Innovative AI-Driven Core Image Analysis for Reservoir Characterization

Abstract This study introduces an AI-driven workflow designed to predict oil saturation along with geological facies from core images, addressing the limitations associated with traditional wireline logging and the inherent subjectivity of visual core analyses. Specifically, the method targets operational scenarios where logging is unavailable or limited due to operational and HSE restrictions, and where core or cutting samples represent primary datasets. The method systematically classifies color variations from core images captured under both ambient white light and ultraviolet (UV) illumination using (1) Photoshop’s color-detection tools and (2) unsupervised machine learning techniques (e.g., Principal Component Analysis and K-means clustering). A custom-developed application converts these classified color features into quantitative saturation logs, automating workflows traditionally performed visually or semi-quantitatively by geologists. Validation against conventional saturation logs demonstrated a strong quantitative agreement, ensuring reliability. Notably, the method proved highly adaptable, and hence can be demonstrating utility for analyzing cutting samples in the absence of core data or wireline logs. The significant novelty lies in transforming previously unused qualitative image data into actionable quantitative insights, effectively bridging qualitative visual assessment with quantitative reservoir characterization. This advancement offers scalable and practical solutions, significantly enhancing subsurface evaluation capabilities and reservoir characterization accuracy, particularly in challenging operational contexts.