Real-Time Detection of Anomalies in Large-Scale Transient Surveys

Abstract

New time-domain surveys, such as the Vera C. Rubin Observatory Legacy Survey of Space and Time (LSST), will observe millions of transient alerts each night, making standard approaches of visually identifying new and interesting transients infeasible. We present two novel methods of automatically detecting anomalous transient light curves in real-time. Both methods are based on the simple idea that if the light curves from a known population of transients can be accurately modelled, any deviations from model predictions are likely anomalies. The first modelling approach is a probabilistic neural network built using Temporal Convolutional Networks (TCNs) and the second is an interpretable Bayesian parametric model of a transient. We demonstrate our methods' ability to provide anomaly scores as a function of time on light curves from the Zwicky Transient Facility. We show that the flexibility of neural networks, the attribute that makes them such a powerful tool for many regression tasks, is what makes them less suitable for anomaly detection when compared with our parametric model. The parametric model is able to identify anomalies with respect to common supernova classes with high precision and recall scores, achieving area under the precision-recall curves (AUCPR) above 0.79 for most rare classes such as kilonovae, tidal disruption events, intermediate luminosity transients, and pair-instability supernovae. Our ability to identify anomalies improves over the lifetime of the light curves. Our framework, used in conjunction with transient classifiers, will enable fast and prioritised followup of unusual transients from new large-scale surveys.

27 pages, 23 figures, accepted for publication in MNRAS

References in corpus (12)

• GW170817: Observation of Gravitational Waves from a Binary Neutron Star Inspiral
• The Transiting Exoplanet Survey Satellite
• The Zwicky Transient Facility: System Overview, Performance, and First Results
• The Zwicky Transient Facility: Science Objectives
• A recurrent neural network for classification of unevenly sampled variable stars
• Anomaly detection in the Zwicky Transient Facility DR3
• Supervised detection of anomalous light-curves in massive astronomical catalogs
• Systematic Serendipity: A Test of Unsupervised Machine Learning as a Method for Anomaly Detection
• PELICAN: deeP architecturE for the LIght Curve ANalysis
• Unsupervised machine learning for transient discovery in Deeper, Wider, Faster light curves
• Automated novelty detection in the WISE survey with one-class support vector machines
• Deep Generative Modeling of Periodic Variable Stars Using Physical Parameters

Cited by in corpus (16)

• Deep Attention-Based Supernovae Classification of Multi-Band Light-Curves
• The ROAD to discovery: machine learning-driven anomaly detection in radio astronomy spectrograms
• SNAD Transient Miner: Finding Missed Transient Events in ZTF DR4 using k-D trees
• Understanding of the properties of neural network approaches for transient light curve approximations
• A Classifier-Based Approach to Multi-Class Anomaly Detection for Astronomical Transients
• Representation Learning for Time-Domain High-Energy Astrophysics: Discovery of Extragalactic Fast X-ray Transient XRT 200515
• Deep Learning and LLM-based Methods Applied to Stellar Lightcurve Classification
• Transfer Learning for Transient Classification: From Simulations to Real Data and ZTF to LSST
• Finding radio transients with anomaly detection and active learning based on volunteer classifications
• Searching for Quasi-Periodic Eruptions using Machine Learning
• Anomaly Detection to identify Transients in LSST Time Series Data
• Real-time Light Curve Classification Framework for the Wide Field Survey Telescope Using Modified Semi-supervised Variational Auto-Encoder
• Quantum Machine Learning for Identifying Transient Events in X-ray Light Curves
• J-PLUS: Understanding outlier white dwarfs in the third data release via dimensionality reduction
• Extracting latent representations from X-ray spectra. Classification, regression, and accretion signatures of Chandra sources
• Enabling New Discoveries with Machine Learning