English

Computing Residual Diffusivity by Adaptive Basis Learning via Super-Resolution Deep Neural Networks

Computational Physics 2019-10-02 v1 Numerical Analysis Numerical Analysis

Abstract

It is expensive to compute residual diffusivity in chaotic in-compressible flows by solving advection-diffusion equation due to the formation of sharp internal layers in the advection dominated regime. Proper orthogonal decomposition (POD) is a classical method to construct a small number of adaptive orthogonal basis vectors for low cost computation based on snapshots of fully resolved solutions at a particular molecular diffusivity D0D_{0}^{*}. The quality of POD basis deteriorates if it is applied to D0D0D_0\ll D_{0}^{*}. To improve POD, we adapt a super-resolution generative adversarial deep neural network (SRGAN) to train a nonlinear mapping based on snapshot data at two values of D0D_{0}^{*}. The mapping models the sharpening effect on internal layers as D0D_0 becomes smaller. We show through numerical experiments that after applying such a mapping to snapshots, the prediction accuracy of residual diffusivity improves considerably that of the standard POD.

Keywords

Cite

@article{arxiv.1910.00403,
  title  = {Computing Residual Diffusivity by Adaptive Basis Learning via Super-Resolution Deep Neural Networks},
  author = {Jiancheng Lyu and Jack Xin and Yifeng Yu},
  journal= {arXiv preprint arXiv:1910.00403},
  year   = {2019}
}
R2 v1 2026-06-23T11:31:36.901Z