Estimating spectroscopic ages of red-giant stars using machine learning

Abstract

Over the last few years, many studies have found an empirical relation between the abundance of a star and its age, rather well known as chemical tagging. Here we estimate spectroscopic stellar ages for 197.000 stars observed by the APOGEE survey. To this end, we use the supervised machine learning technique XGBoost, trained on a set of 3314 stars with asteroseismic ages observed by both APOGEE and Kepler (Miglio et al. 2021). Eventually, to verify the obtained age estimates, we investigated the chemical, kinematic and positional relationship of the stars in respect to their age.