Machine learning prediction of deepwater slope-channel facies using core-analogous outcrop observations

Abstract

Sedimentological (SED) data is often qualitative, making combining it with Machine Learning (ML) workflows challenging. SED data in subsurface exploration incorporates qualitative interpretations that remain valuable to subsequent exploration efforts. These exploration projects often have access to geologic core data that is limited spatially, making subsurface interpretation difficult and highly uncertain. Incorporating core-like data into ML workflows provides a framework to generate consistent interpretation over large datasets. ML, a technique already employed in well-log interpretation, represents an advantage over manual interpretation methods which are time intensive and introduce errors and bias. This research investigates methods to automate geologic interpretation (specifically of sedimentary facies) through ML techniques. Sedimentological observations (grain size, bed thickness) from outcrop measured sections in the deepwater slope strata of the Magallanes Basin provide training and testing features to make ML predictions (classifications) of human-interpreted geologic facies. The study employs seven ML techniques (K-Means, Least Squares Regression, Logistic Regression, Linear Discriminant Analysis, Quadratic Discriminant Analysis, Random Forest, and Neural Networks) to investigate the problem of facies prediction from multiple methodological angles. The results show that some ML methods are not suitable for this classification problem due to their architecture or the qualitative aspects of manually collected SED data. Supervised methods generally provide better results than unsupervised methods (PCA and K-Means). Supervised ML both produces better raw performance metrics (Accuracy, BedThickness Normalized, Accuracy, Recall) than K-Means, and generates qualitatively better predictions of measured sections (Fig. 48; Fig. 49). Among methods that are suitable, a random forest model generates the best facies prediction performance.