DRAFTS: A Deep-learning-based Radio Fast Transient Search Pipeline

Abstract

The detection of fast radio bursts (FRBs) in radio astronomy is a complex task due to the challenges posed by radio-frequency interference and signal dispersion in the interstellar medium. Traditional search algorithms are often inefficient, time-consuming, and generate a high number of false positives. In this paper, we present DRAFTS , a deep-learning-based radio fast transient search pipeline. DRAFTS integrates object detection and binary classification techniques to accurately identify FRBs in radio data. We developed a large, real-world data set of FRBs for training deep-learning models. The search test on Five-hundred-meter Aperture Spherical radio Telescope real observation data demonstrates that DRAFTS performs exceptionally in terms of accuracy, completeness, and search speed. In the re-search of FRB 20190520B observation data, DRAFTS detected more than 3 times the number of bursts compared to Heimdall , highlighting the potential for future FRB detection and analysis.

Keywords

• Radio transient sources
• Convolutional neural networks
• Astronomy software
• Astronomy databases