Anomaly detection in Astrophysics: a comparison between unsupervised Deep and Machine Learning on KiDS data

TL;DR

This paper compares two unsupervised machine learning methods, a convolutional autoencoder and a random forest, for anomaly detection in astrophysics using KiDS DR4 data, aiming to identify peculiar celestial sources.

Contribution

It presents a preliminary comparison of image-based and catalogue-based unsupervised learning algorithms for anomaly detection in large sky survey data.

Findings

Autoencoder can identify interacting galaxies and gravitational lenses.

Random Forest detects objects with unusual magnitudes and colors.

Both methods show promise for automated anomaly detection in astronomy.

Abstract

Every field of Science is undergoing unprecedented changes in the discovery process, and Astronomy has been a main player in this transition since the beginning. The ongoing and future large and complex multi-messenger sky surveys impose a wide exploiting of robust and efficient automated methods to classify the observed structures and to detect and characterize peculiar and unexpected sources. We performed a preliminary experiment on KiDS DR4 data, by applying to the problem of anomaly detection two different unsupervised machine learning algorithms, considered as potentially promising methods to detect peculiar sources, a Disentangled Convolutional Autoencoder and an Unsupervised Random Forest. The former method, working directly on images, is considered potentially able to identify peculiar objects like interacting galaxies and gravitational lenses. The latter instead, working on catalogue data, could identify objects with unusual values of magnitudes and colours, which in turn could indicate the presence of singularities.