Estimating oil and gas recovery factors via machine learning: Database-dependent accuracy and reliability

TL;DR

This study evaluates machine learning models for estimating hydrocarbon recovery factors in reservoirs, highlighting their database dependency and limited reliability across different datasets.

Contribution

It compares three ML models for RF estimation and demonstrates the importance of database similarity for model accuracy.

Findings

XGBoost outperformed SVM and MLR on training and testing datasets.

All models performed poorly on independent databases.

Model accuracy is highly dependent on the similarity of training and testing data distributions.

Abstract

With recent advances in artificial intelligence, machine learning (ML) approaches have become an attractive tool in petroleum engineering, particularly for reservoir characterizations. A key reservoir property is hydrocarbon recovery factor (RF) whose accurate estimation would provide decisive insights to drilling and production strategies. Therefore, this study aims to estimate the hydrocarbon RF for exploration from various reservoir characteristics, such as porosity, permeability, pressure, and water saturation via the ML. We applied three regression-based models including the extreme gradient boosting (XGBoost), support vector machine (SVM), and stepwise multiple linear regression (MLR) and various combinations of three databases to construct ML models and estimate the oil and/or gas RF. Using two databases and the cross-validation method, we evaluated the performance of the ML models. In each iteration 90 and 10% of the data were respectively used to train and test the models. The third independent database was then used to further assess the constructed models. For both oil and gas RFs, we found that the XGBoost model estimated the RF for the train and test datasets more accurately than the SVM and MLR models. However, the performance of all the models were unsatisfactory for the independent databases. Results demonstrated that the ML algorithms were highly dependent and sensitive to the databases based on which they were trained. Statistical tests revealed that such unsatisfactory performances were because the distributions of input features and target variables in the train datasets were significantly different from those in the independent databases (p-value < 0.05).