Neural dynamic mode decomposition for end-to-end modeling of nonlinear dynamics
From MaRDI portal
Publication:6166776
DOI10.3934/JCD.2022029zbMATH Open1522.37090arXiv2012.06191OpenAlexW3112803672MaRDI QIDQ6166776FDOQ6166776
Authors: Tomoharu Iwata, Yoshinobu Kawahara 
Publication date: 6 July 2023
Published in: Journal of Computational Dynamics (Search for Journal in Brave)
Abstract: Koopman spectral analysis has attracted attention for understanding nonlinear dynamical systems by which we can analyze nonlinear dynamics with a linear regime by lifting observations using a nonlinear function. For analysis, we need to find an appropriate lift function. Although several methods have been proposed for estimating a lift function based on neural networks, the existing methods train neural networks without spectral analysis. In this paper, we propose neural dynamic mode decomposition, in which neural networks are trained such that the forecast error is minimized when the dynamics is modeled based on spectral decomposition in the lifted space. With our proposed method, the forecast error is backpropagated through the neural networks and the spectral decomposition, enabling end-to-end learning of Koopman spectral analysis. When information is available on the frequencies or the growth rates of the dynamics, the proposed method can exploit it as regularizers for training. We also propose an extension of our approach when observations are influenced by exogenous control time-series. Our experiments demonstrate the effectiveness of our proposed method in terms of eigenvalue estimation and forecast performance.
Full work available at URL: https://arxiv.org/abs/2012.06191
Recommendations
- Dynamic mode decomposition in vector-valued reproducing kernel Hilbert spaces for extracting dynamical structure among observables
- Linearly recurrent autoencoder networks for learning dynamics
- Koopman Operator Inspired Nonlinear System Identification
- Koopman operator, geometry, and learning of dynamical systems
- Generalizing Koopman Theory to Allow for Inputs and Control
Artificial neural networks and deep learning (68T07) Approximation methods and numerical treatment of dynamical systems (37M99)
Cites Work
- Title not available (Why is that?)
- Dynamic mode decomposition of numerical and experimental data
- Spectral analysis of nonlinear flows
- Dynamical behavior of epidemiological models with nonlinear incidence rates
- Controllability, stabilizability, and continuous-time Markovian jump linear quadratic control
- Robust pole placement in LMI regions
- Spectral properties of dynamical systems, model reduction and decompositions
- On dynamic mode decomposition: theory and applications
- Dynamic mode decomposition with control
- A kernel-based method for data-driven Koopman spectral analysis
- A data-driven approximation of the koopman operator: extending dynamic mode decomposition
- Title not available (Why is that?)
- Computation of eigenvalue and eigenvector derivatives for a general complex-valued eigensystem
- Nonlinear system stabilization via hierarchical switching control
- Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders
- Dynamic mode decomposition for financial trading strategies
- Collected matrix derivative results for forward and reverse mode algorithmic differentiation
- Linearly recurrent autoencoder networks for learning dynamics
- Dynamic mode decomposition in vector-valued reproducing kernel Hilbert spaces for extracting dynamical structure among observables
- On the Koopman operator of algorithms
Cited In (2)
This page was built for publication: Neural dynamic mode decomposition for end-to-end modeling of nonlinear dynamics
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6166776)
