Two Faces of a Galactic Collision: Uncovering the Chemical Story of Gaia–Sausage–Enceladus

This paper uses stellar chemical abundances and machine learning to study the Milky Way’s stellar halo, focusing on the ancient merger Gaia–Sausage–Enceladus. By applying a graph attention network to GALAH survey data, the authors identify chemically coherent groups of stars. They find that GSE splits into two distinct chemical populations, interpreted as stars originating from different regions of the same progenitor galaxy.