HInet: Generating neutral hydrogen from dark matter with neural networks

TL;DR

This paper introduces HInet, a neural network model that efficiently predicts the distribution of neutral hydrogen in the universe from dark matter simulations, outperforming traditional models and enabling large-scale 21cm survey predictions.

Contribution

HInet is a novel neural network approach that accurately maps matter distributions to neutral hydrogen, reducing computational costs compared to hydrodynamic simulations.

Findings

HInet outperforms the Halo Occupation Distribution model in all statistical properties.

The model accurately predicts HI distribution up to non-linear scales $k\lesssim1$ h/Mpc.

Enables large-volume 21cm mock generation with hydrodynamic-like accuracy.

Abstract

Upcoming 21cm surveys will map the spatial distribution of cosmic neutral hydrogen (HI) over very large cosmological volumes. In order to maximize the scientific return of these surveys, accurate theoretical predictions are needed. Hydrodynamic simulations currently are the most accurate tool to provide those predictions in the mildly to non-linear regime. Unfortunately, their computational cost is very high: tens of millions of CPU hours. We use convolutional neural networks to find the mapping between the spatial distribution of matter from N-body simulations and HI from the state-of-the-art hydrodynamic simulation IllustrisTNG. Our model performs better than the widely used theoretical model: Halo Occupation Distribution (HOD) for all statistical properties up to the non-linear scales $k\lesssim1$ h/Mpc. Our method allows the generation of 21cm mocks over very big cosmological volumes with similar properties as hydrodynamic simulations.