Deep Learning Search for Gravitational Waves from Compact Binary Coalescence

Abstract

Gravitational-wave searches rely on a combination of methods, including matched filtering, coherent analyses, and more recent machine-learning-based pipelines. For compact binary coalescences --- where signals originate from the relativistic dynamics of compact objects --- matched filtering remains a central element, but its computational cost will increase substantially with the data volumes and parameter-space coverage required by next-generation interferometers such as the Einstein Telescope. Developing complementary strategies that reduce computational load while preserving detection performance is therefore essential. We investigate a hybrid approach that combines matched-filtering concepts with Convolutional Neural Networks, enabling efficient signal searches without relying on the usual ${\chi }^2$ rejection test. Using simulated data sets that include injected signals in Gaussian noise, transient noise, and physical effects not represented in the template bank --- such as eccentricity, precession and higher-order modes --- we show that the method achieves a detection efficiency comparable to or better than a standard matched-filtering search while offering a more resource-efficient pipeline in all the cases where the physics included in the signals were not represented in the template bank or when glitches were affecting the data. Conversely, the analysis also reveals some loss of detection capability for standard BNS/BBH searches in pure Gaussian noise. These results indicate that deep-learning-assisted searches can support sustainable gravitational-wave data analysis in future detector eras.