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

Abstract

We present a deep learning approach to classify fast radio bursts (FRBs) based purely on morphology as encoded on recorded dynamic spectrum from CHIME/FRB Catalog 2. We implemented transfer learning with a pretrained ConvNext architecture, exploiting its powerful feature extraction ability. ConvNext was adapted to classify dedispersed dynamic spectra (which we treat as images) of the FRBs into one of the two sub-classes, i.e., repeater and non-repeater, based on their various temporal and spectral properties and relation between the sub-pulse structures. Additionally, we also used mathematical model representation of the total intensity data to interpret the deep learning model. Upon fine-tuning the pretrained ConvNext on the FRB spectrograms, we were able to achieve high classification metrics while substantially reducing training time and computing power as compared to training a deep learning model from scratch with random weights and biases without any feature extraction ability. Importantly, our results suggest that the morphological differences between CHIME repeating and non-repeating events persist in Catalog 2 and the deep learning model leveraged these differences for classification. The fine-tuned deep learning model can be used for inference, which enables us to predict whether an FRB's morphology resembles that of repeaters or non-repeaters. Such inferences may become increasingly significant when trained on larger data sets that will exist in the near future.

26 pages, 17 figures, submitted to ApJ

References in corpus (17)

• Array Programming with NumPy
• A bright millisecond radio burst of extragalactic origin
• Rotation-invariant convolutional neural networks for galaxy morphology prediction
• Fast radio bursts as synchrotron maser emission from decelerating relativistic blast waves
• The Repeating Fast Radio Burst FRB 121102 as Seen on Milliarcsecond Angular Scales
• The synchrotron maser emission from relativistic shocks in Fast Radio Bursts: 1D PIC simulations of cold pair plasmas
• On the Time-Frequency Downward Drifting of Repeating Fast Radio Bursts
• Magnetospheric curvature radiation by bunches as emission mechanism for repeating fast radio bursts
• An analysis on the use of autoencoders for representation learning: fundamentals, learning task case studies, explainability and challenges
• Machine learning classification of CHIME fast radio bursts -- I. Supervised methods
• Discovery of a PRS associated with FRB 20240114A
• Exploring the Key Features of Repeating Fast Radio Bursts with Machine Learning
• Classifying FRB spectrograms using nonlinear dimensionality reduction techniques
• Classifying a frequently repeating fast radio burst, FRB 20201124A, with unsupervised machine learning
• Comparative analysis of machine learning techniques for feature selection and classification of Fast Radio Bursts
• FRB cosmology with the RM-PRS Luminosity Correlation
• The Second CHIME/FRB Catalog of Fast Radio Bursts

Cited by in corpus (2)

• 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