Reconstruction of Dark Matter and Baryon Density From Galaxies: A Comparison of Linear, Halo Model and Machine Learning-Based Methods

TL;DR

This paper systematically compares linear, halo model, and machine learning methods for reconstructing dark matter and baryon distributions from galaxy data, finding that a combined GNN-CNN approach performs best on mildly non-linear scales.

Contribution

It provides the first comprehensive comparison of traditional and machine learning methods for matter reconstruction using CAMELS simulations, highlighting the effectiveness of a combined GNN-CNN model.

Findings

GNN-CNN approach yields the best reconstruction accuracy.

Machine learning methods do not always outperform traditional models.

Analysis clarifies relationships among matter, baryons, halos, and galaxies.

Abstract

For many analyses in cosmology it is necessary to reconstruct the likely distribution of unobserved fields, such as dark matter or non-luminous baryons, from observed luminous tracers. The dominant approach in cosmology has been to use the so-called halo model, which assumes radially symmetric profiles centered around luminous tracers such as galaxies. More recently, field-level machine learning methods have been proposed that can learn to estimate the unobserved field after being trained on simulations. However, it is unclear whether machine learning methods indeed significantly improve over linear methods or the halo model. In this paper we make a systematic comparison of different approaches to reconstruct dark matter and non-luminous baryons, from galaxy data using the CAMELS simulations. These simulations are in a $25\ \texttt{Mpc/h}$ box, allowing us to compare performance on the mildly non-linear scales $(k\sim 0.4\ \mathrm{h/Mpc})$ down to the size of individual halos. We find the best results using a combined GNN-CNN approach. We also provide a general analysis and visualization of the relationship of matter, non-luminous baryons, halos, and galaxies in these simulations to interpret our results.