Conditional variational autoencoder with Gaussian process regression recognition for parametric models
From MaRDI portal
Abstract: In this article, we present a data-driven method for parametric models with noisy observation data. Gaussian process regression based reduced order modeling (GPR-based ROM) can realize fast online predictions without using equations in the offline stage. However, GPR-based ROM does not perform well for complex systems since POD projection are naturally linear. Conditional variational autoencoder (CVAE) can address this issue via nonlinear neural networks but it has more model complexity, which poses challenges for training and tuning hyperparameters. To this end, we propose a framework of CVAE with Gaussian process regression recognition (CVAE-GPRR). The proposed method consists of a recognition model and a likelihood model. In the recognition model, we first extract low-dimensional features from data by POD to filter the redundant information with high frequency. And then a non-parametric model GPR is used to learn the map from parameters to POD latent variables, which can also alleviate the impact of noise. CVAE-GPRR can achieve the similar accuracy to CVAE but with fewer parameters. In the likelihood model, neural networks are used to reconstruct data. Besides the samples of POD latent variables and input parameters, physical variables are also added as the inputs to make predictions in the whole physical space. This can not be achieved by either GPR-based ROM or CVAE. Moreover, the numerical results show that CVAE-GPRR may alleviate the overfitting issue in CVAE.
Cites work
- A hybrid model reduction method for stochastic parabolic optimal control problems
- An `empirical interpolation' method: Application to efficient reduced-basis discretization of partial differential equations
- An Introduction to Variational Autoencoders
- Bayesian deep convolutional encoder-decoder networks for surrogate modeling and uncertainty quantification
- Data driven approximation of parametrized PDEs by reduced basis and neural networks
- Data-driven reduced-order modeling for nonautonomous dynamical systems in multiscale media
- Discontinuous Galerkin reduced basis empirical quadrature procedure for model reduction of parametrized nonlinear conservation laws
- Efficient algorithms for solving the p-Laplacian in polynomial time
- scientific article; zbMATH DE number 6826271 (Why is no real title available?)
- Latent-space time evolution of non-intrusive reduced-order models using Gaussian process emulation
- Model reduction and neural networks for parametric PDEs
- Non intrusive reduced order modeling of parametrized PDEs by kernel POD and neural networks
- Non-intrusive reduced order modeling of nonlinear problems using neural networks
- Non-intrusive reduced order modeling of unsteady flows using artificial neural networks with application to a combustion problem
- Notes on the Stationary p-Laplace Equation
- Proper orthogonal decomposition-based model order reduction via radial basis functions for molecular dynamics systems
- Reduced order methods for modeling and computational reduction
- Reduced order modeling for nonlinear structural analysis using Gaussian process regression
- Structured Bayesian Gaussian process latent variable model: applications to data-driven dimensionality reduction and high-dimensional inversion
- Use of reduced-order models in well control optimization
Cited in
(3)- Non-intrusive reduced-order model for time-dependent stochastic partial differential equations utilizing dynamic mode decomposition and polynomial chaos expansion
- Polytopic autoencoders with smooth clustering for reduced-order modeling of flows
- Convolutional neural network based reduced order modeling for multiscale problems
This page was built for publication: Conditional variational autoencoder with Gaussian process regression recognition for parametric models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6056206)
