Hydraulic unit prediction using support vector machine Syed Shujath Ali, Syed Nizamuddin, Abdulazeez Abdulraheem, Md. Rafiul Hassan, M. Enamul Hossain n King Fahd University of Petroleum and Minerals, Dhahran 31260, KSA article info Article history: Received 29 April 2012 Accepted 6 September 2013 Keywords: Kozeny–Carmen equation porosity–permeability wire line logs Nooruddin and Hossain equation reservoir characterization abstract Hydraulic Flow Units or hydraulic units (HUs) concept is becoming popular for grouping reservoir rocks of similar petrophysical properties with the main goal of having a better estimate of permeability. HU approach has an advantage that it addresses the development of permeability in reservoir rocks from fundamentals of geology and physics of flow at pore network scale. The aim of the present study is to predict HUs for the un-cored sections of the wells in a carbonate reservoir using Support Vector Machines (SVMs). HUs for un-cored sections were predicted using wire line logs as input and the associated conventional core values as guides to SVMs. HUs for the core data were identified using three popular correlations such as Kozeny–Carmen (KC) equation, Nooruddin and Hossain equation, and the power law flow unit equation. The experimental results on a Middle East field data show that a better HU prediction accuracy is achieved using Nooruddin and Hossain correlation in comparison with using KC and the power law flow unit correlation. A further analysis to the predicted value reveals that better prediction accuracy is achieved if the granularity of HU class boundary is enlarged to the neighboring classes. Although Nooruddin and Hossain correlation could better relate wire line logs to HUs, however the permeability calculated from the predicted HUs showed less error with the power law flow unit correlation. Considering this, we achieved a maximum of 97% accuracy which encourages the application of SVMs in HU unit prediction using well log data for the un-cored sections of well or for the wells which do not have core data. & 2013 Elsevier B.V. All rights reserved. 1. Introduction Reservoir characterization and simulation is a challenging task due to its inherent chaotic behavior. Rock permeability has been used to simulate reservoirs due to its influence on the hydrocarbon rate of production, ultimate recovery, optimal placement of wells, pressure and fluid contact evaluation. The importance of perme- ability is reflected in the number of studies (Leverett, 1941; Tixier, 1949; Wyllie and Rose, 1950; Timur, 1968; Coates and Dumanoir, 1974; Nooruddin and Hossain, 2011) that have established perme- ability prediction techniques based on correlations with well log data. However, the accuracy and reliability of the reported experi- mental results based on the correlations are limited mainly due to the lack of or a week establishment of correlation between permeability and well logs. HU approach has an advantage that it addresses the develop- ment of permeability in reservoir rocks from fundamentals of geology and physics of flow at pore network scale. A HU is defi- ned as the representative volume of total reservoir rock within which geological properties that control fluid flow are internally consistent and predictably different from properties of other rocks (Bear, 1972). The concept of HU has widely been used in reservoir characterization (Amaefule et al., 1993; Abbaszadeh et al., 1996; Elgaghah et al., 1998; Nooruddin and Hossain, 2011). Existing literature have shown an improved reservoir character- ization by classifying reservoir rock into hydraulic flow units. Gardner and Albrechtsons (1995) observed a significant improve- ment in the reservoir description through the refinement of the permeability model using hydraulic flow unit concept. Guo et al. (2007) showed that hydraulic flow concept proved to be an effective technique for rock-typing in clastic reservoirs in South America. Shahvar et al. (2010) observed an enhanced prediction of relative permeability by discretizing reservoir rock based on hydraulic flow units for a carbonate reservoir in Iran. Shenawi et al. (2009) developed generalized porosity–permeability transforms based on hydraulic unit technique with excellent accuracy for carbonate reservoir in Saudi Arabia. Orodu et al. (2009) expressed a satisfac- tory estimation of permeability from HUs, considering high reser- voir heterogeneity, availability of less number of cored wells and poor well log response correlation to permeability. Svirsky et al. (2004) were able to resolve the challenges in Siberian Oil field using the concept of hydraulic flow units. Usually a generalized KC equation (Wyllie and Gardner, 1958) approximating the fluid flow in a porous medium is used to relate Contents lists available at ScienceDirect journal homepage: www.elsevier.com/locate/petrol Journal of Petroleum Science and Engineering 0920-4105/$ - see front matter & 2013 Elsevier B.V. All rights reserved. http://dx.doi.org/10.1016/j.petrol.2013.09.005 n Corresponding author. Tel.: þ966 13 860 2305; fax: þ966 13 860 4447. E-mail addresses: dr.mehossain@gmail.com, menamul@kfupm.edu.sa (M.E. Hossain). Please cite this article as: Ali, S.S., et al., Hydraulic unit prediction using support vector machine. J. Petrol. Sci. Eng. (2013), http://dx.doi. org/10.1016/j.petrol.2013.09.005i Journal of Petroleum Science and Engineering ∎ (∎∎∎∎) ∎∎∎–∎∎∎