Cataloguing new high-mass Pre-Main Sequence and Classical Be stars using Machine Learning and Gaia

Herbig Ae/Be stars are high-mass Pre-Main Sequence objects which are key to understanding the star formation mechanisms of high-mass stars and the evolution of their protoplanetary discs. By applying Machine Learning techniques to Gaia DR2 data we have constructed a large and homogeneous catalogue of new Pre-Main Sequence sources with, at least, 1361 new Herbig Ae/Be stars. Standard techniques are not efficient for identifying these objects mainly because of their similarity with Classical Be stars, with which they share many characteristics. By focusing on disentangling these two types of objects, our algorithm has also identified 693 new Classical Be stars. The catalogue of new high-mass Pre-Main Sequence stars that we present here increases the number of known objects of the class by an order of magnitude. In this poster I discuss the methodology used and the general properties of the new sources. Furthermore, I present the results of independent spectroscopic observations of these newly discovered Herbig Ae/Be stars.