• Corpus ID: 202541231

A Koopman-based framework for forecasting the spatiotemporal evolution of chaotic dynamics with nonlinearities modeled as exogenous forcings

@article{Khodkar2019AKF,
  title={A Koopman-based framework for forecasting the spatiotemporal evolution of chaotic dynamics with nonlinearities modeled as exogenous forcings},
  author={M. A. Khodkar and Pedram Hassanzadeh and Athanasios C. Antoulas},
  journal={arXiv: Fluid Dynamics},
  year={2019}
}
We introduce a data-driven method and shows its skills for spatiotemporal prediction of high-dimensional chaotic dynamics and turbulence. The method is based on a finite-dimensional approximation of the Koopman operator where the observables are vector-valued and delay-embedded, and the nonlinearities are treated as external forcings. The predictive capabilities of the method are demonstrated for well-known prototypes of chaos such as the Kuramoto-Sivashinsky equation and Lorenz-96 system, for… 
Recurrent neural networks and Koopman-based frameworks for temporal predictions in turbulence
TLDR
This work proposes a stopping criterion based on the computed statistics which effectively avoids overfitting to instantaneous predictions at the cost of deteriorated statistics, and suggests that a new loss function, including the averaged behavior of the flow as well as the instantaneous predictions, may lead to an improved generalization ability of the network.
Data-driven modeling of the wake behind a wind turbine array
The wake flow in a wind turbine array boundary layer is described using the Koopman operator. Dynamics of the flow are decomposed into the linear and forcing terms, and the low-energy delay
Predicting the temporal dynamics of turbulent channels through deep learning
The success of recurrent neural networks (RNNs) has been demonstrated in many applications related to turbulence, including flow control, optimization, turbulent features reproduction as well as
KERNEL ANALOG FORECASTING: MULTISCALE TEST PROBLEMS\ast
TLDR
Kernel analog forecasting methods are studied from the perspective of data generated by multiscale dynamical systems, using both averaging and homogenization to provide guidance for the interpretation of data-driven prediction methods when used in practice.
Kernel Analog Forecasting: Multiscale Test Problems
TLDR
Kernel analog forecasting methods are studied from the perspective of data generated by multiscale dynamical systems to provide guidance for the interpretation of data-driven prediction methods when used in practice.
Two methods to approximate the Koopman operator with a reservoir computer.
TLDR
This paper proposes two novel methods based on a reservoir computer to train the dictionary that rely solely on linear convex optimization and illustrates the efficiency of the method with several numerical examples in the context of data reconstruction, prediction, and computation of the Koopman operator spectrum.
Deep Neural Networks for Nonlinear Model Order Reduction of Unsteady Flows
TLDR
The proposed autoencoder-LSTM method is compared with non-intrusive reduced order models based on dynamic mode decomposition (DMD) and proper orthogonal decomposition and shown to be considerably capable of predicting fluid flow evolution.

References

SHOWING 1-10 OF 58 REFERENCES
Data-driven forecasting of high-dimensional chaotic systems with long short-term memory networks
TLDR
A data-driven forecasting method for high-dimensional chaotic systems using long short-term memory (LSTM) recurrent neural networks and a hybrid architecture, extending the LSTM with a mean stochastic model (MSM–L STM), is proposed to ensure convergence to the invariant measure.
Model-Free Prediction of Large Spatiotemporally Chaotic Systems from Data: A Reservoir Computing Approach.
We demonstrate the effectiveness of using machine learning for model-free prediction of spatiotemporally chaotic systems of arbitrarily large spatial extent and attractor dimension purely from
Chaos as an intermittently forced linear system
TLDR
A universal, data-driven decomposition of chaos as an intermittently forced linear system is presented, combining delay embedding and Koopman theory to decompose chaotic dynamics into a linear model in the leading delay coordinates with forcing by low-energy delay coordinates.
A data-driven Koopman model predictive control framework for nonlinear flows
The Koopman operator theory is an increasingly popular formalism of dynamical systems theory which enables analysis and prediction of the nonlinear dynamics from measurement data. Building on the
A Data–Driven Approximation of the Koopman Operator: Extending Dynamic Mode Decomposition
TLDR
This approach is an extension of dynamic mode decomposition (DMD), which has been used to approximate the Koopman eigenvalues and modes, and if the data provided to the method are generated by a Markov process instead of a deterministic dynamical system, the algorithm approximates the eigenfunctions of the Kolmogorov backward equation.
A variational approach to probing extreme events in turbulent dynamical systems
TLDR
It is found that the intermittent bursts of the energy dissipation are independent of the external forcing and are instead caused by the spontaneous transfer of energy from large scales to the mean flow via nonlinear triad interactions.
Spectral Properties of Dynamical Systems, Model Reduction and Decompositions
In this paper we discuss two issues related to model reduction of deterministic or stochastic processes. The first is the relationship of the spectral properties of the dynamics on the attractor of
Data-driven prediction strategies for low-frequency patterns of North Pacific climate variability
The North Pacific exhibits patterns of low-frequency variability on the intra-annual to decadal time scales, which manifest themselves in both model data and the observational record, and prediction
...
1
2
3
4
5
...