Learning Inspiral-Merger-Ringdown Waveforms from a Post-Newtonian Baseline
gr-qc, astro-ph.HE
Submitted: 2026-09-24
Updated: 2026-09-24
Comments: 6 pages, 2 figures and 9 pages supplemental materials
License: http://creativecommons.org/licenses/by/4.0/
The gist: Modeling the full inspiral-merger-ringdown signal requires combining analytically controlled inspiral physics with the nonlinear strong-field information supplied by numerical relativity.
Terminology
Abstract
Modeling the full inspiral-merger-ringdown signal requires combining analytically controlled inspiral physics with the nonlinear strong-field information supplied by numerical relativity. We represent the numerical relativity contribution beyond an analytic inspiral waveform as residual amplitude and phase corrections. Retaining the leading-order frequency-domain amplitude and the 3.5 Post-Newtonian TaylorF2 phase, we use a Kolmogorov-Arnold network to learn these residual corrections from SXS waveforms. After training, the learned corrections are stored as explicit spline functions, so waveform evaluation no longer requires the network itself. On 75 simulations excluded from training and model selection, the model achieves a median flat-noise mismatch of 2.7 times10-5. Our results demonstrate a machine learning driven waveform modeling strategy in which numerical relativity augments, rather than replaces, analytically known waveform structure.
Sources
- Effective one-body approach to general relativistic two-body dynamics
- Transition from inspiral to plunge in binary black hole coalescences
- Inspiral-merger-ringdown multipolar waveforms of nonspinning black-hole binaries using the effective-one-body formalism
- Inspiral-merger-ringdown waveforms for black-hole binaries with non-precessing spins
- Frequency-domain gravitational waves from non-precessing black-hole binaries. I. New numerical waveforms and anatomy of the signal
- Frequency-domain gravitational waves from non-precessing black-hole binaries. II. A phenomenological model for the advanced detector era
- Fast and accurate prediction of numerical relativity waveforms from binary black hole coalescences using surrogate models
- A Numerical Relativity Waveform Surrogate Model for Generically Precessing Binary Black Hole Mergers
- Surrogate models for precessing binary black hole simulations with unequal masses
- Statistical Gravitational Waveform Models: What to Simulate Next?
- Reduced-order modeling with artificial neurons for gravitational-wave inference
- Regression methods in waveform modeling: a comparative study
- Machine Learning Gravitational Waves from Binary Black Hole Mergers
- Gravitational-wave surrogate models powered by artificial neural networks: The ANN-Sur for waveform generation
- Accelerating multimodal gravitational waveforms from precessing compact binaries with artificial neural networks
- Interpretable AI forecasting for numerical relativity waveforms of quasi-circular, spinning, non-precessing binary black hole mergers
- A Deep Learning Powered Numerical Relativity Surrogate for Binary Black Hole Waveforms
- Learning orbital dynamics of binary black hole systems from gravitational wave measurements
- Learning Post-Newtonian Corrections from Numerical Relativity
- KAN: Kolmogorov-Arnold Networks
Related papers
- Listening to the Horizon: Probing Near-Horizon Reflectivity with GW250114
- A Pairwise Surrogate for Gravitational-Wave Spectra from Highly Relativistic Vacuum Bubble Collisions
- Tests of General Relativity with Einstein Telescope
- A weakly modelled view of the joint compact-binary mass plane: population structure and spectral-siren cosmology
- Unitary quantum matter-bounce in a universe with a positive cosmological constant
- Nonreciprocal black holes with primary hair in beyond Horndeski gravity: Exact solutions and stability