Journal of Cosmology and Astroparticle Physics
https://doi.org/10.1088/1475-7516/2025/10/028
Elahe Khalouei ,a,∗ Cristiano G. Sabiu ,b,∗ Hyung Mok Lee a and A. Gopakumar c
a Astronomy Research Center, Research Institute of Basic Sciences, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, Korea
b Natural Science Research Institute, University of Seoul, 163 Seoulsiripdae-ro, Dongdaemun-gu, Seoul 02504, Republic of Korea
c Department of Astronomy and Astrophysics, Tata Institute of Fundamental Research, Mumbai 400005, India
Abstract: Initial orbital eccentricities of gravitational wave (GW) events associated with merging binary black holes (BBHs) should provide clues to their formation scenarios, mainly because various BBH formation channels predict distinct eccentricity distributions. However, searching for inspiral GWs from eccentric BBHs is computationally challenging due to sophisticated approaches to model such GW events. This ensures that Bayesian parameter estimation methods to characterize such events are computationally daunting. These considerations influenced us to propose a novel approach to identify and characterize eccentric BBH events in the LIGO-Virgo-KAGRA (LVK) collaboration data sets that leverages external attention transformer models. Employing simulated data that mimic LIGO O4 run, eccentric inspiral events modeled by an effective-one-body numerical- relativity waveform family, we show the effectiveness of our approach. By integrating this transformer-based framework with a convolutional neural network (CNN) architecture, we provide efficient way to identify eccentric BBH GW events and accurately characterize their source properties.
Keywords: gravitational waves / experiments, Machine learning
