Modeling the Oil Viscosity of Nigerian Crudes Using Machine Learning

Abstract

Abstract Oil viscosity is an important parameter for estimating the flow behavior of crude oil under varying pressure and temperature regimes encountered in the subsurface and surface components of the petroleum production system. Although experimental data provides the most accurate characterization of this property, obtaining such data in the laboratory is often time-consuming and expensive. Alternatively, one of several empirical correlations can be used, albeit with often poor generalization to samples from differing thermodynamic systems or crude oil types. In this paper, we use a data-driven approach based on machine learning (ML) algorithms to create high-performing models for predicting the dead oil and bubblepoint oil viscosity of Nigerian crudes. Random Forest (RF) and Gradient Boosting (GB) ensembles, as well as Multi-Layer Perceptron (MLP) and Radial Basis Function (RBF) networks, are compared to several widely used correlations, and their performance is evaluated on a large dataset of crude oil samples collected from various Niger Delta oil fields. The ML models are built with minimal and easily accessible input parameters shared by the correlations, allowing for an objective assessment of their superiority to these correlations given the same input framework. These are reservoir temperature and oil API gravity for the dead oil viscosity modeling, and the solution gas-oil ratio and dead oil viscosity for the bubblepoint oil viscosity modeling. Furthermore, the model's reliability is tested by partitioning the dataset into training, validating, and testing sets, and optimal model configurations are achieved through Bayesian Optimization. On the dead oil viscosity modeling task, we achieve a modest improvement over the best-performing correlation developed by Al-Khafaji (1987). The RF model's R2 and mean absolute error (MAE) scores on the testing data are 0.831 and 3.423, respectively, versus 0.809 and 4.439 for the correlation method. However, for the bubblepoint oil viscosity modeling, the improvement recorded using the RF model over the best-performing correlation developed by Beggs and Robinson (1975) is remarkable. In this case, the R2 and MAE scores for the RF model are 0.924 and 0.441, respectively, compared to 0.574 and 0.813 for the correlation method. As a result, our ML models have outperformed conventional correlations for modeling oil viscosity. Ultimately, oil viscosity estimates from the developed ML models can provide a much more accurate characterization of the fluid behavior of Niger Delta crudes than the conventional correlations can. Furthermore, the ML models allow for continuous improvement of their generalization ability by introducing new data from various sources to the models.