Deep learning delay coordinate dynamics for chaotic attractors from partial observable data
arXiv:2211.11061 · doi:10.1103/PhysRevE.107.034215
Abstract
A common problem in time series analysis is to predict dynamics with only scalar or partial observations of the underlying dynamical system. For data on a smooth compact manifold, Takens theorem proves a time delayed embedding of the partial state is diffeomorphic to the attractor, although for chaotic and highly nonlinear systems learning these delay coordinate mappings is challenging. We utilize deep artificial neural networks (ANNs) to learn discrete discrete time maps and continuous time flows of the partial state. Given training data for the full state, we also learn a reconstruction map. Thus, predictions of a time series can be made from the current state and several previous observations with embedding parameters determined from time series analysis. The state space for time evolution is of comparable dimension to reduced order manifold models. These are advantages over recurrent neural network models, which require a high dimensional internal state or additional memory terms and hyperparameters. We demonstrate the capacity of deep ANNs to predict chaotic behavior from a scalar observation on a manifold of dimension three via the Lorenz system. We also consider multivariate observations on the Kuramoto-Sivashinsky equation, where the observation dimension required for accurately reproducing dynamics increases with the manifold dimension via the spatial extent of the system.
References in corpus (32)
- Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
- Machine Learning for Fluid Mechanics
- Koopman invariant subspaces and finite linear representations of nonlinear dynamical systems for control
- Chaos as an Intermittently Forced Linear System
- Sparse identification of nonlinear dynamics for model predictive control in the low-data limit
- The Physics of Climate Variability and Climate Change
- Nonlinear time-series analysis revisited
- Data-Driven Forecasting of High-Dimensional Chaotic Systems with Long Short-Term Memory Networks
- Combining data assimilation and machine learning to emulate a dynamical model from sparse and noisy observations: a case study with the Lorenz 96 model
- Applying deep reinforcement learning to active flow control in turbulent conditions
- Time lagged ordinal partition networks for capturing dynamics of continuous dynamical systems
- Data-driven parameterization of the generalized Langevin equation
- Data-driven non-Markovian closure models
- Symmetry Decomposition of Chaotic Dynamics
- Data-driven discovery of intrinsic dynamics
- Deep learning to discover and predict dynamics on an inertial manifold
- Hyperbolicity and the effective dimension of spatially-extended dissipative systems
- Stabilized Neural Ordinary Differential Equations for Long-Time Forecasting of Dynamical Systems
- Nonlinear stochastic modeling with Langevin regression
- On the Structure of Time-delay Embedding in Linear Models of Non-linear Dynamical Systems
- Machine Learning for Prediction with Missing Dynamics
- Multivariate phase space reconstruction by nearest neighbor embedding with different time delays
- Data-Driven Reduced-Order Modeling of Spatiotemporal Chaos with Neural Ordinary Differential Equations
- State estimation in turbulent channel flow from limited observations
- Combining machine learning and data assimilation to forecast dynamical systems from noisy partial observations
- A unified and automated approach to attractor reconstruction
- Estimating dimension of inertial manifold from unstable periodic orbits
- Learning Latent Dynamics for Partially-Observed Chaotic Systems
- Data-driven control of spatiotemporal chaos with reduced-order neural ODE-based models and reinforcement learning
- Modeling of Missing Dynamical Systems: Deriving Parametric Models using a Nonparametric Framework
- Bounded nonlinear forecasts of partially observed geophysical systems with physics-constrained deep learning
- Reconstruction of Protein Structures from Single-Molecule Time Series