Skip to main content
SpringerLink
Log in

Artificial neural network model for reservoir petrophysical properties: porosity, permeability and water saturation prediction

  • Original Article
  • Published:
Modeling Earth Systems and Environment Aims and scope Submit manuscript

Abstract

Prediction of reservoir petrophysical properties from well-logs data has evolved from the use of experts’ knowledge and statistics to the use of artificial intelligence (AI) models. Several AI models for this purpose are available in the literature; regrettably, most of them are multiple-inputs single-output (MISO) models. Meaning, these models used numerous well-logs to predict a single reservoir petrophysical property. In this study, multiple-inputs multiple-outputs (MIMO) artificial neural network (ANN) model to predict reservoir petrophysical properties: porosity (\(\varphi\)), permeability (\(k\)), and water saturation (\(S_{{\text{w}}}\)), was developed based on wireline logs (gamma ray, resistivity, density and depth interval logs) from 15 fields in the Niger Delta region. The developed ANN model is a feed-forward back-propagation (FFBP) network with 12 neurons in its hidden layer with the Levenberg–Marquardt algorithm as the best learning algorithm than Bayesian regularization and Scaled conjugate gradient. The performance of the developed model resulted in the overall correlation coefficient (R) and Mean Square Error (MSE) values of 0.9945 and 0.7310, respectively. Again, the generalization potential of the developed ANN model with new datasets was determined using five performance indicators: R, coefficient of determination (R2), MSE, root mean square error (RMSE) and average relative error (ARE). The results obtained showed that \(\varphi\) had R of 0.9243, R2 of 0.8544, MSE of 1.7243, RMSE of 1.3131 and ARE of 0.0652, while \(k\) had R of 0.9810, R2 of 0.9624, MSE of 0.0003, RMSE of 0.0173 and ARE of 0.0036. Also, \(S_{{\text{w}}}\) resulted in R, R2, MSE, RMSE and ARE values of 0.9631, 0.9276, 0.0049, 0.0700 and 0.0158, respectively. Furthermore, comparing the performance of the developed ANN model with some existing ones indicated that it performed better than some existing models. Additionally, the developed ANN model is replicable as its threshold weights and biases required to replicate the model are made available, unlike other models in the literature. Furthermore, average contribution factor analysis of the input variables depicted that resistivity log, density log, gamma-ray log and depth interval had the factor of 44.23%, 22.68%, 20.16% and 12.98%, respectively, on the developed ANN model. Hence, the developed ANN model is a more robust tool to predict reservoir’s porosity, permeability and water saturation in the Niger Delta region.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Abbreviations

AC:

Acoustic log

ANFIS:

Artificial neuro-fuzzy interference system

ARE:

Average relative error

AI:

Artificial intelligence

ANN:

Artificial neural network

BR:

Bayesian regularization

CAL:

Caliper log

CEC:

Cation exchange capacity

CNL:

Compensated neutron porosity log

CT:

Conductivity log

DEN:

Formation density log

DT:

Sonic log

FFBP:

Feed-forward back-propagation

FL:

Fuzzy logic

FN:

Functional network

GA:

Genetic algorithm

HGAPSO:

Hybrid GA and PSO

I5FR:

Microspherical focus log

ICA:

Imperialist competitive algorithm

LLD:

Deep laterolog

LLS:

Shallow laterolog

LM:

Levenberg–Marquardt

LSSVM:

Least square support vector machine

MIMO:

Multiple-inputs multiple-outputs

MISO:

Multiple-inputs single-output

MSE:

Mean square error

NMR:

Nuclear magnetic resonance

NPHI:

Neutron-porosity log

PEF:

Photoelastic factor

PHID:

Density-porosity log

PHIE:

Effective porosity

PHIT:

Total porosity

PSO:

Particle swarm optimization

R:

Correlation coefficient

R2 :

Coefficient of determination

RHOB:

Deep density log

RL:

Resistivity log

RMSE:

Root mean square error

SCG:

Scaled conjugate gradient

SFL:

Spherically focused log

SP:

Spontaneous potential

SVM:

Support vector machine

References

  • Adizua OF, Oruade L (2018) Reservoir characterization of an offshore Niger Delta “X” field using well log data. Int J Eng Appl Sci Technol 2(12):1–4

    Google Scholar 

  • Agwu OE, Akpabio JU, Dosunm A (2019) Artificial neural network model for predicting the density of oil-based muds in high-temperature, high-pressure wells. J Pet Explor Prod Technol. https://doi.org/10.1007/s13202-019-00802-6

    Article  Google Scholar 

  • Ahmadi MA, Chen Z (2019) Comparison of machine learning methods for estimating permeability and porosity of oil reservoirs via petro-physical logs. KeAi Pet J 5:271–284. https://doi.org/10.1016/j.petlm.2018.06.002

    Article  Google Scholar 

  • Ahmadi MA, Ahmadi MR, Hosseini SM, Ebadi M (2014) Connectionist model predicts porosity and permeability of petroleum reservoirs by means of petro-physical logs: application of artificial intelligence. J Pet Sci Eng 123:183–200. https://doi.org/10.1016/j.petrol.2014.08.026

    Article  Google Scholar 

  • Akbari MK, Farahni FJ (2007) Dew point pressure estimation of gas condensate reservoirs, using artificial neural network (ANN). In: Paper SPE 107032 presented at the Society of Petroleum Engineers Europec/EAGE annual conference and exhibition, London 11–14 June. https://doi.org/10.2118/107032-MS

  • Al-Bulushi N, King PR, Blunt MJ, Kraaijveld M (2009) Development of artificial neural network models for predicting water saturation and fluid distribution. J Pet Sci Eng 68:197–208

    Article  Google Scholar 

  • Al-Harbi WA (2014) An artificial intelligence approach in predicting water saturation in carbonate reservoirs. Thesis, King Fahd University of Petroleum and Minerals

  • Alobaidi DA (2016) Permeability prediction in one of Iraqi carbonate reservoir using hydraulic flow unit and neural networks. Iraqi J Chem Pet Eng 17(1):1–11

    Google Scholar 

  • Anifowose FA (2011) Artificial intelligence application in reservoir characterization and modeling: whitening the black box. In: Paper SPE 155412 presented at the Society of Petroleum Engineers Saudi Arabia Young professionals technical symposium Dhahran, Saudi Arabia, 14–16 Mar. https://doi.org/10.2118/155413-MS

  • Anifowose FA (2012) Advances in hybrid computational intelligence application in oil and gas reservoir characterization. In: Paper SPE 160921 presented at the Society of Petroleum Engineers Saudi Arabia Young professionals technical symposium Dhahran, Saudi Arabia, 19–21 Mar. https://doi.org/10.2118/160921-MS

  • Anifowose FA, Labadin J, Abdulraheem A (2017) Hybrid intelligent systems in petroleum reservoir characterization and modeling: the journey so far and the challenges ahead. J Petrol Explor Prod Technol 7:251–263

    Article  Google Scholar 

  • Ayoub MA, Esmaeili A (2014) Application of artificial neural netwroks technique for estimating permeability from well log data. J Eng Sci Soc 10(1):31–37

    Google Scholar 

  • Ben-Awuah J, Padmanabhan E (2017) An enhanced approach to predict permeability in reservoir sandstones using artificial neural network (ANN). Arab J Geosci 10(17):1–15

    Google Scholar 

  • Bruce AG, Wong PM, Zhang Y, Salisch HA, Fung CC, Gedeon TA (2000) A state-of-the-art review of neural networks for permeability prediction. J Aust Pet Prod Explor Assoc 40(1):341–354

    Google Scholar 

  • Cao J, Yang J, Wang Y, Wang D, Shi Y (2015) Extreme learning machine for reservoir parameter estimation in heterogeneous sandstone reservoir. J Math Probl Eng 2015:1–10. https://doi.org/10.1155/2015/287816

    Article  Google Scholar 

  • Elkatatny S, Tariq Z, Mahmoudi M, Abdulraheem A (2018) New insights into porosity determination using artificial intelligence techniques for carbonate reservoirs. KeAi Pub 4:408–418

    Google Scholar 

  • Evans AB, Abraham AB, Thompson BE (2019) Integrated reservoir characterization for petrophysical flow units evaluation and performance prediction. Open Chem Eng J 13:97–113

    Article  Google Scholar 

  • Gholami R, Shahraki AR, Paghaleh MJ (2012) Prediction of hydrocarbon reservoirs permeability using support vector machine. J Math Probl Eng. https://doi.org/10.1155/2012/670723

    Article  Google Scholar 

  • Graupe D (2007) Principles of artificial neural networks, 2nd edn. World Scientific Publishing Co. Ltd, Singpore

    Book  Google Scholar 

  • Handhel AM (2009) Prediction of reservoir permeability from wire logs data using artificial neural network. Iraq J Sci 50(1):67–74

    Google Scholar 

  • Hamada GM, Elshafei MA (2010) Neural network prediction of porosity and permeability of heterogeneous gas sand reservoirs using NMR and conventional logs. NAFTA 61(10):451–460

    Google Scholar 

  • Hamada GM, Elsakka A, Chaw YN (2018) Artificial neural network prediction of porosity and water saturation of Shaly sandstone reservoirs. Adv Appl Sci Res 9(2):26–31

    Google Scholar 

  • Helle HB, Bhatt A, Ursin B (2001) Porosity and permeability prediction from wireline logs using artificial neural networks: a North Sea case study. Geophys Prospect 49:431–444

    Article  Google Scholar 

  • Hosseini E, Gholami R, Hajivand F (2019) Geostatistical modeling and spatial distribution analysis of porosity and permeability in the Shurijeh-B reservoir of Khangiran gas field in Iran. J Pet Explor Prod Technol 9:1051–1073. https://doi.org/10.1007/s13202-018-0587-4

    Article  Google Scholar 

  • Huang Z, Shimeld J, Williamson M, Katsube J (1996) Permeability prediction with ANN modeling in the venture gas field offshore Eastern Canada. J Geophys 61(2):422–436

    Article  Google Scholar 

  • Jain RK, Pendharkar U, Srivastava JK, Dave RK (2009) ANN and regression modeling for dissolved solids (DS) removal from industrial effluents. Int J Pollut Res 28(2):165–170

    Google Scholar 

  • Kalaydjian F, Bourbiaux B (2002) Integrated reservoir management: a powerful method to add value to companies’ assets. A modern view of the OER techniques. Oil Gas Sci Technol 57(3):215–258

    Article  Google Scholar 

  • Kamalyar K, Sheikhi Y, Jamialahmadi M (2012) Using an artificial neural network for predicting water saturation in an Iranian oil reservoir. J Pet Sci Technol 30(1):35–45. https://doi.org/10.1080/10916461003752561

    Article  Google Scholar 

  • Kaydani H, Mohebbi A, Baghaie A (2011) Permeability prediction based on reservoir zonation by a hybrid neural genetic algorithm in one of the Iranian heterogeneous oil reservoirs. J Pet Sci Eng 78(2):497–504

    Article  Google Scholar 

  • Kelkar M, Perez G (2002) Applied geostatistics for reservoir characterization. Society of Petroleum Engineers, Richardson

    Google Scholar 

  • Khan MR, Tariq Z, Abdulraheem A (2018) Machine learning derived correlation to determine water saturation in complex lithologies. In: Paper SPE 192307 presented at the Society of Petroleum Engineers kingdom of Saudi Arabia annual technical symposium and exhibition, Dammam, Saudi Arabia, 23–26 Apr. https://doi.org/10.2118/192307-MS

  • Khidir A, Catuneanu O (2010) Reservoir characterization of scollard-age fluvial sandstones, Alberta foredeep. J Mater Pet Geol 27(9):2037–2050

    Article  Google Scholar 

  • Konate AA, Pan H, Khan N, Yang JH (2015) Generalized regression and feed-forward back propagation neural networks in modeling porosity from geophysical well logs. J Pet Explor Prod Technol 5:157–166

    Article  Google Scholar 

  • Kronberger G (2010) Symbolic regression for knowledge discovery bloat, over-fitting, and variable interaction networks. PhD Dissertation, Technisch-Naturwissenschaftliche Fakultat, Johannes Kepler Universitat, Austria

  • Lim J, Kim J (2004) Reservoir porosity and permeability estimation from well logs using fuzzy logic and neural networks. In: Paper SPE 88475 presented at the Society of Petroleum Engineers Asia Pacific oil and gas conference and exhibition, Perth, Australia, 18–20 Oct. https://doi.org/10.2118/88475-MS

  • Mahmoudi S, Mahmoudi A (2014) Water saturation and porosity prediction using back-propagation artificial neural network (BPANN) from well log data. J Eng Technol 5(2):1–8

    Google Scholar 

  • Maharashtra SS (2005) Permeability prediction using artificial neural network (ANN): a case study of Uinta Basin. In: Paper SPE 99286 presented at the International Student paper contest at the Society of Petroleum Engineers annual technical conference and exhibition, Dallas, Texas, 9–12 Oct. https://doi.org/10.2118/99286-STU

  • Majd MT, Hezarkhani A (2011) Estimation of spatial distribution of porosity by using neural networks method in one of oil fields in South of Iran. Aust J Basic Appl Sci 5(8):182–189

    Google Scholar 

  • Mardi M, Nurozi H, Edalatkhah S (2012) Water saturation prediction using ANN and an investigation on cementation factors and saturation exponent variations in an Iranian oil well. J Pet Sci Technol 30(4):425–434

    Article  Google Scholar 

  • Mekanik F, Imteaz M, Gato-Trinidad S, Elmahdi A (2013) Multiple regression and artificial neural network for long term rainfall forecasting using large scale climate modes. J Hydrol 503(2):11–21

    Article  Google Scholar 

  • Moghadam JN, Salahshoor K, Kharrat R (2011) Intelligent prediction of porosity and permeability from well logs for an Iranian fractured carbonate reservoir. Pet Sci Technol J 29:2095–2112

    Article  Google Scholar 

  • Mohammad A (2012) Estimation of permeability using artificial neural networks and regression analysis in an Iran oil field. Int J Phys Sci 7(34):5308–5313

    Article  Google Scholar 

  • Mohammed AKA (2020) A review: controls on sandstone permeability during burial and its measurements comparison—example, Permian Rotliegend sandstone. Model Earth Syst Environ 6:591–603

    Article  Google Scholar 

  • Mohebbi A, Kamalpour R, Keyranloo K, Sarrafi A (2012) The Prediction of permeability from well logging data based on reservoir zoning using ANNs in one of an Iranian heterogeneous oil reservoir. Pet Sci Technol J 30(19):1998–2007. https://doi.org/10.1080/10916466.2010.518187

    Article  Google Scholar 

  • Musa H, Hamisu MA (2019) An artificial neural network model for predictions of impacts of MOSFET transconductance parameter on noise currents. J Res Innov Eng 4(1):16–24

    Google Scholar 

  • Okon AN, Appah D (2016) Neural network models for predicting wellhead pressure-flow rate relationship for Niger Delta oil wells. J Sci Res Rep 12(1):1–14

    Google Scholar 

  • Olayiwola T (2017) Application of artificial neural network to estimate permeability from nuclear magnetic resonance log. In: Paper SPE 189294 presented at the international student paper contest at the Society of Petroleum Engineers annual technical conference and exhibition, San Antonio, Texas, USA, 9–11 Oct. https://doi.org/10.2118/99286-STU

  • Osman EA, Abdel-Wahhab OA, Al-Marhoun MA (2001) Prediction of oil PVT properties using neural networks. In: Paper SPE 68233 presented at the Society of Petroleum Engineers Middle East oil show, Manama, Bahrain, 17–20 Mar. https://doi.org/10.2118/68233-MS

  • Pengyan W, Wei Q (2013) Application of neural network to reservoir porosity prediction. In: Paper presented at the 2nd international conference on geological and environmental science, vol 52. IACSIT Press, Singapore, pp 92–96

  • Saljooghi BS, Hezarkhani A (2014) Comparison of WAVENET and ANN for predicting the porosity obtained from well log data. J Pet Sci Eng 123:172–182

    Article  Google Scholar 

  • Sambo CH, Hermana M, Babasari A, Janjuhah HT, Ghosh DP (2018) Application of artificial intelligent methods for predicting water saturation from new seismic attributes. In: Paper SPE OTC-28221 presented at the offshore technology conference Asia, Kuala Lumpur, Malaysia, 20–23 Mar. https://doi.org/10.2118/28221-MS

  • Saputro OD, Maulana ZL, Latief FDE (2016) Porosity log prediction using ANN. J Phys Conf Ser 739:012092

    Article  Google Scholar 

  • Schaid DJ, Buetow K, Weeks DE, Wijsman E, Guo S, Ott J, Dahl C (1999) Discovery of cancer susceptibility genes: study designs, analytic approaches, and trends in technology. J Natl Cancer Inst Monogr 26:1–16

    Article  Google Scholar 

  • Shedid AS (2001) A Multi-purpose reservoir characterization model. Paper presented at the 2001 Society of Petroleum Engineers Middle East oil show, Bahrain, 17–20 Mar 2001

  • Singh S, Kanli AI, Sevgen S (2015) A general approach for porosity estimation using ANN method: a case study from Kansas Gas field. Stud Geophys Geod 60:130–140. https://doi.org/10.1007/s11200-015-0820-2

    Article  Google Scholar 

  • Soleimani F, Hosseini E, Hajivand F (2020) Estimation of reservoir porosity using analysis of seismic attributes in an Iranian oil field. J Pet Explor Prod Technol 10:1289–1316. https://doi.org/10.1007/s13202-020-00833-4

    Article  Google Scholar 

  • Tarig Z, Mohmoud M, Abdulraheem A (2019) An artificial intelligence approach to predict the water saturation in carbonate reservoir rocks. In: Paper SPE 195804 presented at the Society of Petroleum Engineers annual technical conference and exhibition, Calgary, Alberta, Canada, 30 Sept–2 Oct. https://doi.org/10.2118/192804-MS

  • Tian Y, Zhang Q, Cheng G, Liu X (2012) An application of RBF neural networks for petroleum reservoir characterization. In: Paper presented at the 3rd global congress on intelligent systems conference, Wuhan, China, 6–12 Nov. https://doi.org/10.1109/GCIS.2012.75

  • Tom IU, Okon AN, Okologume WC (2020) Volumetric approach based DOE and ANN models for estimating reservoirs oil in place. Int J Sci Eng Res 11(7):873–883

    Google Scholar 

  • Uguma EM (2019) Artificial intelligence model for characterizing reservoirs in the Niger Delta. BEng Project, University of Uyo

  • Vardian M, Masriani HR, Vardian A, Jowkar S (2016) Porosity and permeability prediction from well logs using an adaptive neuro-fuzzy inference system in a naturally fractured gas-condensate reservoir. Energy Source Part A Recovery Util Environ Effects 38(3):435–441. https://doi.org/10.1080/15567036.2011.592923

    Article  Google Scholar 

  • Verma KA, Cheadle AB, Routray A, Mohanty KM, Mansinha L (2012) Porosity and permeability estimation using neural network approach from well log data. https://www.cspg.org/documents/Conventions/Archives/Annual/2012/160_GC2012_Porosity_and_Permeability_Estimation.pdf. Accessed 11 Feb 2019

  • Worden R, Mayll M, Evans I (2000) The effect of ductile-lithic sand grains and quartz cement on porosity and permeability in Oligocene and lower Miocene clastic, South China Sea; prediction of reservoir quality. AAPG Bull 84:345–359

    Google Scholar 

  • Wood DA (2019) Predicting porosity, permeability and water saturation applying an optimized nearest neighbour, machine-learning and data-mining network of well-log data. J Pet Sci Eng 184:1–17. https://doi.org/10.1016/j.petrol.2019.106587

    Article  Google Scholar 

  • Wu XH, Bi L, Kalla S (2012) Effective parametrization for reliable reservoir performance predictions. Int J Uncertainty Quantification 2(3):259–278. https://doi.org/10.1615/int.J.UncertaintyQuantification.2012003765

    Article  Google Scholar 

  • Yu X, Ma YZ, Psaila D, Pointe PL, Gomez E, Li S (2011) Reservoir characterization and modeling: a look back to see the way forward. In: Ma YZ, La Pointe PR (eds) Uncertainty analysis and reservoir modeling, vol 96. American Association of Petroleum Geologists Memoir, Tulsa, pp 289–309. https://doi.org/10.1306/13301421M963458

    Chapter  Google Scholar 

  • Zagari H, Poordad S, Kharrat R (2013) Porosity and permeability prediction based on computational intelligences as artificial neural networks and adaptive neuro-fuzzy inference systems in southern carbonate reservoir of Iran. J Pet Sci Technol 31(10):1066–1077. https://doi.org/10.1080/10916466.2010.536805

    Article  Google Scholar 

  • Zhang Q, Wei C, Wang Y, Du S, Zhou Y, Song H (2019) Potential for prediction of water saturation distribution in reservoirs utilizing machine method. Energies 12:3597

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Chemical and Petroleum Engineering, University of Uyo, Uyo, Nigeria

    Anietie N. Okon & Emmanuel M. Uguma

  2. Department of Petroleum Engineering, University of Benin, Benin City, Nigeria

    Steve E. Adewole

Authors
  1. Anietie N. Okon
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Steve E. Adewole
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Emmanuel M. Uguma
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Anietie N. Okon.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Okon, A.N., Adewole, S.E. & Uguma, E.M. Artificial neural network model for reservoir petrophysical properties: porosity, permeability and water saturation prediction. Model. Earth Syst. Environ. 7, 2373–2390 (2021). https://doi.org/10.1007/s40808-020-01012-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s40808-020-01012-4

Keywords

Search

Navigation