Real-Time Horizontal Well Correlation Automation: Enhancing Well Placement through Predictive Log Curve Analysis

Abstract Horizontal drilling operations require precise well placement to maximize reservoir exposure and minimize geological uncertainties. Complex scenarios, such as navigating thin sand stringers or avoiding oil-water and gas-water contacts, demand meticulous planning and execution. However, conventional manual correlation methods for horizontal wells are labor-intensive, prone to human error, and can result in suboptimal well placement decisions. This paper introduces a geosteering automation system that leverages predictive analytics to enhance correlation processes during horizontal drilling operations. The proposed workflow incorporates predefined criteria such as well segmentation, search radius and well's inclination to identify relevant offset wells. Well logs are predicted and dynamically compared with actual well logs in real time, generating a matching score that quantifies the correlation accuracy between curves. This real-time process delivers continuous updates to the geological model, enabling precise landing and well placement with accurate determination of distances to reservoir top and fluid contacts, resulting in improved structural modeling throughout the horizontal section. The proposed methodology offers significant advancements for the reservoir development using geosteering techniques. Thereby facilitating precise well landing and optimal well placement, along with real-time dynamic updates of the geological model, ensuring reliable estimation of bed boundaries and clearance from fluid contacts. This innovative approach keeps the asset team informed about the structural changes, stratigraphic positioning, and the reservoir property estimates, enabling well trajectory updates in real-time during the drilling process. Implementing this comprehensive workflow is expected to have a significant positive impact, leading to increased drilling efficiency, reduced geological uncertainty, and enhanced accuracy in decision-making processes throughout the entire operational framework. This paper presents a novel automation framework that revolutionizes the horizontal well correlation process enabling operational geologists to make rapid, informed decisions during drilling. The system fosters collaborative, data-driven decision-making among the drilling team, optimizing hydrocarbon recovery while reducing costs associated with suboptimal trajectories and unnecessary tool deployments. This innovative methodology supports integration of advanced AI-based workflows, establishing a new benchmark for geosteering automation in horizontal drilling.