FETCH: A deep-learning based classifier for fast transient classification

TLDR

Upcoming commensal FRB surveys generate high candidate rates, making machine learning essential for classification and real‑time follow‑up triggers. The study applies transfer learning to train state‑of‑the‑art deep neural networks for classifying FRB and RFI candidates. The authors train convolutional neural networks on radio frequency‑time and dispersion‑measure‑time images, using simulated FRBs and real RFI from Green Bank, and provide an open‑source FETCH package that deploys these models in any commensal pipeline. Eleven models achieve >99.5% accuracy and recall on real RFI and pulsar data, and the algorithms, being telescope‑ and frequency‑agnostic, detect all FRBs with SNR > 10 in ASKAP and Parkes observations.

Abstract

With the upcoming commensal surveys for Fast Radio Bursts (FRBs), and their high candidate rate, usage of machine learning algorithms for candidate classification is a necessity. Such algorithms will also play a pivotal role in sending real-time triggers for prompt follow-ups with other instruments. In this paper, we have used the technique of Transfer Learning to train the state-of-the-art deep neural networks for classification of FRB and Radio Frequency Interference (RFI) candidates. These are convolutional neural networks which work on radio frequency-time and dispersion measure-time images as the inputs. We trained these networks using simulated FRBs and real RFI candidates from telescopes at the Green Bank Observatory. We present 11 deep learning models, each with an accuracy and recall above 99.5% on our test dataset comprising of real RFI and pulsar candidates. As we demonstrate, these algorithms are telescope and frequency agnostic and are able to detect all FRBs with signal-to-noise ratios above 10 in ASKAP and Parkes data. We also provide an open-source python package FETCH (Fast Extragalactic Transient Candidate Hunter) for classification of candidates, using our models. Using FETCH, these models can be deployed along with any commensal search pipeline for real-time candidate classification.