Finding radio transients with anomaly detection and active learning based on volunteer classifications

TL;DR

This paper demonstrates that anomaly detection combined with active learning effectively identifies radio transients in large astronomical datasets, reducing human vetting effort and improving recall, with promising applications for future large-scale surveys.

Contribution

First application of anomaly detection and active learning to radio transient detection, showing significant improvements in recall and efficiency over traditional methods.

Findings

Anomaly detection recalls over 50% of transients in top 10% anomaly scores.

Active learning improves recall by up to 20 percentage points with minimal human labeling.

Feature set choice is critical for optimizing detection performance.

Abstract

In this work we explore the applicability of unsupervised machine learning algorithms to finding radio transients. Facilities such as the Square Kilometre Array (SKA) will provide huge volumes of data in which to detect rare transients; the challenge for astronomers is how to find them. We demonstrate the effectiveness of anomaly detection algorithms using 1.3 GHz light curves from the SKA precursor MeerKAT. We make use of three sets of descriptive parameters ('feature sets') as applied to two anomaly detection techniques in the Astronomaly package and analyse our performance by comparison with citizen science labels on the same dataset. Using transients found by volunteers as our ground truth, we demonstrate that anomaly detection techniques can recall over half of the radio transients in the 10 per cent of the data with the highest anomaly scores. We find that the choice of anomaly detection algorithm makes a minor difference, but that feature set choice is crucial, especially when considering available resources for human inspection and/or follow-up. Active learning, where human labels are given for just 2 per cent of the data, improves recall by up to 20 percentage points, depending on the combination of features and model used. The best performing results produce a factor of 5 times fewer sources requiring vetting by experts. This is the first effort to apply anomaly detection techniques to finding radio transients and shows great promise for application to other datasets, and as a real-time transient detection system for upcoming large surveys.