Navigating Unknowns: Deep Learning Robustness for Gravitational Wave Signal Reconstruction

TL;DR

This paper introduces WaRe, a deep learning model for gravitational wave signal reconstruction that effectively handles unseen complex features and provides uncertainty estimates comparable to traditional methods.

Contribution

The paper presents WaRe, a novel deep learning framework capable of reconstructing gravitational wave signals with unseen parameters and estimating uncertainties, outperforming existing models in robustness.

Findings

WaRe accurately recovers unseen waveform features.

Uncertainty estimates from WaRe match benchmark algorithms.

Model demonstrates robustness on real gravitational wave events.

Abstract

We present a rapid and reliable deep learning-based method for gravitational wave signal reconstruction from elusive, generic binary black hole mergers in LIGO data. We demonstrate that our model, \texttt{AWaRe}, effectively recovers gravitational waves with parameters it has not encountered during training. This includes features like higher black hole masses, additional harmonics, eccentricity, and varied waveform systematics, which introduce complex modulations in the waveform's amplitudes and phases. The accurate reconstructions of these unseen signal characteristics demonstrates \texttt{AWaRe}'s ability to handle complex features in the waveforms. By directly incorporating waveform reconstruction uncertainty estimation into the \texttt{AWaRe} framework, we show that for real gravitational wave events, the uncertainties in \texttt{AWaRe}'s reconstructions align closely with those achieved by benchmark algorithms like BayesWave and coherent WaveBurst. The robustness of our model to real gravitational wave events and its ability to extrapolate to unseen data open new avenues for investigations in various aspects of gravitational wave astrophysics and data analysis, including tests of General Relativity and the enhancement of current gravitational wave search methodologies.