Data-driven discovery of intrinsic dynamics

Abstract

Dynamical models underpin our ability to understand and predict the behavior of natural systems. Whether dynamical models are developed from first-principles derivations or from observational data, they are predicated on our choice of state variables. The choice of state variables is driven by convenience and intuition, and in the data-driven case the observed variables are often chosen to be the state variables. The dimensionality of these variables (and consequently the dynamical models) can be arbitrarily large, obscuring the underlying behavior of the system. In truth, these variables are often highly redundant and the system is driven by a much smaller set of latent intrinsic variables. In this study, we combine the mathematical theory of manifolds with the representational capacity of neural networks to develop a method that learns a system's intrinsic state variables directly from time series data, and also learns predictive models for their dynamics. What distinguishes our method is its ability to reduce data to the intrinsic dimensionality of the nonlinear manifold they live on. This ability is enabled by the concepts of charts and atlases from the theory of manifolds, whereby a manifold is represented by a collection of patches that are sewn together -- a necessary representation to attain intrinsic dimensionality. We demonstrate this approach on several high-dimensional systems with low-dimensional behavior. The resulting framework provides the ability to develop dynamical models of the lowest possible dimension, capturing the essence of a system.

27 pages + 15 pages Supplementary Information

References in corpus (2)

• Using Machine Learning to Replicate Chaotic Attractors and Calculate Lyapunov Exponents from Data
• Data-Driven Reduced-Order Modeling of Spatiotemporal Chaos with Neural Ordinary Differential Equations

Cited by in corpus (13)

• Nonlinear Model Reduction to Fractional and Mixed-Mode Spectral Submanifolds
• Data-driven low-dimensional dynamic model of Kolmogorov flow
• Interpretable statistical representations of neural population dynamics and geometry
• 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
• Finding emergence in data by maximizing effective information
• Physics-agnostic and Physics-infused machine learning for thin films flows: modeling, and predictions from small data
• Scientific machine learning in Hydrology: a unified perspective
• Dynamics of a Data-Driven Low-Dimensional Model of Turbulent Minimal Pipe Flow
• Learning the Latent dynamics of Fluid flows from High-Fidelity Numerical Simulations using Parsimonious Diffusion Maps
• Learning Continuous Network Emerging Dynamics from Scarce Observations via Data-Adaptive Stochastic Processes
• Learning effective good variables from physical data
• Solving continuum and rarefied flows using differentiable programming