Simulator-free solution of high-dimensional stochastic elliptic partial differential equations using deep neural networks

DOI10.1016/j.jcp.2019.109120zbMath1453.65021arXiv1902.05200OpenAlexW2912649832WikidataQ126770901 ScholiaQ126770901MaRDI QIDQ2223019

Sharmila Karumuri, Ilias Bilionis, Jitesh Panchal, Rohit K. Tripathy

Publication date: 28 January 2021

Published in: Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1902.05200

zbMATH Keywords

energy functionalinverse problemselliptic stochastic partial differential equationsdeep residual networkhigh-dimensional uncertainty propagationphysics-informed loss function

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Stochastic partial differential equations (aspects of stochastic analysis) (60H15) PDEs with randomness, stochastic partial differential equations (35R60) Numerical solutions to stochastic differential and integral equations (65C30)

Related Items (36)

GINNs: graph-informed neural networks for multiscale physics ⋮ A probabilistic generative model for semi-supervised training of coarse-grained surrogates and enforcing physical constraints through virtual observables ⋮ A derivative-free method for solving elliptic partial differential equations with deep neural networks ⋮ PhyGeoNet: physics-informed geometry-adaptive convolutional neural networks for solving parameterized steady-state PDEs on irregular domain ⋮ Weak form theory-guided neural network (TgNN-wf) for deep learning of subsurface single- and two-phase flow ⋮ Extended dynamic mode decomposition for inhomogeneous problems ⋮ A neural network multigrid solver for the Navier-Stokes equations ⋮ Surrogate and inverse modeling for two-phase flow in porous media via theory-guided convolutional neural network ⋮ Solving elliptic equations with Brownian motion: bias reduction and temporal difference learning ⋮ Fractional Chebyshev deep neural network (FCDNN) for solving differential models ⋮ Surrogate modeling for fluid flows based on physics-constrained deep learning without simulation data ⋮ DeepParticle: learning invariant measure by a deep neural network minimizing Wasserstein distance on data generated from an interacting particle method ⋮ The deep learning Galerkin method for the general Stokes equations ⋮ AMS-Net: Adaptive Multiscale Sparse Neural Network with Interpretable Basis Expansion for Multiphase Flow Problems ⋮ Multifidelity deep operator networks for data-driven and physics-informed problems ⋮ Wavelet neural operator for solving parametric partial differential equations in computational mechanics problems ⋮ Artificial neural networks for solving elliptic differential equations with boundary layer ⋮ Uncertainty quantification in scientific machine learning: methods, metrics, and comparisons ⋮ Pre-training strategy for solving evolution equations based on physics-informed neural networks ⋮ Error estimates and physics informed augmentation of neural networks for thermally coupled incompressible Navier Stokes equations ⋮ A Chebyshev Polynomial Neural Network Solver for Boundary Value Problems of Elliptic Equations ⋮ Physics informed WNO ⋮ Solution of time‐fractional stochastic nonlinear sine‐Gordon equation via finite difference and meshfree techniques ⋮ A Variational Neural Network Approach for Glacier Modelling with Nonlinear Rheology ⋮ Physics-informed information field theory for modeling physical systems with uncertainty quantification ⋮ PI-VEGAN: Physics Informed Variational Embedding Generative Adversarial Networks for Stochastic Differential Equations ⋮ Bayesian Deep Learning Framework for Uncertainty Quantification in Stochastic Partial Differential Equations ⋮ Level Set Learning with Pseudoreversible Neural Networks for Nonlinear Dimension Reduction in Function Approximation ⋮ Physics-informed variational inference for uncertainty quantification of stochastic differential equations ⋮ Stochastic projection based approach for gradient free physics informed learning ⋮ A hybrid data-driven-physics-constrained Gaussian process regression framework with deep kernel for uncertainty quantification ⋮ An overview on deep learning-based approximation methods for partial differential equations ⋮ Modeling the dynamics of PDE systems with physics-constrained deep auto-regressive networks ⋮ On the eigenvector bias of Fourier feature networks: from regression to solving multi-scale PDEs with physics-informed neural networks ⋮ Efficient uncertainty quantification for dynamic subsurface flow with surrogate by theory-guided neural network ⋮ A novel sequential method to train physics informed neural networks for Allen Cahn and Cahn Hilliard equations

Uses Software

• Diffpack
• FiPy
• Delve Datasets
• TensorFlow
• Keras
• DiffSharp
• PyTorch
• MXNet
• RMSprop
• Adam
• ADADELTA
• Inception-v4

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Multi-output separable Gaussian process: towards an efficient, fully Bayesian paradigm for uncertainty quantification
• Multi-output local Gaussian process regression: applications to uncertainty quantification
• Multilevel Monte Carlo methods and applications to elliptic PDEs with random coefficients
• Kernel principal component analysis for stochastic input model generation
• Gaussian processes with built-in dimensionality reduction: applications to high-dimensional uncertainty propagation
• Uncertainty propagation using infinite mixture of gaussian processes and variational Bayesian inference
• Computational partial differential equations. Numerical methods and Diffpack programming
• Multilayer feedforward networks are universal approximators
• Bayesian deep convolutional encoder-decoder networks for surrogate modeling and uncertainty quantification
• The Deep Ritz Method: a deep learning-based numerical algorithm for solving variational problems
• Deep UQ: learning deep neural network surrogate models for high dimensional uncertainty quantification
• Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data
• Exploiting active subspaces to quantify uncertainty in the numerical simulation of the hyshot II scramjet
• Langevin diffusions and the Metropolis-adjusted Langevin algorithm
• Accelerating Markov Chain Monte Carlo with Active Subspaces
• On the convergence of generalized polynomial chaos expansions
• Introduction to Uncertainty Quantification
• Large-Scale Machine Learning with Stochastic Gradient Descent
• Uncertainty Quantification and Polynomial Chaos Techniques in Computational Fluid Dynamics
• Optimal Scaling of Discrete Approximations to Langevin Diffusions
• Modern Monte Carlo Variants for Uncertainty Quantification in Neutron Transport
• Inverse Problem Theory and Methods for Model Parameter Estimation
• The Wiener--Askey Polynomial Chaos for Stochastic Differential Equations
• Quasi-Monte Carlo Finite Element Methods for a Class of Elliptic Partial Differential Equations with Random Coefficients

This page was built for publication: Simulator-free solution of high-dimensional stochastic elliptic partial differential equations using deep neural networks