"Machine Learning-Based Estimation of Oil Recovery Factor Using XGBoost: Insights from Classification and Data-Driven Analyses"
by Alireza Roustazadeh, Frank Male, Behzad Ghanbarian, Mohammad B. Shadmand, Vahid Taslimitehrani, and Larry W. Lake

Roustazadeh et al. explore the use of machine learning — specifically the XGBoost classification algorithm — to estimate oil recovery factors (RF) from readily available reservoir data. Training and testing across multiple databases, the models achieved moderate accuracy but also revealed a strong dependence on the characteristics of the training dataset, underscoring the sensitivity of database choice.

Feature importance and SHAP (Shapley Additive exPlanations) analysis highlighted reserves, reservoir area, and thickness as the dominant predictors, offering new insights into the key drivers of RF estimation.

Read the full article in InterPore Journal here: https://doi.org/10.69631/ipj.v2i3nr53