Unsupervised Machine Learning for Classifying CHIME Fast Radio Bursts and Investigating Empirical Relations

TL;DR

This paper applies unsupervised machine learning techniques to classify Fast Radio Bursts from CHIME data, successfully identifying potential repeaters and revealing empirical relations that distinguish their physical properties.

Contribution

It introduces a novel unsupervised learning approach for classifying FRBs and identifying potential repeaters using clustering and dimensionality reduction techniques.

Findings

Successfully segregated repeaters and non-repeaters into distinct clusters

Identified over 100 potential repeater candidates

Revealed empirical relations among FRB properties such as scattering time and brightness temperature

Abstract

Fast Radio Bursts (FRBs) are highly energetic millisecond-duration astrophysical phenomena typically categorized as repeaters or non-repeaters. However, observational limitations may result in misclassifications, potentially leading to a higher proportion of repeaters than currently identified. In this study, we leverage unsupervised machine learning techniques to classify FRBs using data from the CHIME/FRB catalogs, including both the first catalog and a recent repeater catalog. By employing Uniform Manifold Approximation and Projection for dimensionality reduction and clustering algorithms (k-means and Hierarchical Density-Based Spatial Clustering of Applications with Noise), we successfully segregate repeaters and non-repeaters into distinct clusters, identifying over 100 potential repeater candidates. Our analysis reveals several empirical relations within the clusters, including the ${\rm log \,}\Delta t_{sc}-{\rm log \,}\Delta t_{rw}$, ${\rm log \,}\Delta t_{sc}-{\rm log \,}T_B$, and $r - \gamma$ correlations, where ${\Delta t_{sc}, \Delta t_{rw}, T_B, r, \gamma}$ represent scattering time, rest-frame width, brightness temperature, spectral running, and spectral index, respectively. The Chow test results reveal that while some repeaters and non-repeaters share similar empirical relationships, the overall distinctions between the two groups remain significant, reinforcing the classification of FRBs into repeaters and non-repeaters. These findings provide new insights into the physical properties and emission mechanisms of FRBs. This study demonstrates the effectiveness of unsupervised learning in classifying FRBs and identifying potential repeaters, paving the way for more precise investigations into their origins and applications in cosmology. Future improvements in observational data and machine learning methodologies are expected to further enhance our understanding of FRBs.