Applying machine learning to Galactic Archaeology: how well can we recover the origin of stars in Milky Way-like galaxies?

Abstract

We present several machine learning (ML) models developed to efficiently separate stars formed in-situ in Milky Way-type galaxies from those that were formed externally and later accreted. These models, which include examples from artificial neural networks, decision trees and dimensionality reduction techniques, are trained on a sample of disc-like, Milky Way-mass galaxies drawn from the ARTEMIS cosmological hydrodynamical zoom-in simulations. We find that the input parameters which provide an optimal performance for these models consist of a combination of stellar positions, kinematics, chemical abundances ([Fe/H] and [$\alpha$/Fe]) and photometric properties. Models from all categories perform similarly well, with area under the precision-recall curve (PR-AUC) scores of $\simeq 0.6$. Beyond a galactocentric radius of $5$~kpc, models retrieve $>90\%$ of accreted stars, with a sample purity close to $60\%$, however the purity can be increased by adjusting the classification threshold. For one model, we also include host galaxy-specific properties in the training, to account for the variability of accretion histories of the hosts, however this does not lead to an improvement in performance. The ML models can identify accreted stars even in regions heavily dominated by the in-situ component (e.g., in the disc), and perform well on an unseen suite of simulations (the Auriga simulations). The general applicability bodes well for application of such methods on observational data to identify accreted substructures in the Milky Way without the need to resort to selection cuts for minimising the contamination from in-situ stars.

References in corpus (23)

• The EAGLE project: Simulating the evolution and assembly of galaxies and their environments
• The EAGLE simulations of galaxy formation: calibration of subgrid physics and model variations
• The mass distribution and gravitational potential of the Milky Way
• The GALAH Survey: Scientific Motivation
• Two Stellar Components in the Halo of the Milky Way
• The Auriga Project: the properties and formation mechanisms of disc galaxies across cosmic time
• Tracing Galaxy Formation with Stellar Halos II: Relating Substructure in Phase- and Abundance-Space to Accretion Histories
• The Dual Origin of Stellar Halos
• 4MOST: Project overview and information for the First Call for Proposals
• Building Late-Type Spiral Galaxies by In-Situ and Ex-Situ Star Formation
• The Global Dynamical Atlas of the Milky Way mergers: Constraints from Gaia EDR3 based orbits of globular clusters, stellar streams and satellite galaxies
• Origin of chemically distinct discs in the Auriga cosmological simulations
• Halo Substructure in the SDSS-Gaia Catalogue : Streams and Clumps
• Disassembling the Galaxy with angle-action coordinates
• The Southern Stellar Stream Spectroscopic Survey (S5): Chemical Abundances of Seven Stellar Streams
• Project overview and update on WEAVE: the next generation wide-field spectroscopy facility for the William Herschel Telescope
• The Galah Survey: Classification and diagnostics with t-SNE reduction of spectral information
• Characterizing the High-Velocity Stars of RAVE: The Discovery of a Metal-Rich Halo Star Born in the Galactic Disk
• Uncloaking hidden repeating fast radio bursts with unsupervised machine learning
• On the Relative Ages of the $\alpha$-Rich and $\alpha$-Poor Stellar Populations in the Galactic Halo
• The diversity of assembly histories leading to disc galaxy formation in a LambdaCDM model
• In-situ vs accreted Milky Way globular clusters: a new classification method and implications for cluster formation
• Differences in the properties of disrupted and surviving satellites of Milky-Way-mass galaxies in relation to their host accretion histories