Petroleum Physical Properties Prediction Application in Enhanced Oil Recovery Process

The Enhanced Oil Recovery (EOR) process is one of the ways in petroleum exploitation so that thick oil can be lifted to surface and produced. EOR referred this study carried out previous studies at laboratory UPN Veteran Yogyakarta Indonesia by adding biosurfactants adjusting temperature. In experiments, each time an amount biosurfactant concentration added temperature adjusted, calculation must done repeatedly determine viscosity, interfacial tension (IFT), density. This experiments takes a long time, requires high cost variety limitation condition. research has succeeded building model with multivariate polynomial regression equations predict value physical properties crude from existing data then classify it into three categories using Naive Bayes, i.e., light oil, medium heavy oil. measured are tension, uses which taken test results Pertamina's KW-55 well as validation. validation result shows Multivariate Polynomial Regression predicting density error values ranging 0% 1% sample data. With low value, application make forecasting more variable conditions. still cannot used independently without Python environment, easily users, built independent installed on user's device. research, prediction been built. made method according petroleum, Naïve Bayes completed several adjustment shift application, including user interface, system, database adjustments.