Integrating kernel support vector machines for efficient rock facies classification in the main pay of Zubair formation in South Rumaila oil field, Iraq

  • Watheq J. Al-Mudhafar
Original Article


Precisely prediction of rock facies leads to adequate reservoir characterization by improving the porosity-permeability relationships and accurately identifying the spatial facies distribution. In this paper, the discrete and conditional posterior probability distributions of well lithofacies were modeled and predicted through the Kernel Support Vector Machines (KSVM) as a function of well log interpretations in a well in the Upper Sandstone Member of Zubair formation in South Rumaila Oil Field, located in Iraq. The log data include neutron porosity, water saturation, and shale volume. The multinomial response factor is the measured vertical Lithofacies sequence that has mainly sand, shale, and shaly sand. KSVM is a supervised statistical learning algorithm that recognizes the discrete classes for the given data based on maximizing the margin around the separating hyperplane and the decision function is fully specified by a subset of the Support vectors. The predicted lithofacies were validated by computing the total correct percent of predicted facies counts matrix, estimated by KSVM. The nonlinear separations of components handled by KSVM led to obtaining high level of accuracy of lithofacies prediction and attained 99.55% of the total correct percent. After depicting the vertical sand, shale, and shaly sand posterior distribution, it was shown that KSVM prediction has compatible between the sand posterior values with the high records of neutron porosity and low intervals of shale volume. Consequently, the KSVM can be considered for Lithofacies prediction in the other wells in the reservoir to provide a solid basis for the geospatial modeling.


Lithofacies classification Posterior distribution Discrete distribution Kernel support vector machines South Rumaila oil field 



The author would like to present his thanks and appreciation to the Institute of International Education for Granting him the International Fulbright Science and Technology Awards that has funded the PhD Research.


  1. Mathisen T, Lee SH, Datta-Gupta A (2003) Improved Permeability estimates in carbonate reservoirs using electrofacies characterization: a case study of the North Robertson Unit, West Texas. SPE Reser Evaluat Eng J 6(03):176–184. doi: 10.2118/84920-PA CrossRefGoogle Scholar
  2. Al-Ameri TK, Al-Khafaji AJ, Zumberge J (2009) Petroleum system analysis of the Mishrif reservoir in the Ratawi, Zubair, North and South Rumaila oil fields, southern Iraq. GeoArabia: 91–108Google Scholar
  3. Al-Ansari R (1993) The petroleum Geology of the Upper sandstone Member of the Zubair Formation in the Rumaila South. Geological Study, Ministry of Oil, Baghdad, IraqGoogle Scholar
  4. Al-Mudhafar WJM (2014) Integrating Markov Chains for Bayesian estimation of vertical facies sequences through linear discriminant analysis. Euro Assoc Geosci Eng. doi: 10.3997/2214-4609.20141336
  5. Al-Mudhafer WJ (2015) Multinomial Logistic Regression for Bayesian Estimation of Vertical Facies Modeling in Heterogeneous Sandstone Reservoirs. Presented at the offshore Technology Conference Asia, Kuala Lumpur, Malaysia. doi: 10.4043/24732-MS
  6. Al-Muhailan, M., I. Hussain, H. Maliekkal, O. Ghoneim, P. Nair, and M. Fayed: New HTHP Cutter Technology Coupled with FEA-Based Bit Selection System Improves ROP by 60% in Abrasive Zubair Formation. International Petroleum Technology Conference, Beijing, China (2013)Google Scholar
  7. Al Naqib KM (1967) Geology of the Arabian Peninsula Southwestern Iraq. Paper 560-G, U.S. Geological Survey Professional. United States Government Printing Office, WashingtonGoogle Scholar
  8. Al-Obaidi RY (2009) Identification of palynozones and age evaluation of Zubair Formation Southern Iraq. J Al-Nahrain Univ 12(3):16–22Google Scholar
  9. Al-Obaidi RY (2010) Determination of palynofades to assess depositional environments and hydrocarbons potential, lower cretaceolls, Zubair Formation South Iraq. J Coll Edu 5:163–174Google Scholar
  10. Ben-Hur A, Weston J (2010) A users guide to support vector machines., Data mining techniques for the life sciencesHumana Press, USAGoogle Scholar
  11. Burges CJC (1998) A Tutorial on Support Vector Machines for Pattern Recognition. Submitted to Data Mining and Knowledge Discovery,
  12. Harris GD (2012) Stratigraphy and Depositional Environment of the Upper Zubair Sandstone (Main Pay), West Qurna 1 Field, Iraq. Hydrocarbon Exploration & Field Development, Istanbul, Turkey, EAGE Workshop on IraqGoogle Scholar
  13. Hastie T, Tibshirani R, Friedman JH (2001) The elements of statistical learning: data mining, inference, and prediction. Springer, Springer series in statistics New YorkCrossRefGoogle Scholar
  14. Karatzoglou A, Smola A, Hornik K (2016) Package ”kernlab”. RCRAN Repository.
  15. Lee SH, Datta-Gupta A (1999) Electrofacies characterization and permeability predictions in carbonate reservoirs: role of multivariate analysis and nonparametric regression. Soc Petrol Eng. doi: 10.2118/56658-MS
  16. Mohammed WJ, Al Jawad MS, Al-Shamaa DA (2010) A Reservoir Flow Simulation study for a Sector in Main Pay-South Rumaila Oil Field. SocPetrol Eng. doi: 10.2118/126427-MS
  17. Moore W, Ma Z, Urdea J, Bratton T (2011) Uncertainty Analysis in Well Log and Petrophysical Interpretations.n book: Uncertainty Analysis and Reservoir Modeling, Chapter: 2, Publisher: AAPG, Editors: Y. Zee Ma and Paul LaPointe, pp 17–28Google Scholar
  18. Nashawi IS, Malallah A (2009) Improved electrofacies characterization and permeability predictions in sandstone reservoirs using a data mining and expert system approach. Petrophysics 5(03):250–268Google Scholar
  19. Pasternack E (2009) Uncertainty in Petrophysical Evaluation. Search and Discovery. Article, No. 120011Google Scholar
  20. Silva FPT, Ghani AA, Al Mansoori A, Bahar A (2002) Rock type constrained 3D reservoir characterization and modeling. Soc Petrol Eng. doi: 10.2118/78504-MS
  21. Teh W, Willhite GP, Doveton JH (2012) Improved reservoir characterization in the ogallah field using petrophysical classifiers within electrofacies. Soc Petrol Eng. doi: 10.2118/154341-MS
  22. Vapnik V (1996) The nature of statistical learning theory. Springer, New YorkGoogle Scholar
  23. Wells M, Kitching D, Finucane D, Kostic B (2013) An Integrated Description of the Stratigraphy and Depositional Environment of the ”Main Pay” Member of the Zubair Formation, Rumaila, Iraq. Second EAGE Workshop on Iraq, Dead sea, JordanGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2017

Authors and Affiliations

  1. 1.Louisiana State UniversityBaton RougeUSA
  2. 2.South Oil CompanyBasrahIraq

Personalised recommendations