Transfer Learning Adapts to Changing PSD in Gravitational Wave Data

TL;DR

This paper presents a transfer learning-based approach with a simplified architecture and novel training methodology that effectively detects gravitational waves in noisy data, adapting rapidly to changing noise conditions with high accuracy.

Contribution

It introduces a new transfer learning method with a simplified model architecture and training strategy for real-time gravitational wave detection amidst complex, evolving noise.

Findings

Achieves over 99% accuracy in non-white noise scenarios

Demonstrates rapid adaptation to changing noise PSD with few epochs

Addresses scalability and reliability issues of previous AI methods

Abstract

The detection of gravitational waves has opened unparalleled opportunities for observing the universe, particularly through the study of black hole inspirals. These events serve as unique laboratories to explore the laws of physics under conditions of extreme energies. However, significant noise in gravitational wave (GW) data from observatories such as Advanced LIGO and Virgo poses major challenges in signal identification. Traditional noise suppression methods often fall short in fully addressing the non-Gaussian effects in the data, including the fluctuations in noise power spectral density (PSD) over short time intervals. These challenges have led to the exploration of an AI approach that, while overcoming previous obstacles, introduced its own challenges, such as scalability, reliability issues, and the vanishing gradient problem. Our approach addresses these issues through a simplified architecture. To compensate for the potential limitations of a simpler model, we have developed a novel training methodology that enables it to accurately detect gravitational waves amidst highly complex noise. Employing this strategy, our model achieves over 99% accuracy in non-white noise scenarios and shows remarkable adaptability to changing noise PSD conditions. By leveraging the principles of transfer learning, our model quickly adapts to new noise profiles with just a few epochs of fine-tuning, facilitating real-time applications in dynamically changing noise environments.