Classification of Galaxy Cluster Membership with Machine Learning

Abstract: We present a classification algorithm based on the Random Forest machine learning model that differentiates galaxies into orbiting, infalling and background (interloper) populations, using phase space information as input. We train and test our model with the galaxies from UniverseMachine mock catalog based on Multi-Dark Planck 2 N-body simulations. We show that we can recover the distribution of orbiting and infalling galaxies in 3D and 2D position and velocity distribution with $<1\%$ error when using probabilistic predictions in the presence of interlopers in the projected phase space. Our machine learning-based galaxy classification method enables a percent level measurements of the dynamics of cluster galaxies. We discuss potential applications of this technique to improve cluster cosmology and galaxy quenching.