Impact of Loss Weight and Model Complexity on Physics-Informed Neural Networks for Computational Fluid Dynamics
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 16 of its 44 references that are in the map. First posted on arXiv 24 Sep 2025.
Builds on
16 of 44 references.
References · 16
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2022Generative Adversarial Networkscited by 5,627
- 2020Implicit Neural Representations with Periodic Activation Functionscited by 2,238
- 2022Scientific Machine Learning through Physics-Informed Neural Networks: Where we are and What's nextcited by 608
- 2021Physics-informed neural networks (PINNs) for fluid mechanics: A reviewcited by 473
- 2020On the eigenvector bias of Fourier feature networks: From regression to solving multi-scale PDEs with physics-informed neural networkscited by 284
- 2021Enhancing Computational Fluid Dynamics with Machine Learningcited by 138
- 2016Accelerating Eulerian Fluid Simulation With Convolutional Networkscited by 130
- 2021PhyCRNet: Physics-informed Convolutional-Recurrent Network for Solving Spatiotemporal PDEscited by 98
- 2021CAN-PINN: A Fast Physics-Informed Neural Network Based on Coupled-Automatic-Numerical Differentiation Methodcited by 93
- 2018Deep Learning of Vortex Induced Vibrationscited by 76
- 2021Learning in Sinusoidal Spaces with Physics-Informed Neural Networkscited by 62
4 more
- 2020A Physics-Informed Machine Learning Approach for Solving Heat Transfer Equation in Advanced Manufacturing and Engineering Applicationscited by 53
- 2020Variational Autoencoders for Learning Nonlinear Dynamics of Physical Systemscited by 50
- 2015Fully Connected Deep Structured Networkscited by 24
- 2019Poisson CNN: Convolutional neural networks for the solution of the Poisson equation on a Cartesian meshcited by 22
Built on by
Citing papers per year: 2026: 2.
2 papers.