Fast-slow neural networks for learning singularly perturbed dynamical systems

DOI10.1016/J.JCP.2025.114090MaRDI QIDQ6935078zbMATH OpenFDO

Authors D. A. Serino, Allen Alvarez Loya, J. Burby, I. G. Kevrekidis, Qi Tang

Publication date 3 September 2025

Published in Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.JCP.2025.114090

zbMATH Keywords

closuresmodel reductionsingularly perturbed dynamical systemsslow manifold

Mathematics Subject Classification ID

Numerical solution of singularly perturbed problems involving ordinary differential equations (65L11) Numerical problems in dynamical systems (65P99) Artificial neural networks and deep learning (68T07)

Cites work

• A computational strategy for multiscale systems with applications to Lorenz 96 model
• A fully discrete nonlinear Galerkin method for the 3D Navier-Stokes equations
• A nonlinear Galerkin method for the Navier-Stokes equations
• A note on Hurwitz stability of matrices
• A parallel cut-cell algorithm for the free-boundary Grad-Shafranov problem
• A survey of projection-based model reduction methods for parametric dynamical systems
• Approximate inertial manifolds for the Kuramoto-Sivashinsky equation: Analysis and computations
• Approximation by superpositions of a sigmoidal function
• Data-based stochastic model reduction for the Kuramoto-Sivashinsky equation
• Data-driven reduced-order modeling of spatiotemporal chaos with neural ordinary differential equations
• Diffusion maps
• Do inertial manifolds apply to turbulence?
• Explicit construction of an inertial manifold for a reaction diffusion equation
• Exponential tracking and approximation of inertial manifolds for dissipative nonlinear equations
• Geometric singular perturbation theory for ordinary differential equations
• Hilbert's 6th problem: exact and approximate hydrodynamic manifolds for kinetic equations
• scientific article; zbMATH DE number 799793 (Why is no real title available?)
• Implicit-explicit Runge-Kutta schemes and applications to hyperbolic systems with relaxation
• Induced trajectories and approximate inertial manifolds
• Inertial manifolds for nonlinear evolutionary equations
• INVITED: Slow manifold reduction for plasma science
• Learning data-driven discretizations for partial differential equations
• Matrix Analysis
• Matrix Analysis and Computations
• Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders
• Model reduction via parametrized locally invariant manifolds: Some examples
• Nonlinear dimensionality reduction then and now: AIMs for dissipative PDEs in the ML era
• Nonlinear normal modes and spectral submanifolds: existence, uniqueness and use in model reduction
• On approximate inertial manifolds to the Navier-Stokes equations
• On the kinetic theory of rarefied gases
• Slow invariant manifolds of singularly perturbed systems via physics-informed machine learning
• Stabilized neural ordinary differential equations for long-time forecasting of dynamical systems
• Sympnets: intrinsic structure-preserving symplectic networks for identifying Hamiltonian systems

This page was built for publication: Fast-slow neural networks for learning singularly perturbed dynamical systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6935078)