International Journal of Nonlinear Analysis and Applications

A machine-learning approach for optimal ionic concentration determination in smart-water EOR applications

Articles in Press

Document Type : Research Paper

Authors

1 Faculty of Petroleum and Natural Gas Engineering, Sahand University of Technology, Tabriz, Iran

2 Ahwaz Faculty of Petroleum Engineering, Petroleum University of Technology, Ahvaz, Iran

Abstract

The smart water-enhanced oil recovery (EOR) process is a pioneering tertiary recovery method in the petroleum industry. Meanwhile, more than half of oil reserves in the world are carbonate. Accordingly, considering the technical and financial aspects, the determination of the accurate concentration of presented ions in smart water is very important. Although several experimental studies considered this issue, no appropriate statistical method has been suggested to deal with this problem during smart water injection in carbonate rocks. In the present article, five different multi-target regression machine learning (ML) algorithms (i.e., Random Forest, Decision Tree, K-Nearest Neighbours, Lasso and Linear), were used to predict the ionic concentration in imbibition tests. A completely reliable dataset of imbibition test results, which were gathered from the literature, was employed in the algorithm learning process to examine their accuracy. After data processing, feature extraction, splitting data and building candidate ML models, an exact hyperparameter tuning was carried out to evaluate the ML models and select the best model. It was found that the Random Forest algorithm is the best-acting approach, with the lowest total root mean squared error (RMSE) of 1.231 and the highest score of 0.981 for predicting ionic concentration in smart water EOR applications. In conclusion, the proposed model is the most efficient approach as compared with commonly used costly laboratory tests, which can be a good candidate for predicting the concentration of ions in smart water injection processes.

Keywords

[1] P. Ahmadi, H. Asaadian, S. Kord, and A. Khadivi, Investigation of the simultaneous chemicals influences to promote oil-in-water emulsions stability during enhanced oil recovery applications, J. Molecul. Liquids 275 (2019), 57–70.
[2] H.S. Al-Hadhrami and M.J. Blunt, Thermally induced wettability alteration to improve oil recovery in fractured reservoirs, SPE Reserv. Eval. Engin. 4 (2001), no. 3, 179–186.
[3] E.W. Al-Shalabi and K. Sepehrnoori, A comprehensive review of low salinity/engineered water injections and their applications in sandstone and carbonate rocks, J. Petrol. Sci. Engin. 139 (2016), 137–161.
[4] M.B. Alotaibi and H.A. Nasr-El-Din, Chemistry of injection water and its impact on oil recovery in carbonate and clastics formations, SPE Int. Conf. Oilfield Chem., SPE, 2009, pp. 121565.
[5] N.S. Altman, An introduction to kernel and nearest-neighbor nonparametric regression, Amer. Statist. 46 (1992), no. 3, 175–185.
[6] T. Austad and D.C. Standnes, Spontaneous imbibition of water into oil-wet carbonates, J. Petrol. Sci. Engin. 39 (2003), 363–376.
[7] E. Bahonar, Y. Ghalenoei, M. Chahardowli, M. Simjoo, New correlations to predict oil viscosity using data mining techniques, J. Petrol. Sci. Engin. 208 (2022), 109736.
[8] M. Belgiu and L. DrĖ˜agu, Random forest in remote sensing: A review of applications and future directions, ISPRS J. Photogram. Remote Sens. 114 (2016), 24–31.
[9] G. Biau, Analysis of a random forests model, J. Mach. Learn. Res. 13 (2012), 1063–1095.
[10] G. Biau and E. Scornet, A random forest guided tour, Test 25 (2016), 197–227.
[11] B. Boehmke and B.M. Greenwell, Hands-on Machine Learning with R, Chapman and Hall/CRC, 2019.
[12] H. Borchani, G. Varando, C. Bielza, and P. Larra˜naga, A survey on multi-output regression, Wiley Interdiscip. Rev.: Data Min. Knowledge Discov. 5 (2015), no. 5, 216–233.
[13] A.L. Boulesteix, S. Janitza, J. Kruppa, and I.R. Konig, Overview of random forest methodology and practical guidance with emphasis on computational biology and bioinformatics, Wiley Interdiscip. Rev.: Data Min. Knowledge Disc. 2 (2012), no. 6, 493–507.
[14] L. Breiman, Random forests, Machine Learn. 45 (2001), 5–32.
[15] L. Breiman, J.H. Friedman, R.A. Olshen, and C.J. Stone, Classification and Regression Trees, 1st Edition, Chap[1]man and Hall/CRC, 2017.
[16] M.Y. Chen, Predicting corporate financial distress based on integration of decision tree classification and logistic regression, Expert Syst. Appl. 38 (2011), 11261–11272.
[17] X. Chen and h. Ishwaran, Random forests for genomic data analysis, Genomics 99 (2012), 323–329.
[18] G.V. Chilingar and T.F. Yen, Some notes on wettability and relative permeabilities of carbonate reservoir rocks, II, Energy Sources 7 (1983), 67–75.
[19] H.E. Copeland, K.E. Doherty, D.E. Naugle, A. Pocewicz, and J.M. Kiesecker, Mapping oil and gas development potential in the US intermountain west and estimating impacts to species, PLoS ONE 4 (2009), 251–257.
[20] A. Criminisi, Decision forests: A unified framework for classification, regression, density estimation, manifold learning and semi-supervised learning, Found. Trends Comput. Graph. Vis. 7 (2011), 81–227.
[21] A. Criminisi, J Shotton, and E. Konukoglu, Decision forests: A unified framework for classification, regression, density estimation, manifold learning and semi-supervised learning, Found. Trends® Comput. Graph. Vis. 7 (2012), no. 2–3, 81–227.
[22] C. Dang, L. Nghiem, E. Fedutenko, E. Gorucu, C. Yang, A. Mirzabozorg, N. Nguyen, and Z. Chen, AI based mechanistic modeling and probabilistic forecasting of hybrid low salinity chemical flooding, Fuel 261 (2020), 116445.
[23] B. Efron and T. Hastie, Computer Age Statistical Inference: Algorithms, Evidence, and Data Science, Cambridge University Press, 2016.
[24] S.J. Fathi, T. Austad, and S. Strand, Smart water as a wettability modifier in chalk: the effect of salinity and ionic composition, Energy Fuels 24 (2010), 2514–2519.
[25] S.J. Fathi, T. Austad, and S. Strand, Water-based enhanced oil recovery (EOR) by smart water: Optimal ionic composition for EOR in carbonates, Energy Fuels 25 (2011), 5173–5179.
[26] J. Gareth, W. Daniela, H. Trevor, and T. Robert, An Introduction to Statistical Learning, Springer, New York, 2013.
[27] J. Ghosn, and Y. Bengio, Multi-Task Learning for Stock Selection, Adv. Neural Inf. Process. Syst. 9 (1996), 946–952.
[28] J. Gillberg, P. Marttinen, M. Pirinen, A.J. Kangas, P. Soininen, M. Ali, A.S. Havulinna, M.-R. J¨arvelin, M. Ala-Korpela, and S. Kaski, Multiple output regression with latent noise, J. Machine Learn. Res. 17 (2016), no. 122, 1–35.
[29] P.O. Gislason, J.A. Benediktsson, and J.R. Sveinsson, Random forest classification of multisource remote sensing and geographic data, IEEE Int. Geosci. Remote Sens. Symp., 2004, pp. 1049–1052.
[30] P.O. Gislason, J.A. Benediktsson, and J.R. Sveinsson, Random forests for land cover classification, Pattern Recogn. Lett. 27 (2006), 294–300.
[31] E. Goel and E. Abhilasha, Random forest: A review, Int. J. Adv. Res. Comput. Sci. Software Engin. 7 (2017), 251–257.
[32] P. Hall, B.U. Park, and R.J. Samworth, Choice of neighbor order in nearest-neighbor classification, Ann. Statist. 36 (2008), 2135–2152.
[33] L.D. Hallenbeck, J.E. Sylte, D.J. Ebbs, and L.K. Thomas, Implementation of the Ekofisk field waterflood, SPE Form. Eval. 6 (1991), 284–290.
[34] T. Hastie and R. Tibshirani, Discriminant adaptive nearest neighbor classification and regression, Adv. Neural Inf. Process. Syst. 8 (1995), 409–415.
[35] G. Hirasaki and D.L. Zhang, Surface chemistry of oil recovery from fractured, oil-wet, carbonate formations, SPE J. 9 (2004), 151–162.
[36] P.A. Hopkins, I. Omland, F. Layti, S. Strand, T. Puntervold, and T. Austad, Crude oil quantity and its effect on chalk surface wetting, Energy Fuels 31 (2017), 4663–4669.
[37] G.F. Hughes, On the mean accuracy of statistical pattern recognizers, IEEE Trans. Inf. Theory 14 (1968), 55–63.
[38] Z. Ibrahim and D. Rusli Predicting students’ academic performance: Comparing artificial neural network, decision tree and linear regression, 21st Ann. SAS Malaysia Forum, 2007, pp.1–6.
[39] S.B. Imandoust and M. Bolandraftar, Application of k-nearest neighbor (kNN) approach for predicting economic events: Theoretical background, J. Engin. Res. Appl. 3 (2013), no. 5, 605–610.
[40] J.H. Jeong, J.P. Resop, N.D. Mueller, D.H. Fleisher, K. Yun, E.E. Butler, D.J. Timlin, K.M. Shim, J.S. Gerber, V.R. Reddy, and S.H. Kim, Random forests for global and regional crop yield predictions, PLoS ONE 11 (2016), 1–15.
[41] R.J. Lewis, An introduction to classification and regression tree (CART) analysis, Ann. Meet. Soc. Acad. Emergency Med. San Francisco, California, Vol. 14. San Francisco, CA, USA: Department of Emergency Medicine Harbor-UCLA Medical Center Torrance, 2000.
[42] C.D. Manning and H. Schutze Foundations of Statistical Natural Language Processing, MIT Press, 1999.
[43] G. Melki, and A. Cano, V. Kecman, and S. Ventura, Multi-target support vector regression via correlation regressor chains, Inf. Sci. 415 (2017), 53–69.
[44] S. Mohammadi, S. Kord, and J. Moghadasi, An experimental investigation into the spontaneous imbibition of surfactant assisted low salinity water in carbonate rocks, Fuel 243 (2019), 142–154.
[45] N.R. Morrow, Wettability and its effect on oil recovery, J. Petrol. Technol. 42 (1990), no. 12, 1476–1484.
[46] C. Nguyen, Y. Wang, and H.N. Nguyen, Random forest classifier combined with feature selection for breast cancer diagnosis and prognostic, J. Biomed. Sci. Engin. 6 (2013), 551–560.
[47] O. Okun and H. Priisalu, Random forest for gene expression based cancer classification: overlooked issues, Iberian Conf. Pattern Recog. Image Anal., Berlin, Heidelberg: Springer Berlin Heidelberg, 2007, pp. 483–490.
[48] M. Pal, Random forests for land cover classification, IEEE Int. Geosci. Remote Sens. Symp., Proc.(IEEE Cat. No. 03CH37477). Vol. 6. IEEE, 2003, pp. 3510–3512.
[49] D.S. Palmer, N.M. O’Boyle, R.C. Glen, and J.B.O. Mitchell, Random forest models to predict aqueous solubility, J. Chem. Inf. Model. 47 (2007), 150–158.
[50] L.E. Peterson, K-nearest neighbor, Scholarpedia 4 (2009), no. 2, 1883.
[51] T. Puntervold, S. Strand, R. Ellouz, and T. Austad, Modified seawater as a smart EOR fluid in chalk, J. Petrol. Sci. Engin. 133 (2015), 440–443.
[52] J. Romanuka, J. Hofman, D.J. Ligthelm, B.M. Suijkerbuijk, A.H. Marcelis, S. Oedai, N.J. Brussee, A. van der Linde, H. Aksulu, and T. Austad, Low salinity EOR in carbonates, SPE Improved Oil Recovery Conf., SPE, 2012.
[53] P. Royston and D.G. Altman, Risk stratification for in-hospital mortality in acutely decompensated heart failure, Jama 293 (2005), no. 20, 2467–2468.
[54] S.F. Shariatpanahi, P. Hopkins, H. Aksulu, S. Strand, T. Puntervold, and T. Austad, Water based EOR by wettability alteration in dolomite, Energy Fuels 30 (2016), no. 1, 180–187.
[55] E. Scornet, On the asymptotics of random forests, J. Multivar. Anal. 146 (2016), 72–83.
[56] E. Scornet, G. Biau, J.P. Vert, Consistency of random forests, Ann. Statist. 43 (2015), 1716–1741.
[57] Y.Y. Song and L.U. Ying, Decision tree methods: Applications for classification and prediction, Shanghai Arch. Psych. 27 (2015), no. 2, 130–135.
[58] D.C. Standnes and T. Austad, Wettability alteration in carbonates: Interaction between cationic surfactant and carboxylates as a key factor in wettability alteration from oil-wet to water-wet conditions, Colloids Surfaces A: Physicochem. Engin. Aspects 216 (2003), 243–259.
[59] S. Strand, T. Puntervold, and T. Austad, Effect of temperature on enhanced oil recovery from mixed-wet chalk cores by spontaneous imbibition and forced displacement using seawater, Energy Fuels 22 (2008), no. 5, 3222–3225.
[60] V. Svetnik, A. Liaw, C. Tong, J.C. Culberson, R.P. Sheridan, and B.P. Feuston, Random forest: A classification and regression tool for compound classification and QSAR modeling, J. Chem. Inf. Comput. Sci. 43 (2003), no. 6, 1947–1958.
[61] K. Tatsumi, Y. Yamashiki, M.A.C. Torres, and C.L.R. Taipe, Crop classification of upland fields using Random forest of time-series Landsat 7 ETM+ data, Comput. Electron. Agricul. 115 (2015), 171–179.
[62] G.K.F. Tso and K.K.W. Yau, Predicting electricity energy consumption: A comparison of regression analysis, decision tree and neural networks, Energy 32 (2007), 1761–1768.
[63] H. Tyralis, G. Papacharalampous, and A. Langousis, A brief review of random forests for water scientists and practitioners and their recent history in water resources, Water 11 (2019), no. 5, 910.
[64] X. Xi, V.S. Sheng, B. Sun, L. Wang, and F. Hu, An empirical comparison on multi-target regression learning, Comput. Mater. Continua 56 (2018), no. 2, 185–198.
[65] M. Xu, P. Watanachaturaporn, P.K. Varshney, and M.K. Arora, Decision tree regression for soft classification of remote sensing data, Remote Sens. Envir. 97 (2005), 322–336.
[66] Z. Yao and W.L. Ruzzo, A regression-based K nearest neighbor algorithm for gene function prediction from het[1]erogenous data, BMC Bioinf. 7 (2006), 1–11.
[67] Z. Yu, F. Haghighat, B.C.M. Fung, and H. Yoshino, A decision tree method for building energy demand modelling, Energy Build. 27 (2015), 1637–1646.
[68] H.M. Zawbaa, M. Hazman, M. Abbass, and A.E. Hassanien, Automatic fruit classification using random forest algorithm, 14th Int. Conf. Hybrid Intell. Syst., 2014, pp. 164–168.
[69] P. Zhang and T. Austad, Wettability and oil recovery from carbonates: Effects of temperature and potential determining ions, Colloids Surfaces A: Physicochem. Engine. Aspects 279 (2006), 179–187.
[70] S. Zhang, X. Li, M. Zong, X. Zhu, and D. Cheng, Learning k for kNN classification, ACM Trans. Intell. Syst. Technol. 8 (2017), no. 3, 1–19.
[71] Y. Zhang and N.R. Morrow, Comparison of secondary and tertiary recovery with change in injection brine composition for crude oil/sandstone combinations, SPE Improved Oil Recovery Conf., SPE, 2006.
[72] X. Zhen, M. Yu, X. He, and S. Li, Multi-target regression via robust low-rank learning, IEEE Trans. Pattern Anal. Machine Intell. 40 (2018), 497–504.
[73] X. Zhen, M. Yu, F. Zheng, I.B. Nachum, M. Bhaduri, D. Laidley, D and S. Li, Multitarget sparse latent regression, IEEE Trans. Neural Networks Learn. Syst. 29 (2017), no. 5, 1575–1586.
[74] A. Ziegler and I.R. Konig, Mining data with random forests: Current options for real-world applications, Wiley Interdiscip. Rev.: Data Min. Knowledge Disc. 4 (2014), 55–63.
International Journal of Nonlinear Analysis and Applications

Articles in Press, Corrected Proof
Available Online from 12 March 2025
  • Receive Date: 28 November 2021
  • Accept Date: 15 January 2022