Stabilized neural ordinary differential equations for long-time forecasting of dynamical systems
Authors:
- Alec J. LinotALAlec J. Linot
- Joshua W. BurbyJBJoshua W. Burby
- Qi TangQTQi Tang
- Prasanna BalaprakashPBPrasanna Balaprakash
- Michael D. GrahamMGMichael D. Graham
- Romit MaulikRMRomit Maulik
Top Cited Papers
- 9 December 2022
- journal article
- research article
- Published by Elsevier in Journal of Computational Physics
- Vol. 474
Abstract
No abstract availableKeywords
All Related Versions
Funding Information
- Advanced Scientific Computing Research (DE-AC02–06CH11357)
- Fusion Energy Sciences
- U.S. Department of Energy
- Argonne National Laboratory
- Los Alamos National Laboratory
- Office of Science (20180756PRD4, DOE-FOA-2493)
This publication has 25 references indexed in Scilit:
- Global dissipativity and inertial manifolds for diffusive burgers equations with low-wavenumber instabilityDiscrete and Continuous Dynamical Systems, 2011
- Reservoir computing approaches to recurrent neural network trainingComputer Science Review, 2009
- Fourth-Order Time-Stepping for Stiff PDEsSIAM Journal on Scientific Computing, 2005
- Postprocessing the Galerkin Method: a Novel Approach to Approximate Inertial ManifoldsSIAM Journal on Numerical Analysis, 1998
- Identification of distributed parameter systems: A neural net based approachComputers & Chemical Engineering, 1998
- Long Short-Term MemoryNeural Computation, 1997
- Nonlinear Galerkin methods: The finite elements caseNumerische Mathematik, 1990
- The nonlinear Galerkin method in computational fluid dynamicsApplied Numerical Mathematics, 1990
- Spectral barriers and inertial manifolds for dissipative partial differential equationsJournal of Dynamics and Differential Equations, 1989
- On the computation of inertial manifoldsPhysics Letters A, 1988