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.

arXiv comment16 pages, 12 figures, to be published in Monthly Notices of the Royal Astronomical Society

References in corpus (62)

• Adam: A Method for Stochastic Optimization
• Scikit-learn: Machine Learning in Python
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Observational Evidence from Supernovae for an Accelerating Universe and a Cosmological Constant
• Measurements of Omega and Lambda from 42 High-Redshift Supernovae
• 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 Man Behind the Curtain: X-rays Drive the UV through NIR Variability in the 2013 AGN Outburst in NGC 2617
• Focal Loss for Dense Object Detection
• First Results from the Catalina Real-time Transient Survey
• 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
• Exploring the Optical Transient Sky with the Palomar Transient Factory
• 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
• Data Mining and Machine Learning in Astronomy
• Early Spectra of the Gravitational Wave Source GW170817: Evolution of a Neutron Star Merger
• SN 2005ap: A Most Brilliant Explosion
• Flash Spectroscopy: Emission Lines from the Ionized Circumstellar Material around $<10$-Day-Old Type II Supernovae
• Calcium-rich gap transients in the remote outskirts of galaxies
• GLADE: A Galaxy Catalogue for Multi-Messenger Searches in the Advanced Gravitational-Wave Detector Era
• Photometric Supernova Classification With Machine Learning
• SuperNNova: an open-source framework for Bayesian, Neural Network based supernova classification
• t-viSNE: Interactive Assessment and Interpretation of t-SNE Projections
• Real-bogus classification for the Zwicky Transient Facility using deep learning
• Automating Discovery and Classification of Transients and Variable Stars in the Synoptic Survey Era
• RAPID: Early Classification of Explosive Transients using Deep Learning
• Using Machine Learning for Discovery in Synoptic Survey Imaging
• Avocado: Photometric Classification of Astronomical Transients with Gaussian Process Augmentation
• Deep Recurrent Neural Networks for Supernovae Classification
• Fink, a new generation of broker for the LSST community
• Machine Learning-based Brokers for Real-time Classification of the LSST Alert Stream
• Optimizing spectroscopic follow-up strategies for supernova photometric classification with active learning
• Machine learning for transient discovery in Pan-STARRS1 difference imaging
• Kernel PCA for type Ia supernovae photometric classification
• Supernova Photometric Classification Pipelines Trained on Spectroscopically Classified Supernovae from the Pan-STARRS1 Medium-Deep Survey
• Deep-Learnt Classification of Light Curves
• Scalable End-to-end Recurrent Neural Network for Variable star classification
• PELICAN: deeP architecturE for the LIght Curve ANalysis
• Deep Learning for Image Sequence Classification of Astronomical Events
• Active Anomaly Detection for time-domain discoveries
• Convolutional Neural Networks for Transient Candidate Vetting in Large-Scale Surveys
• Anomaly Detection in the Open Supernova Catalog
• STACCATO: A Novel Solution to Supernova Photometric Classification with Biased Training Sets
• Transient-optimised real-bogus classification with Bayesian Convolutional Neural Networks -- sifting the GOTO candidate stream
• Imbalance Learning for Variable Star Classification
• The Hyper Suprime-Cam SSP Transient Survey in COSMOS: Overview
• Deep Neural Network Classifier for Variable Stars with Novelty Detection Capability
• Classifying Image Sequences of Astronomical Transients with Deep Neural Networks
• Machine Learning Based Real Bogus System for HSC-SSP Moving Object Detecting Pipeline
• Supernova Photometric Classification Challenge
• The Gravitational-wave Optical Transient Observer (GOTO)
• Machine Learning for Transient Recognition in Difference Imaging With Minimum Sampling Effort
• Optical Observations of the Young Type Ic Supernova SN 2014L in M99
• Photometric classification of HSC transients using machine learning
• Optimising a magnitude-limited spectroscopic training sample for photometric classification of supernovae
• Detecting optical transients using artificial neural networks and reference images from different surveys

Cited by in corpus (9)

• Pan-chromatic photometric classification of supernovae from multiple surveys and transfer learning for future surveys
• Classifying Astronomical Transients Using Only Host Galaxy Photometry
• O'TRAIN: a robust and flexible Real/Bogus classifier for the study of the optical transient sky
• Periodic Variable Star Classification with Deep Learning: Handling Data Imbalance in an Ensemble Augmentation Way
• SNAD Transient Miner: Finding Missed Transient Events in ZTF DR4 using k-D trees
• The Gravitational-wave Optical Transient Observer (GOTO)
• Deep learning-based astronomical multimodal data fusion: A comprehensive review
• Pushing the Limit of Asteroseismic Detection for Cool Dwarfs using TESS and Deep Learning
• Photometric Redshift Estimation with Convolutional Neural Networks and Galaxy Images: A Case Study of Resolving Biases in Data-Driven Methods