Generative Modeling of Turbulence

Abstract

We present a mathematically well founded approach for the synthetic modeling of turbulent flows using generative adversarial networks (GAN). Based on the analysis of chaotic, deterministic systems in terms of ergodicity, we outline a mathematical proof that GAN can actually learn to sample state snapshots form the invariant measure of the chaotic system. Based on this analysis, we study a hierarchy of chaotic systems starting with the Lorenz attractor and then carry on to the modeling of turbulent flows with GAN. As training data, we use fields of velocity fluctuations obtained from large eddy simulations (LES). Two architectures are investigated in detail: we use a deep, convolutional GAN (DCGAN) to synthesise the turbulent flow around a cylinder. We furthermore simulate the flow around a low pressure turbine stator using the pix2pixHD architecture for a conditional DCGAN being conditioned on the position of a rotating wake in front of the stator. The settings of adversarial training and the effects of using specific GAN architectures are explained. We thereby show that GAN are efficient in simulating turbulence in technically challenging flow problems on the basis of a moderate amount of training data. GAN training and inference times significantly fall short when compared with classical numerical methods, in particular LES, while still providing turbulent flows in high resolution. We furthermore analyse the statistical properties of the synthesized and LES flow fields, which agree excellently. We also show the ability of the conditional GAN to generalize over changes of geometry by generating turbulent flow fields for positions of the wake that are not included in the training data.

References in corpus (6)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Conditional Generative Adversarial Nets
• Generative Adversarial Networks
• The Real-World-Weight Cross-Entropy Loss Function: Modeling the Costs of Mislabeling
• An Equivalence of Fully Connected Layer and Convolutional Layer

Cited by in corpus (9)

• Deep Learning Methods for Partial Differential Equations and Related Parameter Identification Problems
• Physics-enhanced deep surrogates for partial differential equations
• Investigation of nonlocal data-driven methods for subgrid-scale stress modelling in large eddy simulation
• Turbulence Scaling from Deep Learning Diffusion Generative Models
• Spectrally Decomposed Diffusion Models for Generative Turbulence Recovery
• Generative Design of a Gas Turbine Combustor Using Invertible Neural Networks
• Neural Network Complexity of Chaos and Turbulence
• A multiscale and multicriteria Generative Adversarial Network to synthesize 1-dimensional turbulent fields
• Synthetic Turbulence via an Instanton Gas Approximation