Model reduction with memory and the machine learning of dynamical systems
From MaRDI portal
Abstract: The well-known Mori-Zwanzig theory tells us that model reduction leads to memory effect. For a long time, modeling the memory effect accurately and efficiently has been an important but nearly impossible task in developing a good reduced model. In this work, we explore a natural analogy between recurrent neural networks and the Mori-Zwanzig formalism to establish a systematic approach for developing reduced models with memory. Two training models-a direct training model and a dynamically coupled training model-are proposed and compared. We apply these methods to the Kuramoto-Sivashinsky equation and the Navier-Stokes equation. Numerical experiments show that the proposed method can produce reduced model with good performance on both short-term prediction and long-term statistical properties.
Recommendations
- \textit{A priori} estimation of memory effects in reduced-order models of nonlinear systems using the Mori-Zwanzig formalism
- Recurrent neural network closure of parametric POD-Galerkin reduced-order models based on the Mori-Zwanzig formalism
- Effective Mori-Zwanzig equation for the reduced-order modeling of stochastic systems
- Renormalized reduced order models with memory for long time prediction
- Neural network closures for nonlinear model order reduction
Cites work
- A dynamic subgrid scale model for large eddy simulations based on the Mori-Zwanzig formalism
- A thermodynamic study of the two-dimensional pressure-driven channel flow
- Efficient implementation of essentially nonoscillatory shock-capturing schemes
- Optimal prediction with memory
- Quantifying and reducing model-form uncertainties in Reynolds-averaged Navier-Stokes simulations: a data-driven, physics-informed Bayesian approach
- Reynolds averaged turbulence modelling using deep neural networks with embedded invariance
- Transport, Collective Motion, and Brownian Motion
Cited in
(41)- Memory-based reduced modelling and data-based estimation of opinion spreading
- Dimension reduction in recurrent networks by canonicalization
- Time-series learning of latent-space dynamics for reduced-order model closure
- Error bounds of the invariant statistics in machine learning of ergodic Itô diffusions
- Kernel-based prediction of non-Markovian time series
- Data-driven model reduction, Wiener projections, and the Koopman-Mori-Zwanzig formalism
- Machine learning for prediction with missing dynamics
- Analytic continuation of noisy data using Adams Bashforth residual neural network
- Effective Mori-Zwanzig equation for the reduced-order modeling of stochastic systems
- Prediction of magnetization dynamics in a reduced dimensional feature space setting utilizing a low-rank kernel method
- Dynamically learning the parameters of a chaotic system using partial observations
- PDE-Net 2.0: learning PDEs from data with a numeric-symbolic hybrid deep network
- Mori-Zwanzig reduced models for uncertainty quantification
- The deep learning Galerkin method for the general Stokes equations
- NySALT: Nyström-type inference-based schemes adaptive to large time-stepping
- An online manifold learning approach for model reduction of dynamical systems
- Multi-level dynamical systems: connecting the Ruelle response theory and the Mori-Zwanzig approach
- \textit{A priori} estimation of memory effects in reduced-order models of nonlinear systems using the Mori-Zwanzig formalism
- Renormalized reduced order models with memory for long time prediction
- Data-driven learning for the Mori-Zwanzig formalism: a generalization of the Koopman learning framework
- scientific article; zbMATH DE number 7625195 (Why is no real title available?)
- Better approximations of high dimensional smooth functions by deep neural networks with rectified power units
- Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks
- Using machine learning to predict extreme events in complex systems
- Simultaneous neural network approximation for smooth functions
- A framework for machine learning of model error in dynamical systems
- Regression-Based Projection for Learning Mori–Zwanzig Operators
- Learning Theory for Dynamical Systems
- Memory-based parameterization with differentiable solver: application to Lorenz '96
- Shock trace prediction by reduced models for a viscous stochastic Burgers equation
- A dynamical systems approach to machine learning
- Ml-GLE: a machine learning enhanced generalized Langevin equation framework for transient anomalous diffusion in polymer dynamics
- Applied unsupervised learning in model reduction of linear dynamic systems
- Learning vector fields of differential equations on manifolds with curvature-adaptive geometrically constrained SINDy
- Overview frequency principle/spectral bias in deep learning
- Data-driven stochastic closure modeling via conditional diffusion model and neural operator
- Deconvolutional artificial-neural-network framework for subfilter-scale models of compressible turbulence
- Scientific machine learning for closure models in multiscale problems: a review
- Limits of learning dynamical systems
- Recurrent neural network closure of parametric POD-Galerkin reduced-order models based on the Mori-Zwanzig formalism
- Problem reduction, renormalization, and memory
This page was built for publication: Model reduction with memory and the machine learning of dynamical systems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5161393)
