Improved deep learning techniques in gravitational-wave data analysis

Abstract

In recent years, convolutional neural network (CNN) and other deep learning models have been gradually introduced into the area of gravitational-wave (GW) data processing. Compared with the traditional matched-filtering techniques, CNN has significant advantages in efficiency in GW signal detection tasks. In addition, matched-filtering techniques are based on the template bank of the existing theoretical waveform, which makes it difficult to find GW signals beyond theoretical expectation. In this paper, based on the task of GW detection of binary black holes, we introduce the optimization techniques of deep learning, such as batch normalization and dropout, to CNN models. Detailed studies of model performance are carried out. Through this study, we recommend to use batch normalization and dropout techniques in CNN models in GW signal detection tasks. Furthermore, we investigate the generalization ability of CNN models on different parameter ranges of GW signals. We point out that CNN models are robust to the variation of the parameter range of the GW waveform. This is a major advantage of deep learning models over matched-filtering techniques.

13 pages, 11 figures; accepted by PRD

References in corpus (10)

• Deep Learning in Neural Networks: An Overview
• GW170817: Observation of Gravitational Waves from a Binary Neutron Star Inspiral
• Popular Ensemble Methods: An Empirical Study
• GW190814: Gravitational Waves from the Coalescence of a 23 M${}_{\odot }$ Black Hole with a 2.6 M${}_{\odot }$ Compact Object
• GW190521: A Binary Black Hole Merger with a Total Mass of $150M_{\odot }$
• An improved effective-one-body model of spinning, nonprecessing binary black holes for the era of gravitational-wave astrophysics with advanced detectors
• BayesWave: Bayesian Inference for Gravitational Wave Bursts and Instrument Glitches
• Validating the effective-one-body model of spinning, precessing binary black holes against numerical relativity
• Validating the Effective-One-Body Numerical-Relativity Waveform Models for Spin-aligned Binary Black Holes along Eccentric Orbits
• Using Deep Learning to Localize Gravitational Wave Sources