3D CNN to predict single-phase flow velocity fields

Stanford Rock Physics & Borehole Geophysics (SRB) Digital Rock Physics (DRP) Toolbox. The codes include image creation, alteration, and computation of physical and geometrical properties.

The MultiScale Network for hierarchical regression (MS-Net) performs 3D regression based on a hierarchical principle: coarse inputs provide broad information about the data, and progressively finer-scale inputs can be used to refine this information.

Codes to measure the grain size distribution from thin sections or µXCT images. The distribution can be calculated based on the sieve method (volume-based), the laser diffraction (frequency-based) method, or the point-count method. The code outputs are (1) grain centroid - a matrix of Cartesian coordinates for each grain, (2) grain radius – a ma…

3D Porosity, Tortuosity, and Permeability Assessment in Randomly Generated 3D Savonnières Carbonate Samples