An implementation of XGBoost algorithm to estimate effective porosity on well log data

Abstract The application of machine learning methods is aimed at providing efficiency and avoiding subjectivity in estimating reservoir porosity data. This study proposes the eXtreme Gradient Boost (XGBoost) algorithm which known to be effective accurate predictions a short time for porosity. model was optimized using GridSearchCV (GS) module, then applied 7 wells from Damar field, Indonesia with variations separation training testing data based on number wells. best evaluation results are achieved when uses 6 one tested well accuracy around 78.36% 1.29 seconds. An increasing amount will increase performance. All did not show any indication overfitting. Therefore, it can concluded that XGBoost effectively estimate area.