LukasMosser/PorousMediaGan

Reconstruction of three-dimensional porous media using generative adversarial neural networks

49
/ 100
Emerging

This project helps geoscientists and engineers working with subsurface rock formations to generate realistic 3D models of porous media, such as sandstone or beadpacks. By inputting real CT scan data of a porous material, it produces new, statistically similar 3D porous media structures. This is ideal for researchers studying fluid flow, reservoir behavior, or material properties who need to explore various microstructures.

189 stars. No commits in the last 6 months.

Use this if you need to create numerous synthetic 3D pore-scale models that capture the complex geometry of real rock samples for simulation and analysis.

Not ideal if you need to analyze existing images or perform direct simulations without generating new microstructures, or if you lack access to CT scan data for training.

porous-media-modeling geoscience petroleum-engineering materials-science rock-characterization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

189

Forks

68

Language

Jupyter Notebook

License

MIT

Last pushed

Aug 02, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/LukasMosser/PorousMediaGan"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.