A new robust predictive model for lost circulation rate using convolutional neural network: A case study from Marun Oilfield

Abstract

A major cause of some of serious issues encountered in a drilling project, including wellbore instability, formation damage, and drilling string stuck -which are known to increase non-productive time (NPT) and hence the drilling cost -is what we know as mud loss. The mud loss can be prevented or at least significantly reduced by taking proper measures beforehand provided the position and intensity of such loss can be properly predicted using an accurate predictor model. Accordingly, in this study, we used the convolutional neural network (CNN) and hybridized forms of multilayer extreme learning machine (MELM) and least square support vector machine (LSSVM) with the Cuckoo optimization algorithm (COA), particle swarm optimization (PSO), and genetic algorithm (GA) for modeling the mud loss rate based on drilling data, mud properties, and geological information of 305 drilling wells penetrating the Marun Oilfield. For this purpose, we began by a pre-processing step to attenuate the effect of noise using the Savitzky-Golay method. The whole set of available data was divided into the modeling (including 2300 data points) and the validation (including 483 data points) subsets. Next, the second generation of the non-dominated sorting genetic algorithm (NSGA-II) was applied to the modeling data to identify the most significant features for estimating the mud loss. The results showed that the prediction accuracy increased with the number of selected features, but the increase became negligible when the number of selected features exceeded 9. Accordingly, the following 9 features were selected as input to the intelligent algorithms (IAs): pump pressure, mud weight, fracture pressure, pore pressure, depth, gel 10 min/gel 10 s, fan 600/fan 300, flowrate, and formation type. Application of the hybrid algorithms and simple forms of LSSVM and CNN to the training data (80% of the modeling data, i.e. 1840 data points) showed that all of the models tend to underestimate the mud loss at higher mud loss rates, although the CNN exhibited lower underestimation levels. Error analysis on different models showed that the CNN provided for a significantly higher degree of accuracy, as compared to other models. The more accurate outputs of the hybrid LSSVM model than those of the simple LSSVM indicated the large potentials of metaheuristic algorithms for achieving optimal solutions. The lower error levels obtained with the CNN model in the testing phase highlighted the excellent generalizability of this model for unseen data. The more accurate predictions obtained with this model, rather than the other models, in the validation phase further proved this latter finding. Therefore, application of this method to other wells in the same field is highly recommended.

Keywords

Lost circulation prediction / Artificial intelligence / Deep learning / Feature selection

References

[1] A. Moazzeni, M. Nabaei, S.G. Jegarluei, Decision making for reduction of nonproductive time through an integrated lost circulation prediction, Petrol. Sci. Technol. 30 (2012) 2097-2107.

[2] A.A. Pilehvari, V.R. Nyshadham, Effect of material type and size distribution on performance of loss/seepage control material, in: Int. Symp. Exhib. Form. Damage Control, OnePetro, 2002.

[3] M. Sabah, M. Mehrad, S.B. Ashrafi, D.A. Wood, S. Fathi, Hybrid machine learning algorithms to enhance lost-circulation prediction and management in the Marun oil field, J. Petrol. Sci. Eng. 198 (2021), 108125, https://doi.org/10.1016/j.petrol.2020.108125.

[4] A. Hemmati-Sarapardeh, A. Larestani, N.A. Menad, S. Hajirezaie, Applications of Artificial Intelligence Techniques in the Petroleum Industry, Gulf Professional Publishing, 2020.

[5] H. Wang, B.F. Towler, M.Y. Soliman,Near wellbore stress analysis and wellbore strengthening for drilling depleted formations, in: Rocky Mt. Oil Gas Technol. Symp., OnePetro, 2007.

[6] F.B. Growcock, N. Kaageson-Loe, J, et al., Wellbore stability, stabilization and strengthening,in:Friedheim, M.W. Sanders, J. Bruton (Eds.), Offshore Mediterr. Conf. Exhib., OnePetro, 2009, 2009.

[7] A. Shadravan, M. Nabaei, M. Amani, Development of underbalanced drilling implementation in Parsi Oilfield, in: Offshore Eur. Oil Gas Conf., Exhib. Sept., 2009, pp. 8-11.

[8] Y. Feng, J.F. Jones, K.E. Gray, A review on fracture-initiation and-propagation pressures for lost circulation and wellbore strengthening, SPE Drill. Complet. 31 (2016) 134-144.

[9] A. Lavrov, Lost Circulation: Mechanisms and Solutions, Gulf professional publishing, 2016.

[10] M. Sabah, M. Talebkeikhah, F. Agin, F. Talebkeikhah, E. Hasheminasab, Application of decision tree, artificial neural networks, and adaptive neurofuzzy inference system on predicting lost circulation: a case study from Marun oil field, J. Petrol. Sci. Eng. 177 (2019) 236-249.

[11] A. Ghalambor, S. Salehi, M.P. Shahri, M. Karimi, Integrated workflow for lost circulation prediction, in: SPE Int. Symp. Exhib. Form. Damage Control, One-Petro, 2014.

[12] A.R. Moazzeni, M. Nabaei, S. Ghadamijegarlooei, Optimizing size distribution of limestone chips and shellfish as lost circulation materials, in: 6th Int. Chem. Eng. Conf., 2009.

[13] R. Nie, H. Xia, L. Mao, M. Cai, Research on conversion time between lost circulation and overflow for the fractured stratum, Petroleum 6 (2020) 98-105.

[14] O. Razavi, A.K. Vajargah, E. van Oort, M. Aldin, S. Govindarajan, Optimum particle size distribution design for lost circulation control and wellbore strengthening, J. Nat. Gas Sci. Eng. 35 (2016) 836-850.

[15] R. Zhong, S. Miska, M. Yu, Parametric study of controllable parameters in fracture-based wellbore strengthening, J. Nat. Gas Sci. Eng. 43 (2017) 13-21.

[16] M. Anemangely, A. Ramezanzadeh, H. Amiri, S.-A. Hoseinpour, Machine learning technique for the prediction of shear wave velocity using petrophysical logs, J. Petrol. Sci. Eng. 174 (2019), https://doi.org/10.1016/j.petrol.2018.11.032.

[17] S.B. Ashrafi, M. Anemangely, M. Sabah, M.J. Ameri, Application of hybrid artificial neural networks for predicting rate of penetration (ROP): a case study from Marun oil field, J. Petrol. Sci. Eng. 175 (2019), https://doi.org/10.1016/j.petrol.2018.12.013.

[18] Z. Geng, H. Wang, M. Fan, Y. Lu, Z. Nie, Y. Ding, M. Chen, Predicting seismicbased risk of lost circulation using machine learning, J. Petrol. Sci. Eng. 176 (2019) 679-688.

[19] X. Hou, J. Yang, Q. Yin, H. Liu, H. Chen, J. Zheng, J. Wang, B. Cao, X. Zhao, M. Hao, Lost circulation prediction in south China sea using machine learning and big data technology, in: Offshore Technol. Conf., OnePetro, 2020.

[20] M. Mehrad, M. Bajolvand, A. Ramezanzadeh, J.G. Neycharan, Developing a new rigorous drilling rate prediction model using a machine learning technique, J. Petrol. Sci. Eng. 192 (2020), 107338, https://doi.org/10.1016/j.petrol.2020.107338.

[21] N. Mohamadian, H. Ghorbani, D.A. Wood, M. Mehrad, S. Davoodi, S. Rashidi, A. Soleimanian, A.K. Shahvand, A geomechanical approach to casing collapse prediction in oil and gas wells aided by machine learning, J. Petrol. Sci. Eng. 196 (2021), 107811, https://doi.org/10.1016/j.petrol.2020.107811.

[22] H. Wang, M. Chen, S. Wei, Y. Lu, Z. Nie, Y. Li, The influence of barrier coastal sedimentary system lost circulation in sandstone, J. Petrol. Sci. Eng. 185 (2020), 106654.

[23] D.J. Armaghani, E.T. Mohamad, M.S. Narayanasamy, N. Narita, S. Yagiz, Development of hybrid intelligent models for predicting TBM penetration rate in hard rock condition, Tunn. Undergr. Space Technol. 63 (2017) 29-43.

[24] H. Kaydani, A. Mohebbi, A comparison study of using optimization algorithms and artificial neural networks for predicting permeability, J. Petrol. Sci. Eng. 112 (2013) 17-23.

[25] M. Anemangely, A. Ramezanzadeh, B. Tokhmechi, A. Molaghab, A. Mohammadian, Drilling rate prediction from petrophysical logs and mud logging data using an optimized multilayer perceptron neural network, J. Geophys. Eng. 15 (2018) 1146-1159.

[26] M. Anemangely, A. Ramezanzadeh, M. Mohammadi Behboud, Geomechanical parameter estimation from mechanical specific energy using artificial intelligence, J. Petrol. Sci. Eng. 175 (2019), https://doi.org/10.1016/j.petrol.2018.12.054.

[27] S. Rashidi, M. Mehrad, H. Ghorbani, D.A. Wood, N. Mohamadian, J. Moghadasi, S. Davoodi, Determination of bubble point pressure & oil formation volume factor of crude oils applying multiple hidden layers extreme learning machine algorithms, J. Petrol. Sci. Eng. 202 (2021), 108425.

[28] S. Mardanirad, D.A. Wood, H. Zakeri, The application of deep learning algorithms to classify subsurface drilling lost circulation severity in large oil field datasets, SN Appl. Sci. 3 (2021) 1-22.

[29] D.A. Wood, S. Mardanirad, H. Zakeri, Effective prediction of lost circulation from multiple drilling variables: a class imbalance problem for machine and deep learning algorithms, J. Pet. Explor. Prod. Technol. 12 (2022) 83-98.

[30] A.K. Abbas, A.A. Bashikh, H. Abbas, H.Q. Mohammed, Intelligent decisions to stop or mitigate lost circulation based on machine learning, Energy 183 (2019) 1104-1113.

[31] P. Hosseini, Estimation of lost circulation amount occurs during under balanced drilling using drilling data and neural network, Egypt, J. Petrol. 26 (2017) 627-634.

[32] A.K. Manshad, H. Rostami, H. Niknafs, A.H. Mohammadi, Integrated lost circulation prediction in drilling operation, in: Heavy Oil Charact. Prod. Emerg. Technol., 2017, pp. 243-253.

[33] H. Toreifi, H. Rostami, New method for prediction and solving the problem of drilling fluid loss using modular neural network and particle swarm optimization algorithm, J. Pet. Explor. Prod. Technol. 4 (2014) 371-379.

[34] M. Alireza, N. Mohammad, A. Ahmad, Reducing consumed energy while drilling an oil well through a deep rig time analysis, Adv. Petrol. Explor. Dev. 1 (2011) 22-31.

[35] A.R. Moazzeni, M. Nabaei, S.G. Jegarluei, Prediction of lost circulation using virtual intelligence in one of Iranian oilfields, in: Niger. Annu. Int. Conf. Exhib., OnePetro, 2010.

[36] B. Alizadeh, A. Telmadarreie, S.R. Shadizadeh, F. Tezhe, Investigating geochemical characterization of Asmari and Bangestan reservoir oils and the source of H2S in the Marun oilfield, Petrol. Sci. Technol. 30 (2012) 967-975.

[37] E. Hosseini, J.N. Ghojogh, B. Habibnia, Characterization of fractures of Asmari Formation by using image logs, case study: Marun Oilfield, Am. J. Oil Chem. Technol. 3 (2015).

[38] H. Amiri Bakhtiar, A. Telmadarreie, M. Shayesteh, M.H. Heidari Fard, H. Talebi, Z. Shirband, Estimating total organic carbon content and source rock evaluation, applying DlogR and neural network methods: Ahwaz and Marun oilfields, SW of Iran, Petrol. Sci. Technol. 29 (2011) 1691-1704.

[39] A. Telmadarreie, S.R. Shadizadeh, B. Alizadeh, An investigation of hydrogen sulfide plume migration in the Asmari Reservoir of the Iranian Marun Oil Field: using repeat formation tests, Energy Sources, Part A Recover, Util. Environ. Eff. 35 (2013) 1991-2001.

[40] C. Nantasenamat, C. Isarankura-Na-Ayudhya, T. Naenna, V. Prachayasittikul, A Practical Overview of Quantitative Structure-Activity Relationship, 2009.

[41] J.I. Maletic, A. Marcus, Iq, in:Citeseer (Ed.), Data Cleansing: beyond Integrity Analysis, 2000, pp. 200-209.

[42] X. Wu, Knowledge Acquisition from Databases, Intellect books, 1995.

[43] L.P.F. Garćia, A.C. de Carvalho, A.C. Lorena, Noisy data set identification, in: Int Conf.Hybrid Artif. Intell. Syst., Springer, 2013, pp. 629-638.

[44] A.C. Lorena, A.C. de Carvalho, Evaluation of noise reduction techniques in the splice junction recognition problem, Genet. Mol. Biol. 27 (2004) 665-672.

[45] I. Guyon, S. Gunn, M. Nikravesh, L.A. Zadeh, Feature Extraction: Foundations and Applications, Springer, 2008.

[46] H. Osman, M. Ghafari, O. Nierstrasz, The Impact Of Feature Selection On Predicting The Number Of Bugs, ArXiv Prepr. ArXiv1807.04486, 2018.

[47] K. Deb, S. Agrawal, A. Pratap, T. Meyarivan, A fast elitist non-dominated sorting genetic algorithm for multi-objective optimization: NSGA-II,in:Int. Conf. Parallel Probl. Solving from Nat., Springer, 2000, pp. 849-858.

[48] A. Konak, D.W. Coit, A.E. Smith, Multi-objective optimization using genetic algorithms: a tutorial, Reliab. Eng. Syst. Saf. 91 (2006) 992-1007.

[49] M. Anemangely, A. Ramezanzadeh, B. Tokhmechi, Shear wave travel time estimation from petrophysical logs using ANFIS-PSO algorithm: a case study from Ab-Teymour Oilfield, J. Nat. Gas Sci. Eng. 38 (2017) 373-387.

[50] E.R. Davies, Computer Vision: Principles, Algorithms, Applications, Learning, Academic Press, 2017.

[51] S. Abirami, P. Chitra, Energy-efficient edge based real-time healthcare support system, in: Adv. Comput., Elsevier, 2020, pp. 339-368.

[52] G.-B. Huang, An insight into extreme learning machines: random neurons, random features and kernels, Cognit. Comput. 6 (2014) 376-390.

[53] G.-B. Huang, Q.-Y. Zhu, C.-K. Siew, Extreme learning machine: theory and applications, Neurocomputing 70 (2006) 489-501.

[54] S.-J. Wang, H.-L. Chen, W.-J. Yan, Y.-H. Chen, X. Fu, Face recognition and microexpression recognition based on discriminant tensor subspace analysis plus extreme learning machine, Neural Process. Lett. 39 (2014) 25-43.

[55] C.-U. Yeom, K.-C. Kwak, Short-term electricity-load forecasting using a TSKbased extreme learning machine with knowledge representation, Energies 10 (2017) 1613.

[56] S. Ding, X. Xu, R. Nie, Extreme learning machine and its applications, Neural Comput. Appl. 25 (2014) 549-556.

[57] I. Ebtehaj, H. Bonakdari, S. Shamshirband, Extreme learning machine assessment for estimating sediment transport in open channels, Eng. Comput. 32 (2016) 691-704.

[58] G.-B. Huang, H. Zhou, X. Ding, R. Zhang, Extreme learning machine for regression and multiclass classification, IEEE Trans. Syst. Man, Cybern. B. 42 (2011) 513-529.

[59] G.-B. Huang, Q.-Y. Zhu, C.-K. Siew, Extreme learning machine: a new learning scheme of feedforward neural networks, Ieee, 2004, in: IEEE Int. Jt. Conf. Neural Networks, IEEE Cat. No. 04CH37541), 2004, pp. 985-990.

[60] N.-Y. Liang, G.-B. Huang, P. Saratchandran, N. Sundararajan, A fast and accurate online sequential learning algorithm for feedforward networks, IEEE Trans. Neural Network. 17 (2006) 1411-1423.

[61] S. Lin, X. Liu, J. Fang, Z. Xu, Is extreme learning machine feasible? A theoretical assessment (Part II), IEEE Transact. Neural Networks Learn. Syst. 26 (2014) 21-34.

[62] X. Liu, L. Shaobo, F. Jian, X. Zongben, Is extreme learning machine feasible? A theoretical assessment (Part I), IEEE Transact. Neural Networks Learn. Syst. 26 (2014) 7-20.

[63] G.-B. Huang, What are extreme learning machines? Filling the gap between Frank Rosenblatt's dream and John von Neumann's puzzle, Cognit. Comput. 7 (2015) 263-278.

[64] L. Zhang, D. Zhang, F. Tian, SVM, ELM, 2015, in: E.L.M. Proc (Ed.), Who Wins? Object Recognition with Deep Convolutional Features from ImageNet, vol. 1, Springer, 2016, pp. 249-263.

[65] J. Cao, Z. Lin, G.-B. Huang, N. Liu, Voting based extreme learning machine, Inf. Sci. 185 (2012) 66-77.

[66] B.-Y. Qu, B.F. Lang, J.J. Liang, A.K. Qin, O.D. Crisalle, Two-hidden-layer extreme learning machine for regression and classification, Neurocomputing 175 (2016) 826-834.

[67] D. Xiao, B. Li, Y. Mao, A multiple hidden layers extreme learning machine method and its application, Math. Probl Eng. 2017 (2017).

[68] Y. Lv, F. Hong, T. Yang, F. Fang, J. Liu, A dynamic model for the bed temperature prediction of circulating fluidized bed boilers based on least squares support vector machine with real operational data, Energy 124 (2017) 284-294.

[69] T. Zhongda, Kernel principal component analysis-based least squares support vector machine optimized by improved grey wolf optimization algorithm and application in dynamic liquid level forecasting of beam pump, Trans. Inst. Meas. Control 42 (2020) 1135-1150.

[70] A. Barati-Harooni, A. Najafi-Marghmaleki, M. Arabloo, A.H. Mohammadi, An accurate CSA-LSSVM model for estimation of densities of ionic liquids, J. Mol. Liq. 224 (2016) 954-964.

[71] H. Wang, Y. Liang, W. Ding, D. Niu, S. Li, F. Wang, The improved least square support vector machine based on wolf pack algorithm and data inconsistency rate for cost prediction of substation projects, Math. Probl Eng. 2020 (2020).

[72] R. Rajabioun, Cuckoo optimization algorithm, Appl. Soft Comput. 11 (2011) 5508-5518.

[73] M. Anemangely, A. Ramezanzadeh, B. Tokhmechi, Determination of constant coefficients of Bourgoyne and Young drilling rate model using a novel evolutionary algorithm, J. Min. Environ. 8 (2017) 693-702.

[74] H. Lu, J. Chen, L. Guo, Energy Quality Management, 2018.

[75] M.E.H. Pedersen, A.J. Chipperfield, Simplifying particle swarm optimization, Appl. Soft Comput. 10 (2010) 618-628.

[76] C.M. Martinez, D. Cao, iHorizon-Enabled Energy Management for Electrified Vehicles, Butterworth-Heinemann, 2018.

[77] C.A.C. Coello, G.B. Lamont, D.A. Van Veldhuizen, Evolutionary Algorithms for Solving Multi-Objective Problems, Springer, 2007, https://doi.org/10.1007/978-0-387-36797-2.

[78] O. Özkaraca, A review on usage of optimization methods in geothermal power generation, Mugla J. Sci. Technol. 4 (2018) 130-136.

[79] Morteza Matinkia, Romina Hashami, Mohammad Mehrad, Mohammad Reza Hajsaeedi, Arian Velayati, Prediction of permeability from well logs using a new hybrid machine learning algorithm, Petroleum (2022), https://doi.org/10.1016/j.petlm.2022.03.003.

[80] Morteza Matinkia, Amirhossein Sheykhinasab, Soroush Shojaei, Ali Vojdani Tazeh Kand, Arad Elmi, Mahdi Bajolvand, Mohammad Mehrad, Developing a new model for drilling rate of penetration prediction using convolutional neural network, Arab. J. Sci. Eng. (2022), https://doi.org/10.1007/s13369-022-06765-x.

[81] Mohammad Mehrad, Ahmad Ramezanzadeh, Mahdi Bajolvand, Mohammad Reza Hajsaeedi, Estimating shear wave velocity in carbonate reservoirs from petrophysical logs using intelligent algorithms, J. Petrol. Sci. Eng. (2022), https://doi.org/10.1016/j.petrol.2022.110254.

[82] Morteza Matinkia, et al., A novel approach to pore pressure modeling based on conventional well logs using convolutional neural network, J. Petrol. Sci. Eng. (2022), https://doi.org/10.1016/j.petrol.2022.110156.