Predictions of turbulent shear flows using deep neural networks

2019/05/07 by Prem A. Srinivasan, P. A. Srinivasan, L. Guastoni +12 · 9 citations
Engineering · Physics and Astronomy · #Computational Physics (physics.comp-ph) #FOS: Physical sciences #Fluid Dynamics (physics.flu-dyn) #Fluid Dynamics and Turbulent Flows #Fluid Dynamics and Vibration Analysis #Model Reduction and Neural Networks #physics.comp-ph #physics.flu-dyn

paper · pdf · doi:10.48550/arxiv.1905.03634

arxiv created 2019/05/07 · openalex publication_date 2019/05/07 · arxiv updated 2019/05/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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 Poincaré 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.

Cited by

• Prediction performance of random reservoirs with different topology for nonlinear dynamical systems with different number of degrees of freedom
• Efficient probabilistic surrogate modeling techniques for partially-observed large-scale dynamical systems
• Extreme Event Precursor Prediction in Turbulent Dynamical Systems via CNN-Augmented Recurrence Analysis
• PVD-ONet: A Multi-scale Neural Operator Method for Singularly Perturbed Boundary Layer Problems
• From large-eddy simulations to deep learning: A U-net model for fast urban canopy flow predictions
• Surrogate normal-forms for the numerical bifurcation and stability analysis of navier-stokes flows via machine learning
• PICT -- A Differentiable, GPU-Accelerated Multi-Block PISO Solver for Simulation-Coupled Learning Tasks in Fluid Dynamics
• A novel hybrid neural network of fluid-structure interaction prediction for two cylinders in tandem arrangement
• Machine-learning-based simulation of turbulent flows over periodic hills using a hybrid U-Net and Fourier neural operator framework

Related

• On the use of recurrent neural networks for predictions of turbulent flows
• Predicting the temporal dynamics of turbulent channels through deep learning
• Towards Long-Term predictions of Turbulence using Neural Operators
• Using LSTM Predictions for RANS Simulations
• Modeling Turbulent Flows with LSTM Neural Network