An enhanced approach to predict permeability in reservoir sandstones using artificial neural networks (ANN)

  • Joel Ben-Awuah
  • Eswaran Padmanabhan
Original Paper


A key challenge in the oil and gas industry is the ability to predict key petrophysical properties such as porosity and permeability. The predictability of such properties is often complicated by the complex nature of geologic materials. This study is aimed at developing models that can estimate permeability in different reservoir sandstone facies types. This has been achieved by integrating geological characterization, regression models and artificial neural network models with porosity as the input data and permeability as the output. The models have been developed, validated and tested using samples from three wells and their predictive accuracy tested by using them to predict the permeability in a fourth well which was excluded from the model development. The results indicate that developing the models on a facies basis provides a better predictive capability and simpler models compared to developing a single model for all the facies combined. The model for the combined facies predicted permeability with a correlation coefficient of 0.41 which is significantly lower than the correlation coefficient of 0.97, 0.93, 0.99, 0.96, 0.96 and 0.85 for the massive coarse-grained sandstones, massive fine-grained sandstones-moderately sorted, massive fine-grained sandstones-poorly sorted, massive very fine-grained sandstones, parallel-laminated sandstones and bioturbated sandstones, respectively. The models proposed in this paper can predict permeability at up to 99% accuracy. The lower correlation coefficient of the bioturbated sandstone facies compared to other facies is attributed to the complex and variable nature of bioturbation activities which controls the petrophysical properties of highly bioturbated rocks.


Artificial neural network modelling Reservoir sandstone facies Bioturbation Porosity Permeability estimation Reservoir rock quality 



This work is partly supported by the FRGS grant awarded to Eswaran Padmanabhan by the Ministry of Higher Education, Malaysia. The authors are grateful to PETRONAS for the samples and permission to publish the data. The first author is also grateful to the Universiti Teknologi PETRONAS (UTP) for funding his PhD studies and the staff at PETROGEO Oil and Gas Consults Ltd. for their technical input and to the anonymous reviewers for their insightful comments.


  1. Ben-Awuah J, Padmanabhan E, Sokkalingam J (2017) Geochemistry of miocene sedimentary rocks from offshore West Baram Delta, Sarawak Basin, Malaysia, South China Sea: implications for weathering, provenance, tectonic setting, paleoclimate and paleoenvironment of depostion. Geosc JGoogle Scholar
  2. Ben-Awuah J, Padmanabhan E, Andriamihaja S, Amponsah PO, Ibrahim Y (2016) Petrophysical and reservoir characteristics of sedimentary rocks from offshore West Baram Delta, Sarawak Basin, Malaysia. Pet and Coal 56(4):414–429Google Scholar
  3. Ben-Awuah J, Padmanabhan E (2015) Effect of bioturbation on reservoir rock quality of sandstones: a case study from the Baram Delta, offshore Sarawak, Malaysia. J Pet Explor Dev 42(2):1–9Google Scholar
  4. Ben-Awuah J, Padmanabhan E (2014) Impact of bioturbation on reservoir quality: a case study of biogenically reduced permeabilities of reservoir sandstones of the Baram Delta, Sarawak, Malaysia. J Appl Sci 14(23):3312–3317CrossRefGoogle Scholar
  5. Boggs S Jr (2009) Petrology of sedimentary rocks, 2nd edn. Cambridge University Press, LondonCrossRefGoogle Scholar
  6. Bromley RG (1990) Trace fossils: biology and taphonomy. Unwin Hyman, LondonGoogle Scholar
  7. Camargo SD, Engel PM (2012) Predicting reservoir quality in sandstones through neural modelling. Vetor 22(1):57–70Google Scholar
  8. Cullen A (2014) Nature and significance of the West Baram and Tinjar Lines, NW Borneo. Mar Pet Geol 51:197–209CrossRefGoogle Scholar
  9. Doust H (1981) Geology and exploration history of offshore central Sarawak, Energy resources of the pacific region Am Assoc Pet Geol Stud Geol 12:117–132.Google Scholar
  10. Evans D, Jones AJ (2002) A proof of the gamma test. Proc Roy Soc London A458:2759–2799CrossRefGoogle Scholar
  11. Fausett LV (1994) Fundamentals of neural networks: architecture, algorithms, and applications. Prentice-Hall, New JerseyGoogle Scholar
  12. Gingras MK, Baniak G, Gordon J, Hovikoski J, Konhauser KO, La Croix A, Lemiski R, Mendoza C, Pemberton SG, Polo C, Zonneveld JP (2012) Porosity and permeability in bioturbated sediments. Dev Sedimentol 64:837–868CrossRefGoogle Scholar
  13. Gordon JB, Pemberton SG, Gingras MK, Konhauser KO (2010) Biogenically enhanced permeability: a petrographic analysis of Macaronichnus segregatus in the Lower Cretaceous Bluesky Formation, Alberta, Canada. Am Assoc Pet Geol Bull 94(11):1779–1795Google Scholar
  14. Goncalves CA, Harvey PK, Lovell MA (1997) Prediction of petrophysical parameter from logs using a multilayer backpropagation neural network. In: Lovell MA, Harvey PK (eds) Developments in Petrophysics, vol 122. Geol Soc Spec Publ, London, pp 169–180Google Scholar
  15. Hall R (2002) Cenozoic geological and plate tectonics evolution of SE Asia and the SW Pacific: computer-based reconstructions, model and animations. J Asian Earth Sci 20:353–431CrossRefGoogle Scholar
  16. Haykin SS (1999) Neural networks: a comprehensive foundation, 2nd edn. Prentice Hall, New JerseyGoogle Scholar
  17. Ho KF (1978) Stratigraphic framework for oil exploration in Sarawak. Bull Geol Soc Malays 10:1–13Google Scholar
  18. Hsieh AI, Allen DM, MacEachern JA (2015) Statistical modelling of biogenically enhanced permeability in tight reservoir rocks. Mar Pet Geol 65:114–125CrossRefGoogle Scholar
  19. Hutchinson CS (2005) Geology of north West Borneo: Sarawak, Brunei and Sabah, 1st edn. Elsevier, New YorkGoogle Scholar
  20. Iturraran-Viveros U, Parra JO (2014) Artificial Neural Networks applied to estimate permeability, porosity and intrinsic attenuation using seismic attributes and well-log data. J Appl Geophys 107:45–54CrossRefGoogle Scholar
  21. Jensen J, Currie I (1990) A new method for estimating the Dykstra-Parsons coefficient to characterize reservoir heterogeneity. SPE Reserv Eng 5(3):369–374CrossRefGoogle Scholar
  22. Johnson HD, Kudd T, Dundang A (1989) Sedimentology and reservoir geology of the Betty field, Baram Delta Province, offshore Sarawak, NW Borneo. Bull Geol Soc Malays 25:119–161Google Scholar
  23. Jones AJ (2004) New tools in non-linear modeling and prediction. Comput Manag Sci 1:109–149CrossRefGoogle Scholar
  24. Khidir A, Catuneanu O (2010) Reservoir characterization of Scollard-age fluvial sandstones, Alberta foredeep. J Mar Pet Geol 27(9):2037–2050CrossRefGoogle Scholar
  25. Khidir A, Catuneanu O (2009) Basin-scale distribution of authigenic clay minerals in the late Maastrichtian-Early Paleocene fluvial strata of the Alberta foredeep: implications for burial depth. Bull Can Petrol Geol 57(3):251–274CrossRefGoogle Scholar
  26. Ligtenberg JH, Wansink AG (2001) Neural network prediction of permeability in the EL Garia Formation, Ashtart oilfield, offshore Tunisia. J Pet Geol 4:389–404CrossRefGoogle Scholar
  27. Love KM, Strohmenger C, Woronow A, Rockenbauch K (1997) Predicting reservoir quality using linear regression models and neural networks. In: Kupecz JA, Gluyas J, Bloch S (eds) Reservoir quality prediction in sandstones and carbonate. Am Assoc Pet Geol 69:47–60Google Scholar
  28. Madon M, Cheng Ly K, Wong R (2013) The structure and stratigraphy of deepwater Sarawak, Malaysia: implications for tectonic evolution. J Asian Earth Sci 76:312–333CrossRefGoogle Scholar
  29. Madon M (1999) Geological setting of Sarawak. In: Meng LK (ed) The petroleum geology and resources of Malaysia. PETRONAS, Kuala Lumpur, pp 275–290Google Scholar
  30. Martens H, Naes T (1992) Multivariate calibration. Wiley, ChichesterGoogle Scholar
  31. Morad S, Al-Ramadan K, Ketzer JM, De Ros LF (2010) The impact of diagenesis on the heterogeneity of sandstone reservoirs: a review of the role of depositional facies and sequence stratigraphy. Am Assoc Pet Geol Bull 94:1267–1309Google Scholar
  32. Moraes MA, Surdam RC (1993) Diagenetic heterogeneity and reservoir quality; fluvial, deltaic and turbiditic sandstone reservoirs Potiguar and Reconcavo rift basins Brazil. Am Assoc Pet Geol Bull 77:1142–1158Google Scholar
  33. Molnar P, Tapponnier P (1975) Cenozoic tectonics of Asia: effects of a continental collision. Sci New Ser 189:419–426Google Scholar
  34. Pemberton SG, Gingras MK (2005) Classification and characterization of biogenically enhanced permeability. Am Assoc Pet Geol Bull 89:1493–1517Google Scholar
  35. Pettijohn FJ (1975) Sedimentary rocks. Harper and Row, New YorkGoogle Scholar
  36. Rogers SJ, Chen HC, Kopaska-Merkel DC, Fang JH (1995) Predicting permeability from porosity using artificial neural networks. Am Assoc Pet Geol Bull 79:1786–1797Google Scholar
  37. Roller C, Driskill B, Manrique J (2009) Use of the Allan variance for characterizing reservoir heterogeneity. SPWLA 50th Ann Logg Symp, TexasGoogle Scholar
  38. Rijks EJH (1981) Baram Delta geology and hydrocarbon occurrence (Sarawak). Geol Soc Malays Bull 14:1–8Google Scholar
  39. Ryan WBF, Carbotte SM, Coplan JO, O’Hara S, Melkonian A, Arko R, Zemsky R (2009) Global multi-resolution topography synthesis. Geochem Geoph Geosys 10(3)Google Scholar
  40. Selly RC (1996) Ancient sedimentary environments and their sub-surface diagnosis. Chapman and Hall, LondonGoogle Scholar
  41. Stefansson A, Koncar N, Jones AJ (1997) A note on the gamma test. Neural Comp and Applic 5:131–133CrossRefGoogle Scholar
  42. Singh S, Kanli AI, Sevgen S (2016) A general approach for porosity estimation using artificial neural network method: a case study from Kansas gas field. Studia Geoph Et Geod 60:130–140CrossRefGoogle Scholar
  43. Singh S, Kanli AI (2016) Estimating shear wave velocities in oil fields: a neural network approach. Geosci J 20:221–228CrossRefGoogle Scholar
  44. Sudirman SB, Samsudin YB, Darman NH (2007) Planning for regional EOR pilot for Baram Delta, offshore Sarawak, Malaysia: Case study, lessons learnt and way forward. SPE Asia Pac Oil Gas Conf, JakartaGoogle Scholar
  45. Tan DNK, Abd. Rahman AH, Anuar A, Bait B, Tho CK (1999) West Baram Delta. In: Meng LK (ed) The petroleum geology and resources of Malaysia. PETRONAS, Kuala Lumpur, pp 291–341Google Scholar
  46. Taner M (1995) Neural networks and computation of neural network weights and biases by the generalized delta rule and back-propagation of errors. Rock Solid Images (
  47. Taylor AM, Goldring R (1993) Description and analysis of bioturbation and ichnofabric. J Geol Soc 150:141–148CrossRefGoogle Scholar
  48. Tobin RC (1997) Porosity prediction in frontier basins: a systematic approach to estimating subsurface reservoir quality from outcrop samples. In: Kupecz JA, Gluyas J, Bloch S (eds) Reservoir quality prediction in sandstones and carbonate. Am Assoc Pet Geol Mem 69:1–18Google Scholar
  49. Tonkin NS, McIlroy D, Meyer R, Moore-Turpin A (2010) Bioturbation influence on reservoir quality: a case study from the Cretaceous Ben Nevis Formation, Jeanne d’Arc Basin, offshore Newfoundland, Canada. Am Assoc Pet Geol Bull 94:1059–1078Google Scholar
  50. Tucker ME (2003) Sedimentary rocks in the field, 3rd edn. Wiley, LondonGoogle Scholar
  51. Verma AK, Cheadle BA, Routray A, Mohanty WK, Mansinha L (2014) Porosity and permeability estimation using neural network approach from well log data. Am Assoc Pet Geol Search Disc 41276Google Scholar
  52. Washburn KE, Birdwell JE (2013) Multivariate analysis of ATR-FTIR spectra for assessment of oil shale organic geochemical properties. Org Geochem 63:1–7CrossRefGoogle Scholar

Copyright information

© Saudi Society for Geosciences 2017

Authors and Affiliations

  1. 1.Department of Chemical and Petroleum EngineeringUCSI UniversityKuala LumpurMalaysia
  2. 2.Department of Geosciences, Faculty of Geosciences and Petroleum EngineeringUniversiti Teknologi PETRONASSeri IskandarMalaysia

Personalised recommendations