English

Differentiable Turbulence: Closure as a partial differential equation constrained optimization

Fluid Dynamics 2024-03-29 v2 Machine Learning

Abstract

Deep learning is increasingly becoming a promising pathway to improving the accuracy of sub-grid scale (SGS) turbulence closure models for large eddy simulations (LES). We leverage the concept of differentiable turbulence, whereby an end-to-end differentiable solver is used in combination with physics-inspired choices of deep learning architectures to learn highly effective and versatile SGS models for two-dimensional turbulent flow. We perform an in-depth analysis of the inductive biases in the chosen architectures, finding that the inclusion of small-scale non-local features is most critical to effective SGS modeling, while large-scale features can improve pointwise accuracy of the \textit{a-posteriori} solution field. The velocity gradient tensor on the LES grid can be mapped directly to the SGS stress via decomposition of the inputs and outputs into isotropic, deviatoric, and anti-symmetric components. We see that the model can generalize to a variety of flow configurations, including higher and lower Reynolds numbers and different forcing conditions. We show that the differentiable physics paradigm is more successful than offline, \textit{a-priori} learning, and that hybrid solver-in-the-loop approaches to deep learning offer an ideal balance between computational efficiency, accuracy, and generalization. Our experiments provide physics-based recommendations for deep-learning based SGS modeling for generalizable closure modeling of turbulence.

Keywords

Cite

@article{arxiv.2307.03683,
  title  = {Differentiable Turbulence: Closure as a partial differential equation constrained optimization},
  author = {Varun Shankar and Dibyajyoti Chakraborty and Venkatasubramanian Viswanathan and Romit Maulik},
  journal= {arXiv preprint arXiv:2307.03683},
  year   = {2024}
}
R2 v1 2026-06-28T11:24:41.156Z