. and Wang L. (2022). "Using Physics Informed Neural Networks for Supernova Radiative Transfer Simulation." arXiv 2022. https://arxiv.org/abs/2211.05219
Abstract: We use physics informed neural networks (PINNs) to solve the radiative transfer equation and calculate a synthetic spectrum for a Type Ia supernova (SN~Ia) SN~2011fe. The calculation is based on local thermodynamic equilibrium (LTE) and 9 elements are included. Physical processes included are approximate radiative equilibrium, bound-bound transitions, and the Doppler effect. A PINN based gamma-ray scattering approximation is used for radioactive decay energy deposition. The PINN synthetic spectrum is compared to an observed spectrum, a synthetic spectrum calculated by the Monte-Carlo radiative transfer program TARDIS, and the formal solution of the radiative transfer equation. We discuss the challenges and potential of this deep-learning based radiative transfer equation solver. In fact, PINNs offer the prospect of simultaneous solution of the atmosphere problem for both radiation field and thermal state throughout spacetime. We have made modest steps to realizing that prospect with our calculations which required many approximations in order to be feasible at this point in the development of PINN atmosphere solutions.