SLICK: Strong Lensing Identification of Candidates Kindred in gravitational wave data

TL;DR

This paper introduces SLICK, a deep learning pipeline for identifying strongly lensed gravitational wave signals, achieving higher efficiency and accuracy than previous methods, and validated on real LIGO-Virgo data.

Contribution

The paper presents a novel deep learning-based pipeline, SLICK, that improves the speed and accuracy of detecting lensed gravitational waves compared to prior approaches.

Findings

SLICK outperforms previous models by a factor of 5 in efficiency at a false positive rate of 0.001.

Including SGP maps with QT maps enhances detection performance.

The model correctly classifies all real LIGO-Virgo events, consistent with no lensing detection.

Abstract

By the end of the next decade, we hope to have detected strongly lensed gravitational waves by galaxies or clusters. Although there exist optimal methods for identifying lensed signal, it is shown that machine learning (ML) algorithms can give comparable performance but are orders of magnitude faster than non-ML methods. We present the SLICK pipeline which comprises a parallel network based on deep learning. We analyse the Q-transform maps (QT maps) and the Sine-Gaussian maps (SGP-maps) generated for the binary black hole signals injected in Gaussian as well as real noise. We compare our network performance with the previous work and find that the efficiency of our model is higher by a factor of 5 at a false positive rate of 0.001. Further, we show that including SGP maps with QT maps data results in a better performance than analysing QT maps alone. When combined with sky localisation constraints, we hope to get unprecedented accuracy in the predictions than previously possible. We also evaluate our model on the real events detected by the LIGO--Virgo collaboration and find that our network correctly classifies all of them, consistent with non-detection of lensing.