Astronomaly at scale: searching for anomalies amongst 4 million galaxies

Abstract

Modern astronomical surveys are producing datasets of unprecedented size and richness, increasing the potential for high-impact scientific discovery. This possibility, coupled with the challenge of exploring a large number of sources, has led to the development of novel machine-learning-based anomaly detection approaches, such as Astronomaly. For the first time, we test the scalability of Astronomaly by applying it to almost 4 million images of galaxies from the Dark Energy Camera Legacy Survey. We use a trained deep learning algorithm to learn useful representations of the images and pass these to the anomaly detection algorithm isolation forest, coupled with Astronomaly's active learning method, to discover interesting sources. We find that data selection criteria have a significant impact on the trade-off between finding rare sources such as strong lenses and introducing artefacts into the dataset. We demonstrate that active learning is required to identify the most interesting sources and reduce artefacts, while anomaly detection methods alone are insufficient. Using Astronomaly, we find 1635 anomalies among the top 2000 sources in the dataset after applying active learning, including eight strong gravitational lens candidates, 1609 galaxy merger candidates, and 18 previously unidentified sources exhibiting highly unusual morphology. Our results show that by leveraging the human-machine interface, Astronomaly is able to rapidly identify sources of scientific interest even in large datasets.

arXiv comment15 pages, 9 figures. Comments welcome, especially suggestions about the anomalous sources

References in corpus (40)

• Astropy: A Community Python Package for Astronomy
• The Sloan Digital Sky Survey: Technical Summary
• The Wide-field Infrared Survey Explorer (WISE): Mission Description and Initial On-orbit Performance
• The Astropy Project: Building an inclusive, open-science project and status of the v2.0 core package
• UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
• The Astropy Project: Sustaining and Growing a Community-oriented Open-source Project and the Latest Major Release (v5.0) of the Core Package
• LSST: from Science Drivers to Reference Design and Anticipated Data Products
• The Galaxy Evolution Explorer: A Space Ultraviolet Survey Mission
• The SIMBAD astronomical database
• A Tutorial on Principal Component Analysis
• Overview of the DESI Legacy Imaging Surveys
• Galaxy Zoo : Morphologies derived from visual inspection of galaxies from the Sloan Digital Sky Survey
• The Sixteenth Data Release of the Sloan Digital Sky Surveys: First Release from the APOGEE-2 Southern Survey and Full Release of eBOSS Spectra
• The 6dF Galaxy Survey: Final Redshift Release (DR3) and Southern Large-Scale Structures
• Galaxy Zoo 1 : Data Release of Morphological Classifications for nearly 900,000 galaxies
• Galaxy groups in the 2dFGRS: the group-finding algorithm and the 2PIGG catalogue
• The Eighteenth Data Release of the Sloan Digital Sky Surveys: Targeting and First Spectra from SDSS-V
• GLADE: A Galaxy Catalogue for Multi-Messenger Searches in the Advanced Gravitational-Wave Detector Era
• ANNz2 - photometric redshift and probability distribution function estimation using machine learning
• Galaxy Zoo DECaLS: Detailed Visual Morphology Measurements from Volunteers and Deep Learning for 314,000 Galaxies
• Automated supervised classification of variable stars I. Methodology
• The SAGA Survey. II. Building a Statistical Sample of Satellite Systems around Milky Way-like Galaxies
• The CFHTLS-Strong Lensing Legacy Survey (SL2S): Investigating the group-scale lenses with the SARCS sample
• Galaxy Zoo: Probabilistic Morphology through Bayesian CNNs and Active Learning
• The Strong Gravitational Lens Finding Challenge
• The Asiago Supernova Catalogue- 10 years after
• The weirdest SDSS galaxies: results from an outlier detection algorithm
• The Sloan Lens ACS Survey. XIII. Discovery of 40 New Galaxy-Scale Strong Lenses
• Finding Strong Gravitational Lenses in the DESI DECam Legacy Survey
• Discovering New Strong Gravitational Lenses in the DESI Legacy Imaging Surveys
• Luminosity and Redshift Dependence of the Covering Factor of AGNs viewed with WISE and SDSS
• Astronomaly: Personalised Active Anomaly Detection in Astronomical Data
• Systematic Serendipity: A Test of Unsupervised Machine Learning as a Method for Anomaly Detection
• DeepMerge II: Building Robust Deep Learning Algorithms for Merging Galaxy Identification Across Domains
• Anomaly detection in Hyper Suprime-Cam galaxy images with generative adversarial networks
• Automated novelty detection in the WISE survey with one-class support vector machines
• Compact Groups of Galaxies in Sloan Digital Sky Survey and LAMOST Spectral Survey: I. The Catalogs
• The Discovery of QSOs Behind M31 and M33
• Harnessing the Hubble Space Telescope Archives: A Catalogue of 21,926 Interacting Galaxies
• Morphological classification of astronomical images with limited labelling

Cited by in corpus (7)

• Enabling Unsupervised Discovery in Astronomical Images through Self-Supervised Representations
• Anomaly Detection and Radio-frequency Interference Classification with Unsupervised Learning in Narrowband Radio Technosignature Searches
• A Classifier-Based Approach to Multi-Class Anomaly Detection for Astronomical Transients
• Finding radio transients with anomaly detection and active learning based on volunteer classifications
• Interpreting anomaly detection of SDSS spectra
• The Dyson Minds 2025 Workshop: SETI around Black Holes
• Enabling New Discoveries with Machine Learning