Deep Learning generated observations of galaxy clusters from dark-matter-only simulations

TL;DR

This study explores using deep learning to generate observable galaxy cluster maps from dark matter-only simulations, enabling larger volume studies without costly hydrodynamical simulations.

Contribution

It demonstrates the feasibility of deep learning models to predict observable maps from dark matter data, bridging the gap between simulations and observations.

Findings

High accuracy in predicting observable maps for massive clusters

Excellent agreement with ground-truth data for clusters above 2x10^{14} h^{-1} M_sun

Percentage errors around 0.5% for key scaling parameters

Abstract

Hydrodynamical simulations play a fundamental role in modern cosmological research, serving as a crucial bridge between theoretical predictions and observational data. However, due to their computational intensity, these simulations are currently constrained to relatively small volumes. Therefore, this study investigates the feasibility of utilising dark matter-only simulations to generate observable maps of galaxy clusters using a deep learning approach based on the U-Net architecture. We focus on reconstructing Compton-y parameter maps (SZ maps) and bolometric X-ray surface brightness maps (X-ray maps) from total mass density maps. We leverage data from \textsc{The Three Hundred} simulations, selecting galaxy clusters ranging in mass from $10^{13.5} h^{-1}M_{\odot}\leq M_{200} \leq 10^{15.5} h^{-1}M_{\odot}$. Despite the machine learning models being independent of baryonic matter assumptions, a notable limitation is their dependency on the underlying physics of hydrodynamical simulations. To evaluate the reliability of our generated observable maps, we employ various metrics and compare the observable-mass scaling relations. For clusters with masses greater than $2 \times 10^{14} h^{-1} M_{\odot}$, the predictions show excellent agreement with the ground-truth datasets, with percentage errors averaging (0.5 $\pm$ 0.1)\% for the parameters of the scaling laws.