Unsupervised Electrofacies Classification and Porosity Characterization in the Offshore Keta Basin Using Wireline Logs

2026-04-29

AI Summary

In the context of scarce core data from the Keta Basin offshore Ghana, conventional approaches to electrofacies classification and porosity characterization are significantly constrained. This study proposes an unsupervised machine learning framework that relies solely on well-log data to perform multivariate clustering on approximately 11,195 depth samples from Well C. The optimal K-means clustering configuration is determined using metrics such as inertia and silhouette score, yielding four geologically meaningful electrofacies units with an average silhouette coefficient of approximately 0.50. These units effectively delineate a continuous depositional sequence ranging from shale to clean sandstone, capturing variations in clay content, porosity, and rock matrix composition. The methodology offers a reproducible and practical workflow for early-stage stratigraphic evaluation in frontier offshore basins where core data are unavailable.

Abstract

This study presents an unsupervised machine learning workflow for electrofacies analysis in the offshore Keta Basin, Ghana, where core data are scarce. Six standard wireline logs from Well~C were analysed over a depth interval comprising approximately $11{,}195$ samples. K-means clustering was applied in multivariate log space, with the clustering structure evaluated using inertia and silhouette diagnostics. Four clusters were identified, supported by an average silhouette coefficient of approximately $0.50$, indicating moderate but meaningful separation. The resulting electrofacies exhibit systematic, depth-continuous patterns associated with variations in clay content, porosity, and rock framework properties, forming a geological continuum from shale-dominated to cleaner sandstone-dominated units. The results demonstrate that log-only, unsupervised clustering supported by quantitative metrics provides a robust and reproducible framework for subsurface characterisation. The proposed workflow offers a practical tool for early-stage formation evaluation in frontier offshore basins and a foundation for future integrated studies.

Problem

• electrofacies classification
• porosity characterization
• unsupervised learning
• wireline logs
• offshore basin

Innovation

• unsupervised machine learning
• electrofacies classification
• wireline log analysis
• K-means clustering
• porosity characterization