Neural Network Based Performance Evaluation of a Waterflooded Oil Reservoir

  IJETT-book-cover  International Journal of Recent Engineering Science (IJRES)          
© 2021 by IJRES Journal
Volume-8 Issue-3
Year of Publication : 2021
Authors : Mahlon Marvin Kida, Zakiyyu Muhammad Sarkinbaka, Abdulhalim Musa Abubakar, Aminullah Zakariyyah Abdul


MLA Style: Mahlon Marvin Kida, Zakiyyu Muhammad Sarkinbaka, Abdulhalim Musa Abubakar, Aminullah Zakariyyah Abdul  "Neural Network Based Performance Evaluation of a Waterflooded Oil Reservoir"International Journal of Recent Engineering Science 8.3(2021):1-6. 

APA Style: Mahlon Marvin Kida, Zakiyyu Muhammad Sarkinbaka, Abdulhalim Musa Abubakar, Aminullah Zakariyyah Abdul. Neural Network Based Performance Evaluation of a Waterflooded Oil Reservoir  International Journal of Recent Engineering Science, 8(3), 1-6.

In this paper, we considered the use of neural networks in the identification and prediction of a waterflooded reservoir consisting of eight injection wells and one production well with a 40% porosity. The data used for the non-linear identification was generated from a reservoir modelled in MATLAB Reservoir Simulation Toolbox (MRST). Likewise, in this study, the effect of number of hidden neurons on the accuracy, Mean Squared Error and oil production prediction of the reservoir was investigated.
The study asserted the efficacy of the neural networks as regards to its predictive capacity. For the oil production rate, a mean squared error was recorded to be minimal for 2 hidden neurons as compared to the other three cases of neuron number. For water production rate, 8 hidden neurons were observed to be optimal compared to other cases. Oil and water production rate for a peak NPV value of 3 billion US dollars was recorded to be 2000m3/day and 4500m3/day respectively. The response was optimal for all cases except for the net present value, which requires a more substantial amount of data for the neural network model.

[1] N. Jude, Dynamic optimization of a water flood reservoir, MSc Thesis submitted to mewbourne school of petroleum and geoligical engineering, University of Oklahoma, Norman, Oklahoma, 2006.
[2] I. A. Omar, Z. Chen, and A. E. khalifa, Predicating Water-flooding performance into Stratified Reservoirs using a data driven proxy model, J. Pet. Gas Eng., 8(7) (2017) 60–78.
[3] X. Xinwei and J. L. Kyung, Data driven model to optimize the injection well placement for waterflooding in heterogeneous reserviors applying artificial neural networks and reducing observation cost, Energy Explor. Exploit., 38(6) (2020) 2413–2435.
[4] A. A. Mohammad, S. Reza, L. Moonyong, K. Tomoaki, and B. Alireza, Determination of oil well production performance using artificial neural network (ANN) linked to the particle swarm optimization (PSO) tool, Adv. Res. Evol. Sci., 1(2015) 118–132.
[5] G. M. Hamada, A. Elsakka, and C. Y. Nyein, Artificial neural network (ANN) prediction of porosity and water saturation of shaly sandstone reserviors, Adv. Appl. Sci. Res., 9(2) (2018) 26–31.
[6] E. Turgay and S. Qian, Artificial Intelligence Applications in Reservoir Engineering: A status check, Energ. MDPI, 12(2019).
[7] U. Jackson et al., Review of field development optimization of waterflooding, EOR, and well placement focusing on history matching and optimization algorithm, Process. MDPI, 5(34) (2017).
[8] Y. C. Rene, S. C. Aaron, K.-C. Jayashree, F. Michael Chiang, and J. C. Peter, Introduction to machine learning, neural networks and deep learning, Transl. Vis. Sci. Technol., 9(2) (2000) 14.
[9] M. NEGASH, Berihun and D. YAW, Atta, Artificial Neural Network based production forecasting for a hydrocarbon reservior under water Injection, Pet. Explor. Dev., 47(2) (2020) 383–392.
[10] H. David M., Application of Artificial Neural Networks in Chemical Engineering, Korean J. Chem. Eng., 17(4) (2000) 373–392.
[11] Z. Zhang, Z. Wu, R. David, and C. Panagoitis D., Real Time Optimization and Control of Non-linear Processe Using Machine Learning, mathematics, 7 (2019) 890–915.
[12] G. Rzevski, Artificial Intelligence in Engineering: past, present and future, Trans. Inf. Commun. Technol., 8 (1995).
[13] A. Ehsan and J. C. Zhangxing, Cognitive data driven proxy modelling for perfromance forecasting of waterflooding process, Glob. J. Technol. Optim., 8(1) (2017) 207.
[14] J. M. Robert, R. M. Holger, C. D. Graeme, and G. F. T.M.K, Non-linear variable selection for artificial neural networks using partial mutual information, Environ. Model. Softw., 23 (2008) 1312–1326.
[15] A. S. Grema, D. Baba, U. H. Taura, M. B. Grema, and L. T. Popoola, Optimization and Non linear Identification of Reservior water flooding process, Arid Zone J. Engieering Technol. Environ., 13(5) (2017) 610–619.
[16] E. Saber Khaled, Application of function approximations to reservoir engineering, Degree of Doctor of Philosohpy in Process systems engineering, University of Regina, 2012.
[17] G. Edison, Improving the simulation of a waterflooding recovery process using artificial neural networks, MSc Thesis submitted to the College of Engineering and Mineral Resources, West Virginia University, Morgantown, West Virginia, 2000.
[18] S. Sandhya, Neural networks for Time series forecasting, in Neural Networks for Applied Sciences and Engineering : From fundamentals to complex pattern recognition, USA: Auarbach publications. Taylor and Francis Group, 2006.
[19] G. Daniel, Principle of artificial neural networks, 3rd ed., vol. 7. Singapore: World Scientific Publishing Co. Pte. Ltd, 2013.

MRST, Artificial Neural Networks, Net Present Value, Oil Reservoir, Oil production, water production