TY - JOUR
T1 - Ensemble SVM for characterisation of crude oil viscosity
AU - Oloso, Munirudeen
AU - Hassan Sayed, Mohamed
AU - Bader-El-Den, Mohamed
AU - Buick, James
PY - 2017/6/1
Y1 - 2017/6/1
N2 - This paper develops ensemble machine learning model for the prediction of dead oil, saturated and undersaturated viscosities. Easily acquired field data have been used as the input parameters for the machine learning process. Different functional forms for each property have been considered in the simulation. Prediction performance of the ensemble model is better than the compared commonly used correlations based on the error statistical analysis. This work also gives insight into the reliability and performance of different functional forms that have been used in the literature to formulate these viscosities. As the improved predictions of viscosity are always craved for, the developed ensemble support vector regression models could potentially replace the empirical correlation for viscosity prediction.
AB - This paper develops ensemble machine learning model for the prediction of dead oil, saturated and undersaturated viscosities. Easily acquired field data have been used as the input parameters for the machine learning process. Different functional forms for each property have been considered in the simulation. Prediction performance of the ensemble model is better than the compared commonly used correlations based on the error statistical analysis. This work also gives insight into the reliability and performance of different functional forms that have been used in the literature to formulate these viscosities. As the improved predictions of viscosity are always craved for, the developed ensemble support vector regression models could potentially replace the empirical correlation for viscosity prediction.
U2 - 10.1007/s13202-017-0355-x
DO - 10.1007/s13202-017-0355-x
M3 - Article
SN - 2190-0558
JO - Journal of Petroleum Exploration and Production Technology
JF - Journal of Petroleum Exploration and Production Technology
ER -