Light curve classification with recurrent neural networks for GOTO: dealing with imbalanced data

Abstract

The advent of wide-field sky surveys has led to the growth of transient and variable source discoveries. The data deluge produced by these surveys has necessitated the use of machine learning (ML) and deep learning (DL) algorithms to sift through the vast incoming data stream. A problem that arises in real-world applications of learning algorithms for classification is imbalanced data, where a class of objects within the data is underrepresented, leading to a bias for over-represented classes in the ML and DL classifiers. We present a recurrent neural network (RNN) classifier that takes in photometric time-series data and additional contextual information (such as distance to nearby galaxies and on-sky position) to produce real-time classification of objects observed by the Gravitational-wave Optical Transient Observer (GOTO), and use an algorithm-level approach for handling imbalance with a focal loss function. The classifier is able to achieve an Area Under the Curve (AUC) score of 0.972 when using all available photometric observations to classify variable stars, supernovae, and active galactic nuclei. The RNN architecture allows us to classify incomplete light curves, and measure how performance improves as more observations are included. We also investigate the role that contextual information plays in producing reliable object classification.

16 pages, 12 figures, to be published in Monthly Notices of the Royal Astronomical Society

References in corpus (22)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• GW170817: Observation of Gravitational Waves from a Binary Neutron Star Inspiral
• Advanced Virgo: a 2nd generation interferometric gravitational wave detector
• Multi-messenger Observations of a Binary Neutron Star Merger
• The Zwicky Transient Facility: System Overview, Performance, and First Results
• The Zwicky Transient Facility: Data Processing, Products, and Archive
• LIGO: The Laser Interferometer Gravitational-Wave Observatory
• Swope Supernova Survey 2017a (SSS17a), the Optical Counterpart to a Gravitational Wave Source
• A kilonova as the electromagnetic counterpart to a gravitational-wave source
• Light Curves of the Neutron Star Merger GW170817/SSS17a: Implications for R-Process Nucleosynthesis
• The Combined Ultraviolet, Optical, and Near-Infrared Light Curves of the Kilonova Associated with the Binary Neutron Star Merger GW170817: Unified Data Set, Analytic Models, and Physical Implications
• The Electromagnetic Counterpart of the Binary Neutron Star Merger LIGO/VIRGO GW170817. IV. Detection of Near-infrared Signatures of r-process Nucleosynthesis with Gemini-South
• SN 2005ap: A Most Brilliant Explosion
• Machine learning for transient discovery in Pan-STARRS1 difference imaging
• Scalable End-to-end Recurrent Neural Network for Variable star classification
• PELICAN: deeP architecturE for the LIght Curve ANalysis
• Convolutional Neural Networks for Transient Candidate Vetting in Large-Scale Surveys
• Transient-optimised real-bogus classification with Bayesian Convolutional Neural Networks -- sifting the GOTO candidate stream
• The Hyper Suprime-Cam SSP Transient Survey in COSMOS: Overview
• Deep Neural Network Classifier for Variable Stars with Novelty Detection Capability
• The Gravitational-wave Optical Transient Observer (GOTO)
• Photometric classification of HSC transients using machine learning

Cited by in corpus (3)

• Periodic Variable Star Classification with Deep Learning: Handling Data Imbalance in an Ensemble Augmentation Way
• The Gravitational-wave Optical Transient Observer (GOTO)
• Deep learning-based astronomical multimodal data fusion: A comprehensive review