4.2 Article

Dimension reduced turbulent flow data from deep vector quantisers

期刊

JOURNAL OF TURBULENCE
卷 23, 期 4-5, 页码 232-264

出版社

TAYLOR & FRANCIS LTD
DOI: 10.1080/14685248.2022.2060508

关键词

Turbulence; deep learning; data compression; vector qunatisation; physics-informed machine learning

资金

  1. National Science Foundation [ACI-1548562]
  2. Office of Naval Research (ONR) [N00014-18-1-2244]

向作者/读者索取更多资源

This study applies a physics-informed deep learning technique based on vector quantisation to compress three-dimensional turbulent flow simulations, generating a discrete low-dimensional representation. The accuracy of the model is validated using statistical, comparison-based similarity, and physics-based metrics. Compared to a conventional autoencoder, this model demonstrates significant improvements in compression ratio and mean square error. This compression model is an attractive solution for situations requiring fast, high-quality, and low-overhead encoding and decoding of large data.
Analysing large-scale data from simulations of turbulent flows is memory intensive, requiring significant resources. This major challenge highlights the need for data compression techniques. In this study, we apply a physics-informed Deep Learning technique based on vector quantisation to generate a discrete, low-dimensional representation of data from simulations of three-dimensional turbulent flows. The deep learning framework is composed of convolutional layers and incorporates physical constraints on the flow, such as preserving incompressibility and global statistical characteristics of the velocity gradients. The accuracy of the model is assessed using statistical, comparison-based similarity and physics-based metrics. The training data set is produced from Direct Numerical Simulation of an incompressible, statistically stationary, isotropic turbulent flow. The performance of this lossy data compression scheme is evaluated not only with unseen data from the stationary, isotropic turbulent flow, but also with data from decaying isotropic turbulence, a Taylor-Green vortex flow, and a turbulent channel flow. Defining the compression ratio (CR) as the ratio of original data size to the compressed one, the results show that our model based on vector quantisation can offer CR= 85 with a mean square error (MSE) of O(10(-3)), and predictions that faithfully reproduce the statistics of the flow, except at the very smallest scales where there is some loss. Compared to the recent study of Glaws. et al. [Deep learning for in situ data compression of large turbulent flow simulations. Phys Rev Fluids. 2020;5(11):114602], which was based on a conventional autoencoder (where compression is performed in a continuous space), our model improves the CR by more than 30%, and reduces the MSE by an order of magnitude. Our compression model is an attractive solution for situations where fast, high quality and low-overhead encoding and decoding of large data are required.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.2
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据