A machine learning classifier for fast radio burst detection at the VLBA

Wagstaff, K. and Tang, B. and Thompson, D. and Khudikyan, S. and Wyngaard, J. and Deller, A. and Palaniswamy, D. et al. 2016. A machine learning classifier for fast radio burst detection at the VLBA. Publications of the Astronomical Society of the Pacific. 128 (966): Article ID 084503.

Source Title

Publications of the Astronomical Society of the Pacific

DOI

10.1088/1538-3873/128/966/084503

ISSN

0004-6280

School

Curtin Institute of Radio Astronomy (Physics)

Remarks

This is an author-created, un-copy edited version of an article accepted for publication in Publications of the Astronomical Society of the Pacific. The publisher is not responsible for any errors or omissions in this version of the manuscript or any version derived from it. The Version of Record is available online at http://doi.org/10.1088/1538-3873/128/966/084503

URI

http://hdl.handle.net/20.500.11937/28711

Collection

Curtin Research Publications

Abstract

Time domain radio astronomy observing campaigns frequently generate large volumes of data. Our goal is to develop automated methods that can identify events of interest buried within the larger data stream. The V-FASTR fast transient system was designed to detect rare fast radio bursts within data collected by the Very Long Baseline Array. The resulting event candidates constitute a significant burden in terms of subsequent human reviewing time. We have trained and deployed a machine learning classifier that marks each candidate detection as a pulse from a known pulsar, an artifact due to radio frequency interference, or a potential new discovery. The classifier maintains high reliability by restricting its predictions to those with at least 90% confidence. We have also implemented several efficiency and usability improvements to the V-FASTR web-based candidate review system. Overall, we found that time spent reviewing decreased and the fraction of interesting candidates increased. The classifier now classifies (and therefore filters) 80%–90% of the candidates, with an accuracy greater than 98%, leaving only the 10%–20% most promising candidates to be reviewed by humans.