Deep Learning-Based Detection of Gravitational Wave Signals in Noisy Time-Series Data

Read full text Summarise with VIRAT
Authors: deng
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The detection of gravitational waves (GWs) from compact binary coalescences has become a cornerstone of modern astrophysics, yet remains challenging due to the presence of strong, non-stationary detector noise. In this work, we investigate the feasibility of using deep learning techniques for gravitational wave signal detection in noisy time-series data. We develop a one-dimensional convolutional neural network (1D CNN) and evaluate its performance on a simulated dataset consisting of chirp-like waveforms embedded in Gaussian noise. The model is trained to distinguish between signal-present and noise-only samples in a binary classification framework. Our results show that the proposed model achieves a validation accuracy of approximately $80\%$, demonstrating its ability to identify weak transient signals in noise-dominated environments. Despite the low signal-to-noise ratio (SNR), the network is able to extract non-trivial temporal features associated with chirp-like structures, indicating the effectiveness of data-driven approaches in this context. While the present study is based on simplified simulated data, it provides a proof-of-concept demonstration of the applicability of deep learning methods to gravitational wave data analysis. These results suggest that such approaches may serve as computationally efficient complements to traditional matched-filtering techniques, with potential applications in rapid signal detection and real-time multimessenger astrophysics.

Fields of Study & Subjects

Pulsars and Gravitational Waves Research Seismology and Earthquake Studies Gamma-ray bursts and supernovae

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
21 March 2026
Language
EN