Fourier Neural Operator for Parametric Partial Differential Equations
From MaRDI portal
Abstract: The classical development of neural networks has primarily focused on learning mappings between finite-dimensional Euclidean spaces. Recently, this has been generalized to neural operators that learn mappings between function spaces. For partial differential equations (PDEs), neural operators directly learn the mapping from any functional parametric dependence to the solution. Thus, they learn an entire family of PDEs, in contrast to classical methods which solve one instance of the equation. In this work, we formulate a new neural operator by parameterizing the integral kernel directly in Fourier space, allowing for an expressive and efficient architecture. We perform experiments on Burgers' equation, Darcy flow, and Navier-Stokes equation. The Fourier neural operator is the first ML-based method to successfully model turbulent flows with zero-shot super-resolution. It is up to three orders of magnitude faster compared to traditional PDE solvers. Additionally, it achieves superior accuracy compared to previous learning-based solvers under fixed resolution.
Cited in
(47)- Randomized neural operator for parametric PDEs with fast training and conformal uncertainty quantification
- Fourier-Diagonalized Natural Gradients and Sobolev Mirror Descent
- A spectral-subspace-augmented POD-Galerkin method for parametrized PDEs with limited snapshot data
- Kernel-based Operator Learning: Error Analysis, Budget Allocation, and a Physics-Informed Extension
- Time-Invariant Neural Operators with Applications in Solving Time-Dependent PDEs
- Domain decomposition methods with Physics-informed neural networks for elliptic equations on manifolds
- Physics-Informed Neural Embeddings of PDE Solution Families
- Residual-Certified Adaptive Tracking of Solution Manifolds in Parametric Dynamical Systems
- PG-KINN: A Physics-Informed Petrov-Galerkin Kolmogorov-Arnold Network for Solving Forward and Inverse PDEs
- Geometry-aware LegONet for PDE Learning on Arbitrary Domains
- Elliptic Regularity Theory in Barron Spaces and Applications to the Deep Ritz Method
- On the post-hoc Evaluation of PDE Discovery: A Multifaceted Challenge of Scientific Advancement
- Learning features from Newton's algorithm: a way to accelerate nonlinear parametrized PDE solvers
- A Physics-Informed Neural Operator for Thermal Ranking of Low-Cost Wall Materials in Hot-Dry Climates
- Physics-informed token transformer methodology for nonlinear balance laws. I. Schwarzschild--Burgers fluid flows
- iSMART: An Iterative Sampling-and-Regression Technique for Solving Martingale-Based PDEs
- Gradient Descent on Point Clouds and Applications in Learned Operator Correction
- A neural operator view on U-Nets for inverse imaging problems
- Physics-informed reduced-order modelling with equivariant spectral submanifolds
- A Neural-network-based multiscale Hybridizable Discontinuous Galerkin method for solving PDEs in porous media
- Learning Informative Prior with Infinite-Dimensional Continuous Normalizing Flow for Bayesian Inverse Problem
- Deep operator learning for efficient sampling from invariant measures of stochastic differential equations
- FrFNO:Injecting the analytic Mittag-Leffler propagator into a resolution-robust neural operator for space-time fractional PDEs
- Cost-Accuracy Trade-offs: Neural Operator vs Classical Numerical Solver
- NeSTR: Neural S-Transform Reconstruction for Gaussian SPDEs
- Domain-decomposed Evolutional Deep Neural Network with Random Features for Transient Pressure Diffusion with Discontinuous and High-Contrast Coefficients
- KATOsuper: Surrogate-accelerated neural topology optimization with sensitivity-consistent Fourier neural operators
- Elucidating the Conformal Structure of the Brinkman Penalisation Method for Geometry-Adapted, Structure-Preserving Operator Learning of Hamiltonian PDEs
- Optimal Recovery for Solving Variational Problems
- Deep-Learning Solvers and Surrogates for Infinity and p-Laplace Problems
- Latent Twin Operator
- Why Directly Learning Periodic Trajectories Can Fail
- Preconditioned Physics-Informed Neural Operator Training
- Adaptive Multiresolution Diffusion Operators: A Variational Theory on Evolving Multiresolution Spaces
- Structure-preserving Fourier Neural Operators for Long-time Cahn-Hilliard Dynamics under Coarse Temporal Supervision
- Comparison of neural and spline representations for physics-informed learning
- Global error estimators for parametric monotone nonlinearities and neural approximations
- Inferring physical fields in coupled systems with unknown parameters from incomplete observations using physics-constrained attentive neural operators
- Multiresolution Sobolev Trained Fourier Neural Operator for Cross-Resolution Surrogate Modelling of Parametric Two-Phase Darcy Flows in Porous Media
- Learned Adaptive Multiresolution Diffusion Imaging
- Physics is the Best Teacher: Consistency Learning for Time-Invariant Operators of Chaotic Dynamics
- Learning PDE solution operators with variable initial conditions via Latent Dynamics Networks
- Data-Driven Free-Energy Learning from Trajectories via Structure-Preserving Exponential Time Differencing
- Learning the Willmore flow with a lightweight neural operator
- Improving Learning of Green's Functions Through Kernel Decomposition
- CAFE+FNO: Fourier Kernel Generation via Multiplicative Feature Composition
- Variationally correct loss functions for nonlinear parametric problems and their neural approximations
This page was built for publication: Fourier Neural Operator for Parametric Partial Differential Equations
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6351561)
