Application of supervised machine learning to predict the enhanced gas recovery by CO₂ injection in shale gas reservoirs

Abstract

The technique of Enhanced Gas Recovery by CO₂ injection (CO₂-EGR) into shale reservoirs has brought increasing attention in the recent decade. CO₂-EGR is a complex geophysical process that is controlled by several parameters of shale properties and engineering design. Nevertheless, more challenges arise when simulating and predicting CO₂/CH₄ displacement within the complex pore systems of shales. Therefore, the petroleum industry is in need of developing a cost-effective tool/approach to evaluate the potential of applying CO₂ injection to shale reservoirs. In recent years, machine learning applications have gained enormous interest due to their high-speed performance in handling complex data and efficiently solving practical problems. Thus, this work proposes a solution by developing a supervised machine learning (ML) based model to preliminary evaluate CO₂-EGR efficiency. Data used for this work was drawn across a wide range of simulation sensitivity studies and experimental investigations. In this work, linear regression and artificial neural networks (ANNs) implementations were considered for predicting the incremental enhanced CH₄. Based on the model performance in training and validation sets, our accuracy comparison showed that (ANNs) algorithms gave 15% higher accuracy in predicting the enhanced CH₄ compared to the linear regression model. To ensure the model is more generalizable, the size of hidden layers of ANNs was adjusted to improve the generalization ability of ANNs model. Among ANNs models presented, ANNs of 100 hidden layer size gave the best predictive performance with the coefficient of determination (R²) of 0.78 compared to the linear regression model with R² of 0.68. Our developed ML-based model presents a powerful, reliable and cost-effective tool which can accurately predict the incremental enhanced CH₄ by CO₂ injection in shale gas reservoirs.

Keywords

Artificial intelligence / Supervised Machine Learning / Shale Gas / Enhanced Shale Gas Recovery CO₂ Injection / CO₂ sequestration

Declaration of competing interest

The authors declare that there is no conflict of interest in this work.

References

[1] IEA,World Energy Outlook 2021, 2021. Retrieved from, https://www.iea.org/reports/world-energy-outlook-2021.

[2] A. Fatah, Z. Bennour, H. Ben Mahmud, R. Gholami, M. Hossain,A Review on the influence of CO2/shale interaction on shale properties: implications of CCS in shales, Energies 13 (12) (2020) 3200.

[3] EIA,Shale Gas Production Drives World Natural Gas Production Growth, 2016. Retrieved from, https://www.eia.gov/todayinenergy/detail.php?id=27512.

[4] D. Rahm, Regulating hydraulic fracturing in shale gas plays: the case of Texas, Energy Pol. 39 (5) (2011) 2974-2981, https://doi.org/10.1016/j.enpol.2011.03.009.

[5] Huang, Evaluation of CO₂ injection into shale gas reservoirs considering dispersed distribution of kerogen, Appl. Energy 260 (2020), 114285, https://doi.org/10.1016/j.apenergy.2019.114285.

[6] J. Hardy,Characterization Of Organic Pores Within High-Maturation Shale Gas Reservoirs, 2019. Paper presented at the SPE Annual Technical Conference and Exhibition, Calgary, Alberta, Canada, https://doi.org/10.2118/199773-STU, https://www.onepetro.org:443/download/conference-paper/SPE-199773-STU?id=conference-paper%2FSPE-199773-STU.

[7] J.H. Frantz, W.K. Sawyer, R.J. MacDonald, J.R. Williamson, D. Johnston, G. Waters, Evaluating Barnett Shale Production Performance-Using an Integrated Approach, 2005. Paper presented at the SPE annual technical conference and exhibition).

[8] J.P. Vermylen, Geomechanical Studies of the Barnett Shale, Stanford University, Texas, USA, 2011.

[9] A.K. Dahaghi, Numerical Simulation and Modeling of Enhanced Gas Recovery and CO₂ Sequestration in Shale Gas Reservoirs: A Feasibility Study, 2010. Paper presented at the SPE International Conference on CO₂ Capture, Storage, and Utilization, New Orleans, Louisiana, USA, https://doi.org/10.2118/139701-MS , https://www.onepetro.org/conference-paper/SPE-139701-MS.

[10] B.C. Nuttal,Reassessment of CO₂ Sequestration Capacity and Enhanced Gas Recovery Potential of Middle and Upper Devonian Black Shales in the Appalachian Basin, 2010. MRCSP Phase II Topical Report October 2005eOctober 2010. Midwest Regional Carbon Sequestration Partnership. In.

[11] B.C. Nuttal, C. Eble, R.M. Bustin, J.A. Drahovzal, -Analysis of Devonian black shales in Kentucky for potential carbon dioxide sequestration and enhanced natural gas production,in: E. S. Rubin, D.W. Keith, C.F. Gilboy, M. Wilson, T. Morris, J. Gale, K. Thambimuthu (Greenhouse Gas Control Technologies 7, Elsevier Science Ltd,Eds.), Oxford, 2005, pp. 2225-2228.

[12] K.C. Schepers, B.C. Nuttall, A.Y. Oudinot, R.J. Gonzalez, Reservoir Modeling and Simulation of the Devonian Gas Shale of Eastern Kentucky for Enhanced Gas Recovery and CO₂ Storage, 2009. Paper presented at the SPE International Conference on CO₂ Capture, Storage, and Utilization, San Diego, California, USA, https://doi.org/10.2118/126620-MS , https://www.onepetro.org:443/download/conference-paper/SPE-126620-MS?id=conference-paper%2FSPE-126620-MS.

[13] X. Du, M. Gu, S. Duan, X. Xian, The influences of CO₂ injection pressure on CO₂ dispersion and the mechanism of CO₂-CH4 displacement in shale, J. Energy Resour. Technol. 140 (1) (2017), https://doi.org/10.1115/1.4037687, 012907-012907-012909.

[14] W. Yu, K. Sepehrnoori, T.W. Patzek, Modeling gas adsorption in marcellus shale with Langmuir and BET isotherms, SPE J. 21 (2) (2016) 589-600, https://doi.org/10.2118/170801-pa.

[15] I. Klewiah, D.S. Berawala, H.C. Alexander Walker, P.Ø. Andersen, P.H. Nadeau, Review of experimental sorption studies of CO₂ and CH4 in shales, J. Nat. Gas Sci. Eng. 73 (2020), 103045, https://doi.org/10.1016/j.jngse.2019.103045.

[16] M. Godec, G. Koperna, R. Petrusak, A. Oudinot, Potential for enhanced gas recovery and CO₂ storage in the Marcellus Shale in the Eastern United States, Int. J. Coal Geol. 118 (2013) 95-104, https://doi.org/10.1016/j.coal.2013.05.007.

[17] D. Liu, R. Agarwal, Y. Li, Numerical simulation and optimization of CO₂ enhanced shale gas recovery using a genetic algorithm, J. Clean. Prod. 164 (2017) 1093-1104, https://doi.org/10.1016/j.jclepro.2017.07.040.

[18] M. Mansi, M. Almobarak, C. Lagat, Q. Xie, Effect of reservoir pressure and total organic content on adsorbed gas production in shale reservoirs: a numerical modelling study, Arabian J. Geosci. 15 (2) (2022) 134, https://doi.org/10.1007/s12517-021-09416-x.

[19] M.O. Eshkalak, E.W. Al-shalabi, A. Sanaei, U. Aybar, K. Sepehrnoori, Enhanced Gas Recovery by CO₂ Sequestration versus Re-fracturing Treatment in Unconventional Shale Gas Reservoirs, 2014. Paper presented at the Abu Dhabi International Petroleum Exhibition and Conference, Abu Dhabi, UAE, https://doi.org/10.2118/172083-MS , https://www.onepetro.org:443/download/conference-paper/SPE-172083-MS?id=conference-paper%2FSPE-172083-MS.

[20] F. Liu, K. Ellett, Y. Xiao, J.A. Rupp, Assessing the feasibility of CO₂ storage in the New Albany Shale (DevonianeMississippian) with potential enhanced gas recovery using reservoir simulation, Int. J. Greenh. Gas Control 17 (2013) 111-126, https://doi.org/10.1016/j.ijggc.2013.04.018.

[21] R. Xu, K. Zeng, C. Zhang, P. Jiang, Assessing the feasibility and CO₂ storage capacity of CO₂ enhanced shale gas recovery using Triple-Porosity reservoir model, Appl. Therm. Eng. 115 (2017) 1306-1314, https://doi.org/10.1016/j.applthermaleng.2017.01.062.

[22] W. Yu, E.W. Al-Shalabi, K. Sepehrnoori, A Sensitivity Study of Potential CO₂ Injection for Enhanced Gas Recovery in Barnett Shale Reservoirs, 2014. Paper presented at the SPE Unconventional Resources Conference, The Woodlands, Texas, USA, https://doi.org/10.2118/169012-MS , https://www.onepetro.org:443/download/conference-paper/SPE-169012-MS?id=conference-paper% 2FSPE-169012-MS.

[23] T.H. Kim, S.S. Park, K.S. Lee, Modeling of CO₂ Injection Considering Multi-Component Transport and Geomechanical Effect in Shale Gas Reservoirs, 2015 (Paper presented at the SPE/IATMI Asia Pacific Oil & Gas Conference and Exhibition, Nusa Dua, Bali, Indonesia).

[24] Z. Li, D. Elsworth, Controls of CO₂-N₂ gas flood ratios on enhanced shale gas recovery and ultimate CO₂ sequestration, J. Petrol. Sci. Eng. 179 (2019) 1037-1045, https://doi.org/10.1016/j.petrol.2019.04.098.

[25] H. Sun, J. Yao, S.-h. Gao, D.-y. Fan, C.-c. Wang, Z.-x. Sun, Numerical study of CO₂ enhanced natural gas recovery and sequestration in shale gas reservoirs, Int. J. Greenh. Gas Control 19 (2013) 406-419, https://doi.org/10.1016/j.ijggc.2013.09.011.

[26] E. Fathi, I.Y. Akkutlu, Multi-component gas transport and adsorption effects during CO₂ injection and enhanced shale gas recovery, Int. J. Coal Geol. 123 (2014) 52-61, https://doi.org/10.1016/j.coal.2013.07.021.

[27] T.H. Kim, J. Cho, K.S. Lee, Evaluation of CO₂ injection in shale gas reservoirs with multi-component transport and geomechanical effects, Appl. Energy 190 (2017) 1195-1206, https://doi.org/10.1016/j.apenergy.2017.01.047.

[28] K. Bybee, Proper evaluation of shale-gas reservoirs leads to more-effective hydraulic-fracture stimulation, J. Petrol. Technol. 61 (7) (2009) 59-61, https://doi.org/10.2118/0709-0059-JPT.

[29] G. Zhu, Q. Jin, S. Zhang, L. Zhang, Forming mechanisms and heterogeneity of source rock: a case study in Dongying Depression, J. Mineral. Petrol. 23 (4) (2003) 95-100.

[30] D.S. Berawala, P. Østebø Andersen, Evaluation of Multicomponent Adsorption Kinetics for CO₂ Enhanced Gas Recovery from Tight Shales, 2019. Paper presented at the SPE Europec featured at 81st EAGE Conference and Exhibition.

[31] L. Huang, Z. Ning, H. Li, Q. Wang, H. Ye, H. Qin, Molecular Simulation of CO₂ Sequestration and Enhanced Gas Recovery in Gas Rich Shale: an Insight Based on Realistic Kerogen Model, 2017. Paper presented at the Abu Dhabi International Petroleum Exhibition & Conference, Abu Dhabi, UAE, https://doi.org/10.2118/188216-MS , https://www.onepetro.org:443/download/conferencepaper/SPE-188216-MS?id=conference-paper%2FSPE-188216-MS.

[32] B. Mahesh, Machine learning algorithms-a review, Int. J. Sci. Res. 9 (2020) 381e386 [Internet].

[33] E. Alpaydin, Introduction to Machine Learning, MIT press, 2020.

[34] T. Hastie, R. Tibshirani, J. Friedman, Overview of supervised learning, in: The Elements of Statistical Learning, Springer, 2009, pp. 9-41.

[35] 19- 20 Dec. 2009 H. Wang, C. Ma, L. Zhou, A Brief Review of Machine Learning and its Application, 2009. Paper presented at the 2009 International Conference on Information Engineering and Computer Science.

[36] 14- 16 Feb. 2019 S. Ray, A Quick Review of Machine Learning Algorithms, 2019. Paper presented at the 2019 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COMITCon).

[37] J. Ali, Neural Networks: a New Tool for the Petroleum Industry?, 1994. Paper presented at the European petroleum computer conference).

[38] A. Sircar, K. Yadav, K. Rayavarapu, N. Bist, H. Oza, Application of machine learning and artificial intelligence in oil and gas industry, Petrol. Res. 6 (4) (2021) 379-391, https://doi.org/10.1016/j.ptlrs.2021.05.009.

[39] Anifowose, Ensemble machine learning: an untapped modeling paradigm for petroleum reservoir characterization, J. Petrol. Sci. Eng. 151 (2017) 480-487, https://doi.org/10.1016/j.petrol.2017.01.024.

[40] R. Rezaee, J. Ekundayo, Permeability prediction using machine learning methods for the CO₂ injectivity of the precipice sandstone in surat basin, Australia, Energies 15 (6) (2022) 2053. Retrieved from, https://www.mdpi.com/1996-1073/15/6/2053.

[41] S. Bhattacharya, P.K. Ghahfarokhi, T.R. Carr, S. Pantaleone, Application of predictive data analytics to model daily hydrocarbon production using petrophysical, geomechanical, fiber-optic, completions, and surface data: a case study from the Marcellus Shale, North America, J. Petrol. Sci. Eng. 176 (2019) 702-715, https://doi.org/10.1016/j.petrol.2019.01.013.

[42] D. Vikara, D. Remson, V. Khanna, Machine learning-informed ensemble framework for evaluating shale gas production potential: case study in the Marcellus Shale, J. Nat. Gas Sci. Eng. 84 (2020), 103679.

[43] P.F. Orrù, A. Zoccheddu, L. Sassu, C. Mattia, R. Cozza, S. Arena, Machine learning approach using MLP and SVM algorithms for the fault prediction of a centrifugal pump in the oil and gas industry, Sustainability 12 (11) (2020) 4776. Retrieved from, https://www.mdpi.com/2071-1050/12/11/4776.

[44] B. Chen, D.R. Harp, Y. Lin, E.H. Keating, R.J. Pawar, Geologic CO₂ sequestration monitoring design: a machine learning and uncertainty quantification based approach, Appl. Energy 225 (2018) 332-345, https://doi.org/10.1016/j.apenergy.2018.05.044.

[45] P. Cunningham, M. Cord, S.J. Delany, Supervised learning, in: Machine Learning Techniques for Multimedia, Springer, 2008, pp. 21-49.

[46] 13- 15 Oct. 2005 W. Haifeng, H. Dejin, Comparison of SVM and LS-SVM for Regression, 2005. Paper presented at the 2005 International Conference on Neural Networks and Brain.

[47] N.K. Bhatia, A.H. El-Hag, K.B. Shaban, Machine Learning-Based Regression and Classification Models for Oil Assessment of Power Transformers, 2020. Paper presented at the 2020 IEEE international conference on informatics, IoT, and enabling technologies (ICIoT).

[48] C.Y. Zhao, H.X. Zhang, X.Y. Zhang, M.C. Liu, Z.D. Hu, B.T. Fan, Application of support vector machine (SVM) for prediction toxic activity of different data sets, Toxicology 217 (2) (2006) 105-119, https://doi.org/10.1016/j.tox.2005.08.019.

[49] J. Zou, Y. Han, S.-S. So, Overview of artificial neural networks, Artif. Neural Netw. (2008) 14-22.

[50] J. Schmidhuber, Deep learning in neural networks: an overview, Neural Network. 61 (2015) 85-117, https://doi.org/10.1016/j.neunet.2014.09.003.

[51] R. Bala, D. Kumar, Classification using ANN: a review, Int. J. Comput. Intell. Res. 13 (7) (2017) 1811-1820.

[52] S.B. Kotsiantis, Decision trees: a recent overview, Artif. Intell. Rev. 39 (4) (2013) 261-283.

[53] A.J. Myles, R.N. Feudale, Y. Liu, N.A. Woody, S.D. Brown, An introduction to decision tree modeling, J. Chemometr.: J. Chemometr. Soc. 18 (6) (2004) 275-285.

[54] Y.-Y. Song, Y. Lu, Decision tree methods: applications for classification and prediction, Shanghai Arch. Psychiatr. 27 (2) (2015) 130-135, https://doi.org/10.11919/j.issn.1002-0829.215044.

[55] Z. Allah Bukhsh, A. Saeed, I. Stipanovic, A.G. Doree, Predictive maintenance using tree-based classification techniques: a case of railway switches, Transport. Res. C Emerg. Technol. 101 (2019) 35-54, https://doi.org/10.1016/j.trc.2019.02.001.

[56] K. Fawagreh, M.M. Gaber, E. Elyan, Random forests: from early developments to recent advancements, Syst. Sci. Control Eng.: Open Access J. 2 (1) (2014) 602-609.

[57] R. Choudhary, H.K. Gianey,Comprehensive Review on Supervised Machine Learning Algorithms, 2017. Paper presented at the 2017 International Conference on Machine Learning and Data Science (MLDS).

[58] A. Liaw, M. Wiener, Classification and regression by randomForest, R. News 2 (3) (2002) 18-22.

[59] B. Mahesh, Machine Learning Algorithms -A Review, 2019.

[60] Z. Ghahramani, Unsupervised Learning, 2003. Paper presented at the Summer school on machine learning).

[61] M.E. Celebi, K. Aydin, Unsupervised Learning Algorithms, Springer, 2016.

[62] T.A. Badgwell, J.H. Lee, K.-H. Liu, Reinforcement learningeoverview of recent progress and implications for process control, Comput. Aided Chem. Eng. 44 (2018) 71-85.

[63] K. Arulkumaran, M.P. Deisenroth, M. Brundage, A.A. Bharath, Deep reinforcement learning: a brief survey, IEEE Signal Process. Mag. 34 (6) (2017) 26-38.

[64] S. Mahdi, X. Wang, N. Shah, Interactions between the design and operation of shale gas networks, including CO₂ sequestration, Engineering 3 (2) (2017) 244-256, https://doi.org/10.1016/J.ENG.2017.02.007.

[65] X. Li, D. Elsworth, Effect of CO₂ Injectivity on Enhanced Shale Gas Recovery, 2014. Paper presented at the 48th U.S. Rock Mechanics/Geomechanics Symposium, Minneapolis, Minnesota.

[66] D. Liu, Y. Li, S. Yang, Evaluation of the role of water-shale-gas reactions on CO₂ enhanced shale gas recovery, Energy Proc. 154 (2018) 42-47, https://doi.org/10.1016/j.egypro.2018.11.008.

[67] J. Liu, L. Xie, Y. Yao, Q. Gan, P. Zhao, L. Du, Preliminary study of influence factors and estimation model of the enhanced gas recovery stimulated by carbon dioxide utilization in shale, ACS Sustain. Chem. Eng. 7 (24) (2019) 20114-20125.

[68] J. Josse, F. Husson, Handling missing values in exploratory multivariate data analysis methods, J. Soc. Fr. Stat. 153 (2) (2012) 79-99.

[69] D.B. Rubin, Inference and missing data, Biometrika 63 (3) (1976) 581-592.

[70] M. Saar-Tsechansky, F. Provost, Handling Missing Values when Applying Classification Models, 2007.

[71] M. Ezekiel, Methods of Correlation Analysis, 1941.

[72] A. Jović, K. Brkić, N. Bogunović, A Review of Feature Selection Methods with Applications, 2015. Paper presented at the 2015 38th international convention on information and communication technology, electronics and microelectronics (MIPRO).

[73] J.C. De Winter, S.D. Gosling, J. Potter, Comparing the Pearson and Spearman correlation coefficients across distributions and sample sizes: a tutorial using simulations and empirical data, Psychol. Methods 21 (3) (2016) 273.

[74] A. Akossou, R. Palm, Impact of data structure on the estimators R-square and adjusted R-square in linear regression, Int. J. Math. Comput. 20 (3) (2013) 84-93.

[75] K.-Y. Lee, K.-H. Kim, J.-J. Kang, S.-J. Choi, Y.-S. Im, Y.-D. Lee, Y.-S. Lim, Comparison and analysis of linear regression & artificial neural network, Int. J. Appl. Eng. Res. 12 (20) (2017) 9820-9825.