Astronomical Classification of Light Curves with an Ensemble of Gated Recurrent Units

TL;DR

This paper explores the use of an ensemble of Gated Recurrent Units (GRUs) for classifying astronomical light curves, demonstrating high accuracy with minimal preprocessing, contributing to automated analysis of large-scale astronomical data.

Contribution

It introduces a deep learning ensemble of GRU and Dense networks for astronomical light curve classification, showing effectiveness without extensive data preprocessing or augmentation.

Findings

Achieved 76.243% accuracy on PLAsTiCC dataset

GRUs are effective for handling astronomical time series data

Open-source code available for reproducibility

Abstract

With an ever-increasing amount of astronomical data being collected, manual classification has become obsolete; and machine learning is the only way forward. Keeping this in mind, the Large Synoptic Survey Telescope (LSST) Team hosted the Photometric LSST Astronomical Time-Series Classification Challenge (PLAsTiCC) in 2018. The aim of this challenge was to develop models that accurately classify astronomical sources into different classes, scaling from a limited training set to a large test set. In this text, we report our results of experimenting with Bidirectional Gated Recurrent Unit (GRU) based deep learning models to deal with time series data of the PLAsTiCC dataset. We demonstrate that GRUs are indeed suitable to handle time series data. With minimum preprocessing and without augmentation, our stacked ensemble of GRU and Dense networks achieves an accuracy of 76.243%. Data from astronomical surveys such as LSST will help researchers answer questions pertaining to dark matter, dark energy and the origins of the universe; accurate classification of astronomical sources is the first step towards achieving this. Our code is open-source and has been made available on GitHub here: https://github.com/AKnightWing/Astronomical-Classification-PLASTICC