

Article
Predictions of turbulent shear flows using deep neural networks
Authors: 
Srinivasan, P. A., Guastoni, L., Azizpour, H., Schlatter, P., Vinuesa, R. 
Document Type: 
Article 
Pubstate: 
Published 
Journal: 
Physical Review Fluids 
Volume: 
4
054603 
Year: 
2019 
AbstractIn the present work we assess the capabilities of neural networks to predict temporally evolving turbulent flows. In particular, we use the nineequation 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 shortterm 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 Poincaré maps and Lyapunov exponents). This is an exploratory study where we consider a loworder representation of nearwall turbulence. Based on the present results, the proposed machinelearning framework may underpin future applications aimed at developing accurate and efficient datadriven subgridscale models for largeeddy simulations of more complex wallbounded turbulent flows, including channels and developing boundary layers.

