Solving the Teukolsky equation with physics-informed neural networks

Abstract

We use physics-informed neural networks (PINNs) to compute the first quasi-normal modes of the Kerr geometry via the Teukolsky equation. This technique allows us to extract the complex frequencies and separation constants of the equation without the need for sophisticated numerical techniques, and with an almost immediate implementation under the \texttt{PyTorch} framework. We are able to compute the oscillation frequencies and damping times for arbitrary black hole spins and masses, with accuracy typically below the percentual level as compared to the accepted values in the literature. We find that PINN-computed quasi-normal modes are indistinguishable from those obtained through existing methods at signal-to-noise ratios (SNRs) larger than 100, making the former reliable for gravitational-wave data analysis in the mid term, before the arrival of third-generation detectors like LISA or the Einstein Telescope, where SNRs of $\mathcal{O}(1000)$ might be achieved.

12 pages, 7 figures. v2: Matches published version, minor typos corrected

References in corpus (7)

• Model Waveform Accuracy Standards for Gravitational Wave Data Analysis
• Quasinormal-mode spectrum of Kerr black holes and its geometric interpretation
• Matched-filtering and parameter estimation of ringdown waveforms
• Observational Black Hole Spectroscopy: A time-domain multimode analysis of GW150914
• Gravitational perturbations of the Kerr geometry: High-accuracy study
• Linear mode stability of Kerr-Newman and its quasinormal modes
• Using physics-informed neural networks to compute quasinormal modes

Cited by in corpus (13)

• Unveiling the optimization process of Physics Informed Neural Networks: How accurate and competitive can PINNs be?
• Shadow and quasinormal modes of the rotating Einstein-Euler-Heisenberg black holes
• Applications of machine learning in gravitational wave research with current interferometric detectors
• Modelling Force-Free Neutron Star Magnetospheres using Physics-Informed Neural Networks
• A Tutorial on the Use of Physics-Informed Neural Networks to Compute the Spectrum of Quantum Systems
• Solving the Pulsar Equation using Physics-Informed Neural Networks
• Quasinormal Modes in Modified Gravity using Physics-Informed Neural Networks
• Addressing the Non-perturbative Regime of the Quantum Anharmonic Oscillator by Physics-Informed Neural Networks
• Hamiltonian Neural Networks approach to fuzzball geodesics
• An approximate Riemann solver approach in Physics-Informed Neural Networks for hyperbolic conservation laws
• Towards asteroseismology of neutron stars with physics-informed neural networks
• Ringdown of a black hole sourced by a Burkert-density effective anisotropic source
• APRIL: Auxiliary Physically-Redundant Information in Loss -- A physics-informed framework for parameter estimation with a gravitational-wave case study