Machine learning assisted enhancement of petrophysical property dataset of fractured Variscan granites of the Cornubian Batholith, SW UK

Outcrop analogue studies play an important role in advancing our comprehension of reservoir architectures, offering insights into hidden reservoir rocks prior to drilling, in a cost-effective manner. These studies contribute to the delineation of the three-dimensional geometry of geological structures, the characterization of petro- and thermo-physical properties, and the structural geological aspects of reservoir rocks. Nevertheless, several challenges, including inaccessible sampling sites, limited resources, and the dimensional constraints of different laboratories hinder the acquisition of comprehensive datasets. In this study, we employ machine learning techniques to predict missing data in a petrophysical dataset of fractured Variscan granites from the Cornubian Batholith in Southwest UK. The utilization of mean, k-nearest neighbors, and random forest imputation methods addresses the challenge of missing data, thereby revealing the effectiveness of random forest imputation in providing realistic estimations. Subsequently, supervised classification models are trained to classify samples according to their pluton origins, with promising accuracy achieved by models trained with imputed values. Variable importance ranking of the models showed that the choice of imputation method influences the inferred importance of specific petrophysical properties. While porosity (POR) and grain density (GD) were among important variables, variables with high missingness ratio were not among the top variables. This study demonstrates the value of machine learning in enhancing petrophysical datasets, while emphasizing the importance of careful method selection and model validation for reliable results. The findings contribute to a more informed decision-making process in geothermal exploration and reservoir characterization efforts, thereby demonstrating the potential of machine learning in advancing subsurface characterization techniques. • New study aimed at predicting missing data in the recently published (on 02.02.2024) dataset of fractured Variscan granites. • Demonstrates the effectiveness of machine learning models (mean, k-nearest neighbors, and random forest imputation methods) in classifying granite samples by their pluton origins, showing high accuracy even when trained with imputed data. • Offering transferable findings for similar geological settings globally. • Offering a timely reassessment of the petrophysical dataset needed for geothermal projects that provide decarbonization and improved energy security.