With the emergence of digital rock analysis, its application to whole cores and derived samples is bringing a tremendous help in their analysis and characterization.
While visualization of core data is indeed an appreciated support, derived digital properties bring crucial information to validate and enhance laboratory analysis.
In this paper, we will go further, by applying feature augmentation Machine Learning models applied to Whole Core for facies identification. The main goal being to help petrophysicists and geologists to determine geological and petrophysical facies, by both bringing added value and filling missing information in their estimation, and applying a model defined on a subset to a whole well, in order to dramatically accelerate its characterization.
We will apply the methodology to 35 meters of cored well data acquired from the Late Jurassic Upper Jubayla Formation, equivalent to the lower Arab-D reservoir in Saudi Arabia. The main goal of the study will be to bring machine learning models from original and derived digital rock properties, to automatically extract facies in the whole well, from a preliminary definition of the geological and petrophysical facies.
We will first present how a dynamic visualization platform, capable of mixing 3D CT data, Bore Hole images, Wireline Logs, thin sections, can be used as a database and complement laboratory analysis. Then, we will derive digital rock data, such as textural rock types segmentation, whole core CT intensity and heterogeneity logs, porosity estimation from thin sections, pore size distributions, porosity logs, petrophysical properties from extracted plugs scanned with microCT, and integrate them in the visualization ecosystem, in order to fill missing features, and enhance the well description. We will show the preliminary description of the different facies in a sub section of the core, obtained by laboratory and human analysis. Then, we will expose and prove how machine learning models developed with Python using third party libraries, applied to the whole well, can automatically determine rock facies by augmenting the preliminary analysis by the integration of digital rock derived properties. We will be able to compare the numerical scores obtained by the evaluation metrics, depending on the digital rock used entries, and then propose a robust and trustable model.
