Towards DM-free search for Fast Radio Bursts with Machine Learning -- I. An implementation on multibeam data

TL;DR

This paper introduces a machine learning approach using EfficientNet to detect fast radio bursts directly from raw multibeam data, eliminating the need for traditional dedispersion and improving detection efficiency and RFI mitigation.

Contribution

The study presents the first implementation of ML-based FRB detection without dedispersion, demonstrating high accuracy and efficiency on multibeam data from real telescopes.

Findings

Achieved over 92% accuracy and precision in FRB recognition.

Significantly faster detection compared to conventional methods.

Effective mitigation of radio frequency interference in multibeam data.

Abstract

Searching for fleeting radio transients like fast radio bursts (FRBs) with wide-field radio telescopes has become a common challenge in data-intensive science. Conventional algorithms normally cost enormous time to seek candidates by finding the correct dispersion measures, of which the process is so-called dedispersion. Here we present a novel scheme to identify FRB signals from raw data without dedispersion using Machine Learning (ML). Under the data environment for multibeam receivers, we train the EfficientNet model and achieve both exceeding 92% accuracy and precision in FRB recognition. We find that the searching efficiency can be significantly enhanced without the procedure of dedispersion compared with conventional softwares like TransientX and presto. Specifically, the impact of radio frequency interference (RFI) for single-beam and multibeam data has been investigated, and we find ML can naturally mitigate RFI under the multibeam environment. Finally, we validate the trained model on actual data from the current FRB surveys carried out by the Five-hundred-meter Aperture Spherical radio Telescope, which provides considerable potential for real implementation in the future.