Lost Circulation Prediction Using Decision Tree, Random Forest, and Extra Trees Algorithms for an Iraqi Oil Field

Abstract

Drilling soft and fragile areas such as high permeable, cavernous, fractured, and sandy formations are often accompanied by many problems. One of the most important of these problems is the loss of drilling fluid into these formations in whole or in part. The loss of drilling fluid can lead to bigger and more complex problems, including pipe stucking or kicking and finally closing the well. The drilling muds are relatively expensive, especially the muds that contain oil-based mud or that contain special additives, so it is not economically beneficial to waste and lose these muds. The treatment of drilling fluid losses is also somewhat expensive as a result of the wasted time that it caused, as well as the high cost of materials used in the treatment such as heavy materials, cement, and others. The best way to deal with drilling fluid losses is to prevent them. Artificial intelligence through supervised machine learning provides the possibility of predicting these losses before they occur based on equivalent circulating density, yield point, plastic viscosity, rate of penetration, flow rate, and losses rate of wells suffered from losses problem located in the same area. In this paper, three supervised machine learning models, namely, decision tree, random forest, and extra trees, were built to predict drilling fluid losses in the Rumaila oil field in southern Iraq. The results show that the extra trees model with an R2 of 0.9681was able to predict the new lost circulation events with high accuracy.