Non-equispaced Fourier Neural Solvers for PDEs
- URL: http://arxiv.org/abs/2212.04689v2
- Date: Sat, 18 Mar 2023 08:52:33 GMT
- Title: Non-equispaced Fourier Neural Solvers for PDEs
- Authors: Haitao Lin, Lirong Wu, Yongjie Xu, Yufei Huang, Siyuan Li, Guojiang
Zhao, Stan Z. Li
- Abstract summary: textscNFS is the first ML-based method with mesh invariant inference ability to successfully model turbulent flows in non-equispaced scenarios.
It achieves superior performance with $42.85%$ improvements on MAE, and is able to handle non-equispaced data with a tiny loss of accuracy.
- Score: 43.42089594581029
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Solving partial differential equations is difficult. Recently proposed neural
resolution-invariant models, despite their effectiveness and efficiency,
usually require equispaced spatial points of data. However, sampling in spatial
domain is sometimes inevitably non-equispaced in real-world systems, limiting
their applicability. In this paper, we propose a Non-equispaced Fourier PDE
Solver (\textsc{NFS}) with adaptive interpolation on resampled equispaced
points and a variant of Fourier Neural Operators as its components.
Experimental results on complex PDEs demonstrate its advantages in accuracy and
efficiency. Compared with the spatially-equispaced benchmark methods, it
achieves superior performance with $42.85\%$ improvements on MAE, and is able
to handle non-equispaced data with a tiny loss of accuracy. Besides, to our
best knowledge, \textsc{NFS} is the first ML-based method with mesh invariant
inference ability to successfully model turbulent flows in non-equispaced
scenarios, with a minor deviation of the error on unseen spatial points.
Related papers
- Solving Poisson Equations using Neural Walk-on-Spheres [80.1675792181381]
We propose Neural Walk-on-Spheres (NWoS), a novel neural PDE solver for the efficient solution of high-dimensional Poisson equations.
We demonstrate the superiority of NWoS in accuracy, speed, and computational costs.
arXiv Detail & Related papers (2024-06-05T17:59:22Z) - Solving partial differential equations with sampled neural networks [1.8590821261905535]
Approximation of solutions to partial differential equations (PDE) is an important problem in computational science and engineering.
We discuss how sampling the hidden weights and biases of the ansatz network from data-agnostic and data-dependent probability distributions allows us to progress on both challenges.
arXiv Detail & Related papers (2024-05-31T14:24:39Z) - Filtered Partial Differential Equations: a robust surrogate constraint in physics-informed deep learning framework [1.220743263007369]
We propose a surrogate constraint (filtered PDE, FPDE in short) of the original physical equations to reduce the influence of noisy and sparse observation data.
In the noise and sparsity experiment, the proposed FPDE models have better robustness than the conventional PDE models.
For combining real-world experiment data into physics-informed training, the proposed FPDE constraint is useful.
arXiv Detail & Related papers (2023-11-07T07:38:23Z) - A Metaheuristic for Amortized Search in High-Dimensional Parameter
Spaces [0.0]
We propose a new metaheuristic that drives dimensionality reductions from feature-informed transformations.
DR-FFIT implements an efficient sampling strategy that facilitates a gradient-free parameter search in high-dimensional spaces.
Our test data show that DR-FFIT boosts the performances of random-search and simulated-annealing against well-established metaheuristics.
arXiv Detail & Related papers (2023-09-28T14:25:14Z) - Score-based Diffusion Models in Function Space [137.70916238028306]
Diffusion models have recently emerged as a powerful framework for generative modeling.
This work introduces a mathematically rigorous framework called Denoising Diffusion Operators (DDOs) for training diffusion models in function space.
We show that the corresponding discretized algorithm generates accurate samples at a fixed cost independent of the data resolution.
arXiv Detail & Related papers (2023-02-14T23:50:53Z) - Solving High-Dimensional PDEs with Latent Spectral Models [74.1011309005488]
We present Latent Spectral Models (LSM) toward an efficient and precise solver for high-dimensional PDEs.
Inspired by classical spectral methods in numerical analysis, we design a neural spectral block to solve PDEs in the latent space.
LSM achieves consistent state-of-the-art and yields a relative gain of 11.5% averaged on seven benchmarks.
arXiv Detail & Related papers (2023-01-30T04:58:40Z) - Fourier Neural Operator with Learned Deformations for PDEs on General Geometries [75.91055304134258]
We propose a new framework, viz., geo-FNO, to solve PDEs on arbitrary geometries.
Geo-FNO learns to deform the input (physical) domain, which may be irregular, into a latent space with a uniform grid.
We consider a variety of PDEs such as the Elasticity, Plasticity, Euler's, and Navier-Stokes equations, and both forward modeling and inverse design problems.
arXiv Detail & Related papers (2022-07-11T21:55:47Z) - Adaptive Self-supervision Algorithms for Physics-informed Neural
Networks [59.822151945132525]
Physics-informed neural networks (PINNs) incorporate physical knowledge from the problem domain as a soft constraint on the loss function.
We study the impact of the location of the collocation points on the trainability of these models.
We propose a novel adaptive collocation scheme which progressively allocates more collocation points to areas where the model is making higher errors.
arXiv Detail & Related papers (2022-07-08T18:17:06Z) - Bayesian Deep Learning for Partial Differential Equation Parameter
Discovery with Sparse and Noisy Data [0.0]
We propose to use Bayesian neural networks (BNN) in order to recover the full system states from measurement data.
We show that it is possible to accurately capture physics of varying complexity without overfitting.
We demonstrate our approach on a handful of example applied to physics and non-linear dynamics.
arXiv Detail & Related papers (2021-08-05T19:43:15Z) - Weak SINDy For Partial Differential Equations [0.0]
We extend our Weak SINDy (WSINDy) framework to the setting of partial differential equations (PDEs)
The elimination of pointwise derivative approximations via the weak form enables effective machine-precision recovery of model coefficients from noise-free data.
We demonstrate WSINDy's robustness, speed and accuracy on several challenging PDEs.
arXiv Detail & Related papers (2020-07-06T16:03:51Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.