Deep-Learnt Classification of Light Curves

TL;DR

This paper introduces a deep learning approach using convolutional neural networks to classify astronomical light curves by transforming time series data into 2D representations, enabling effective broad classification of variable stars.

Contribution

The work demonstrates that CNN-based classifiers applied to transformed light curves outperform traditional methods for classifying diverse astronomical objects.

Findings

CNN classifiers achieve high accuracy on CRTS datasets.

Transforming light curves into 2D improves classification performance.

Method enables quick and broad categorization of variable stars.

Abstract

Astronomy light curves are sparse, gappy, and heteroscedastic. As a result standard time series methods regularly used for financial and similar datasets are of little help and astronomers are usually left to their own instruments and techniques to classify light curves. A common approach is to derive statistical features from the time series and to use machine learning methods, generally supervised, to separate objects into a few of the standard classes. In this work, we transform the time series to two-dimensional light curve representations in order to classify them using modern deep learning techniques. In particular, we show that convolutional neural networks based classifiers work well for broad characterization and classification. We use labeled datasets of periodic variables from CRTS survey and show how this opens doors for a quick classification of diverse classes with several possible exciting extensions.