• Benarbia, A.
• Khalifa, Houdaifa
• Dehdouh, A.
• Berrehal, B. E.
• Tomomewo, O. S.

Abstract

<jats:sec><jats:title>Abstract</jats:title><jats:p>Hole deviation in drilling, influenced by geological formations and drilling mechanics, brings about increased operational costs, boundary disputes, collision risks, and safety concerns. Traditional measurement tools, susceptible to magnetic interference, often produce skewed readings. In addressing this challenge, our research introduces an ML model leveraging data from gyro runs, which are immune to magnetic interferences. After processing a comprehensive dataset of geophysical well log parameters, various ML models were trained. The Random Forest Classifier emerged as the most efficient, boasting a 97% accuracy rate. To validate its robustness, the model underwent a blind test on two distinct new wells, achieving an overall accuracy of 89%, further underscoring its reliability. This model, aptly named "Path Guard", was subsequently deployed as a user-friendly web application, offering the industry an accessible tool for predicting drilling path deviations. Through the integration of artificial intelligence and data science into drilling and geomechanics, our approach not only enhances current operations but also paves the way for potential real-time, automated systems in drilling deviation management.</jats:p></jats:sec>

Topics

• random
• size-exclusion chromatography
• machine learning
• informatics