Differentiable Turbulence: Closure as a partial differential equation constrained optimization

arXiv:2307.03683v2 Announce Type: replace-cross
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 …

abstract accuracy arxiv combination concept cs.lg deep learning differentiable differential differential equation equation grid improving optimization physics physics.flu-dyn scale sgs simulations solver turbulence type