Permeability governs fluid transport in porous media and is crucial for optimal reservoir performance. Estimating permeability in tight rocks, such as organic shale or tight sandstones/carbonates, is technically challenging and often associated with significant uncertainties. Big data algorithms combined with mercury injection capillary pressure (MICP) analytics provide valuable insights into pore geometry and connectivity—key factors influencing permeability. Traditional methods proposed by Purcell (1949), Thomeer (1960), and Swanson (1981) are often constrained by limiting assumptions, hence constraining their effectiveness across heterogeneous rocks or various rock types. To address this challenge, we develop a generalized data-driven method leveraging large core data sets to estimate permeability across a diverse range of geological formations.

We analyzed 199 samples from 7 hydrocarbon fields, incorporating MICP and routine core analysis (RCA) data spanning marine mud, tight gas, carbonate, and sandstone formations. Parametric fitting was performed using Thomeer's method, Gaussian cumulative distribution and its probability distribution function (CDF-PDF), and generalized extreme-value (GEV) CDF-PDF. Optimized fitting parameters from GEV, including location (μ), scale (σgev), and weighting constraints, served as inputs for machine-learning methods to estimate permeability. Ridge regression, random forests, and artificial neural networks (ANNs) were applied to estimate logarithmic permeability from porosity and optimized parameters and benchmarked against Swanson's method.

The GEV CDF-PDF method achieved the strongest correlation with permeability, with an R2 of 95%. Incorporating Gaussian Mixture Modeling (GMM) with k-Means++ initialization enhanced the accuracy of the estimation. Ridge regression and random forests improved to 81%, while ANNs achieved 89%. In contrast, Swanson's method consistently overestimated permeability in tight rocks.

This universal method developed in this paper exhibits robust applicability and computational efficiency, yielding permeability estimations in under one minute of CPU time on standard hardware. Nonlinear machine-learning methods with regularization and ANN, combined with prior classification, are recommended for improved accuracy. Ensuring diverse training datasets is essential to maximize reliability of results as well as accurate permeability estimation across varied rock types.