Advancing Artificial Neural Network Parameterization for Atmospheric Turbulence Using a Variational Multiscale Model

Data-driven parameterizations offer considerable potential for improving the fidelity of General Circulation Models. However, ensuring that these remain consistent with the governing equations while still producing stable simulations remains a challenge. In this paper, we propose a combined Variational-Multiscale (VMS) Artificial Neural...

Application and extension of a data-driven turbulence modeling method using Machine Learning

In recent years, many data-driven approaches which leverage high-fidelity reference data have been developed to augment the performance of Reynolds Averaged Navier–Stokes (RANS) turbulence models by providing an improved closure to the governing fluid flow equations. The goal of this M.Sc. thesis is to apply and extend one such data-driven...

Data driven turbulence modelling

RANS simulation are one of the most used tools for aerodynamic analysis. The advantage of RANS simulations is the reduced computational cost compared to other methods such as LES or DNS. This is because by solving the RANS equations one only solves for the mean flow. However, this reduction in computational cost comes at the price of uncertainty...

Inferring algebraic stress models from high-fidelity data and applying machine learning to enhance and generalize turbulence lag models

Adverse pressure gradients, separation and other forms of non-equilibrium flows are often encountered in flows of interest. In these type of flows, the Boussinesq hypothesis does not hold and often leads to erroneous predictions by eddy viscosity models. In an attempt to capture these non-equilibrium effects, lag parameter models introduce a lag...

Machine Learning of Atmospheric Turbulence in a Variational Multiscale Model

Today's leading projections of climate change predicate on Atmospheric General Circulation Models (GCMs). Since the atmosphere consists of a staggering range of scales that impact global trends, but computational constraints prevent many of these scales from being directly represented in numerical simulations, GCMs require "parameterisations'' -...

A Machine Learning Approach to Unresolved-Scale Modeling for Burgers’ Equation

This thesis is part of a greater effort to use machine learning for the development of flexible and universal unresolved-scale models in large eddy simulation (LES). The novelty in the current work is that a neural network learns to predict the integral forms of the unresolved-scale terms directly without a priori assumptions on the underlying...

Field inversion and machine learning in turbulence modeling

Turbulence closure models will continue to be necessary in order to perform computationally affordable simulations in the foreseeable future. It is expected that Reynolds-averaged Navier-Stokes (RANS) turbulence models will still be useful with the further development of the more accurate, but computationally expensive large eddy simulation (LES...

Machine Learning for Data-Driven RANS Turbulence Modelling

The application of machine learning algorithms as data-driven turbulence modelling tools for Reynolds Averaged Navier-Stokes (RANS) simulations is presented. A novel machine learning algorithm, called the Tensor Basis Random Forest (TBRF) is introduced, which is able to predict the Reynolds stress anisotropy tensor. The algorithm is trained on...