Time-series learning of latent-space dynamics for reduced-order model closure
Preprint
Abstract
We study the performance of long short-term memory networks (LSTMs) and neural ordinary differential equations (NODEs) in learning latent-space representations of dynamical equations for an advection-dominated problem given by the viscous Burgers equation. Our formulation is devised in a non-intrusive manner with an equation-free evolution of dynamics in a reduced space with the latter being obtained through a proper orthogonal decomposition. In addition, we leverage the sequential nature of learning for both LSTMs and NODEs to demonstrate their capability for closure in systems which are not completely resolved in the reduced space. We assess our hypothesis for two advection-dominated problems given by the viscous Burgers equation. It is observed that both LSTMs and NODEs are able to reproduce the effects of the absent scales for our test cases more effectively than intrusive dynamics evolution through a Galerkin projection. This result empirically suggests that time-series learning techniques implicitly leverage a memory kernel for coarse-grained system closure as is suggested through the Mori-Zwanzig formalism.Keywords
All Related Versions
This publication has 30 references indexed in Scilit:
- Deep Neural Networks Motivated by Partial Differential EquationsJournal of Mathematical Imaging and Vision, 2019
- Physically constrained data‐driven correction for reduced‐order modeling of fluid flowsInternational Journal for Numerical Methods in Fluids, 2018
- Neural network closures for nonlinear model order reductionAdvances in Computational Mathematics, 2018
- Explicit and implicit LES closures for Burgers turbulenceJournal of Computational and Applied Mathematics, 2018
- An evolve‐then‐filter regularized reduced order model for convection‐dominated flowsInternational Journal for Numerical Methods in Fluids, 2017
- Statistics in Function Space2016
- Principal interval decomposition framework for POD reduced‐order modeling of convective Boussinesq flowsInternational Journal for Numerical Methods in Fluids, 2015
- Supremizer stabilization of POD–Galerkin approximation of parametrized steady incompressible Navier–Stokes equationsInternational Journal for Numerical Methods in Engineering, 2014
- Proper orthogonal decomposition closure models for turbulent flows: A numerical comparisonComputer Methods in Applied Mechanics and Engineering, 2012
- Efficient non‐linear model reduction via a least‐squares Petrov–Galerkin projection and compressive tensor approximationsInternational Journal for Numerical Methods in Engineering, 2010