A learning approach to the detection of gravitational wave transients

TL;DR

This paper introduces a novel machine learning-based method for detecting gravitational wave transients, which learns filter banks from training data without requiring explicit signal models, improving detection performance for poorly modeled signals.

Contribution

The paper proposes a non-parametric, data-driven approach to gravitational wave detection that learns filters directly from training data, bypassing the need for explicit probability density functions.

Findings

Applied to supernovae core collapse signals with simulated data

Achieved improved detection performance over traditional methods

Demonstrated effectiveness with real waveform catalogs

Abstract

We investigate the class of quadratic detectors (i.e., the statistic is a bilinear function of the data) for the detection of poorly modeled gravitational transients of short duration. We point out that all such detection methods are equivalent to passing the signal through a filter bank and linearly combine the output energy. Existing methods for the choice of the filter bank and of the weight parameters rely essentially on the two following ideas: (i) the use of the likelihood function based on a (possibly non-informative) statistical model of the signal and the noise, (ii) the use of Monte-Carlo simulations for the tuning of parametric filters to get the best detection probability keeping fixed the false alarm rate. We propose a third approach according to which the filter bank is "learned" from a set of training data. By-products of this viewpoint are that, contrarily to previous methods, (i) there is no requirement of an explicit description of the probability density function of the data when the signal is present and (ii) the filters we use are non-parametric. The learning procedure may be described as a two step process: first, estimate the mean and covariance of the signal with the training data; second, find the filters which maximize a contrast criterion referred to as deflection between the "noise only" and "signal+noise" hypothesis. The deflection is homogeneous to the signal-to-noise ratio and it uses the quantities estimated at the first step. We apply this original method to the problem of the detection of supernovae core collapses. We use the catalog of waveforms provided recently by Dimmelmeier et al. to train our algorithm. We expect such detector to have better performances on this particular problem provided that the reference signals are reliable.