Variational Autoencoders for Learning Nonlinear Dynamics of Physical Systems
arXiv:2012.03448
Abstract
We develop data-driven methods for incorporating physical information for priors to learn parsimonious representations of nonlinear systems arising from parameterized PDEs and mechanics. Our approach is based on Variational Autoencoders (VAEs) for learning from observations nonlinear state space models. We develop ways to incorporate geometric and topological priors through general manifold latent space representations. We investigate the performance of our methods for learning low dimensional representations for the nonlinear Burgers equation and constrained mechanical systems.
References in corpus (13)
- Auto-Encoding Variational Bayes
- Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
- Deep learning for universal linear embeddings of nonlinear dynamics
- Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
- Variational Encoding of Complex Dynamics
- Black box variational inference for state space models
- Physics-informed Autoencoders for Lyapunov-stable Fluid Flow Prediction
- Meshfree Methods on Manifolds for Hydrodynamic Flows on Curved Surfaces: A Generalized Moving Least-Squares (GMLS) Approach
- Physics-informed deep generative models
- Explorations in Homeomorphic Variational Auto-Encoding
- Time-series machine-learning error models for approximate solutions to parameterized dynamical systems
- Active Learning for Nonlinear System Identification with Guarantees
- Variational Autoencoders with Riemannian Brownian Motion Priors