Solving parametric PDE problems with artificial neural networks
arXiv:1707.03351 · doi:10.1017/S0956792520000182
Abstract
The curse of dimensionality is commonly encountered in numerical partial differential equations (PDE), especially when uncertainties have to be modeled into the equations as random coefficients. However, very often the variability of physical quantities derived from a PDE can be captured by a few features on the space of the coefficient fields. Based on such an observation, we propose using a neural-network (NN) based method to parameterize the physical quantity of interest as a function of input coefficients. The representability of such quantity using a neural-network can be justified by viewing the neural-network as performing time evolution to find the solutions to the PDE. We further demonstrate the simplicity and accuracy of the approach through notable examples of PDEs in engineering and physics.
17 pages, 4 figures, 2 tables
References in corpus (3)
Cited by in corpus (29)
- A Physics Informed Neural Network for Time-Dependent Nonlinear and Higher Order Partial Differential Equations
- Algorithms for Solving High Dimensional PDEs: From Nonlinear Monte Carlo to Machine Learning
- A proof that artificial neural networks overcome the curse of dimensionality in the numerical approximation of Black-Scholes partial differential equations
- DNN Expression Rate Analysis of High-dimensional PDEs: Application to Option Pricing
- Latent Space Data Assimilation by using Deep Learning
- Normalizing field flows: Solving forward and inverse stochastic differential equations using physics-informed flow models
- In-Context Operator Learning with Data Prompts for Differential Equation Problems
- Nonlocal Kernel Network (NKN): a Stable and Resolution-Independent Deep Neural Network
- Deep Neural Helmholtz Operators for 3D Elastic Wave Propagation and Inversion
- Deep learning probability flows and entropy production rates in active matter
- Deep-learning quasi-particle masses from QCD equation of state
- Operator Learning Using Random Features: A Tool for Scientific Computing
- Fourier Neural Operator Networks: A Fast and General Solver for the Photoacoustic Wave Equation
- opPINN: Physics-Informed Neural Network with operator learning to approximate solutions to the Fokker-Planck-Landau equation
- Multi-scale Time-stepping of Partial Differential Equations with Transformers
- Deep neural network approximations for Monte Carlo algorithms
- Optimizing Variational Physics-Informed Neural Networks Using Least Squares
- Learning the random variables in Monte Carlo simulations with stochastic gradient descent: Machine learning for parametric PDEs and financial derivative pricing
- Learning quantities of interest from parametric PDEs: An efficient neural-weighted Minimal Residual approach
- Learning phase field mean curvature flows with neural networks
- Forward and backward problems for coupled subdiffusion systems
- Meta-Auto-Decoder: A Meta-Learning Based Reduced Order Model for Solving Parametric Partial Differential Equations
- Studying First Passage Problems using Neural Networks: A Case Study in the Slit-Well Microfluidic Device
- A Natural Deep Ritz Method for Essential Boundary Value Problems
- A Low Rank Neural Representation of Entropy Solutions
- Turbulence closure modeling with data-driven techniques: Investigation of generalizable deep neural networks
- Surrogate-data-enriched Physics-Aware Neural Networks
- Probabilistic partition of unity networks for high-dimensional regression problems
- A survey of unsupervised learning methods for high-dimensional uncertainty quantification in black-box-type problems