Forecasting small scale dynamics of fluid turbulence using deep neural networks

Abstract

Turbulent flows consist of a wide range of interacting scales. Since the scale range increases as some power of the flow Reynolds number, a faithful simulation of the entire scale range is prohibitively expensive at high Reynolds numbers. The most expensive aspect concerns the small scale motions; thus, major emphasis is placed on understanding and modeling them, taking advantage of their putative universality. In this work, using physics-informed deep learning methods, we present a modeling framework to capture and predict the small scale dynamics of turbulence, via the velocity gradient tensor. The model is based on obtaining functional closures for the pressure Hessian and viscous Laplacian contributions as functions of velocity gradient tensor. This task is accomplished using deep neural networks that are consistent with physical constraints and incorporate Reynolds number dependence explicitly to account for small-scale intermittency. We then utilize a massive direct numerical simulation database, spanning two orders of magnitude in the large-scale Reynolds number, for training and validation. The model learns from low to moderate Reynolds numbers, and successfully predicts velocity gradient statistics at both seen and higher (unseen) Reynolds numbers. The success of our present approach demonstrates the viability of deep learning over traditional modeling approaches in capturing and predicting small scale features of turbulence.

arXiv comment12 pages, 5 figures

References in corpus (20)

• Turbulence Modeling in the Age of Data
• Deep Neural Networks for Data-Driven Turbulence Models
• Unsupervised deep learning for super-resolution reconstruction of turbulence
• Lagrangian Tetrad Dynamics and the Phenomenology of Turbulence
• Lagrangian dynamics and statistical geometric structure of turbulence
• Extreme velocity gradients in turbulent flows
• Anomalous Scaling of Structure Functions and Dynamic Constraints on Turbulence Simulations
• Pressure Hessian and viscous contributions to velocity gradient statistics based on Gaussian random fields
• Vortex stretching and enstrophy production in high Reynolds number turbulence
• Self-attenuation of extreme events in Navier-Stokes turbulence
• Dissipation range of the energy spectrum in high Reynolds number turbulence
• A closure for Lagrangian velocity gradient evolution in turbulence using recent deformation mapping of initially Gaussian fields
• Small-scale isotropy and ramp-cliff structures in scalar turbulence
• Turbulence is an ineffective mixer when Schmidt numbers are large
• Vorticity-strain rate dynamics and the smallest scales of turbulence
• Generation of intense dissipation in high Reynolds number turbulence
• Intermittency of turbulent velocity and scalar fields using 3D local averaging
• Capturing Velocity Gradients and Particle Rotation Rates in Turbulence
• A highly scalable particle tracking algorithm using partitioned global address space (PGAS) programming for extreme-scale turbulence simulations
• Lagrangian acceleration in fully developed turbulence and its Eulerian decompositions

Cited by in corpus (5)

• Simulating fluid flows with quantum computing
• Saturation and multifractality of Lagrangian and Eulerian scaling exponents in 3D isotropic turbulence
• Role of pressure in generation of intense velocity gradients in turbulent flows
• Generalization capabilities and robustness of hybrid models grounded in physics compared to purely deep learning models
• Universality of extreme events in turbulent flows