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

Abstract

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.

References in corpus (6)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Applied Koopmanism
• Hyperbolicity and the effective dimension of spatially-extended dissipative systems
• Reduction of SO(2) symmetry for spatially extended dynamical systems
• Turbulence forecasting via Neural ODE
• Reduced-order Model for Fluid Flows via Neural Ordinary Differential Equations

Cited by in corpus (11)

• Data-driven discovery of intrinsic dynamics
• Combining physics-based and data-driven models: advancing the frontiers of research with Scientific Machine Learning
• Data-driven low-dimensional dynamic model of Kolmogorov flow
• Data-driven control of spatiotemporal chaos with reduced-order neural ODE-based models and reinforcement learning
• Deep learning delay coordinate dynamics for chaotic attractors from partial observable data
• Data-driven state-space and Koopman operator models of coherent state dynamics on invariant manifolds
• Neural Dynamical Operator: Continuous Spatial-Temporal Model with Gradient-Based and Derivative-Free Optimization Methods
• Real-time forecasting of chaotic dynamics from sparse data and autoencoders
• Dynamics of a Data-Driven Low-Dimensional Model of Turbulent Minimal Pipe Flow
• Elastoinertial turbulence: Data-driven reduced-order model based on manifold dynamics
• Data-driven guessing and gluing of unstable periodic orbits