Exploring the Key Features of Repeating Fast Radio Bursts with Machine Learning

Abstract

Fast radio bursts (FRBs) are enigmatic high-energy events with unknown origins, which are observationally divided into two categories, i.e., repeaters and nonrepeaters. However, there are potentially a number of nonrepeaters that may be misclassified, as repeating bursts are missed due to the limited sensitivity and observation periods, thus misleading the investigation of their physical properties. In this work, we propose a repeater identification method based on the t-distributed Stochastic Neighbor Embedding algorithm and apply the classification to the first Canadian Hydrogen Intensity Mapping Experiment Fast Radio Burst (CHIME/FRB) catalog. We find that the spectral morphology parameters, specifically spectral running (r), represent the key features for identifying repeaters from the nonrepeaters. Also, the results suggest that repeaters are more biased toward narrowband emission, whereas nonrepeaters are inclined toward broadband emission. We provide a list of 163 repeater candidates, five of which are confirmed with an updated repeater catalog from CHIME/FRB. Our findings improve our understanding of the various properties underlying repeaters and nonrepeaters, as well as guidelines for future FRB detection and categorization.