A Challenge of Developing a Classifier for Multi-Band Classification of Variable Stars

Abstract: Variable stars play a very important role in our understanding of the Milky Way and the universe. In recent years, many survey projects have generated a large amount of photometric data, necessitating classifiers that can quickly identify various types of variable stars. However, obtaining these classifiers often requires substantial manpower and computational resources. To conserve these resources, it would be best to have a classifier that can be used across surveys. We explore the possibility that a classifier created in one optical band can also work in other bands, likely from different survey facilities. We construct a random forest classifier based on photometric data in ASAS-SN V-band and OGLE I-band, and apply the classifier on ASAS-SN V-band and ZTF r-band light curves of variable star samples. We explore the classification differences of using the magnitude light-curves or the normalized flux light-curves, the periods derived from single band light-curves or the periods derived from the multi-band combined light-curves, and with or without color-related features. We find it feasible to develop a classifier capable of working in both V and r bands for certain types of variable stars, such as RRAB variables. For other types of variable stars, like Cepheids, the classifier is unable to make accurate identifications.