A black box for dark sector physics: Predicting dark matter annihilation feedback with conditional GANs

Abstract

Traditionally, incorporating additional physics into existing cosmological simulations requires re-running the cosmological simulation code, which can be computationally expensive. We show that conditional Generative Adversarial Networks (cGANs) can be harnessed to predict how changing the underlying physics alters the simulation results. To illustrate this, we train a cGAN to learn the impact of dark matter annihilation feedback (DMAF) on the gas density distribution. The predicted gas density slices are visually difficult to distinguish from their real brethren and the peak counts differ by less than 10 per cent for all test samples (the average deviation is < 3 per cent). Finally, we invert the problem and show that cGANs are capable of endowing smooth density distributions with realistic substructure. The cGAN does however have difficulty generating new knots as well as creating/eliminating bubble-like structures. We conclude that trained cGANs can be an effective approach to provide mock samples of cosmological simulations incorporating DMAF physics from existing samples of standard cosmological simulations of the evolution of cosmic structure.