Predictions of turbulent shear flows using deep neural networks

TL;DR

This study demonstrates that deep neural networks, especially LSTM, can accurately predict the evolution of turbulent shear flows using a low-order model, paving the way for data-driven turbulence modeling.

Contribution

It introduces a neural network framework, particularly LSTM, for predicting turbulent flow dynamics, outperforming MLPs in accuracy and capturing key turbulence statistics.

Findings

LSTM outperforms MLP in flow prediction accuracy.

LSTM achieves low relative errors in turbulence statistics.

The approach can inform future turbulence modeling efforts.

Abstract

In the present work we assess the capabilities of neural networks to predict temporally evolving turbulent flows. In particular, we use the nine-equation shear flow model by Moehlis et al. [New J. Phys. 6, 56 (2004)] to generate training data for two types of neural networks: the multilayer perceptron (MLP) and the long short-term memory (LSTM) network. We tested a number of neural network architectures by varying the number of layers, number of units per layer, dimension of the input, weight initialization and activation functions in order to obtain the best configurations for flow prediction. Due to its ability to exploit the sequential nature of the data, the LSTM network outperformed the MLP. The LSTM led to excellent predictions of turbulence statistics (with relative errors of 0.45% and 2.49% in mean and fluctuating quantities, respectively) and of the dynamical behavior of the system (characterized by Poincar\'e maps and Lyapunov exponents). This is an exploratory study where we consider a low-order representation of near-wall turbulence. Based on the present results, the proposed machine-learning framework may underpin future applications aimed at developing accurate and efficient data-driven subgrid-scale models for large-eddy simulations of more complex wall-bounded turbulent flows, including channels and developing boundary layers.