A long short-term memory embedding for hybrid uplifted reduced order models

DOI10.1016/j.physd.2020.132471zbMath1505.76071arXiv1912.06756OpenAlexW3014674130MaRDI QIDQ2125587

Shady E. Ahmed, Traian Iliescu, Adil Rasheed, Omer San

Publication date: 14 April 2022

Published in: Physica D (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1912.06756

zbMATH Keywords

Navier-Stokes equationsproper orthogonal decompositionBurgers equationsmodel reductionvorticity-streamfunction formulationGalerkin projectionsupervised machine learninghybrid analysisGrassmann manifold interpolation

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Navier-Stokes equations for incompressible viscous fluids (76D05) Incompressible viscous fluids (76D99) Basic methods in fluid mechanics (76M99)

Related Items

Numerical Assessment of a Nonintrusive Surrogate Model Based on Recurrent Neural Networks and Proper Orthogonal Decomposition: Rayleigh–Bénard Convection ⋮ A POD-Galerkin reduced order model for the Navier-Stokes equations in stream function-vorticity formulation ⋮ Neural-network-augmented projection-based model order reduction for mitigating the Kolmogorov barrier to reducibility ⋮ Hybrid analysis and modeling, eclecticism, and multifidelity computing toward digital twin revolution ⋮ Physics Guided Machine Learning for Variational Multiscale Reduced Order Modeling ⋮ \textit{FastSVD-ML-ROM}: a reduced-order modeling framework based on machine learning for real-time applications ⋮ A non-intrusive reduced-order modeling for uncertainty propagation of time-dependent problems using a B-splines Bézier elements-based method and proper orthogonal decomposition: application to dam-break flows ⋮ A nudged hybrid analysis and modeling approach for realtime wake-vortex transport and decay prediction ⋮ Efficient computations for linear feedback control problems for target velocity matching of Navier-Stokes flows via POD and LSTM-ROM ⋮ Multi-fidelity meta modeling using composite neural network with online adaptive basis technique ⋮ Assessments of epistemic uncertainty using Gaussian stochastic weight averaging for fluid-flow regression ⋮ Latent-space time evolution of non-intrusive reduced-order models using Gaussian process emulation

Uses Software

• pyMOR
• Keras

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Non-linear Petrov-Galerkin methods for reduced order modelling of the Navier-Stokes equations using a mixed finite element pair
• Reduced-order modelling for flow control. Papers based on the presentations at the course, Udine, Italy, September 2008
• Calibrated reduced-order POD-Galerkin system for fluid flow modelling
• Proper orthogonal decomposition closure models for turbulent flows: a numerical comparison
• A stabilized proper orthogonal decomposition reduced-order model for large scale quasigeostrophic ocean circulation
• Enablers for robust POD models
• A reduced-order method for simulation and control of fluid flows
• A spectral viscosity method for correcting the long-term behavior of POD models.
• Riemannian geometry of Grassmann manifolds with a view on algorithmic computation
• On low-dimensional Galerkin models for fluid flow
• Stability properties of POD-Galerkin approximations for the compressible Navier-Stokes equations
• Galerkin v. least-squares Petrov-Galerkin projection in nonlinear model reduction
• Projection-based model reduction: formulations for physics-based machine learning
• An `empirical interpolation' method: Application to efficient reduced-basis discretization of partial differential equations
• Linear predictors for nonlinear dynamical systems: Koopman operator meets model predictive control
• Krylov subspace techniques for reduced-order modeling of large-scale dynamical systems
• Model reduction for compressible flows using POD and Galerkin projection
• Optimal reduced space for variational data assimilation
• A localized reduced-order modeling approach for PDEs with bifurcating solutions
• Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders
• Deep learning algorithm for data-driven simulation of noisy dynamical system
• A fast and robust sub-optimal control approach using reduced order model adaptation techniques
• Certified PDE-constrained parameter optimization using reduced basis surrogate models for evolution problems
• Multiobjective optimal control methods for the Navier-Stokes equations using reduced order modeling
• Computational design for long-term numerical integration of the equations of fluid motion: two-dimensional incompressible flow. Part I
• Über die beste Annäherung von Funktionen einer gegebenen Funktionenklasse
• pyMOR -- Generic Algorithms and Interfaces for Model Order Reduction
• Efficient non-linear model reduction via a least-squares Petrov-Galerkin projection and compressive tensor approximations
• Model Reduction for Flow Analysis and Control
• Nonlinear Model Reduction via Discrete Empirical Interpolation
• On the stability and convergence of a Galerkin reduced order model (ROM) of compressible flow with solid wall and far-field boundary treatment
• Machine Learning for Fluid Mechanics
• Cluster-based reduced-order modelling of a mixing layer
• Optimal nonlinear eddy viscosity in Galerkin models of turbulent flows
• An intrinsic stabilization scheme for proper orthogonal decomposition based low-dimensional models
• A method for interpolating on manifolds structural dynamics reduced-order models
• Merger and cancellation of strained vortices
• Turbulence and the dynamics of coherent structures. I. Coherent structures
• The Geometry of Algorithms with Orthogonality Constraints
• Total variation diminishing Runge-Kutta schemes
• A New Look at Proper Orthogonal Decomposition
• Intermodal energy transfers in a proper orthogonal decomposition–Galerkin representation of a turbulent separated flow
• A hierarchy of low-dimensional models for the transient and post-transient cylinder wake
• Vortex merging in quasi-geostrophic flows
• Data-driven forecasting of high-dimensional chaotic systems with long short-term memory networks
• Data-Driven Filtered Reduced Order Modeling of Fluid Flows
• Geometric Subspace Updates with Applications to Online Adaptive Nonlinear Model Reduction
• Some Recent Developments in Turbulence Closure Modeling
• Space--Time Least-Squares Petrov--Galerkin Projection for Nonlinear Model Reduction
• Stabilization of projection‐based reduced‐order models
• Model Order Reduction in Fluid Dynamics: Challenges and Perspectives
• An Evolve-Filter-Relax Stabilized Reduced Order Stochastic Collocation Method for the Time-Dependent Navier--Stokes Equations
• Kernel Methods for the Approximation of Nonlinear Systems
• On the need for a nonlinear subscale turbulence term in POD models as exemplified for a high-Reynolds-number flow over an Ahmed body
• Deep learning in fluid dynamics
• Turbulence Modeling in the Age of Data
• Linearly Recurrent Autoencoder Networks for Learning Dynamics
• Turbulence, Coherent Structures, Dynamical Systems and Symmetry
• A training set and multiple bases generation approach for parameterized model reduction based on adaptive grids in parameter space
• Galerkin proper orthogonal decomposition methods for parabolic problems