Saved in:
Bibliographic Details
Main Authors: Straub, Christopher, Brendel, Philipp, Medvedev, Vlad, Rosskopf, Andreas
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.01093
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917973569044480
author Straub, Christopher
Brendel, Philipp
Medvedev, Vlad
Rosskopf, Andreas
author_facet Straub, Christopher
Brendel, Philipp
Medvedev, Vlad
Rosskopf, Andreas
contents We present a novel approach to hard-constrain Neumann boundary conditions in physics-informed neural networks (PINNs) using Fourier feature embeddings. Neumann boundary conditions are used to described critical processes in various application, yet they are more challenging to hard-constrain in PINNs than Dirichlet conditions. Our method employs specific Fourier feature embeddings to directly incorporate Neumann boundary conditions into the neural network's architecture instead of learning them. The embedding can be naturally extended by high frequency modes to better capture high frequency phenomena. We demonstrate the efficacy of our approach through experiments on a diffusion problem, for which our method outperforms existing hard-constraining methods and classical PINNs, particularly in multiscale and high frequency scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2504_01093
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hard-constraining Neumann boundary conditions in physics-informed neural networks via Fourier feature embeddings
Straub, Christopher
Brendel, Philipp
Medvedev, Vlad
Rosskopf, Andreas
Machine Learning
Artificial Intelligence
Computational Physics
We present a novel approach to hard-constrain Neumann boundary conditions in physics-informed neural networks (PINNs) using Fourier feature embeddings. Neumann boundary conditions are used to described critical processes in various application, yet they are more challenging to hard-constrain in PINNs than Dirichlet conditions. Our method employs specific Fourier feature embeddings to directly incorporate Neumann boundary conditions into the neural network's architecture instead of learning them. The embedding can be naturally extended by high frequency modes to better capture high frequency phenomena. We demonstrate the efficacy of our approach through experiments on a diffusion problem, for which our method outperforms existing hard-constraining methods and classical PINNs, particularly in multiscale and high frequency scenarios.
title Hard-constraining Neumann boundary conditions in physics-informed neural networks via Fourier feature embeddings
topic Machine Learning
Artificial Intelligence
Computational Physics
url https://arxiv.org/abs/2504.01093