Impact of Loss Weight and Model Complexity on Physics-Informed Neural Networks for Computational Fluid Dynamics

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chou, Yi En, Liu, Te Hsin, Lin, Chao-An
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916978850004992
author Chou, Yi En
Liu, Te Hsin
Lin, Chao-An
author_facet Chou, Yi En
Liu, Te Hsin
Lin, Chao-An
contents Physics Informed Neural Networks offer a mesh free framework for solving PDEs but are highly sensitive to loss weight selection. We propose two dimensional analysis based weighting schemes, one based on quantifiable terms, and another also incorporating unquantifiable terms for more balanced training. Benchmarks on heat conduction, convection diffusion, and lid driven cavity flows show that the second scheme consistently improves stability and accuracy over equal weighting. Notably, in high Peclet number convection diffusion, where traditional solvers fail, PINNs with our scheme achieve stable, accurate predictions, highlighting their robustness and generalizability in CFD problems.
format Preprint
id arxiv_https___arxiv_org_abs_2509_21393
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Impact of Loss Weight and Model Complexity on Physics-Informed Neural Networks for Computational Fluid Dynamics
Chou, Yi En
Liu, Te Hsin
Lin, Chao-An
Machine Learning
Fluid Dynamics
Physics Informed Neural Networks offer a mesh free framework for solving PDEs but are highly sensitive to loss weight selection. We propose two dimensional analysis based weighting schemes, one based on quantifiable terms, and another also incorporating unquantifiable terms for more balanced training. Benchmarks on heat conduction, convection diffusion, and lid driven cavity flows show that the second scheme consistently improves stability and accuracy over equal weighting. Notably, in high Peclet number convection diffusion, where traditional solvers fail, PINNs with our scheme achieve stable, accurate predictions, highlighting their robustness and generalizability in CFD problems.
title Impact of Loss Weight and Model Complexity on Physics-Informed Neural Networks for Computational Fluid Dynamics
topic Machine Learning
Fluid Dynamics
url https://arxiv.org/abs/2509.21393