Data-Driven Reduced-Order Modeling of Spatiotemporal Chaos with Neural Ordinary Differential Equations

08/31/2021
by   Alec J. Linot, et al.
0

Dissipative partial differential equations that exhibit chaotic dynamics tend to evolve to attractors that exist on finite-dimensional manifolds. We present a data-driven reduced order modeling method that capitalizes on this fact by finding the coordinates of this manifold and finding an ordinary differential equation (ODE) describing the dynamics in this coordinate system. The manifold coordinates are discovered using an undercomplete autoencoder – a neural network (NN) that reduces then expands dimension. Then the ODE, in these coordinates, is approximated by a NN using the neural ODE framework. Both of these methods only require snapshots of data to learn a model, and the data can be widely and/or unevenly spaced. We apply this framework to the Kuramoto-Sivashinsky for different domain sizes that exhibit chaotic dynamics. With this system, we find that dimension reduction improves performance relative to predictions in the ambient space, where artifacts arise. Then, with the low-dimensional model, we vary the training data spacing and find excellent short- and long-time statistical recreation of the true dynamics for widely spaced data (spacing of  0.7 Lyapunov times). We end by comparing performance with various degrees of dimension reduction, and find a "sweet spot" in terms of performance vs. dimension.

READ FULL TEXT

page 16

page 20

research
01/11/2023

Dynamics of a data-driven low-dimensional model of turbulent minimal Couette flow

Because the Navier-Stokes equations are dissipative, the long-time dynam...
research
09/06/2020

OnsagerNet: Learning Stable and Interpretable Dynamics using a Generalized Onsager Principle

We propose a systematic method for learning stable and interpretable dyn...
research
05/01/2023

Autoencoders for discovering manifold dimension and coordinates in data from complex dynamical systems

While many phenomena in physics and engineering are formally high-dimens...
research
06/30/2023

Exact dimension reduction for rough differential equations

In this paper, practically computable low-order approximations of potent...
research
12/23/2020

Learning emergent PDEs in a learned emergent space

We extract data-driven, intrinsic spatial coordinates from observations ...
research
03/03/2023

Interpretable reduced-order modeling with time-scale separation

Partial Differential Equations (PDEs) with high dimensionality are commo...
research
11/23/2018

Estimating of the inertial manifold dimension for a chaotic attractor of complex Ginzburg-Landau equation using a neural network

Dimension of an inertial manifold for a chaotic attractor of spatially d...

Please sign up or login with your details

Forgot password? Click here to reset