Support Vector Regression and Functional Networks for Viscosity and Gas/Oil Ratio Curves Estimation

Abstract

In oil and gas industry, prior prediction of certain properties is needed ahead of exploration and facility design. Viscosity and gas/oil ratio (GOR) are among those properties described through curves with their values varying over a specific range of reservoir pressures. However, the usual single point prediction approach could result into curves that are inconsistent, exhibiting scattered behavior as compared to the real curves. Support Vector Regressors and Functional Networks are explored in this paper to solve this problem. Inputs into the developed models include hydrocarbon and non-hydrocarbon crude oil compositions and other strongly correlating reservoir parameters. Graphical plots and statistical error measures, including root mean square error and average absolute percent relative error, have been used to evaluate the performance of the models. A comparative study is performed between the two techniques and with the conventional feed forward artificial neural networks. Most importantly, the predicted curves are consistent with the shapes of the physical curves of the mentioned oil properties, preserving the need of such curves for interpolation and ensuring conformity of the predicted curves with the conventional properties.

Ensemble SVM for characterisation of crude oil viscosity

“…A novel approach was introduced in (Khoukhi et al 2011) to predict the entire viscosity by training the parameters of the curve and bubble-point viscosity. However, the caveat to this method is its dependent on oil compositions which cannot be determined easily on the field, limiting the potential adoption of such methods for industrial application.…”

Implementing ANFIS for prediction of reservoir oil solution gas-oil ratio

“…Osman and AlMarhoun (Osman and Al-Marhoun, 2005) applied radial basis functions and multilayer perceptron neural networks and developed two intelligent models to predict oil field brines PVT properties. In 2009, Khoukhi et al (Khoukhi et al, 2011) published predictive models based on three different artificial intelligent models. Artificial neural network (ANN), support vector regression (SVR) and functional networks (FN) were implemented to predict gas solubility for a range of reservoir pressures by using three different data sets.…”

“…Artificial neural network (ANN), support vector regression (SVR) and functional networks (FN) were implemented to predict gas solubility for a range of reservoir pressures by using three different data sets. Khoukhi et al (Khoukhi et al, 2011) concluded that support vector regression (SVR) has best prediction results for gas solubility. In 2010, Dutta and Gupta (Dutta and Gupta, 2010) proposed correlations for saturation pressure (P b ), solution gas oil ratio and some other PVT properties of Indian west coast crude using ANN model based on multilayer perceptron and bayesian regularization coupled with hybrid genetic algorithm (GA) as an optimizer.…”

Computational Intelligence Techniques With Application to Crude Oil Price Projection: A Literature Survey From 2001–2012

“…Successfully applied neural networks paved the way for computational intelligence (CI) techniques which have begun to play a major role in the energy (oil and gas) sector as claimed by [9]. Several CI techniques emerged inspired by original biological systems, for instance artificial neural networks, evolutional computation, simulated annealing and swarm intelligence which copied the functions of the nervous system and applied the principles of natural selection and thermodynamics and even mimicked the specific behavior of insects.…”