A Deep Learning Powered Numerical Relativity Surrogate for Binary Black Hole Waveforms

TL;DR

This paper introduces DANSur, a neural network-based surrogate model for binary black hole waveforms that combines approximant data and numerical relativity data for rapid, accurate gravitational waveform generation suitable for parameter estimation.

Contribution

The paper presents a novel dual-stage training approach for neural network surrogates that improves speed and accuracy in gravitational waveform modeling.

Findings

Generates waveforms in under 20ms on GPU

Achieves mean mismatch with NR around 10^{-4}

Successfully integrated into parameter estimation workflows

Abstract

Gravitational-wave approximants are essential for gravitational-wave astronomy, allowing the coverage binary black hole parameter space for inference or match filtering without costly numerical relativity (NR) simulations, but generally trading some accuracy for computational efficiency. To reduce this trade-off, NR surrogate models can be constructed using interpolation within NR waveform space. We present a 2-stage training approach for neural network-based NR surrogate models. Initially trained on approximant-generated waveforms and then fine-tuned with NR data, these dual-stage artificial neural surrogate (\texttt{DANSur}) models offer rapid and competitively accurate waveform generation, generating millions in under 20ms on a GPU while keeping mean mismatches with NR around $10^{-4}$. Implemented in the \textsc{bilby} framework, we show they can be used for parameter estimation tasks.