Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Spline-PINN: Approaching PDEs without Data using Fast, Physics-Informed Hermite-Spline CNNs

About

Partial Differential Equations (PDEs) are notoriously difficult to solve. In general, closed-form solutions are not available and numerical approximation schemes are computationally expensive. In this paper, we propose to approach the solution of PDEs based on a novel technique that combines the advantages of two recently emerging machine learning based approaches. First, physics-informed neural networks (PINNs) learn continuous solutions of PDEs and can be trained with little to no ground truth data. However, PINNs do not generalize well to unseen domains. Second, convolutional neural networks provide fast inference and generalize but either require large amounts of training data or a physics-constrained loss based on finite differences that can lead to inaccuracies and discretization artifacts. We leverage the advantages of both of these approaches by using Hermite spline kernels in order to continuously interpolate a grid-based state representation that can be handled by a CNN. This allows for training without any precomputed training data using a physics-informed loss function only and provides fast, continuous solutions that generalize to unseen domains. We demonstrate the potential of our method at the examples of the incompressible Navier-Stokes equation and the damped wave equation. Our models are able to learn several intriguing phenomena such as Karman vortex streets, the Magnus effect, Doppler effect, interference patterns and wave reflections. Our quantitative assessment and an interactive real-time demo show that we are narrowing the gap in accuracy of unsupervised ML based methods to industrial CFD solvers while being orders of magnitude faster.

Nils Wandel, Michael Weinmann, Michael Neidlin, Reinhard Klein• 2021

Related benchmarks

TaskDatasetResultRank
Solving PDEAllen-Cahn
Relative Error0.15
14
Solving Helmholtz equationsHigh-Dimensional Helmholtz equations 2D
Relative Error0.746
14
Solving PDEHelmholtz
Relative Error0.12
14
Solving Helmholtz equationsHigh-Dimensional Helmholtz equations 3D
Relative Error0.725
14
Solving PDEBurgers
Relative Error45
14
Solving PDEFlow-Mixing
Relative Error18
14
Showing 6 of 6 rows

Other info

Follow for update