New applications of Graph Neural Networks in Cosmology

TL;DR

This paper explores the use of Graph Neural Networks to analyze large-scale structure data in cosmology, enabling high-accuracy discrimination of dark energy models and precise estimation of cosmological parameters.

Contribution

It introduces a novel graph-based data representation and applies GNNs to cosmological data, demonstrating improved model discrimination and parameter estimation capabilities.

Findings

GNNs achieve 99% accuracy in binary classification of dark energy models.

GNNs achieve 97% accuracy in multi-class classification of cosmological models.

The method provides high-precision constraints on the dark energy parameter w_0.

Abstract

Upcoming cosmological surveys will provide unprecedented amount of data, which will require innovative statistical methods to maximize the scientific exploitation. Standard cosmological analyses based on abundances, two-point and higher-order statistics of cosmic tracers have been widely used to investigate the properties of the cosmic web and Large Scale Structure. However, these statistics can only exploit a subset of the entire information content available. Our goal is thus to implement new data analysis techniques based on machine learning to extract cosmological information through forward modelling, by directly exploiting the spatial coordinates and other observed properties of galaxies and galaxy clusters. Specifically, we investigated a new representation of large-scale structure data in the form of graphs. This data format can be directly fed to Graph Neural Networks, a recently proposed class of supervised Deep Learning algorithms. We tested the method on dark matter halo catalogues in different cosmologies, finding promising results. In particular, the method can discriminate among different dark energy models with high accuracy, through both binary classification ($99\%-$accuracy) and multi-class classification ($97\%-$accuracy). Moreover, it provides constraints on the value of $w_0$, through regression, with high precision.