A data-driven framework for permeability prediction of natural porous rocks via microstructural characterization and pore-scale simulation

Abstract

Understanding the microstructure–property relationships of porous media is of great practical significance, based on which macroscopic physical properties can be directly derived from measurable microstructural informatics. However, establishing reliable microstructure–property mappings in an explicit manner is difficult, due to the intricacy, stochasticity, and heterogeneity of porous microstructures. In this paper, a data-driven computational framework is presented to investigate the inherent microstructure–permeability linkage for natural porous rocks, where multiple techniques are integrated together, including microscopy imaging, stochastic reconstruction, microstructural characterization, pore-scale simulation, feature selection, and data-driven modeling. A large number of 3D digital rocks with a wide porosity range are acquired from microscopy imaging and stochastic reconstruction techniques. A broad variety of morphological descriptors are used to quantitatively characterize pore microstructures from different perspectives, and they compose the raw feature pool for feature selection. High-fidelity lattice Boltzmann simulations are conducted to resolve fluid flow passing through porous media, from which reliable permeability references are obtained. The optimal feature set that best represents permeability is identified through a performance-oriented feature selection process, upon which a cost-effective surrogate model is rapidly fitted to approximate the microstructure-permeability mapping via data-driven modeling. This surrogate model exhibits great advantages over empirical/analytical formulas in terms of prediction accuracy and generalization capacity, which can predict reliable permeability values spanning four orders of magnitude. Besides, feature selection also greatly enhances the interpretability of the data-driven prediction model, from which new insights into the mechanism of how microstructural characteristics determine intrinsic permeability are obtained.

Machine Learning Assisted Prediction of Porosity and Related Properties Using Digital Rock Images

“…Previous studies reported that morphological properties like porosity, tortuosity, and pore-to-throat ratio correlate with the porous media’s permeability. 63 − 65 Our findings underscore the paramount role of tortuosity, which emerged as the most significant factor with an importance percentage of ∼28%, indicating the complexity of fluid paths within the rock as a crucial determinant of permeability. Additionally, porosity and pore region volume were identified as important features with importance percentages of ∼9%, highlighting the significance of void spaces within the rock for fluid storage and transmissibility.…”

“…Second, the 3D CNN algorithm is highly computationally intensive and requires excessive memory . In contrast, simple regression models like random forest (RF), support vector machine (SVM), and gradient boost (GB) algorithms are much easier to interpret and less memory intensive. , Further investigation is required to define a systematic workflow focusing on data preprocessing and predicting various petrophysical properties and microstructural characteristics of a digital rock sample. Furthermore, although numerous previously published works have used an image-based approach using CNN to predict permeability, significantly less focus has been placed on simple regression models, which are computationally less intensive than CNN.…”

Predicting and Analyzing Rock Mechanical Properties Using Image Processing Techniques

“…The accurate prediction of rock mechanical properties is of great importance for the design of geological engineering, disaster prevention, petroleum exploration, and other fields [1][2][3]. Traditional analyses of rock mechanical properties rely on macroscopic physical experiments, which are often timeconsuming, costly, and unable to reveal details at the microscopic level [4][5][6][7]. The microstructure of rocks, such as the size, distribution, and shape of grains and pores, directly affects their macroscopic mechanical behavior.…”