Transient-optimised real-bogus classification with Bayesian Convolutional Neural Networks -- sifting the GOTO candidate stream

Abstract

Large-scale sky surveys have played a transformative role in our understanding of astrophysical transients, only made possible by increasingly powerful machine learning-based filtering to accurately sift through the vast quantities of incoming data generated. In this paper, we present a new real-bogus classifier based on a Bayesian convolutional neural network that provides nuanced, uncertainty-aware classification of transient candidates in difference imaging, and demonstrate its application to the datastream from the GOTO wide-field optical survey. Not only are candidates assigned a well-calibrated probability of being real, but also an associated confidence that can be used to prioritise human vetting efforts and inform future model optimisation via active learning. To fully realise the potential of this architecture, we present a fully-automated training set generation method which requires no human labelling, incorporating a novel data-driven augmentation method to significantly improve the recovery of faint and nuclear transient sources. We achieve competitive classification accuracy (FPR and FNR both below 1%) compared against classifiers trained with fully human-labelled datasets, whilst being significantly quicker and less labour-intensive to build. This data-driven approach is uniquely scalable to the upcoming challenges and data needs of next-generation transient surveys. We make our data generation and model training codes available to the community.

17 pages, 12 figures, resubmitted to MNRAS following reviewer comments

References in corpus (20)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• GW170817: Observation of Gravitational Waves from a Binary Neutron Star Inspiral
• Multi-messenger Observations of a Binary Neutron Star Merger
• How transferable are features in deep neural networks?
• The Zwicky Transient Facility: System Overview, Performance, and First Results
• Weight Uncertainty in Neural Networks
• cuDNN: Efficient Primitives for Deep Learning
• Spectroscopic identification of r-process nucleosynthesis in a double neutron star merger
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Deep Bayesian Active Learning with Image Data
• Machine Learning for the Zwicky Transient Facility
• WISE x SuperCOSMOS photometric redshift catalog: 20 million galaxies over 3pi steradians
• Deep-HiTS: Rotation Invariant Convolutional Neural Network for Transient Detection
• Theoretical Models of Optical Transients. I. A Broad Exploration of the Duration-Luminosity Phase Space
• Machine learning for transient discovery in Pan-STARRS1 difference imaging
• How to Find More Supernovae with Less Work: Object Classification Techniques for Difference Imaging
• The Needle in the 100 deg2 Haystack: Uncovering Afterglows of Fermi GRBs with the Palomar Transient Factory
• Convolutional Neural Networks for Transient Candidate Vetting in Large-Scale Surveys
• Cosmic Explosions (Optical Transients)
• Automated Transient Detection with Shapelet Analysis in Image-subtracted Data

Cited by in corpus (1)

• The Gravitational-wave Optical Transient Observer (GOTO)