81 New Candidate Fast Radio Bursts in Parkes Archive

TL;DR

This study utilized machine learning to analyze a vast archive of Parkes radio telescope data, identifying 81 new candidate fast radio bursts to guide future follow-up observations.

Contribution

The paper introduces a novel machine learning approach using ResNet to classify and identify new FRB candidates from archival data.

Findings

Identified 81 new candidate FRBs in Parkes data.

Candidates detected in single beams with low S/N thresholds.

Some candidates have dispersion measures close to Galactic expectations.

Abstract

We have searched for weak fast radio burst (FRB) events using a database containing 568,736,756 transient events detected using the Parkes radio telescope between 1997 and 2001. In order to classify these pulses, and to identify likely FRB candidates, we used a machine learning algorithm based on ResNet. We identified 81 new candidate FRBs and provide details of their positions, event times, and dispersion measures. These events were detected in only one beam of the Parkes multibeam receiver. We used a relatively low S/N cutoff threshold when selecting these bursts and some have dispersion measures only slightly exceeding the expected Galactic contribution. We therefore present these candidate FRBs as a guide for follow-up observations in the search for repeating FRBs.