Real Time Event Detection in Astronomical Data Streams: Lessons from the VLBA

TL;DR

This paper discusses V-FASTR, a real-time adaptive system at VLBA that detects fast radio transients by self-tuning to changing conditions, demonstrating the feasibility of commensal, real-time anomaly detection in large astronomical data streams.

Contribution

It introduces a novel self-tuning, online pattern recognition system for real-time detection of transient events in astronomical data streams, applicable to next-generation observatories.

Findings

V-FASTR has operated since 2011, making it the longest-running real-time commensal radio transient experiment.

The system effectively adapts to changing noise and instrument conditions, maintaining sensitivity.

Synthetic event injection improves detection performance through continual retraining.

Abstract

A new generation of observational science instruments is dramatically increasing collected data volumes in a range of fields. These instruments include the Square Kilometre Array (SKA), Large Synoptic Survey Telescope (LSST), terrestrial sensor networks, and NASA satellites participating in "decadal survey" missions. Their unprecedented coverage and sensitivity will likely reveal wholly new categories of unexpected and transient events. Commensal methods passively analyze these data streams, recognizing anomalous events of scientific interest and reacting in real time. We report on a case example: V-FASTR, an ongoing commensal experiment at the Very Long Baseline Array (VLBA) that uses online adaptive pattern recognition to search for anomalous fast radio transients. V-FASTR triages a millisecond-resolution stream of data and promotes candidate anomalies for further offline analysis. It tunes detection parameters in real time, injecting synthetic events to continually retrain itself for optimum performance. This self-tuning approach retains sensitivity to weak signals while adapting to changing instrument configurations and noise conditions. The system has operated since July 2011, making it the longest-running real time commensal radio transient experiment to date.