Emulating CO line radiative transfer with deep learning

ABSTRACT Modelling carbon monoxide (CO) line radiation is computationally expensive for traditional numerical solvers, especially when applied to complex, 3D stellar atmospheres. We present COEmuNet, a 3D convolutional neural network-based surrogate model that emulates CO line radiation transport with high accuracy and efficiency. It consists of an asymmetric encoder–decoder design that takes 3D hydrodynamical models as inputs and generates synthetic observations of evolved stellar atmospheres. The model is trained on data from hydrodynamic simulations of asymptotic giant branch stars perturbed by a companion. Given a set of input parameters, including velocity fields, kinetic temperature distribution, and CO molecular number densities, the COEmuNet model emulates spectral line observations with a median relative error of $\sim 7{{\ \rm per\ cent}}$ compared to a classical numerical solver of the radiative transfer equation, measured over seven frequency channels and arbitrary viewing directions. Besides, COEmuNet delivers a 1000 times speedup, enabling efficient model fitting to observational data sets, real-time visualization of simulations and progress toward integration in large-scale cosmological simulations.