ARCHIVES

Gravitational waves (GWs), predicted by general relativity, are ripples in spacetime generated by massive astrophysical events such as binary neutron star mergers and black hole collisions. Traditional detection techniques, such as matched filtering used in detectors like LIGO, are computationally intensive and less robust in noisy environments. This paper proposes a machine learning-based framework for detecting gravitational wave signatures from Gamma-Ray Burst (GRB) data obtained from Swift BAT. The methodology integrates data preprocessing using HEASoft, feature extraction via Fourier Transform, and classification using supervised learning algorithms. Experimental results demonstrate improved detection accuracy, reduced computational cost, and enhanced robustness compared to traditional methods. The study highlights the potential of artificial intelligence in advancing gravitational wave astronomy.