From EMBER to FIRE*predicting high resolution baryon fields from dark matter silations with deep learning

Abstract

Hydrodynamic silations provide a powerful, but computationally expensive, approach to study the interplay of dark matter and baryons in cosmological structure foation. Here, we introduce the EMulating Baryonic EnRichment (EMBER) Deep Learning framework to predict baryon fields based on dark matter-only silations thereby reducing computational cost. EMBER comprises two network architectures, U-Net and Wasserstein Generative Adversarial Networks (WGANs), to predict 2D gas and H i densities from dark matter fields. We design the conditional WGANs as stochastic elators, such that ltiple target fields can be sampled from the same dark matter input. For training we combine cosmological volume and zoom-in hydrodynamical silations from the Feedback in Realistic Environments (FIRE) project to represent a large range of scales. Our fiducial WGAN model reproduces the gas and H i power spectra within 10 per cent accuracy down to 10 kpc scales. Furtheore, we investigate the capability of EMBER to predict high resolution baryon fields from low resolution dark matter inputs through upsampling techniques. As a practical application, we use this methodology to elate high-resolution H i maps for a dark matter silation of a $L=100,{Mpc}, h{ -1}$ comoving cosmological box. The gas content of dark matter haloes and the H i column density distributions predicted by EMBER agree well with results of large volume cosmological silations and abundance matching models. Our method provides a computationally efficient, stochastic elator for augmenting dark matter only silations with physically consistent maps of baryon fields.