A Machine Learning Classifier for Fast Radio Burst Detection at the VLBA

Kiri L. Wagstaff, Benyang Tang, David R. Thompson, Shakeh Khudikyan, Jane Wyngaard, Adam T. Deller, Divya Palaniswamy, Steven John Tingay et al.

Publications of the Astronomical Society of the Pacific 2016 article cited by 44

Source Open-access PDF More in Physics & Astronomy

importance 4/10 ai assisted Radio Astronomy Observations and Technology radio astronomy stage: deployed

Problem

Fast transient searches like V-FASTR on the Very Long Baseline Array produce huge numbers of candidate detections that burden astronomers with manual review time.

Why it matters

Human review time limits how quickly rare cosmic events like fast radio bursts can be identified in large data streams.

What the AI did

A trained machine learning classifier labels each candidate as a known pulsar pulse, radio frequency interference artifact, or potential new discovery, restricting predictions to those with at least 90% confidence.

Results

Time spent reviewing decreased and the fraction of interesting candidates increased; classifier only predicts at ≥90% confidence (no numeric metrics stated)

Impact

The deployed classifier reduced human review burden and improved candidate yield in the V-FASTR system.

Record

Venue	Publications of the Astronomical Society of the Pacific
Published	2016
Work type	article
Authors	Kiri L. Wagstaff, Benyang Tang, David R. Thompson, Shakeh Khudikyan, Jane Wyngaard, Adam T. Deller, Divya Palaniswamy, Steven John Tingay et al.
Citations	44 (OpenAlex, at import time)
References	27
Model or method	machine learning classifier (type not stated in source)
Organization	not stated in source
Primary source	https://doi.org/10.1088/1538-3873/128/966/084503
Open access	bronze
Keywords	machine learning, fast radio bursts, VLBA, candidate classification, V-FASTR

Importance rating

4 / 10

real but narrower advance

Abstract states candidate detections are a significant human reviewing burden in V-FASTR transient searches; a deployed classifier filters 80-90% of candidates, easing discovery of rare events in one astronomy system.

Basis: stated. The source itself states the scale. Stated scale: not stated in source. Method and limits.

More in Physics & Astronomy

#	Paper	Year	Citations	Importance
1	Magnetic control of tokamak plasmas through deep reinforcement learning Jonas Degrave, Federico Felici, Jonas Buchli, Michael Neunert, Brendan...	2022	739	7
2	Solving the quantum many-body problem with artificial neural networks Giuseppe Carleo, Matthias Troyer	2017	2,205	7
3	Learning high-accuracy error decoding for quantum processors Johannes Bausch, Andrew Senior, Francisco J. H. Heras, Thomas Edlich,...	2024	90	7
4	Optimizing Quantum Error Correction Codes with Reinforcement Learning Hendrik Poulsen Nautrup, Nicolas Delfosse, Vedran Dunjko, Hans J. Brie...	2019	158	7
5	Machine-learning-assisted correction of correlated qubit errors in a topological code Paul Baireuther, Thomas E. O’Brien, Brian Tarasinski, C. W. J. Beenakk...	2018	141	7