Machine learning estimation of crude oil viscosity as function of API, temperature, and oil composition: Model optimization and design space

Abstract

Measurement of viscosity of crude oil is critical for reservoir simulators. Computational modeling is a useful tool for correlation of crude oil viscosity to reservoir conditions such as pressure, temperature, and fluid compositions. In this work, multiple distinct models are applied to the available dataset to predict heavy-oil viscosity as function of a variety of process parameters and oil properties. The computational techniques utilized in this work are Decision Tree (DT), MLP, and GRNN which were utilized in estimation of heavy crude oil samples collected from middle eastern oil fields. For the estimation of viscosity, the firefly algorithm (FA) was employed to optimize the hyper-parameters of the machine learning models. The RMSE error rates for the final models of DT, MLP, and GRNN are 40.52, 25.08, and 30.83, respectively. Also, the R2-scores are 0.921, 0. 978, and 0.933, respectively. Based on this and other criteria, MLP is chosen as the best model for this study in estimating the values of crude oil viscosity.

Expansion of Nanotechnology-Based Chemically Enhanced Oil Recovery Field Applications in Colombia: An Approach from Laboratory Experiments, Effluent Follow-Up, and Machine Learning

“…This is similar to what was reported by other authors. 89,90 Acknowledging the importance of a robust data division strategy, a sensitivity analysis is performed on the effect of splitting the training and testing data sets. This analysis confirmed the stability of the model's performance across various data splits, ensuring that predictive insights are reliable and robust.…”

“…Hyperparameters were tuned to improve the performance and generalizability of the model. This is similar to what was reported by other authors. , …”

Development of a New Temperature-Dependent Viscosity Model for Crude Oils

“…The application of the theoretical models is limited to pure hydrocarbons and light crude oils due to the uncertainty with the prediction of critical properties and acentric factor for heavier oils . Recently, ANN techniques have been used to predict the viscosity of crude oils at different temperatures. ,,, However, these ANN techniques are strongly dependent on the reliability and quantity of experimental data and fail to give directly a mathematical expression to describe the viscosity–temperature relationship.…”

“…15 Recently, ANN techniques have been used to predict the viscosity of crude oils at different temperatures. 8,10,12,16 However, these ANN techniques are strongly dependent on the reliability and quantity of experimental data and fail to give directly a mathematical expression to describe the viscosity−temperature relationship. Many empirical temperature-dependent viscosity models have been developed and widely applied to predict crude oil viscosity, as they directly give the temperature-dependent viscosity expression and are easy to be used, especially for those with fewer parameters in the models.…”