The presence of a massive body between the Earth and a gravitational-wave source will produce the so-called gravitational lensing effect. In the case of strong lensing, it leads to the observation of multiple deformed copies of the initial wave. Machine-learning (ML) models have been proposed for identifying these copies much faster than optimal Bayesian methods, as will be needed with the detection rate of next-generation detector. Most of these ML models are based on a time-frequency representation of the data that discards the phase information. We introduce a neural network that directly uses the time series data to retain the phase, limit the pre-processing time and keep a one-dimensional input. We show that our model is more efficient than the base model used on time-frequency maps at any False Alarm Rate (FPR), up to ∼5 times more for an FPR of 10−4. We also show that it is not significantly impacted by the choice of waveform model, by lensing-induced phase shifts and by reasonable errors on the merger time that induce a misalignment of the waves in the input.
@article{arxiv.2411.12453,
title = {Using time series to identify strongly-lensed gravitational waves with deep learning},
author = {Arthur Offermans and Tjonnie G. F. Li},
journal= {arXiv preprint arXiv:2411.12453},
year = {2024}
}