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

Abstract

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. 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 7050 autocorrelation-based spectrograms from the Low Frequency Array (LOFAR) telescope and assign 10 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. 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. We demonstrate that our system is 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 0.89, outperforming other related works.

References in corpus (28)

• LOFAR: The LOw-Frequency ARray
• The Sloan Digital Sky Survey Photometric Camera
• The Five-Hundred-Meter Aperture Spherical Radio Telescope (FAST) Project
• Deep Neural Networks to Enable Real-time Multimessenger Astrophysics
• LOFAR facet calibration
• Faceting for direction-dependent spectral deconvolution
• Systematic effects in LOFAR data: A unified calibration strategy
• Galaxy Zoo DECaLS: Detailed Visual Morphology Measurements from Volunteers and Deep Learning for 314,000 Galaxies
• Initial deep LOFAR observations of Epoch of Reionization windows: I. The North Celestial Pole
• Accelerating incoherent dedispersion
• Applying Deep Learning to Fast Radio Burst Classification
• Astronomaly: Personalised Active Anomaly Detection in Astronomical Data
• Calibration Challenges for Future Radio Telescopes
• Anomaly detection in the Zwicky Transient Facility DR3
• Detecting outliers in astronomical images with deep generative networks
• A Deep Learning Approach for Active Anomaly Detection of Extragalactic Transients
• IQRM: real-time adaptive RFI masking for radio transient and pulsar searches
• Cobalt: A GPU-based correlator and beamformer for LOFAR
• LOFAR observations of the quiet solar corona
• Engineering and Science Highlights of the KAT-7 Radio Telescope
• Anomaly detection in Hyper Suprime-Cam galaxy images with generative adversarial networks
• Real-Time Dedispersion for Fast Radio Transient Surveys, using Auto Tuning on Many-Core Accelerators
• Correlating Radio Astronomy Signals with Many-Core Hardware
• Learning to detect RFI in radio astronomy without seeing it
• Autoencoding Galaxy Spectra I: Architecture
• Real-Time Detection of Anomalies in Large-Scale Transient Surveys
• Deep Learning Assisted Data Inspection for Radio Astronomy
• Data Challenges for Next-generation Radio Telescopes

Cited by in corpus (5)

• Anomaly Detection and Radio-frequency Interference Classification with Unsupervised Learning in Narrowband Radio Technosignature Searches
• Finding radio transients with anomaly detection and active learning based on volunteer classifications
• A Deep Neural Network Based Reverse Radio Spectrogram Search Algorithm
• Technology Research Software: An Often Overlooked Category of Research Software
• J-PLUS: Understanding outlier white dwarfs in the third data release via dimensionality reduction