Sequence modeling of higher-order wave modes of binary black hole mergers

Abstract

Higher-order gravitational wave modes from quasi-circular, spinning, non-precessing binary black hole mergers encode key information about these systems' nonlinear dynamics. We model these waveforms using transformer architectures, targeting the evolution from late inspiral through ringdown. Our data is derived from the \texttt{NRHybSur3dq8} surrogate model, which includes spherical harmonic modes up to $\ell \le 4$ (excluding $(4,0)$, $(4,\pm 1)$ and including $(5,5)$ modes). These waveforms span mass ratios $q\le 8$, spin components $s_{1,2}^z\in [-0.8,0.8]$, and inclination angles $\theta \in [0,\pi ]$. The model processes input data over the time interval $t\in [-5000\text{M},-100\text{M})$ and generates predictions for the plus and cross polarizations, $(h_{+},h_{\times })$, over the interval $t\in [-100\text{M},130\text{M}]$. Utilizing 16 NVIDIA A100 GPUs on the Delta supercomputer, we trained the transformer model in 15 hours on over 14 million samples. The model's performance was evaluated on a test dataset of 840,000 samples, achieving mean and median overlap scores of 0.996 and 0.997, respectively, relative to the surrogate-based ground truth signals. We further benchmark the model on numerical relativity waveforms from the SXS catalog, finding that it generalizes well to out-of-distribution systems, capable of reproducing the dynamics of systems with mass ratios up to $q=15$ and spin magnitudes up to 0.998, with a median overlap of 0.969 across 521 NR waveforms and up to 0.998 in face-on/off configurations. These results demonstrate that transformer-based models can capture the nonlinear dynamics of binary black hole mergers with high accuracy, even outside the surrogate training domain, enabling fast sequence modeling of higher-order wave modes.

32 pages, 2 appendices, 17 figures

References in corpus (45)

• GW190521: A Binary Black Hole Merger with a Total Mass of $150M_{\odot }$
• Properties of the Binary Black Hole Merger GW150914
• An improved effective-one-body model of spinning, nonprecessing binary black holes for the era of gravitational-wave astrophysics with advanced detectors
• Angular Resolution of the LISA Gravitational Wave Detector
• The SXS Collaboration catalog of binary black hole simulations
• Inspiral, merger and ringdown of unequal mass black hole binaries: a multipolar analysis
• Surrogate models for precessing binary black hole simulations with unequal masses
• High-accuracy comparison of numerical relativity simulations with post-Newtonian expansions
• Deep Learning for Real-time Gravitational Wave Detection and Parameter Estimation: Results with Advanced LIGO Data
• Spinning-black-hole binaries: The orbital hang up
• Surrogate model of hybridized numerical relativity binary black hole waveforms
• Real-time gravitational-wave science with neural posterior estimation
• Matching matched filtering with deep networks in gravitational-wave astronomy
• Fast prediction and evaluation of gravitational waveforms using surrogate models
• Glitch Classification and Clustering for LIGO with Deep Transfer Learning
• Deep Transfer Learning: A new deep learning glitch classification method for advanced LIGO
• Enhancing Gravitational-Wave Science with Machine Learning
• Gravitational-wave parameter estimation with autoregressive neural network flows
• Simulations of black-hole binaries with unequal masses or non-precessing spins: accuracy, physical properties, and comparison with post-Newtonian results
• Accelerated, Scalable and Reproducible AI-driven Gravitational Wave Detection
• The Current Status of Binary Black Hole Simulations in Numerical Relativity
• Gravitational-wave surrogate models powered by artificial neural networks: The ANN-Sur for waveform generation
• Comparing Gravitational Waveform Extrapolation to Cauchy-Characteristic Extraction in Binary Black Hole Simulations
• Impact of Higher-order Modes on the Detection of Binary Black Hole Coalescences
• Fixing the BMS Frame of Numerical Relativity Waveforms
• Deep learning for gravitational wave forecasting of neutron star mergers
• Numerical relativity surrogate model with memory effects and post-Newtonian hybridization
• Convolutional neural networks for the detection of the early inspiral of a gravitational-wave signal
• Deep Residual Networks for Gravitational Wave Detection
• Assessing the model waveform accuracy of gravitational waves
• Transition from Inspiral to Plunge: A Complete Near-Extremal Trajectory and Associated Waveform
• Compact Binary Waveform Center-of-Mass Corrections
• Generalized Approach to Matched Filtering using Neural Networks
• Inference-optimized AI and high performance computing for gravitational wave detection at scale
• Gravitational wave populations and cosmology with neural posterior estimation
• Measuring properties of primordial black hole mergers at cosmological distances: effect of higher order modes in gravitational waves
• Deep Learning with Quantized Neural Networks for Gravitational Wave Forecasting of Eccentric Compact Binary Coalescence
• New Gravitational Wave Discoveries Enabled by Machine Learning
• Applications of machine learning in gravitational wave research with current interferometric detectors
• Interpretable AI forecasting for numerical relativity waveforms of quasi-circular, spinning, non-precessing binary black hole mergers
• Deep Learning Model on Gravitational Waveforms in Merging and Ringdown Phases of Binary Black Hole Coalescences
• Astroconformer: The Prospects of Analyzing Stellar Light Curves with Transformer-Based Deep Learning Models
• Black hole mergers as tracers of spinning massive black hole and galaxy populations in the OBELISK simulation
• Simulating binary black hole mergers using discontinuous Galerkin methods
• A Deep Learning Powered Numerical Relativity Surrogate for Binary Black Hole Waveforms