[Paper Review] Physics-Informed Neural Networks for Turbulence Modeling

Paper Information#

• Authors: Raissi, M., Perdikaris, P., Karniadakis, G. E.
• Journal: Journal of Computational Physics, Vol. 378, pp. 686–707, 2019
• DOI: 10.1016/j.jcp.2018.10.045
• arXiv: 1711.10561

One-Line Summary#

The paper proposes a method to reconstruct the entire velocity field from just a few pressure sensors by embedding the Navier-Stokes equations directly into the neural network's loss function (Physics-Informed).

Background#

Existing CFD methods sit somewhere between two extremes.

Traditional Methods (k-ε, k-ω SST): Rely on empirical closure coefficients. These coefficients must be re-tuned when the Reynolds number or geometry changes, limiting generalization capability.

Pure Data-Driven Deep Learning: Requires large amounts of labeled data, and the trained models do not guarantee mass or momentum conservation. The loss function is unaware if the model produces physically nonsensical predictions.

PINNs attempt to bridge this gap. Even with sparse data, physical laws act as a regularizer.

Core Methodology#

The total loss function of a PINN is the sum of two terms:

$\mathcal{L} = \mathcal{L}_{\text{data}} + \lambda \, \mathcal{L}_{\text{physics}}$

Data Loss $\mathcal{L}_{\text{data}}$ is the difference between observations (e.g., pressure sensors) and neural network predictions.

Physics Loss $\mathcal{L}_{\text{physics}}$ is the residual of the incompressible Navier-Stokes equations:

$\mathcal{L}_{\text{physics}} = \left\| \frac{\partial \mathbf{u}}{\partial t} + (\mathbf{u} \cdot \nabla)\mathbf{u} + \nabla p - \frac{1}{Re}\nabla^2\mathbf{u} \right\|^2 + \left\| \nabla \cdot \mathbf{u} \right\|^2$

The second term is the continuity equation (mass conservation). Since the neural network is trained to minimize this residual toward zero, the predictions always approximately satisfy the N-S equations.

Derivatives are calculated using automatic differentiation in PyTorch/TensorFlow, eliminating the need for separate numerical discretization.

Key Results#

The inverse problem capability is particularly impressive. It is possible to estimate the Reynolds number from the flow field or restore a hidden pressure field from velocity data alone—problems that are impossible or extremely difficult with traditional methods.

Practical Applicability#

When is it useful?

• Situations with sparse experimental measurement data (only a few sensors available).
• Inverse problems: When physical properties (viscosity, Re) need to be calculated back from measurements.
• Physics-based data interpolation: Filling in gaps in experimental data using physical laws.

Can it replace OpenFOAM/Fluent immediately?

Not yet. Training time is tens to hundreds of times slower than an FVM solver. A simple channel flow can take several hours on a GPU. It is currently unsuitable for real-time engineering analysis.

However, research into hybrid use with OpenFOAM is active—using FVM for an approximate solution and PINN for fine-grained calibration.

# Example of physics loss calculation implemented in PyTorch
def physics_loss(model, x, t, Re):
    x.requires_grad_(True)
    t.requires_grad_(True)
 
    output = model(x, t)
    u, v, p = output[:, 0], output[:, 1], output[:, 2]
 
    # Calculate partial derivatives using automatic differentiation
    u_t = torch.autograd.grad(u.sum(), t, create_graph=True)[0]
    u_x = torch.autograd.grad(u.sum(), x, create_graph=True)[0][:, 0]
    u_y = torch.autograd.grad(u.sum(), x, create_graph=True)[0][:, 1]
    p_x = torch.autograd.grad(p.sum(), x, create_graph=True)[0][:, 0]
 
    # X-momentum equation residual
    residual_u = u_t + u * u_x + v * u_y + p_x - (1/Re) * (u_x + u_y)
 
    return (residual_u**2).mean()

Limitations and Future Work#

Current Limitations:

• Difficulty scaling to 3D high-Re turbulent flows. Neural networks have limits in representing high-frequency components (small eddies).
• Training becomes unstable for stiff PDEs (very high Re or thin boundary layers).
• Standard PINNs do not provide Uncertainty Quantification (UQ), making it hard to know how reliable a prediction is.

Future Directions:

• XPINNs (Extended PINNs): Domain decomposition for parallel training → scalability for large-scale problems.
• OpenFOAM Hybrid Solvers: Combining FVM + PINN.
• Transfer learning: Quickly adapting a model trained at one Re to another Re.

“

Bottom Line: "A paper that defines the intersection of CFD and deep learning. While it won't replace OpenFOAM right now, it is already practical for inverse problems and sparse data reconstruction."

Tweak λ_PDE / λ_BC / λ_data to see how brittle the PINN loss balance is.