Learning subgrid-scale models with neural ordinary differential equations

DOI10.1016/j.compfluid.2023.105919zbMath1521.65059arXiv2212.09967OpenAlexW4372311799MaRDI QIDQ6160037

Shinhoo Kang, Emil M. Constantinescu

Publication date: 23 June 2023

Published in: Computers and Fluids (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2212.09967

zbMATH Keywords

discontinuous Galerkin methodaccelerationcouplingmachine learningneural ordinary differential equationsLorenz 96

Mathematics Subject Classification ID

Numerical methods for initial value problems involving ordinary differential equations (65L05)

Cites Work

• Runge-Kutta pairs of order \(5(4)\) satisfying only the first column simplifying assumption
• A family of embedded Runge-Kutta formulae
• Neural network closures for nonlinear model order reduction
• Stabilized neural ordinary differential equations for long-time forecasting of dynamical systems
• Explicit and implicit LES closures for Burgers turbulence
• Accelerating high order discontinuous Galerkin solvers using neural networks: 1D Burgers' equation
• Can the dynamic eddy-viscosity class of subgrid-scale models capture inertial-range properties of Burgers turbulence?
• Subgrid modelling studies with Burgers’ equation
• Burgulence
• Neural ODEs as the deep limit of ResNets with constant weights

This page was built for publication: Learning subgrid-scale models with neural ordinary differential equations