Identification of Lensed Gravitational Waves with Deep Learning

TL;DR

This paper demonstrates that deep learning can effectively identify gravitational wave lensing signatures, particularly beating patterns caused by small lenses, aiding in the detection and analysis of lensed gravitational waves.

Contribution

The study introduces a deep learning approach for detecting lensing signatures in gravitational waves, especially for small lenses with short time delays, without relying on precise waveform templates.

Findings

Deep learning models can recognize lensed GW patterns in noisy spectrograms.

The method can distinguish lensed from unlensed GWs with high accuracy.

Potential to estimate physical and lensing parameters from detected signals.

Abstract

Similar to light, gravitational waves (GWs) can be lensed. Such lensing phenomena can magnify the waves, create multiple images observable as repeated events, and superpose several waveforms together, inducing potentially discernible patterns on the waves. In particular, when the lens is small, $\lesssim 10^5 M_\odot$, it can produce lensed images with time delays shorter than the typical gravitational-wave signal length that conspire together to form ``beating patterns''. We present a proof-of-principle study utilizing deep learning for identification of such a lensing signature. We bring the excellence of state-of-the-art deep learning models at recognizing foreground objects from background noises to identifying lensed GWs from noise present spectrograms. We assume the lens mass is around $10^3 M_\odot$ -- $10^5 M_\odot$, which can produce the order of millisecond time delays between two images of lensed GWs. We discuss the feasibility of distinguishing lensed GWs from unlensed ones and estimating physical and lensing parameters. Suggested method may be of interest to the study of more complicated lensing configurations for which we do not have accurate waveform templates.