Data-driven reduced order modeling for time-dependent problems

  title={Data-driven reduced order modeling for time-dependent problems},
  author={Mengwu Guo and Jan S. Hesthaven},
  journal={Computer Methods in Applied Mechanics and Engineering},
  • Mengwu Guo, J. Hesthaven
  • Published 1 March 2019
  • Computer Science
  • Computer Methods in Applied Mechanics and Engineering
Data-Driven Model Order Reduction for Problems with Parameter-Dependent Jump-Discontinuities
  • N. Sarna, P. Benner
  • Mathematics, Computer Science
    Computer Methods in Applied Mechanics and Engineering
  • 2021
A comprehensive deep learning-based approach to reduced order modeling of nonlinear time-dependent parametrized PDEs
Numerical results indicate that DL-ROMs whose dimension is equal to the intrinsic dimensionality of the PDE solutions manifold are able to efficiently approximate the solution of parametrized PDEs, especially in cases for which a huge number of POD modes would have been necessary to achieve the same degree of accuracy.
Deep-HyROMnet: A deep learning-based operator approximation for hyper-reduction of nonlinear parametrized PDEs
A novel strategy for learning nonlinear ROM operators using deep neural networks (DNNs) is proposed, which is a physics-based model, still relying on the RB method approach, however employing a DNN architecture to approximate reduced residual vectors and Jacobian matrices once a Galerkin projection has been performed.
Data-driven reduced order modeling of environmental hydrodynamics using deep autoencoders and neural ODEs
Findings indicate that deep autoencoders can leverage nonlinear manifold learning to achieve a highly efficient compression of spatial information and define a latent-space that appears to be more suitable for capturing the temporal dynamics through the NODE framework.
Reduced Order Modeling Using Advection-Aware Autoencoders
An advection-aware (AA) autoencoder network that can address some of these limitations by learning efficient, physics-informed, nonlinear embeddings of the high-fidelity system snapshots is developed.
Learning reduced order models from data for hyperbolic PDEs
This work decomposes the solution by expressing it as a composition of a transformed solution and a de-transformer and resorts to the dynamic mode decomposition (DMD) methodology to learn a reduced order model (ROM).


Reduced order modeling for nonlinear structural analysis using Gaussian process regression
Non-intrusive reduced order modeling of nonlinear problems using neural networks
Nonlinear model order reduction based on local reduced‐order bases
A new approach for the dimensional reduction via projection of nonlinear computational models based on the concept of local reduced‐order bases is presented. It is particularly suited for problems
Dynamic mode decomposition - data-driven modeling of complex systems
This first book to address the DMD algorithm presents a pedagogical and comprehensive approach to all aspects of DMD currently developed or under development, and blends theoretical development, example codes, and applications to showcase the theory and its many innovations and uses.
A Reduced Order Model for Multi-Group Time-Dependent Parametrized Reactor Spatial Kinetics
The proposed ROM is capable to efficiently reproduce the neutron flux distribution allowing to take into account the spatial effects induced by the movement of the control rod with a computational speed-up of 30000 times, with respect to the “truth” model.
Efficient model reduction of parametrized systems by matrix discrete empirical interpolation
Nonintrusive reduced‐order modeling of parametrized time‐dependent partial differential equations
A nonintrusive reduced‐order modeling method based on the notion of space‐time‐parameter proper orthogonal decomposition (POD) for approximating the solution of nonlinear parametrized time‐dependent partial differential equations that leads to reduced‐ order models that accurately capture the behavior of the field variables as a function of the spatial coordinates, the parameter vector and time.
Error modeling for surrogates of dynamical systems using machine learning
The proposed framework for modeling the error introduced by surrogate models of parameterized dynamical systems is applied to model errors in reduced‐order models of nonlinear oil‐water subsurface flow simulations, with time‐varying well‐control (bottom‐hole pressure) parameters.
Nonlinear Model Reduction via Discrete Empirical Interpolation
A dimension reduction method called discrete empirical interpolation is proposed and shown to dramatically reduce the computational complexity of the popular proper orthogonal decomposition (POD)