Data-driven discovery of intrinsic dynamics

Dynamical models underpin our ability to understand and predict the behaviour 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 data-driven cases, 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 behaviour 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, as well as 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 behaviour. The resulting framework provides the ability to develop dynamical models of the lowest possible dimension, capturing the essence of a system.