• Corpus ID: 239049847

Reduced Basis Approximations of Parameterized Dynamical Partial Differential Equations via Neural Networks

@article{Sentz2021ReducedBA,
  title={Reduced Basis Approximations of Parameterized Dynamical Partial Differential Equations via Neural Networks},
  author={Peter Sentz and Kris Beckwith and Eric C. Cyr and Luke N. Olson and Ravi Patel},
  journal={ArXiv},
  year={2021},
  volume={abs/2110.10775}
}
Projection-based reduced order models are effective at approximating parameter-dependent differential equations that are parametrically separable. When parametric separability is not satisfied, which occurs in both linear and nonlinear problems, projection-based methods fail to adequately reduce the computational complexity. Devising alternative reduced order models is crucial for obtaining efficient and accurate approximations to expensive high-fidelity models. In this work, we develop a time… 

References

SHOWING 1-10 OF 32 REFERENCES
EFFICIENT REDUCED-BASIS TREATMENT OF NONAFFINE AND NONLINEAR PARTIAL DIFFERENTIAL EQUATIONS
In this paper, we extend the reduced-basis approximations developed earlier for linear elliptic and parabolic partial differential equations with affine parameter dependence to problems in- volving
Data-Driven Deep Learning of Partial Differential Equations in Modal Space
TLDR
A framework for recovering/approximating unknown time-dependent partial differential equation (PDE) using its solution data by approximate the evolution operator of the underlying PDE numerically, using a deep neural network structure based on residual network using the given data.
Reduced Basis Approximation for Nonlinear Parametrized Evolution Equations based on Empirical Operator Interpolation
TLDR
A new algorithm is introduced, the PODEI-greedy algorithm, which constructs the reduced basis spaces for the empirical interpolation and for the numerical scheme in a synchronized way, and it is shown that the resulting reduced scheme is able to capture the evolution of both smooth and discontinuous solutions.
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-fidelity
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)
CERTIFIED REDUCED BASIS METHODS FOR NONAFFINE LINEAR TIME-VARYING AND NONLINEAR PARABOLIC PARTIAL DIFFERENTIAL EQUATIONS
We present reduced basis approximations and associated a posteriori error bounds for parabolic partial differential equations involving (i) a nonaffine dependence on the parameter and (ii ) a
A comprehensive deep learning-based approach to reduced order modeling of nonlinear time-dependent parametrized PDEs
TLDR
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.
Neural Ordinary Differential Equations
TLDR
This work shows how to scalably backpropagate through any ODE solver, without access to its internal operations, which allows end-to-end training of ODEs within larger models.
Reduced Basis Approximation and a Posteriori Error Estimation for Affinely Parametrized Elliptic Coercive Partial Differential Equations
In this paper we consider (hierarchical, Lagrange) reduced basis approximation and a posteriori error estimation for linear functional outputs of affinely parametrized elliptic coercive partial
Non-intrusive reduced order modeling of unsteady flows using artificial neural networks with application to a combustion problem
TLDR
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.
...
1
2
3
4
...