Using Machine Learning to Augment Coarse-Grid Computational Fluid Dynamics Simulations

Abstract

Simulation of turbulent flows at high Reynolds number is a computationally challenging task relevant to a large number of engineering and scientific applications in diverse fields such as climate science, aerodynamics, and combustion. Turbulent flows are typically modeled by the Navier-Stokes equations. Direct Numerical Simulation (DNS) of the Navier-Stokes equations with sufficient numerical resolution to capture all the relevant scales of the turbulent motions can be prohibitively expensive. Simulation at lower-resolution on a coarse-grid introduces significant errors. We introduce a machine learning (ML) technique based on a deep neural network architecture that corrects the numerical errors induced by a coarse-grid simulation of turbulent flows at high-Reynolds numbers, while simultaneously recovering an estimate of the high-resolution fields. Our proposed simulation strategy is a hybrid ML-PDE solver that is capable of obtaining a meaningful high-resolution solution trajectory while solving the system PDE at a lower resolution. The approach has the potential to dramatically reduce the expense of turbulent flow simulations. As a proof-of-concept, we demonstrate our ML-PDE strategy on a two-dimensional turbulent (Rayleigh Number $Ra=10^9$) Rayleigh-Bénard Convection (RBC) problem.

Corrected typographical errors in the previous version related to the incorrectly formatted accented character "é" appearing in various places in the manuscript

Cited by in corpus (11)

• Machine learning accelerated computational fluid dynamics
• Stable a posteriori LES of 2D turbulence using convolutional neural networks: Backscattering analysis and generalization to higher Re via transfer learning
• Graph neural networks for laminar flow prediction around random 2D shapes
• Weak baselines and reporting biases lead to overoptimism in machine learning for fluid-related partial differential equations
• Learned discretizations for passive scalar advection in a 2-D turbulent flow
• Discovery of interpretable structural model errors by combining Bayesian sparse regression and data assimilation: A chaotic Kuramoto-Sivashinsky test case
• HYPPO: A Surrogate-Based Multi-Level Parallelism Tool for Hyperparameter Optimization
• Accelerating GMRES with Deep Learning in Real-Time
• A Model-Constrained Tangent Slope Learning Approach for Dynamical Systems
• Using machine-learning modelling to understand macroscopic dynamics in a system of coupled maps
• Machine learning accelerated particle-in-cell plasma simulations