Neural network models for preferential concentration of particles in two-dimensional turbulence

TL;DR

This paper evaluates various neural network models, especially GANs, for synthesizing particle concentration fields in 2D turbulence, demonstrating superior performance of GANs and exploring applications like supersampling and flow statistics prediction.

Contribution

It compares multiple neural network architectures for particle concentration synthesis in turbulence and introduces supersampling to reduce DNS computational costs.

Findings

GANs outperform other models in predicting clusters and voids

Neural networks can effectively perform supersampling of particle data

Potential to predict flow statistics from particle measurements

Abstract

Cluster and void formations are key processes in the dynamics of particle-laden turbulence. In this work, we assess the performance of various neural network models for synthesizing preferential concentration fields of particles in turbulence. A database of direct numerical simulations of homogeneous isotropic two-dimensional turbulence with one-way coupled inertial point particles, is used to train the models using vorticity as the input to predict the particle number density fields. We compare autoencoder, U--Net, generative adversarial network (GAN), and diffusion model approaches, and assess the statistical properties of the generated particle number density fields. We find that the GANs are superior in predicting clusters and voids, and therefore result in the best performance. Additionally, we explore a concept of ``supersampling", where neural networks can be used to predict full particle data using only the information of few particles, which yields promising perspectives for reducing the computational cost of expensive DNS computations by avoiding the tracking of millions of particles. We also explore the inverse problem of synthesizing the enstrophy fields using the particle number density distribution as the input at different Stokes numbers. Hence, our study also indicates the potential use of neural networks to predict turbulent flow statistics using experimental measurements of inertial particles.