NeuralFlowNet: Towards Data-Free Physics-Informed Neural Network Solutions of Navier-Stokes Equations Across Low and High Reynolds Numbers
Abstract
Physics-informed neural networks (PINNs) have emerged as a compelling pathway toward trustworthy artificial-intelligence-based computational fluid dynamics (CFD) by embedding governing equations directly into the learning process. Many existing AI flow models require large simulation or experimental datasets and often remain problem-specific, limiting their generalization and physical reliability. Data-free PINN frameworks offer an alternative by learning flow solutions from the Navier-Stokes equations and prescribed boundary conditions, potentially reducing dependence on expensive CFD datasets while retaining physical consistency. However, traditional PINN frameworks have struggled at high Reynolds numbers, limiting their application in CFD. In this work, we present NeuralFlowNet, a data-free, physics-informed proof-of-concept framework designed to solve steady Navier-Stokes problems across low- to high-Reynolds-number conditions. We describe the proposed methodological framework and demonstrate its applicability using benchmark problems with increasing physical and geometric complexity. The results demonstrate that NeuralFlowNet can accurately recover steady flow fields across a broad Reynolds-number range, including cases with strong pressure gradients, without training on external flow-field data and while maintaining good agreement with reference numerical solutions. These findings establish NeuralFlowNet as a reliable framework for future testing of unsteady and more complex simulations and could provide a basis for developing trustworthy and efficient AI solvers for high-Reynolds-number fluid dynamics.
Related
- Physics-informed neural networks for soliton solutions and parameter identification of the two-mode Korteweg–de Vries equation
- Physics-Informed Kolmogorov-Arnold networks for viscoelastic fluid equations
- Split Complex-Valued Physics-Informed Neural Networks for Forward and Inverse Nonlinear Partial Differential Equations
- Projection-based segregated, iterative, and multi-stage physics-informed neural network for incompressible Navier-stokes equations
- Physics-Informed Method of Group Data Handling: Adaptive Construction of Functional Representations with an Application to the Navier-Stokes Equations
BibTeX
@misc{samarasinghe2026neuralflownet,
title = {{NeuralFlowNet: Towards Data-Free Physics-Informed Neural Network Solutions of Navier-Stokes Equations Across Low and High Reynolds Numbers}},
author = {Jayanga T. Samarasinghe and Luis De la Fuente and Laura V. Alvarez},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2608.28935},
eprint = {2608.28935},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.28935},
}
RIS
TY - UNPB
TI - NeuralFlowNet: Towards Data-Free Physics-Informed Neural Network Solutions of Navier-Stokes Equations Across Low and High Reynolds Numbers
AU - Jayanga T. Samarasinghe
AU - Luis De la Fuente
AU - Laura V. Alvarez
PY - 2026
DA - 2026/09/07
PB - arXiv
DO - 10.48550/arxiv.2608.28935
UR - https://arxiv.org/abs/2608.28935
AB - Physics-informed neural networks (PINNs) have emerged as a compelling pathway toward trustworthy artificial-intelligence-based computational fluid dynamics (CFD) by embedding governing equations directly into the learning process. Many existing AI flow models require large simulation or experimental datasets and often remain problem-specific, limiting their generalization and physical reliability. Data-free PINN frameworks offer an alternative by learning flow solutions from the Navier-Stokes equations and prescribed boundary conditions, potentially reducing dependence on expensive CFD datasets while retaining physical consistency. However, traditional PINN frameworks have struggled at high Reynolds numbers, limiting their application in CFD. In this work, we present NeuralFlowNet, a data-free, physics-informed proof-of-concept framework designed to solve steady Navier-Stokes problems across low- to high-Reynolds-number conditions. We describe the proposed methodological framework and demonstrate its applicability using benchmark problems with increasing physical and geometric complexity. The results demonstrate that NeuralFlowNet can accurately recover steady flow fields across a broad Reynolds-number range, including cases with strong pressure gradients, without training on external flow-field data and while maintaining good agreement with reference numerical solutions. These findings establish NeuralFlowNet as a reliable framework for future testing of unsteady and more complex simulations and could provide a basis for developing trustworthy and efficient AI solvers for high-Reynolds-number fluid dynamics.
ER -