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 (58)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Scikit-learn: Machine Learning in Python
• Measurements of Omega and Lambda from 42 High-Redshift Supernovae
• Astropy: A Community Python Package for Astronomy
• GW170817: Observation of Gravitational Waves from a Binary Neutron Star Inspiral
• The Astropy Project: Building an inclusive, open-science project and status of the v2.0 core package
• Multi-messenger Observations of a Binary Neutron Star Merger
• LSST: from Science Drivers to Reference Design and Anticipated Data Products
• How transferable are features in deep neural networks?
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• 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
• The Fermi Gamma-Ray Burst Monitor
• Galaxy Zoo : Morphologies derived from visual inspection of galaxies from the Sloan Digital Sky Survey
• A method for optimal image subtraction
• Weight Uncertainty in Neural Networks
• ATLAS: A High-Cadence All-Sky Survey System
• The Palomar Transient Factory: System Overview, Performance and First Results
• Multi-messenger observations of a flaring blazar coincident with high-energy neutrino IceCube-170922A
• cuDNN: Efficient Primitives for Deep Learning
• Spectroscopic identification of r-process nucleosynthesis in a double neutron star merger
• Nearby Supernova Rates from the Lick Observatory Supernova Search. II. The Observed Luminosity Functions and Fractions of Supernovae in a Complete Sample
• The IceCube Neutrino Observatory: Instrumentation and Online Systems
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• The Pan-STARRS1 Surveys
• A glimpse of the end of the dark ages: the gamma-ray burst of 23 April 2009 at redshift 8.3
• Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference
• Deep Bayesian Active Learning with Image Data
• Bayesian Active Learning for Classification and Preference Learning
• Design and operation of the ATLAS Transient Science Server
• A First Catalog of Variable Stars Measured by the Asteroid Terrestrial-impact Last Alert System (ATLAS)
• BAGAN: Data Augmentation with Balancing GAN
• Proper image subtraction - optimal transient detection, photometry and hypothesis testing
• GLADE: A Galaxy Catalogue for Multi-Messenger Searches in the Advanced Gravitational-Wave Detector Era
• SuperNNova: an open-source framework for Bayesian, Neural Network based supernova classification
• Nearby Supernova Rates from the Lick Observatory Supernova Search. I. The Methods and Database
• Real-bogus classification for the Zwicky Transient Facility using deep learning
• Galaxy Zoo: Probabilistic Morphology through Bayesian CNNs and Active Learning
• Automating Discovery and Classification of Transients and Variable Stars in the Synoptic Survey Era
• Automated Transient Identification in the Dark Energy Survey
• Machine Learning for the Zwicky Transient Facility
• WISE x SuperCOSMOS photometric redshift catalog: 20 million galaxies over 3pi steradians
• Using Machine Learning for Discovery in Synoptic Survey Imaging
• Deep-HiTS: Rotation Invariant Convolutional Neural Network for Transient Detection
• Searching for Electromagnetic Counterparts to Gravitational-wave Merger Events with the Prototype Gravitational-wave Optical Transient Observer (GOTO-4)
• 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
• Unveiling the Distinct Formation Pathways of the Inner and Outer Discs of the Milky Way with Bayesian Machine Learning
• Alert Classification for the ALeRCE Broker System: The Real-time Stamp Classifier
• The Needle in the 100 deg2 Haystack: Uncovering Afterglows of Fermi GRBs with the Palomar Transient Factory
• catsHTM - A tool for fast accessing and cross-matching large astronomical catalogs
• Convolutional Neural Networks for Transient Candidate Vetting in Large-Scale Surveys
• Prediction of transits of solar system objects in Kepler/K2 images: An extension of the Virtual Observatory service SkyBoT
• Vetting the optical transient candidates detected by the GWAC network using convolutional neural networks
• Machine Learning for Transient Recognition in Difference Imaging With Minimum Sampling Effort
• Cosmic Explosions (Optical Transients)
• Automated Transient Detection with Shapelet Analysis in Image-subtracted Data

Cited by in corpus (23)

• Improving the open cluster census. II. An all-sky cluster catalogue with Gaia DR3
• GLADE+: An Extended Galaxy Catalogue for Multimessenger Searches with Advanced Gravitational-wave Detectors
• Machine Learning for Observational Cosmology
• Light curve classification with recurrent neural networks for GOTO: dealing with imbalanced data
• The Gravitational-wave Optical Transient Observer (GOTO)
• AI-driven spatio-temporal engine for finding gravitationally lensed type Ia supernovae
• O'TRAIN: a robust and flexible Real/Bogus classifier for the study of the optical transient sky
• Searching For Fermi GRB Optical Counterparts With The Prototype Gravitational-Wave Optical Transient Observer (GOTO)
• The Evryscope Fast Transient Engine: Real-Time Detection for Rapidly Evolving Transients
• The Gravitational-wave Optical Transient Observer (GOTO)
• Ask The Machine: Systematic detection of wind-type outflows in low-mass X-ray binaries
• Deep-learning Real/Bogus classification for the Tomo-e Gozen transient survey
• Identifying Transients in the Dark Energy Survey using Convolutional Neural Networks
• Self-Supervised Clustering on Image-Subtracted Data with Deep-Embedded Self-Organizing Map
• The classification of real and bogus transients using active learning and semi-supervised learning
• GRB 241105A: A test case for GRB classification and rapid r-process nucleosynthesis channels
• The ATLAS Virtual Research Assistant
• Uncertainty estimation for time series classification: Exploring predictive uncertainty in transformer-based models for variable stars
• The Gravitational-wave Optical Transient Observer (GOTO): prototype performance and prospects for transient science
• Textual interpretation of transient image classifications from large language models
• Discovery and Analysis of Afterglows from Poorly Localised GRBs with the Gravitational-wave Optical Transient Observer (GOTO) All-sky Survey
• Explainable machine learning classification of \textit{Chandra} X-ray sources: SHAP analysis of multi-wavelength features
• Investigating the Effects of Point Source Injection Strategies on KMTNet Real/Bogus Classification