Digital Rock Typing DRT Algorithm Formulation with Optimal Supervised Semantic Segmentation
This addresses the need for non-destructive rock property analysis for scientists and engineers in geology and petroleum engineering, but appears incremental as it builds on existing digital rock physics and rock typing approaches.
The paper tackles the problem of rock typing in geological models by proposing a Digital Rock Typing (DRT) algorithm that integrates digital rock physics advances and computer vision to classify rock types from micro-CT and MRI images, aiming to replace destructive laboratory methods.
Each grid block in a 3D geological model requires a rock type that represents all physical and chemical properties of that block. The properties that classify rock types are lithology, permeability, and capillary pressure. Scientists and engineers determined these properties using conventional laboratory measurements, which embedded destructive methods to the sample or altered some of its properties (i.e., wettability, permeability, and porosity) because the measurements process includes sample crushing, fluid flow, or fluid saturation. Lately, Digital Rock Physics (DRT) has emerged to quantify these properties from micro-Computerized Tomography (uCT) and Magnetic Resonance Imaging (MRI) images. However, the literature did not attempt rock typing in a wholly digital context. We propose performing Digital Rock Typing (DRT) by: (1) integrating the latest DRP advances in a novel process that honors digital rock properties determination, while; (2) digitalizing the latest rock typing approaches in carbonate, and (3) introducing a novel carbonate rock typing process that utilizes computer vision capabilities to provide more insight about the heterogeneous carbonate rock texture.