Corpus ID: 236428901

Non-intrusive reduced order modeling of natural convection in porous media using convolutional autoencoders: comparison with linear subspace techniques

  title={Non-intrusive reduced order modeling of natural convection in porous media using convolutional autoencoders: comparison with linear subspace techniques},
  author={T. Kadeethum and Francesco Ballarin and Y. Cho and Daniel O'Malley and H. Yoon and Nikolaos Bouklas},
Natural convection in porous media is a highly nonlinear multiphysical problem relevant to many engineering applications (e.g., the process of CO2 sequestration). Here, we present a non-intrusive reduced order model of natural convection in porous media employing deep convolutional autoencoders for the compression and reconstruction and either radial basis function (RBF) interpolation or artificial neural networks (ANNs) for mapping parameters of partial differential equations (PDEs) on the… Expand


Non-intrusive reduced order modeling of nonlinear problems using neural networks
We develop a non-intrusive reduced basis (RB) method for parametrized steady-state partial differential equations (PDEs). The method extracts a reduced basis from a collection of high-fidelityExpand
Data-driven reduced order modeling of poroelasticity of heterogeneous media based on a discontinuous Galerkin approximation
A simulation tool capable of speeding up the calculation for linear poroelasticity problems in heterogeneous porous media is of large practical interest for engineers, in particular, to effectivelyExpand
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 approximate the solution of parametrized PDEs in situations where a huge number of POD modes would be necessary to achieve the same degree of accuracy. Expand
Non-intrusive reduced order modeling of unsteady flows using artificial neural networks with application to a combustion problem
The proposed reduced-basis method, referred as the POD-NN, fully decouples the online stage and the high-fidelity scheme, and is thus able to provide fast and reliable solutions of complex unsteady flows. Expand
Non-Intrusive Inference Reduced Order Model for Fluids Using Deep Multistep Neural Network
A data-driven learning framework for reduced order modeling of fluid dynamics that optimally approximates the full order model in the low-dimensional space with a given supervised learning task and is significantly more accurate than standard projection-based approaches. Expand
Nonintrusive reduced‐order modeling of parametrized time‐dependent partial differential equations
We propose a nonintrusive reduced-order modeling method based on the notion of space-time-parameter proper orthogonal decomposition (POD) for approximating the solution of nonlinear parametrizedExpand
Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders
The ability of the method to significantly outperform even the optimal linear-subspace ROM on benchmark advection-dominated problems is demonstrated, thereby demonstrating the method's ability to overcome the intrinsic $n$-width limitations of linear subspaces. Expand
A fast and accurate physics-informed neural network reduced order model with shallow masked autoencoder
A fast and accurate physics-informed neural network ROM, namely nonlinear manifold ROM (NM-ROM), which can better approximate high-fidelity model solutions with a smaller latent space dimension than the LS-ROMs. Expand
A mixed finite element solver for natural convection in porous media using automated solution techniques
The design, implementation and verification of a fully coupled finite element solver for the simulation of natural convection in porous media, by making use of automated solution techniques are presented. Expand
Model identification of reduced order fluid dynamics systems using deep learning
Summary This paper presents a novel model reduction method: deep learning reduced order model, which is based on proper orthogonal decomposition and deep learning methods. The deep learning approachExpand