Using physics-informed neural networks to compute quasinormal modes

Abstract

In recent years there has been an increased interest in neural networks, particularly with regard to their ability to approximate partial differential equations. In this regard, research has begun on so-called physics-informed neural networks (PINNs) which incorporate into their loss function the boundary conditions of the functions they are attempting to approximate. In this paper, we investigate the viability of obtaining the quasi-normal modes (QNMs) of non-rotating black holes in 4-dimensional space-time using PINNs, and we find that it is achievable using a standard approach that is capable of solving eigenvalue problems (dubbed the eigenvalue solver here). In comparison to the QNMs obtained via more established methods (namely, the continued fraction method and the 6th-order Wentzel, Kramer, Brillouin method) the PINN computations share the same degree of accuracy as these counterparts. In other words, our PINN approximations had percentage deviations as low as $(\delta {\omega }_{{}_{Re}},\delta {\omega }_{{}_{Im}})=(<0.01\%,<0.01\%)$. In terms of the time taken to compute QNMs to this accuracy, however, the PINN approach falls short, leading to our conclusion that the method is currently not to be recommended when considering overall performance.

arXiv comment43 pages, 12 figures

References in corpus (16)

• DeepXDE: A deep learning library for solving differential equations
• Quasinormal modes of black holes and black branes
• Quasi-Normal Modes of Stars and Black Holes
• Quasinormal modes of black holes: from astrophysics to string theory
• Quasinormal behavior of the D-dimensional Schwarzshild black hole and higher order WKB approach
• Testing the no-hair theorem with GW150914
• Higher order WKB formula for quasinormal modes and grey-body factors: recipes for quick and accurate calculations
• Quasi-Normal Modes of Schwarzschild Anti-De Sitter Black Holes: Electromagnetic and Gravitational Perturbations
• On the convergence of physics informed neural networks for linear second-order elliptic and parabolic type PDEs
• Quasinormal modes of the near extremal Schwarzschild-de Sitter black hole
• Hamiltonian neural networks for solving equations of motion
• Quasinormal modes of d-dimensional spherical black holes with a near extreme cosmological constant
• Constraints on quasi-normal-mode frequencies with LIGO-Virgo binary-black-hole observations
• A note on electromagnetic and gravitational perturbations of the Bardeen de Sitter black hole: quasinormal modes and greybody factors
• Scalar Perturbations of a Single-Horizon Regular Black Hole
• (Quasi)-exactly solvable quasinormal modes

Cited by in corpus (10)

• Solving the Teukolsky equation with physics-informed neural networks
• Applications of machine learning in gravitational wave research with current interferometric detectors
• Quasinormal Modes in Modified Gravity using Physics-Informed Neural Networks
• Hamiltonian Neural Networks approach to fuzzball geodesics
• Unraveling particle dark matter with Physics-Informed Neural Networks
• Physics-Informed Neural Network for Elastic Wave-Mode Separation
• Towards asteroseismology of neutron stars with physics-informed neural networks
• Neural Infalling Cloud Equations (NICE): Increasing the Efficacy of Subgrid Models and Scientific Equation Discovery using Neural ODEs and Symbolic Regression
• APRIL: Auxiliary Physically-Redundant Information in Loss -- A physics-informed framework for parameter estimation with a gravitational-wave case study
• Quasinormal spectra of a wormhole family: overtone features and a parameter-controlled redshift