# Cataloging Accreted Stars within Gaia DR2 using Deep Learning

## TL;DR

This paper develops a deep learning method using phase space data to identify accreted stars in Gaia DR2, significantly expanding the number of classifiable stars and aiding understanding of the Milky Way's merger history.

## Contribution

It introduces a transfer learning approach with deep learning to classify accreted stars using only 5D kinematics, applicable to a larger dataset than traditional methods.

## Key findings

- Identified approximately 767,000 accreted stars in Gaia DR2.
- Validated transfer learning method on mock and real data.
- Enhanced sensitivity to accreted star properties.

## Abstract

The goal of this study is to present the development of a machine learning based approach that utilizes phase space alone to separate the Gaia DR2 stars into two categories: those accreted onto the Milky Way from those that are in situ. Traditional selection methods that have been used to identify accreted stars typically rely on full 3D velocity, metallicity information, or both, which significantly reduces the number of classifiable stars. The approach advocated here is applicable to a much larger portion of Gaia DR2. A method known as "transfer learning" is shown to be effective through extensive testing on a set of mock Gaia catalogs that are based on the FIRE cosmological zoom-in hydrodynamic simulations of Milky Way-mass galaxies. The machine is first trained on simulated data using only 5D kinematics as inputs and is then further trained on a cross-matched Gaia/RAVE data set, which improves sensitivity to properties of the real Milky Way. The result is a catalog that identifies around 767,000 accreted stars within Gaia DR2. This catalog can yield empirical insights into the merger history of the Milky Way and could be used to infer properties of the dark matter distribution.