Gas leakage recognition for CO2 geological sequestration based on the time series neural network

doi:10.1016/j.cjche.2020.06.014

Chinese Journal of Chemical Engineering ›› 2020, Vol. 28 ›› Issue (9): 2343-2357.DOI: 10.1016/j.cjche.2020.06.014

• Process Systems Engineering and Process Safety • Previous Articles Next Articles

Gas leakage recognition for CO₂ geological sequestration based on the time series neural network

Denglong Ma¹, Jianmin Gao¹, Zhiyong Gao¹, Hongquan Jiang¹, Zaoxiao Zhang², Juntai Xie¹

1 School of Mechanical Engineering, Xi'an Jiaotong University, Xi'an 710049, China;
2 School of Chemical Engineering and Technology, Xi'an Jiaotong University, Xi'an 710049, China

Received:2020-01-16 Revised:2020-05-06 Online:2020-10-21 Published:2020-09-28
Contact: Denglong Ma
Supported by:
Financial support was provided by the National Natural Science Foundation of China (21808181), China Postdoctoral Science Foundation (2019M653651), Shaanxi Provincial Science and Technology Department (2017ZDXM-GY-115), Basic Research Project of Natural Science in Shaanxi Province (2020JM-021).

Gas leakage recognition for CO₂ geological sequestration based on the time series neural network

Denglong Ma¹, Jianmin Gao¹, Zhiyong Gao¹, Hongquan Jiang¹, Zaoxiao Zhang², Juntai Xie¹

1 School of Mechanical Engineering, Xi'an Jiaotong University, Xi'an 710049, China;
2 School of Chemical Engineering and Technology, Xi'an Jiaotong University, Xi'an 710049, China

通讯作者: Denglong Ma
基金资助:
Financial support was provided by the National Natural Science Foundation of China (21808181), China Postdoctoral Science Foundation (2019M653651), Shaanxi Provincial Science and Technology Department (2017ZDXM-GY-115), Basic Research Project of Natural Science in Shaanxi Province (2020JM-021).

Abstract

Abstract: The leakage of stored and transported CO₂ is a risk for geological sequestration technology. One of the most challenging problems is to recognize and determine CO₂ leakage signal in the complex atmosphere background. In this work, a time series model was proposed to forecast the atmospheric CO₂ variation and the approximation error of the model was utilized to recognize the leakage. First, the fitting neural network trained with recently past CO₂ data was applied to predict the daily atmospheric CO₂. Further, the recurrent nonlinear autoregressive with exogenous input (NARX) model was adopted to get more accurate prediction. Compared with fitting neural network, the approximation errors of NARX have a clearer baseline, and the abnormal leakage signal can be seized more easily even in small release cases. Hence, the fitting approximation of time series prediction model is a potential excellent method to capture atmospheric abnormal signal for CO₂ storage and transportation technologies.

Key words: Leakage identification, Process safety, Gas leakage, Monitoring carbon sequestration, CO₂ storage

摘要： The leakage of stored and transported CO₂ is a risk for geological sequestration technology. One of the most challenging problems is to recognize and determine CO₂ leakage signal in the complex atmosphere background. In this work, a time series model was proposed to forecast the atmospheric CO₂ variation and the approximation error of the model was utilized to recognize the leakage. First, the fitting neural network trained with recently past CO₂ data was applied to predict the daily atmospheric CO₂. Further, the recurrent nonlinear autoregressive with exogenous input (NARX) model was adopted to get more accurate prediction. Compared with fitting neural network, the approximation errors of NARX have a clearer baseline, and the abnormal leakage signal can be seized more easily even in small release cases. Hence, the fitting approximation of time series prediction model is a potential excellent method to capture atmospheric abnormal signal for CO₂ storage and transportation technologies.

关键词: Leakage identification, Process safety, Gas leakage, Monitoring carbon sequestration, CO₂ storage

Denglong Ma, Jianmin Gao, Zhiyong Gao, Hongquan Jiang, Zaoxiao Zhang, Juntai Xie. Gas leakage recognition for CO₂ geological sequestration based on the time series neural network[J]. Chinese Journal of Chemical Engineering, 2020, 28(9): 2343-2357.

References

[1] IEA, World Energy Outlook 2017, Paris, IEA Publications, France, 2017.
[2] IPCC, IPCC Special Report:Carbon Capture and Storage, Cambridge University Press, Cambridge, 2005.
[3] M. Shakiba, M. Riazi, S. Ayatollahi, M. Takband, The impact of connate water saturation and salinity on oil recovery and CO₂ storage capacity during carbonated water injection in carbonate rock, Chin. J. Chem. Eng. 27(7) (2019) 1699-1707.
[4] Z.H. Yang, M. Jin, M.Y. LI, Z.X. Dong, P. Yan, Implication of geochemical simulation for CO₂ storage using data of York reservoir, Chin. J. Chem. Eng. 19(6) (2011) 1052-1059.
[5] 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. Energ. 225(2018) 332-345.
[6] P. Joshi, B. Prem, Q. Wang, Consequence analysis of accidental release of supercritical carbon dioxide from high pressure pipelines, Int. J. Greenh. Gas Con. 55(2016) 166-176.
[7] D.L. Ma, W. Tan, Q.S. Wang, Z.X. Zhang, J.M. Gao, X.Q. Wang, F.S. Xia, Location of contaminant emission source in atmosphere based on optimal correlated matching of concentration distribution, Process Saf. Environ. 117(2018) 498-510.
[8] R. Arts, O. Eiken, A. Chadwick, P. Zweigel, L. van der Meer, B. Zinszner, Monitoring of CO₂ injected at Sleipner using time-lapse seismic data, Energ. 29(2004) 1383-1392.
[9] J.B. Riding, C.A. Rochelle, The IEA Weyburn CO₂ Monitoring and Storage Project:Final Report of the European Research Team, British Geological Survey 2005.
[10] C.R. Jenkins, P.J. Cook, J. Ennis-King, et al., Safe storage and effective monitoring of CO₂ in depleted gas fields, Proc. Natl. Acad. Sci. 109(2) (2012) 35-41.
[11] U. Sauer, N. Watanabe, A. Singh, P. Dietrich, O. Kolditz, C. Schütze, Joint interpretation of geoelectrical and soil-gas measurements for monitoring CO₂ releases at a natural analogue, Near Surf. Geophys. 12(1) (2014) 165-187.
[12] K.K. Lee, S.H. Lee, S.H. Yun, S.W. Jeen, Shallow groundwater system monitoring on controlled CO₂ release sites:A review on field experimental methods and efforts for CO₂ leakage detection, Geosci. J. 20(4) (2016) 569-583.
[13] D. Kiessling, C. Schmidt-Hattenbergera, H. Schuett, et al., Geoelectrical methods for monitoring geological CO₂ storage:First results from cross-hole and surface-downhole measurements from the CO₂SINK test site at Ketzin (Germany), Int. J. Greenh. Gas Con. 4(2010) 816-826.
[14] NETL 2014 Carbon storage technology program plan, Available at http://www.netl.doe.gov/research/coal/carbon-storage.
[15] D. Atamanchuk, A. Tengberg, D. Aleynik, P. Fietzek, K. Shitashima, A. Lichtschlag, P.O. J. Hall, H. Stahl, Detection of CO₂ leakage from a simulated sub-seabed storage site using three different types of pCO₂ sensors, Int. J. Greenh. Gas Con. 38(2015) 121-134.
[16] J.L. Lewicki, G.E. Hilley, Eddy covariance network design for mapping and quantification of surface CO₂ leakage fluxes, Int. J. Greenh. Gas Con. 7(2012) 137-144.
[17] D.G. Jones, A.K.A.P. Barkwith, S. Hannis, T.R. Lister, F. Gal, S. Graziani, S.E. Beaubien, D. Widory, Monitoring of near surface gas seepage from a shallow injection experiment at the CO₂ Field Lab, Norway, Int. J. Greenh. Gas Con. 28(2014) 300-317.
[18] M.D. Escarra, L.T. Le, N.M. Urban, M. Oppenheimer, C.F. Gmachl, Quantum cascade laser-based sensing for carbon sequestration leakage monitoring, IEEE Sensors J. 13(6) (2013) 2348-2356.
[19] C.V. Leeuwen, H.A.J. Meijer, Detection of CO₂ leaks from carbon capture and storage sites with combined atmospheric CO₂ and O₂ measurements, Int. J. Greenh. Gas Con. 41(3) (2015) 194-209.
[20] D.L. Ma, J.Q. Deng, Z.X. Zhang, Correlation analysis for online CO₂ leakage monitoring in geological sequestration, Energy Proced. 37(2013) 4374-4382.
[21] D.L. Ma, J.Q. Deng, Z.X. Zhang, CO₂ leakage identification in geosequestration based on real time correlation analysis between atmospheric O₂ and CO₂, Chin. J. Chem. Eng. 22(6) (2014) 634-642.
[22] D.L. Ma, W. Tan, Z.X. Zhang, X.Q. Wang, J. Hu, Recognition of leak CO₂ with wavelet analysis based on correlation monitoring between CO₂ and O₂ in atmosphere, Process Saf. Environ. 114(2018) 64-78.
[23] N.M. Pak, O. Rempillo, A.L. Norman, D.B. Layzell, Early atmospheric detection of carbon dioxide from carbon capture and storage sites, J. Air Waste Manage. Assoc. 66(8) (2016) 739-747.
[24] H. Li, D. Yan, Z. Zhang, E. Lichtfouse, Prediction of CO₂ absorption by physical solvents using a chemoinformatics-based machine learning model, Environ. Chem. Lett. 17(2019) 1397-1404.
[25] J.A. Watheq, Polynomial and nonparametric regressions for efficient predictive proxy meta modeling:Application through the CO₂-EOR in shale oil reservoirs, J. Nat.Gas Sci.Eng. 2(2019) 103038.
[26] P.J. Brockwel, R.A. Davis, Introduction to Time Series and Forecasting, 3rd edition Springer, Cham, 2016.
[27] A. Grigorievskiy, J. Karhunen, Gaussian Process Kernels for Popular State-Space Time Series Models, International Joint Conference on Neural Networks, Vancouver, Canada, 2016.
[28] W. Waheeb, R. Ghazali, H. Shah, Nonlinear Autoregressive Moving-Average (NARMA) Time Series Forecasting Using Neural Networks, 2019 International Conference on Computer and Information Sciences (ICCIS), Sakaka, Saudi Arabia, 2019.
[29] S.A. Billings, Nonlinear System Identification:NARMAX Methods in the Time, Frequency, and Spatio-Temporal Domains, John Wiley &Sons, U.K., 2013
[30] J.T. Connor, Recurrent neural networks and robust time series prediction, IEEE T. Neural Networks 5(2) (1994) 240-254.
[31] M. José, A.B. Guilherme, Long-term time series prediction with the NARX network:An empirical evaluation, Neurocomputing 71(16-18) (2008) 3335-3343.
[32] S. Ines, M.B. Najiba, Solar Radiation Prediction Using NARX Model, Advanced Applications for Artificial Neural Networks, IntechOpen, Adel El-Shahat, 2018.
[33] D.L. Ma, J.M. Gao, Z.X. Zhang, H. Zhao, Q.S. Wang, Locating the gas leakage source in the atmosphere using the dispersion wave method, J. Loss Prevent. Proc. 63(2020) 104031.

Gas leakage recognition for CO₂ geological sequestration based on the time series neural network

Gas leakage recognition for CO₂ geological sequestration based on the time series neural network

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 6

Recommended Articles

Metrics

Comments

[1]	Jikai Dong, Bing Wang, Xinjie Wang, Chenxi Cao, Shikuan Chen, Wenli Du. Optimization of sensor deployment sequences for hazardous gas leakage monitoring and source term estimation [J]. Chinese Journal of Chemical Engineering, 2023, 56(4): 169-179.
[2]	Haoyu Zhai, Shaomeng Wang, Diankun Chen, Xuanying Cheng, Chuanxin Xie. Research on thermal risk and decomposition behavior of methyl nitrite [J]. Chinese Journal of Chemical Engineering, 2020, 28(8): 2131-2136.
[3]	Mahmood Shakiba, Masoud Riazi, Shahab Ayatollahi, Mostafa Takband. The impact of connate water saturation and salinity on oil recovery and CO₂ storage capacity during carbonated water injection in carbonate rock [J]. Chinese Journal of Chemical Engineering, 2019, 27(7): 1699-1707.
[4]	Junjie Feng, Bin Zhang, Wei Xu, Bing Sun, Fan Zhang, Jie Jiang. Development of index system for inherently safer process design using an integrated approach [J]. Chinese Journal of Chemical Engineering, 2019, 27(11): 2725-2733.
[5]	MA Denglong, DENG Jianqiang, ZHANG Zaoxiao . CO₂ Leakage Identification in Geosequestration Based on Real Time Correlation Analysis Between Atmospheric O₂ and CO₂ [J]. Chin.J.Chem.Eng., 2014, 22(6): 634-642.
[6]	YANG Zihao, JIN Min, LI Mingyuan, DONG Zhaoxia, YAN Peng. Implication of Geochemical Simulation for CO₂ Storage Using Data of York Reservoir [J]. , 2011, 19(6): 1052-1059.