May 31, 2021 to June 4, 2021
Europe/Berlin timezone

Deep learning enhancement of micro-CT images for large-scale flow simulation

May 31, 2021, 10:25 AM
Oral Presentation (MS15) Machine Learning and Big Data in Porous Media MS15


Dr Samuel Jackson (CSIRO)


There are inherent resolution and field-of-view trade-offs in X-Ray micro-computed tomography imaging, which limit the characterization, analysis and model development of porous systems with multi-scale heterogeneities. In this work, we overcome these tradeoffs by utilising a deep convolution neural network to create enhanced, high-resolution data over large spatial scales from low-resolution data.

We use paired high-resolution (2 micrometres) and low-resolution (6 micrometres) images from two structurally-different Bentheimer rock samples to train an Enhanced Deep Super Resolution (EDSR) convolutional neural network. The generated high-resolution images are validated against the true high-resolution images through textual analysis, segmentation behaviour and pore-network model (PNM) multiphase flow simulations. The final trained EDSR network is then used to generate high-resolution digital rock cores of the whole samples with dimensions of 1.2cm × 1.2cm × 6-7cm. The 3D digital rock cores are populated with continuum properties predicted from subvolume PNMs, and used to simulate a range of experimental multiphase flow experiments. We present a consistent workflow to analyse multi-scale heterogeneous systems that are otherwise intractable using conventional methods.

Time Block Preference Time Block A (09:00-12:00 CET)
Acceptance of Terms and Conditions Click here to agree

Primary author

Dr Samuel Jackson (CSIRO)


Yufu Niu (University of New South Wales) Sojwal Manoorkar Peyman Mostaghimi Ryan Armstrong

Presentation materials

There are no materials yet.