Based on the microscopic assessment of rock microstructures from four reservoir lithologies with different compositions (presented in the ternary diagram) and their associated measured porosity and permeability (below), a machine learning model was traine (IMAGE)
Caption
Based on the microscopic assessment of rock microstructures from four reservoir lithologies with different compositions (presented in the ternary diagram) and their associated measured porosity and permeability (below), a machine learning model was trained to predict porosity and permeability. Based on SHAP (SHapley Additive exPlanations) beeswarm, waterfall, and dependance plots, geological criteria affecting predictions are extracted, to shed a new light in the post important properties controlling properties of porous media.
Credit
Benjamin Busch
Usage Restrictions
Credit must be given to the creator. Only noncommercial uses of the work are permitted. No derivatives or adaptations of the work are permitted.
License
CC BY-NC-ND