A Classifier-Based Approach to Multi-Class Anomaly Detection for Astronomical Transients

Abstract

Automating real-time anomaly detection is essential for identifying rare transients, with modern survey telescopes generating tens of thousands of alerts per night, and future telescopes, such as the Vera C. Rubin Observatory, projected to increase this number dramatically. Currently, most anomaly detection algorithms for astronomical transients rely either on hand-crafted features extracted from light curves or on features generated through unsupervised representation learning, coupled with standard anomaly detection algorithms. In this work, we introduce an alternative approach: using the penultimate layer of a neural network classifier as the latent space for anomaly detection. We then propose a novel method, Multi-Class Isolation Forests (\texttt{MCIF}), which trains separate isolation forests for each class to derive an anomaly score for a light curve from its latent space representation. This approach significantly outperforms a standard isolation forest. We also use a simpler input method for real-time transient classifiers which circumvents the need for interpolation and helps the neural network handle irregular sampling and model inter-passband relationships. Our anomaly detection pipeline identifies rare classes including kilonovae, pair-instability supernovae, and intermediate luminosity transients shortly after trigger on simulated Zwicky Transient Facility light curves. Using a sample of our simulations matching the population of anomalies expected in nature (54 anomalies and 12,040 common transients), our method discovered $41\pm 3$ anomalies (~75% recall) after following up the top 2000 (~15%) ranked transients. Our novel method shows that classifiers can be effectively repurposed for real-time anomaly detection.

19 pages, 17 figures, 2 tables. Accepted to RAS Techniques and Instruments (RASTI)

References in corpus (34)

• Array Programming with NumPy
• The Astropy Project: Sustaining and Growing a Community-oriented Open-source Project and the Latest Major Release (v5.0) of the Core Package
• The Transiting Exoplanet Survey Satellite
• Multi-messenger Observations of a Binary Neutron Star Merger
• LSST: from Science Drivers to Reference Design and Anticipated Data Products
• The Zwicky Transient Facility: System Overview, Performance, and First Results
• EXPANSE: A Deep Continual / Progressive Learning System for Deep Transfer Learning
• A Review of Deep Transfer Learning and Recent Advancements
• Seeing the Collision of a Supernova with its Companion Star
• SNANA: A Public Software Package for Supernova Analysis
• Photometric Supernova Classification With Machine Learning
• SuperNNova: an open-source framework for Bayesian, Neural Network based supernova classification
• RAPID: Early Classification of Explosive Transients using Deep Learning
• Models and Simulations for the Photometric LSST Astronomical Time Series Classification Challenge (PLAsTiCC)
• Alert Classification for the ALeRCE Broker System: The Light Curve Classifier
• A mildly relativistic outflow from the energetic, fast-rising blue optical transient CSS161010 in a dwarf galaxy
• Avocado: Photometric Classification of Astronomical Transients with Gaussian Process Augmentation
• Deep Recurrent Neural Networks for Supernovae Classification
• Machine Learning-based Brokers for Real-time Classification of the LSST Alert Stream
• Astronomaly: Personalised Active Anomaly Detection in Astronomical Data
• Anomaly detection in the Zwicky Transient Facility DR3
• Systematic Serendipity: A Test of Unsupervised Machine Learning as a Method for Anomaly Detection
• PELICAN: deeP architecturE for the LIght Curve ANalysis
• A Deep Learning Approach for Active Anomaly Detection of Extragalactic Transients
• Active Anomaly Detection for time-domain discoveries
• Anomaly Detection in the Open Supernova Catalog
• The Dark Energy Survey Supernova Program: Modelling selection efficiency and observed core collapse supernova contamination
• Classifying Supernovae Using Only Galaxy Data
• 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
• Real-Time Detection of Anomalies in Large-Scale Transient Surveys
• Astronomaly at scale: searching for anomalies amongst 4 million galaxies
• Towards Real-time Classification of Astronomical Transients
• A classification algorithm for time-domain novelties in preparation for LSST alerts: Application to variable stars and transients detected with DECam in the Galactic Bulge

Cited by in corpus (4)

• ORACLE: A Real-Time, Hierarchical, Deep-Learning Photometric Classifier for the LSST
• Transfer Learning for Transient Classification: From Simulations to Real Data and ZTF to LSST
• FALCO: a Foundation model of Astronomical Light Curves for time dOmain astronomy
• Enabling New Discoveries with Machine Learning