Linearly Recurrent Autoencoder Networks for Learning Dynamics

DOI10.1137/18M1177846zbMath1489.65164arXiv1712.01378OpenAlexW2963765797WikidataQ128144452 ScholiaQ128144452MaRDI QIDQ5383200

Samuel E. Otto, Clarence W. Rowley

Publication date: 20 June 2019

Published in: SIAM Journal on Applied Dynamical Systems (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1712.01378

zbMATH Keywords

nonlinear systemsneural networksreduced-order modelingKoopman operatorhigh-dimensional systemsdata-driven analysis

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20) Time series analysis of dynamical systems (37M10) Linear composition operators (47B33) Computational methods for ergodic theory (approximation of invariant measures, computation of Lyapunov exponents, entropy, etc.) (37M25) Numerical problems in dynamical systems (65P99)

Related Items (42)

Nonintrusive Reduced Order Modelling of Convective Boussinesq Flows ⋮ A long short-term memory embedding for hybrid uplifted reduced order models ⋮ A data-driven, physics-informed framework for forecasting the spatiotemporal evolution of chaotic dynamics with nonlinearities modeled as exogenous forcings ⋮ State estimation with limited sensors -- a deep learning based approach ⋮ Koopman analysis of quantum systems* ⋮ tgEDMD: approximation of the Kolmogorov operator in tensor train format ⋮ Modern Koopman Theory for Dynamical Systems ⋮ Learning nonlinear state-space models using autoencoders ⋮ Generative Stochastic Modeling of Strongly Nonlinear Flows with Non-Gaussian Statistics ⋮ Koopman analysis of nonlinear systems with a neural network representation ⋮ Transformers for modeling physical systems ⋮ Hybrid analysis and modeling, eclecticism, and multifidelity computing toward digital twin revolution ⋮ Assessment of end-to-end and sequential data-driven learning for non-intrusive modeling of fluid flows ⋮ Deep Koopman model predictive control for enhancing transient stability in power grids ⋮ A study on data-driven identification and representation of nonlinear dynamical systems with a physics-integrated deep learning approach: Koopman operators and nonlinear normal modes ⋮ Generalizing dynamic mode decomposition: balancing accuracy and expressiveness in Koopman approximations ⋮ Parsimony as the ultimate regularizer for physics-informed machine learning ⋮ Parametric dynamic mode decomposition for reduced order modeling ⋮ Unnamed Item ⋮ Koopman operator learning using invertible neural networks ⋮ Time-Delay Observables for Koopman: Theory and Applications ⋮ Physics-Informed Probabilistic Learning of Linear Embeddings of Nonlinear Dynamics with Guaranteed Stability ⋮ Data-driven feedback stabilisation of nonlinear systems: Koopman-based model predictive control ⋮ Model reduction for the material point method via an implicit neural representation of the deformation map ⋮ Neural dynamic mode decomposition for end-to-end modeling of nonlinear dynamics ⋮ Leveraging reduced-order models for state estimation using deep learning ⋮ Rigorous data‐driven computation of spectral properties of Koopman operators for dynamical systems ⋮ Active-learning-driven surrogate modeling for efficient simulation of parametric nonlinear systems ⋮ Data-Driven Identification of Parametric Partial Differential Equations ⋮ Recovering missing CFD data for high-order discretizations using deep neural networks and dynamics learning ⋮ Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders ⋮ The structure of reconstructed flows in latent spaces ⋮ Deep learning for model order reduction of multibody systems to minimal coordinates ⋮ Inverse multiobjective optimization: inferring decision criteria from data ⋮ Kernel methods for detecting coherent structures in dynamical data ⋮ Variational approach for learning Markov processes from time series data ⋮ Scalable Extended Dynamic Mode Decomposition Using Random Kernel Approximation ⋮ Data-Driven Model Predictive Control using Interpolated Koopman Generators ⋮ Sparsity-promoting algorithms for the discovery of informative Koopman-invariant subspaces ⋮ On Koopman mode decomposition and tensor component analysis ⋮ A Tailored Convolutional Neural Network for Nonlinear Manifold Learning of Computational Physics Data Using Unstructured Spatial Discretizations ⋮ Deep learning models for global coordinate transformations that linearise PDEs

Cites Work

• Unnamed Item
• Unnamed Item
• Discovering governing equations from data by sparse identification of nonlinear dynamical systems
• A kernel-based method for data-driven Koopman spectral analysis
• A data-driven approximation of the koopman operator: extending dynamic mode decomposition
• Stability and transition in shear flows
• Why does deep and cheap learning work so well?
• Spectral properties of dynamical systems, model reduction and decompositions
• Optimal mode decomposition for unsteady flows
• Applied Koopmanism
• Model Reduction for Flow Analysis and Control
• Dynamic mode decomposition of numerical and experimental data
• Spectral analysis of nonlinear flows
• Principal component analysis in linear systems: Controllability, observability, and model reduction
• Balanced realization and model reduction for unstable systems
• Extended dynamic mode decomposition with dictionary learning: A data-driven adaptive spectral decomposition of the Koopman operator
• Partially-Linear Least-Squares Regularized Regression for System Identification
• Kernel based partially linear models and nonlinear identification
• MODEL REDUCTION FOR FLUIDS, USING BALANCED PROPER ORTHOGONAL DECOMPOSITION
• Turbulence, Coherent Structures, Dynamical Systems and Symmetry

This page was built for publication: Linearly Recurrent Autoencoder Networks for Learning Dynamics