Untangling the Galaxy. III. Photometric Search for Pre-main-sequence Stars with Deep Learning

Abstract A reliable census of pre-main-sequence stars with known ages is critical to our understanding early stellar evolution, but historically there has been difficulty in separating such from the field. We present a trained neural network model, Sagitta, that relies on Gaia DR2 and 2 Micron All-Sky Survey photometry identify derive their age estimates. Our model successfully recovers populations properties associated star-forming regions up five kpc. Furthermore, it allows for detailed look at history solar neighborhood, particularly ranges which we were not previously sensitive. In particular, observe several bubbles distribution stars, most notable ring Local Bubble, may have common origins Gould’s Belt.