Comparison of outlier detection methods on astronomical image data

Abstract

Among the many challenges posed by the huge data volumes produced by the new generation of astronomical instruments there is also the search for rare and peculiar objects. Unsupervised outlier detection algorithms may provide a viable solution. In this work we compare the performances of six methods: the Local Outlier Factor, Isolation Forest, k-means clustering, a measure of novelty, and both a normal and a convolutional autoencoder. These methods were applied to data extracted from SDSS stripe 82. After discussing the sensitivity of each method to its own set of hyperparameters, we combine the results from each method to rank the objects and produce a final list of outliers.

arXiv commentPreprint version of the accepted manuscript to appear in the Volume "Intelligent Astrophysics" of the series "Emergence, Complexity and Computation", Book eds. I. Zelinka, D. Baron, M. Brescia, Springer Nature Switzerland, ISSN: 2194-7287

References in corpus (5)

• The Sloan Digital Sky Survey: Technical Summary
• The Seventh Data Release of the Sloan Digital Sky Survey
• Photometric redshift estimation via deep learning
• The weirdest SDSS galaxies: results from an outlier detection algorithm
• Systematic Serendipity: A Test of Unsupervised Machine Learning as a Method for Anomaly Detection

Cited by in corpus (3)

• Preparing to discover the unknown with Rubin LSST -- I: Time domain
• Prospecting MeerKAT Continuum Data for Enigmatic Radio Sources with Unsupervised Vector-Quantised Variational Autoencoders
• A Treasure Hunt in the Pool of Spectra Classified as High-redshift QSOs by the Spectroscopic Pipeline of the SDSS DR16