Deep learning for clustering of continuous gravitational wave candidates II: identification of low-SNR candidates

TL;DR

This paper develops a deep learning approach to improve clustering of faint continuous gravitational wave signals, enhancing detection efficiency while maintaining low false alarm rates.

Contribution

It introduces a cascade of two deep learning networks for clustering both strong and weak signals, advancing gravitational wave candidate identification.

Findings

High detection efficiency across various signal strengths

False alarm rate comparable or lower than existing methods

Effective identification of low-SNR gravitational wave candidates

Abstract

Broad searches for continuous gravitational wave signals rely on hierarchies of follow-up stages for candidates above a given significance threshold. An important step to simplify these follow-ups and reduce the computational cost is to bundle together in a single follow-up nearby candidates. This step is called clustering and we investigate carrying it out with a deep learning network. In our first paper [1], we implemented a deep learning clustering network capable of correctly identifying clusters due to large signals. In this paper, a network is implemented that can detect clusters due to much fainter signals. These two networks are complementary and we show that a cascade of the two networks achieves an excellent detection efficiency across a wide range of signal strengths, with a false alarm rate comparable/lower than that of methods currently in use.