Role of Supervised Machine Learning for the Prediction of Elastic Logs. A Case Study from Middle Indus Basin, Pakistan

In artificial intelligence, machine learning is the branch of the field that can learn from data and recognize patterns in order to make judgments with little or no human interaction. Because of the abundance of easily available data, the petroleum industry is particularly well positioned to benefit from machine learning. This study employed a total of four wells. The purpose of this work is to do the best possible prediction of missing curves which are S-sonic (DTS) with use of four different algorithms of supervised machine learning. The machine learning random forest system was trained on two selected wells in order to forecast the essential DTS curve in missing wells, resulting in an ۸۰% match. Therefore, the use of sophisticated statistical, machine learning, and pattern recognition approaches to solve such challenges has piqued the interest of researchers in the oil and gas industry.

Keywords:

Supervised Machine Learning , Random Forest , Gradient Booster , Support Vector Machine , Decision Tree