Comparative analysis of machine learning techniques for feature selection and classification of Fast Radio Bursts

Abstract

Fast Radio Bursts (FRBs) are millisecond-duration radio transients of extragalactic origin, exhibiting a wide range of physical and observational properties. Distinguishing between repeating and non-repeating FRBs remains a key challenge in understanding their nature. In this work, we apply unsupervised machine learning techniques to classify FRBs based on both primary observables from the CHIME catalog and physically motivated derived features. We evaluate three hybrid pipelines combining dimensionality reduction with clustering: Principal Component Analysis (PCA) + k-means, t-distributed Stochastic Neighbor Embedding (t-SNE) + Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN), and t-SNE + Spectral Clustering. To identify optimal hyperparameters, we implement a comprehensive grid search using a custom scoring function that prioritizes recall while penalizing excessive cluster fragmentation and noise. Feature relevance is assessed using principal component loadings, mutual information with the known repeater label, and permutation-based F\textsubscript{2} score sensitivity. Our results demonstrate that the derived features, including redshift, luminosity, and spectral properties, such as the spectral index and the spectral running, significantly enhance the classification performance. Finally, we identify a set of FRBs currently labeled as non-repeaters that consistently cluster with known repeaters across all methods, highlighting promising candidates for future follow-up observations and reinforcing the utility of unsupervised approaches in FRB population studies.

References in corpus (21)

• A bright millisecond radio burst of extragalactic origin
• A New Electron Density Model for Estimation of Pulsar and FRB Distances
• Fast Radio Bursts
• The First CHIME/FRB Fast Radio Burst Catalog
• Cosmological implications of Fast Radio Burst / Gamma-Ray Burst Associations
• The Physics of Fast Radio Bursts
• CHIME/FRB Discovery of 25 Repeating Fast Radio Burst Sources
• The prevalence of repeating fast radio bursts
• The Galactic Halo Contribution to the Dispersion Measure of Extragalactic Fast Radio Bursts
• Cosmic Sparks from Superconducting Strings
• Extragalactic dispersion measures of fast radio bursts
• Blinkverse: A Database of Fast Radio Bursts
• Cosmology-insensitive estimate of IGM baryon mass fraction from five localized fast radio bursts
• No redshift evolution of non-repeating fast radio-burst rates
• Uncloaking hidden repeating fast radio bursts with unsupervised machine learning
• Machine learning classification of CHIME fast radio bursts -- I. Supervised methods
• Machine learning classification of CHIME fast radio bursts: II. Unsupervised Methods
• Classifying FRB spectrograms using nonlinear dimensionality reduction techniques
• Exploring the Key Features of Repeating Fast Radio Bursts with Machine Learning
• Hybrid Pulsar-Magnetar Model for FRB 20191221A
• Unsupervised Machine Learning for Classifying CHIME Fast Radio Bursts and Investigating Empirical Relations

Cited by in corpus (4)

• Repeating versus Nonrepeating Fast Radio Bursts: A Deep Learning Approach to Morphological Characterization
• 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