About this document
Spe 233385 Pa by Mahfoud AMMOUR is a document available to read on EtoBox.
This document presents a unified data-driven framework for estimating saturation-dependent relative permeability and capillary pressure in porous media using machine learning techniques, specifically through the fitting of generalized extreme value distributions. The proposed method demonstrates improved accuracy and computational efficiency compared to traditional Brooks-Corey and Burdine models, particularly for heterogeneous, bimodal pore/throat rocks. The machine learning models achieve a coefficient of
- Author
- Mahfoud AMMOUR
- Language
- EN