Extended dynamic mode decomposition with dictionary learning: a data-driven adaptive spectral decomposition of the Koopman operator

Abstract

Numerical approximation methods for the Koopman operator have advanced considerably in the last few years. In particular, data-driven approaches such as dynamic mode decomposition (DMD) and its generalization, the extended-DMD (EDMD), are becoming increasingly popular in practical applications. The EDMD improves upon the classical DMD by the inclusion of a flexible choice of dictionary of observables that spans a finite dimensional subspace on which the Koopman operator can be approximated. This enhances the accuracy of the solution reconstruction and broadens the applicability of the Koopman formalism. Although the convergence of the EDMD has been established, applying the method in practice requires a careful choice of the observables to improve convergence with just a finite number of terms. This is especially difficult for high dimensional and highly nonlinear systems. In this paper, we employ ideas from machine learning to improve upon the EDMD method. We develop an iterative approximation algorithm which couples the EDMD with a trainable dictionary represented by an artificial neural network. Using the Duffing oscillator and the Kuramoto Sivashinsky PDE as examples, we show that our algorithm can effectively and efficiently adapt the trainable dictionary to the problem at hand to achieve good reconstruction accuracy without the need to choose a fixed dictionary a priori. Furthermore, to obtain a given accuracy we require fewer dictionary terms than EDMD with fixed dictionaries. This alleviates an important shortcoming of the EDMD algorithm and enhances the applicability of the Koopman framework to practical problems.

References in corpus (15)

• Discovering governing equations from data: Sparse identification of nonlinear dynamical systems
• An overview of gradient descent optimization algorithms
• A Data-Driven Approximation of the Koopman Operator: Extending Dynamic Mode Decomposition
• On Dynamic Mode Decomposition: Theory and Applications
• Linear predictors for nonlinear dynamical systems: Koopman operator meets model predictive control
• Applied Koopmanism
• Koopman invariant subspaces and finite linear representations of nonlinear dynamical systems for control
• On Convergence of Extended Dynamic Mode Decomposition to the Koopman Operator
• Data-driven model reduction and transfer operator approximation
• Non-strongly-convex smooth stochastic approximation with convergence rate O(1/n)
• Isostables, isochrons, and Koopman spectrum for the action-angle representation of stable fixed point dynamics
• Variational Koopman models: slow collective variables and molecular kinetics from short off-equilibrium simulations
• On the correspondence between Koopman mode decomposition, resolvent mode decomposition, and invariant solutions of the Navier-Stokes equations
• A Kernel-Based Approach to Data-Driven Koopman Spectral Analysis
• Data Fusion via Intrinsic Dynamic Variables: An Application of Data-Driven Koopman Spectral Analysis

Cited by in corpus (92)

• Machine Learning for Fluid Mechanics
• Deep learning for universal linear embeddings of nonlinear dynamics
• Machine learning for molecular simulation
• Data-driven discovery of coordinates and governing equations
• Data-driven approximation of the Koopman generator: Model reduction, system identification, and control
• Lift & Learn: Physics-informed machine learning for large-scale nonlinear dynamical systems
• Deep Neural Networks with Koopman Operators for Modeling and Control of Autonomous Vehicles
• Deep Neural Networks for Nonlinear Model Order Reduction of Unsteady Flows
• Transformers for Modeling Physical Systems
• On Explaining the Surprising Success of Reservoir Computing Forecaster of Chaos? The Universal Machine Learning Dynamical System with Contrasts to VAR and DMD
• Discovery of Nonlinear Multiscale Systems: Sampling Strategies and Embeddings
• Deep Learning in Deterministic Computational Mechanics
• Physics-Informed Probabilistic Learning of Linear Embeddings of Non-linear Dynamics With Guaranteed Stability
• Graph Dynamical Networks for Unsupervised Learning of Atomic Scale Dynamics in Materials
• Assessment of unsteady flow predictions using hybrid deep learning based reduced order models
• Data-Driven Model Predictive Control using Interpolated Koopman Generators
• Uniformly Accurate Machine Learning Based Hydrodynamic Models for Kinetic Equations
• Residual Dynamic Mode Decomposition: Robust and verified Koopmanism
• Sparsity-promoting algorithms for the discovery of informative Koopman invariant subspaces
• OnsagerNet: Learning Stable and Interpretable Dynamics using a Generalized Onsager Principle
• A new approach for determining optimal placement of PM2.5 air quality sensors: case study for the contiguous United States
• Deep Learning Enhanced Dynamic Mode Decomposition
• Deep Learning Models for Global Coordinate Transformations that Linearize PDEs
• Variational approach for learning Markov processes from time series data
• Koopman Operator and its Approximations for Systems with Symmetries
• Data-driven closures for stochastic dynamical systems
• PySINDy: A Python package for the Sparse Identification of Nonlinear Dynamics from Data
• Efficient space-time reduced order model for linear dynamical systems in Python using less than 120 lines of code
• On the Koopman operator of algorithms
• On analytical construction of observable functions in extended dynamic mode decomposition for nonlinear estimation and prediction
• Identification of MIMO Wiener-type Koopman Models for Data-Driven Model Reduction using Deep Learning
• Extended Dynamic Mode Decomposition for Inhomogeneous Problems
• The Linear-Time-Invariance Notion of the Koopman Analysis-Part 1: The Architecture, Practical Rendering on the Prism Wake, and Fluid-Structure Association
• Koopman operator learning using invertible neural networks
• Kernel methods for detecting coherent structures in dynamical data
• An overview of Koopman-based control: From error bounds to closed-loop guarantees
• Data-driven state-space and Koopman operator models of coherent state dynamics on invariant manifolds
• Data-driven modelling of brain activity using neural networks, Diffusion Maps, and the Koopman operator
• Nonequilibrium Statistical Mechanics and Optimal Prediction of Partially-Observed Complex Systems
• Koopman analysis of quantum systems
• DDK: A Deep Koopman Approach for Dynamics Modeling and Trajectory Tracking of Autonomous Vehicles
• Estimating asymptotic phase and amplitude functions of limit-cycle oscillators from time series data
• CD-ROM: Complemented Deep-Reduced Order Model
• Two methods to approximate the Koopman operator with a reservoir computer
• Controlling nonlinear PDEs using low-dimensional bilinear approximations obtained from data
• Data-driven feedback stabilization of nonlinear systems: Koopman-based model predictive control
• Koopman-based spectral clustering of directed and time-evolving graphs
• Data-Driven Inference of High-Accuracy Isostable-Based Dynamical Models in Response to External Inputs
• Koopman Operator Theory for Nonlinear Dynamic Modeling using Dynamic Mode Decomposition
• Predictive Accuracy of Dynamic Mode Decomposition
• Koopman Operator Dynamical Models: Learning, Analysis and Control
• Data-Driven Koopman Controller Synthesis Based on the Extended ${\mathcal{H}}_2$ Norm Characterization
• Extended dynamic mode decomposition with dictionary learning using neural ordinary differential equations
• Promoting global stability in data-driven models of quadratic nonlinear dynamics
• On Koopman Mode Decomposition and Tensor Component Analysis
• Phase autoencoder for rapid data-driven synchronization of rhythmic spatiotemporal patterns
• Discovering time-varying aeroelastic models of a long-span suspension bridge from field measurements by sparse identification of nonlinear dynamical systems
• Dynamical Systems and Neural Networks
• Approximations of the Reproducing Kernel Hilbert Space (RKHS) Embedding Method over Manifolds
• Online learning of Koopman operator using streaming data from different dynamical regimes
• Koopman Learning with Episodic Memory
• Koopmon trajectories in nonadiabatic quantum-classical dynamics
• Numerical methods to evaluate Koopman matrix from system equations
• Modes of Homogeneous Gradient Flows
• Decomposition of Nonlinear Dynamical Systems Using Koopman Gramians
• Kernel Embedding based Variational Approach for Low-dimensional Approximation of Dynamical Systems
• Data-driven Initial Gap Identification of Piecewise-linear Systems using Sparse Regression and Universal Approximation Theorem
• The Effect of Sensor Fusion on Data-Driven Learning of Koopman Operators
• Challenges in Dynamic Mode Decomposition
• Data-Augmented Predictive Deep Neural Network: Enhancing the extrapolation capabilities of non-intrusive surrogate models
• Non-intrusive model combination for learning dynamical systems
• Extraction of nonlinearity in neural networks with Koopman operator
• Transformer-based Koopman Autoencoder for Linearizing Fisher's Equation
• Finite-time Koopman Identifier: A Unified Batch-online Learning Framework for Joint Learning of Koopman Structure and Parameters
• Learning Bounded Koopman Observables: Results on Stability, Continuity, and Controllability
• A multichannel generalization of the HAVOK method for the analysis of nonlinear dynamical systems
• Extracting Latent State Representations with Linear Dynamics from Rich Observations
• On the Physical Interpretation of Proper Orthogonal Decomposition and Dynamic Mode Decomposition for Liquid Injection
• Bridging the Gap between Koopmanism and Response Theory: Using Natural Variability to Predict Forced Response
• Definition and data-driven reconstruction of asymptotic phase and amplitudes of stochastic oscillators via Koopman operator theory
• Learning dynamical systems from data: Gradient-based dictionary optimization
• State-Of-The-Art Algorithms For Low-Rank Dynamic Mode Decomposition
• Robust Control Design and Analysis Based on Lifting Linearization of Nonlinear Systems Under Uncertain Initial Conditions
• Is the Finite-Time Lyapunov Exponent Field a Koopman Eigenfunction?
• Extending dynamic mode decomposition to data from multiple outputs
• Towards Scalable Koopman Operator Learning: Convergence Rates and A Distributed Learning Algorithm
• Learning Stable Koopman Embeddings
• Extraction of Discrete Spectra Modes from Video Data Using a Deep Convolutional Koopman Network
• Deep Koopman Economic Model Predictive Control of a Pasteurisation Unit
• Data-driven network analysis using local delay embeddings
• Operator Autoencoders: Learning Physical Operations on Encoded Molecular Graphs
• A purely data-driven framework for prediction, optimization, and control of networked processes: application to networked SIS epidemic model