From EMBER to FIRE: predicting high resolution baryon fields from dark matter simulations with Deep Learning

TL;DR

This paper introduces EMBER, a deep learning framework that predicts high-resolution baryon fields from dark matter simulations, significantly reducing computational costs while maintaining accuracy in cosmological structure modeling.

Contribution

EMBER combines U-Net and WGAN architectures to efficiently emulate baryon fields from dark matter data, enabling high-resolution predictions with stochastic sampling capabilities.

Findings

Reproduces gas and HI power spectra within 10% accuracy at small scales

Successfully upscales low-resolution dark matter inputs to high-resolution baryon fields

Produces HI maps consistent with large volume simulations and abundance matching models

Abstract

Hydrodynamic simulations provide a powerful, but computationally expensive, approach to study the interplay of dark matter and baryons in cosmological structure formation. Here we introduce the EMulating Baryonic EnRichment (EMBER) Deep Learning framework to predict baryon fields based on dark-matter-only simulations thereby reducing computational cost. EMBER comprises two network architectures, U-Net and Wasserstein Generative Adversarial Networks (WGANs), to predict two-dimensional gas and HI densities from dark matter fields. We design the conditional WGANs as stochastic emulators, such that multiple target fields can be sampled from the same dark matter input. For training we combine cosmological volume and zoom-in hydrodynamical simulations from the Feedback in Realistic Environments (FIRE) project to represent a large range of scales. Our fiducial WGAN model reproduces the gas and HI power spectra within 10% accuracy down to ~10 kpc scales. Furthermore, 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 emulate high-resolution HI maps for a dark matter simulation of a L=100 Mpc/h comoving cosmological box. The gas content of dark matter haloes and the HI column density distributions predicted by EMBER agree well with results of large volume cosmological simulations and abundance matching models. Our method provides a computationally efficient, stochastic emulator for augmenting dark matter only simulations with physically consistent maps of baryon fields.