ROGER: Reconstructing Orbits of Galaxies in Extreme Regions using machine learning techniques

TL;DR

ROGER is a machine learning-based tool that classifies galaxies in and around clusters by their orbital history using phase-space data, aiding understanding of galaxy evolution in dense environments.

Contribution

The paper introduces ROGER, a novel machine learning code that accurately classifies galaxy orbits in clusters using phase-space information, validated on large cosmological simulations.

Findings

K-Nearest Neighbours achieved the best classification performance.

ROGER effectively distinguishes galaxy orbital types in simulated clusters.

The method can be applied to observational data for galaxy evolution studies.

Abstract

We present the ROGER (Reconstructing Orbits of Galaxies in Extreme Regions) code, which uses three different machine learning techniques to classify galaxies in, and around, clusters, according to their projected phase-space position. We use a sample of 34 massive, $M_{200}>10^{15} h^{-1} M_{\odot}$, galaxy clusters in the MultiDark Planck 2 (MDLP2) simulation at redshift zero. We select all galaxies with stellar mass $M_{\star} \ge 10^{8.5} h^{-1}M_{\odot}$, as computed by the semi-analytic model of galaxy formation SAG, that are located in, and in the vicinity of, the clusters and classify them according to their orbits. We train ROGER to retrieve the original classification of the galaxies out of their projected phase-space positions. For each galaxy, ROGER gives as output the probability of being a cluster galaxy, a galaxy that has recently fallen into a cluster, a backsplash galaxy, an infalling galaxy, or an interloper. We discuss the performance of the machine learning methods and potential uses of our code. Among the different methods explored, we find the K-Nearest Neighbours algorithm achieves the best performance.