Impact of Loss Weight and Model Complexity on Physics-Informed Neural Networks for Computational Fluid Dynamics
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| 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 |