DeepAI AI Chat
Log In Sign Up

Charts and atlases for nonlinear data-driven models of dynamics on manifolds

by   Daniel Floryan, et al.
University of Wisconsin-Madison

We introduce a method for learning minimal-dimensional dynamical models from high-dimensional time series data that lie on a low-dimensional manifold, as arises for many processes. For an arbitrary manifold, there is no smooth global coordinate representation, so following the formalism of differential topology we represent the manifold as an atlas of charts. We first partition the data into overlapping regions. Then undercomplete autoencoders are used to find low-dimensional coordinate representations for each region. We then use the data to learn dynamical models in each region, which together yield a global low-dimensional dynamical model. We apply this method to examples ranging from simple periodic dynamics to complex, nominally high-dimensional non-periodic bursting dynamics of the Kuramoto-Sivashinsky equation. We demonstrate that it: (1) can yield dynamical models of the lowest possible dimension, where previous methods generally cannot; (2) exhibits computational benefits including scalability, parallelizability, and adaptivity; and (3) separates state space into regions of distinct behaviours.


Decomposed Linear Dynamical Systems (dLDS) for learning the latent components of neural dynamics

Learning interpretable representations of neural dynamics at a populatio...

Deep learning delay coordinate dynamics for chaotic attractors from partial observable data

A common problem in time series analysis is to predict dynamics with onl...

Visualizing High Dimensional Dynamical Processes

Manifold learning techniques for dynamical systems and time series have ...

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

While many phenomena in physics and engineering are formally high-dimens...

Latent Dynamics Networks (LDNets): learning the intrinsic dynamics of spatio-temporal processes

Predicting the evolution of systems that exhibit spatio-temporal dynamic...

Twisty Takens: A Geometric Characterization of Good Observations on Dense Trajectories

In nonlinear time series analysis and dynamical systems theory, Takens' ...

Autoencoding for the 'Good Dictionary' of eigen pairs of the Koopman Operator

Reduced order modelling relies on representing complex dynamical systems...