Predicting the pore flow velocity directly from the sub-sampled pore structure is an ill-conditioned problem. Inspired by multi-grid methods for solving systems of linear equations, we use velocity fields simulated on coarse meshes to remedy such ill-conditioning. This leads to a super-resolution-assisted geometry-to-velocity mapping for porous media.
The methodology was developed by Xu-Hui Zhou and Dr. Heng Xiao at Virginia Tech: Data-Enabled Computational Mechanics Laboratory at Virgnia Tech.
This repository contains the code and data for the following paper(s):
- X-H. Zhou, J. McClure, C. Chen, and H. Xiao. Neural network--based pore flow field prediction in porous media using super resolution. Physical Review Fluids 7, 074302, 2022. DOI: 10.1103/PhysRevFluids.7.074302. Also available at arXiv: https://arxiv.org/abs/2109.09863
- Xu-Hui Zhou
- James McClure
- Cheng Chen
- Heng Xiao
Contact: Xu-Hui Zhou
Email address: [email protected]