Learning orbital dynamics of binary black hole systems from gravitational wave measurements

TL;DR

This paper presents a neural network-based method to infer the equations of motion for binary black hole systems from gravitational wave data, capturing complex relativistic effects without prior models.

Contribution

It introduces a universal differential equation framework that learns BBH dynamics directly from waveform data, including relativistic phenomena, using physics-informed neural network optimization.

Findings

Successfully models BBH systems with various mass ratios and orbital configurations.

Captures relativistic effects like perihelion precession and radiation reaction.

Applicable to time spans longer than the training data.

Abstract

We introduce a gravitational waveform inversion strategy that discovers mechanical models of binary black hole (BBH) systems. We show that only a single time series of (possibly noisy) waveform data is necessary to construct the equations of motion for a BBH system. Starting with a class of universal differential equations parameterized by feed-forward neural networks, our strategy involves the construction of a space of plausible mechanical models and a physics-informed constrained optimization within that space to minimize the waveform error. We apply our method to various BBH systems including extreme and comparable mass ratio systems in eccentric and non-eccentric orbits. We show the resulting differential equations apply to time durations longer than the training interval, and relativistic effects, such as perihelion precession, radiation reaction, and orbital plunge, are automatically accounted for. The methods outlined here provide a new, data-driven approach to studying the dynamics of binary black hole systems.