Performance Evaluation of Machine Learning Algorithms in Predicting Dew Point Pressure of Gas Condensate Reservoirs

Accurate knowledge of the dew point pressure for a gas condensate reservoir is necessary for the design of a field development plan and timing for optimization of mitigation operations for resources management. This study explores the use of machine learning models in predicting the dew point pressure of gas condensate reservoirs. 535 experimental dew point pressure data-points with max temperature and pressure of 304F and 10500psi were used for this analysis. First, multiple linear regression (MLR) was used as a benchmark for comparing the performance of the machine learning models. Neural Networks (NN) [optimized for the number of neurons and hidden layers], Support Vector Machine (SVM) [using radial basis function kernel] and Decision Tree [Gradient boost Method (GBM) and XG Boost (XGB)] algorithms were then used in predicting the dew point pressure using gas composition, specific gravity, the molecular weight of the heavier component and compressibility factor as input parameters. The performances of these algorithms were analyzed using root mean square error (RMSE), absolute average relative deviation percentage (AARD %) and coefficient of determination (R2). This work concludes that for large data sets neural network is preferred but for smaller data sizes, SVM shows better performance