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

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 $\log \Delta t_{sc}-\log \Delta t_{rw}$, $\log \Delta t_{sc}-\log T_B$, 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.

24 pages, 9 figures, 6 tables

References in corpus (61)

• A bright millisecond radio burst of extragalactic origin
• A Population of Fast Radio Bursts at Cosmological Distances
• The Physics of Gamma-Ray Bursts and Relativistic Jets
• A Repeating Fast Radio Burst
• Fast Radio Burst Discovered in the Arecibo Pulsar ALFA Survey
• The First CHIME/FRB Fast Radio Burst Catalog
• FRBCAT: The Fast Radio Burst Catalogue
• The CHIME Fast Radio Burst Project: System Overview
• A repeating fast radio burst associated with a persistent radio source
• A possible connection between Fast Radio Bursts and Gamma-Ray Bursts
• Cosmological implications of Fast Radio Burst / Gamma-Ray Burst Associations
• Making a Short Gamma-Ray Burst from a Long one: Implications for the Nature of GRB 060614
• Nine New Repeating Fast Radio Burst Sources from CHIME/FRB
• A fast radio burst source at a complex magnetised site in a barred galaxy
• Fast Radio Burst 121102 Pulse Detection and Periodicity: A Machine Learning Approach
• Fast radio bursts as a cosmic probe?
• CHIME/FRB Discovery of 25 Repeating Fast Radio Burst Sources
• The Physics of Fast Radio Bursts
• The Galactic Position Dependence of Fast Radio Bursts and the Discovery of FRB 011025
• FETCH: A deep-learning based classifier for fast transient classification
• Fast Radio Burst/Gamma-Ray Burst Cosmography
• The prevalence of repeating fast radio bursts
• Faint Repetitions from a Bright Fast Radio Burst Source
• The Five-hundred-meter Aperture Spherical Radio Telescope (FAST) Project
• A Distant Fast Radio Burst Associated to its Host Galaxy with the Very Large Array
• Identifying the source of perytons at the Parkes radio telescope
• Blinkverse: A Database of Fast Radio Bursts
• Fast radio bursts from activities of neutron stars newborn in BNS mergers: offset, birth rate and observational properties
• Extracting host galaxy dispersion measure and constraining cosmological parameters using fast radio burst data
• Cosmology-independent estimate of the fraction of baryon mass in the IGM from fast radio burst observations
• On the energy and redshift distributions of fast radio bursts
• Gaussian processes reconstruction of dark energy from observational data
• DSA-10: A Prototype Array for Localizing Fast Radio Bursts
• Large host-galaxy dispersion measure of fast radio bursts
• Uncloaking hidden repeating fast radio bursts with unsupervised machine learning
• A review of unsupervised learning in astronomy
• A Machine Learning Classifier for Fast Radio Burst Detection at the VLBA
• A universal energy distribution for FRB 121102
• Machine learning classification of CHIME fast radio bursts -- I. Supervised methods
• The Future of Fast Radio Burst Science
• On the magnetospheric origin of Repeating Fast Radio Bursts
• Machine learning classification of CHIME fast radio bursts: II. Unsupervised Methods
• Fast Radio Burst Distributions Consistent with the First CHIME/FRB Catalog
• An 8.0\% Determination of the Baryon Fraction in the Intergalactic Medium from Localized Fast Radio Bursts
• Constraining the Evolution of the Baryon Fraction in the IGM with FRB and H(z) data
• Single Pulse Detection Algorithms for Real-time Fast Radio Burst Searches using GPUs
• A sample of Fast Radio Bursts discovered and localised with MeerTRAP at the MeerKAT telescope
• Reconstructing the Fraction of Baryons in the Intergalactic Medium with Fast Radio Bursts via Gaussian Processes
• Cosmic Anisotropy and Fast Radio Bursts
• Long and Short Fast Radio Bursts are Different from Repeating and Non-repeating Transients
• Effect of Redshift Distributions of Fast Radio Bursts on Cosmological Constraints
• Exploring the Key Features of Repeating Fast Radio Bursts with Machine Learning
• New Insights into the Criteria of Fast Radio Burst in the Light of FRB 20121102A
• Classifying FRB spectrograms using nonlinear dimensionality reduction techniques
• 81 New Candidate Fast Radio Bursts in Parkes Archive
• Classifying a frequently repeating fast radio burst, FRB 20201124A, with unsupervised machine learning
• A Possible Subclassification of Fast Radio Bursts
• Machine Learning Classification of Repeating FRBs from FRB121102
• Modeling Current and Future High-Cadence Surveys of Repeating FRB Populations
• Fast Radio Bursts
• Fast Radio Bursts as Standard Candles for Cosmology

Cited by in corpus (4)

• Comparative analysis of machine learning techniques for feature selection and classification of Fast Radio Bursts
• Identifying highly magnetized white dwarfs: A dimensionality reduction framework for estimating magnetic fields
• A Practical Framework for Estimating the Repetition Likelihood of Fast Radio Bursts from Spectral Morphology
• Unveiling the spectral morphological division of fast radio bursts with CHIME/FRB Catalog 2