Spatial Variations Prediction in Carbonate Porosity Using Artificial Neural Network: Subis Limestones, Sarawak, Malaysia

  • Yasir AliEmail author
  • Eswaran Padmanabhan
  • S. Andriamihaja
  • A. Faisal
Conference paper
Part of the Advances in Science, Technology & Innovation book series (ASTI)


The estimation and modeling of carbonate porosity is of increasing interest in different aspects of geology. Several models have been developed to visualize the pore network systems of carbonate rocks. However, no modeling tools have been designed to predict changes in pore system resulting from dissolution. Therefore, this paper introduced an algorithm for predicting spatial variations in pore network. Carbonate outcropped samples representing different facies from Subis limestone, Sarawak, of Miocene age were used for this study. Continuous imagery along a 10 cm rock chip was conducted using Micro Computer Tomography (CT) scan imagery. The Artificial Neural Network (ANN) predictive code receives images which were read as a matrix. The images were processed using the Image Analysis, coded before use as a training and input data set for ANN. The ANN produced a predicted image with the same properties (such as bits, scalar or raster …etc.) as the input images and at the same interval. The predicted image was compared to the original one to estimate the prediction accuracy. The method proved to give good results in terms of the predicted images accuracy. The method can be applied to study the dissolution phenomenon in carbonates as well as siliciclastic rocks to predict spatial variations and development in a pore network system.


Artificial neural network Spatial variations Carbonate rocks Porosity Subis limestone 


  1. 1.
    Schlumberger: Carbonate Reservoir, Meeting Unique Challenges to Maximize Recovery, pp. 1–16 (2008)Google Scholar
  2. 2.
    Chilingar, G.V. (ed.): Fairbridge: Carbonate Rocks: Origin, Occurrence and Classification, p. 471. Elsevier, Amsterdam, London, New York (1967)Google Scholar
  3. 3.
    Mackenzie, J.W.: Geochemistry of Sedimentary Carbonates, p. 706. Elsevier, Amsterdam (1990)Google Scholar
  4. 4.
    Clyde, M.: Carbonate Reservoirs: Porosity Evaluation and Diagenesis in a Sequence Stratigraphic Framework (Developments in sedimentology 5), p. 444 (2001)Google Scholar
  5. 5.
    Fliigel, E.: Microfacies of Carbonate Rocks: Analysis, Interpretation, p. 669. Springer, Berlin, Heidelberg, New York (1967)Google Scholar
  6. 6.
    Ahr, W.M.: Geology of Carbonates: The Identification, Description, and Characterization of Hydrocarbon Reservoirs in Carbonate Rocks, p. 296. Wiley, Canada (2008)CrossRefGoogle Scholar
  7. 7.
    Nurgalieva, N.D.: Porosity estimation of carbonate rocks with. ARPN J. Eng. Appl. Sci., 20–24 (2014)Google Scholar
  8. 8.
    Srivastava, R.M.: An Overview of Stochastic Methods for Reservoir Characterization, Stochastic Modeling and Geostatistics Principles, Methods, and Case Studies, 2nd edn, p. 370. The American Association of Petroleum Geologists, Tulsa, Oklahoma, USA (1994)Google Scholar
  9. 9.
    Wang, X., Ghassemi, A.: A three-dimensional stochastic fracture network model for geothermal reservoir stimulation. In: Proceedings, Thirty-Sixth Workshop on Geothermal Reservoir Engineering, (p. 11). California (1982)Google Scholar
  10. 10.
  11. 11.
    Zinszer, A.: A Geoscientist guide to Petrophysics, p. 363. Editions Technip, Paris (2007)Google Scholar
  12. 12.
    Bohling, G.: Stochastic Simulation and Reservoir Model Framework, p. 20. Kansas Geological Survey, Kansas (2005)Google Scholar
  13. 13.
    Noel, P., et al.: Origin of Carbonate Rocks, p. 464. Wiley, Canada (2015)Google Scholar
  14. 14.
    Sleumer, B.H.: The Subis Limestone Complex—Sarawak, Malaysia: Abstract-Proceedings of the Carbonate Seminar. In: AAPG Indonesian Petroleum Association, pp. 120–121 (1976)Google Scholar
  15. 15.
    Hartmann CT Scanning–Techniques and Applications, p. 358 (Subburaj, K., ed.) Croatia: Janeza Trdine 9, 51000 Rijeka (2011)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Yasir Ali
    • 1
    Email author
  • Eswaran Padmanabhan
    • 2
  • S. Andriamihaja
    • 2
  • A. Faisal
    • 2
  1. 1.Red Sea UniversityPort SudanSudan
  2. 2.University Teknologi PETRONASTronohMalaysia

Personalised recommendations