Analysis of light curves emanating from various celestial bodies is of paramount importance in order to enable ourselves with quantify the variability in sky and discover time-varying objects. Large Synoptic Survey Telescope (LSST)gather voluminous time-series data. However, classifying these events from large-scale surveys is a challenging task that requires efficient and robust machine learning methods. In this paper, we present a novel approach for astronomical time series classification using gradient boost, a powerful ensemble technique that combines weak learners into a strong classifier. We apply our method to two datasets from the Catalina and Zwicky TransientFacility surveys, which contain light curves of various types of transients and variables. We compare our results with state-of-the-art methods that use different features and models. We show that our method achieves superior performance in terms of accuracy with comparable computational complexity. We also discuss the advantages and limitations of our method and suggest possible directions for future work.
Masood et al. (Fri,) studied this question.