Figure 3 - available via license: Creative Commons Attribution-ShareAlike 4.0 International
Content may be subject to copyright.
Download
View publication
Simulated concentration field c (top) and mass flux magnitude | j | (bottom) on a 100 3 voxel cube. The left column presents Sample (0,1), the right one Sample (0,0.5) corresponding to the wetting-phase distribution of Sample (0,1) at sw = 0.5.

Simulated concentration field c (top) and mass flux magnitude | j | (bottom) on a 100 3 voxel cube. The left column presents Sample (0,1), the right one Sample (0,0.5) corresponding to the wetting-phase distribution of Sample (0,1) at sw = 0.5.

Source publication
Figure 3: Simulated concentration field c (top) and mass flux magnitude...
Figure 4: Relative diffusion D rel over partial saturation sw for 18...
Figure 5: Correlation between relative diffusion D rel and partial...
Figure 6: Accuracy of CNN predictions: Correlation plots between...
Estimating relative diffusion from 3D micro-CT images using CNNs
Preprint
Full-text available
  • Aug 2022
In the past several years, convolutional neural networks (CNNs) have proven their capability to predict characteristic quantities in porous media research directly from pore-space geometries. Due to the frequently observed significant reduction in computation time in comparison to classical computational methods, bulk parameter prediction via CNNs...
Cite
Download full-text

Context in source publication

Context 1
... performed on an unrefined mesh already provide sufficient accuracy for our purposes. In Figure 3, we illustrate the concentration fields and diffu- ...