The ROAD to discovery: Machine-learning-driven anomaly detection in radio astronomy spectrograms

Abstract

Context. As radio telescopes increase in sensitivity and flexibility, so do their complexity and data rates. For this reason, automated system health management approaches are becoming increasingly critical to ensure nominal telescope operations. Aims. We propose a new machine-learning anomaly detection framework for classifying both commonly occurring anomalies in radio telescopes as well as detecting unknown rare anomalies that the system has potentially not yet seen. To evaluate our method, we present a dataset consisting of 6708 autocorrelation-based spectrograms from the Low Frequency Array (LOFAR) telescope and assign ten different labels relating to the system-wide anomalies from the perspective of telescope operators. This includes electronic failures, miscalibration, solar storms, network and compute hardware errors, among many more. Methods. We demonstrate how a novel self-supervised learning (SSL) paradigm, that utilises both context prediction and reconstruction losses, is effective in learning normal behaviour of the LOFAR telescope. We present the Radio Observatory Anomaly Detector (ROAD), a framework that combines both SSL-based anomaly detection and a supervised classification, thereby enabling both classification of both commonly occurring anomalies and detection of unseen anomalies. Results. We demonstrate that our system works in real time in the context of the LOFAR data processing pipeline, requiring <1ms to process a single spectrogram. Furthermore, ROAD obtains an anomaly detection F-2 score of 0.92 while maintaining a false positive rate of 2%, as well as a mean per-class classification F-2 score of 0.89, outperforming other related works.