Abstract We present a deep learning approach to classify fast radio bursts (FRBs) based purely on morphology as encoded on recorded dynamic spectrum from Canadian Hydrogen Intensity Mapping Experiment (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 subclasses, i.e., repeater and nonrepeater, based on their various temporal and spectral properties and the relation between the subpulse structures. Additionally, we also used a 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 repeating and nonrepeating CHIME 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 nonrepeaters. Such inferences may become increasingly significant when trained on larger datasets that will exist in the near future.
Kharel et al. (Fri,) studied this question.