The proposed study enhances the methodology for estimating rock mechanical properties, such as Young's modulus, through the innovative use of SEM images from drill cuttings in unconventional plays across North America. Unlike traditional methods that involve extensive lab measurements or interpretive well logs, our approach leverages image-based analyses, significantly reducing the subjectivity and computational burden often encountered in previous strategies.
In our analysis, we processed SEM images from 14 plays to extract both textural and shape-based features. Textural attributes such as entropy, homogeneity, contrast, and energy provide insights into the disorder and mineralogical contrasts within the rock, while shape-based features like area, aspect ratio, circularity, solidity, extent, eccentricity, Euler number, and orientation describe the geometric properties of mineral constituents. We utilized these attributes to construct various predictive models and integrating deep learning inputs to enhance accuracy.
Our models correlate these features with empirically measured Young’s modulus values using non-parametric regression. This integrated approach has shown to provide a robust and generalizable model capable of estimating Young's modulus across a diverse set of geological formations with high reliability, even when tested against previously unseen images.
The inclusion of both textural and shape attributes as proxies for mineralogy and their spatial arrangement addresses key controls in the mechanical behavior of rock samples. Notably, this study acknowledges the limitations related to textural attributes, such as their inability to fully account for complex pore systems like lenticular pores, which may lead to overestimations of Young's modulus. We addressed these challenges through targeted modifications in our methodology, thereby enhancing the model's applicability across varied mineralogical and porosity conditions.
Our findings indicate that the combination of texture and shape analyses, coupled with machine learning techniques, can efficiently and accurately predict mechanical properties in tight rocks. This method represents a significant advancement over traditional approaches, providing a fast, non-subjective, and computationally efficient tool for preliminary rock mechanics analysis. This work underscores the potential of using SEM image analyses as a powerful tool for rapid screening and detailed rock mechanics studies, moving towards more streamlined and data-driven exploration and production strategies.
