1887
Volume 72, Issue 2
  • E-ISSN: 1365-2478

Abstract

Abstract

The field of geophysics faces the daunting task of monitoring complex reservoir dynamics and imaging carbon dioxide storage up to several decades into the future. This presents numerous challenges, including sensitivity to parameter changes, resolution of obtained results and the cost of long‐term deployment. To effectively store CO subsurface, it is necessary to monitor and account for the injected CO. The gravity method provides several advantages for CO monitoring, as changes in fluid saturation correspond directly and uniquely to observed density changes. Three‐axis borehole gravity has demonstrated significant promise as a next‐generation tool for reliably monitoring reservoir dynamics across a range of depths and sizes. However, the gravity inverse problem is highly ill‐posed, necessitating regularization that incorporates prior knowledge. To address this issue, we propose using a feed‐forward neural network, a machine learning method, to invert time‐lapse three‐axis borehole gravity data and monitor CO movement within a reservoir. By training the neural network on models that analyse changes in density and corresponding gravity responses resulting from perturbations made to the reservoir model, we can create scenarios that train the algorithm to identify unexpected CO migration in addition to the normal movement of CO. Our method is demonstrated using reservoir models for the Johansen formation in offshore Norway. We convert reservoir saturation models into density changes and generate their corresponding three‐axis gravity data in a set of boreholes. Our results show that the developed machine learning inversion algorithm has high reliability and resolution for imaging density change associated with CO plumes, as demonstrated in the Johansen reservoir models utilized by the simulator. We also investigate machine learning inversion using regularization parameters and show that it is robust, with a strong tolerance for higher levels of noise. Our study demonstrates that the developed machine learning algorithm is a powerful tool for inverting three‐axis borehole gravity data and monitoring the migration and long‐term storage of injected CO.

© 2024 European Association of Geoscientists & Engineers. © 2023 European Association of Geoscientists & Engineers.
Loading

Article metrics loading...

/content/journals/10.1111/1365-2478.13413
2024-01-30
2026-04-21

  • From This Site

    /content/journals/10.1111/1365-2478.13413
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Adler, J. & Öktem, O. (2017) Solving ill‐posed inverse problems using iterative deep neural networks. Inverse Problems, 33(12), 124007.
     [Google Scholar]
  2. Alyousuf, T., Li, Y. & Krahenbuhl, R. (2022) Machine learning inversion of time‐lapse three‐axis borehole gravity data for CO2 monitoring. Paper read at SEG/AAPG International Meeting for Applied Geoscience & Energy, 28 August–1 September 2022, Houston, Texas, USA. Houston, TX/Tulsa, OK, SEG/AAPG.
  3. Ayani, M., Grana, D. & Liu, M. (2020) Stochastic inversion method of time‐lapse controlled source electromagnetic data for CO2 plume monitoring. International Journal of Greenhouse Gas Control, 100, 103098.
     [Google Scholar]
  4. Bergmo, P.E.S., Grimstad, A.‐A. & Lindeberg, E. (2011) Simultaneous CO2 injection and water production to optimise aquifer storage capacity. International Journal of Greenhouse Gas Control, 5(3), 555–564.
     [Google Scholar]
  5. Bijani, R., Lelièvre, P.G., Ponte‐Neto, C.F. & Farquharson, C.G. (2017) Physical‐property‐, lithology‐and surface‐geometry‐based joint inversion using Pareto Multi‐Objective Global Optimization. Geophysical Journal International, 209(2), 730–748.
     [Google Scholar]
  6. Bishop, C.M. (1995) Training with noise is equivalent to Tikhonov regularization. Neural Computation, 7(1), 108–116.
     [Google Scholar]
  7. Bjorlykke, K. (2010) Petroleum geoscience: from sedimentary environments to rock physics. Berlin, Heidelberg: Springer Science & Business Media.
     [Google Scholar]
  8. Blackford, J., Bull, J.M., Cevatoglu, M., Connelly, D., Hauton, C., James, R.H., et al. (2015) Marine baseline and monitoring strategies for carbon dioxide capture and storage (CCS). International Journal of Greenhouse Gas Control, 38, 221–229.
     [Google Scholar]
  9. Caine, J.S., Evans, J.P. & Forster, C.B. (1996) Fault zone architecture and permeability structure. Geology, 24(11), 1025–1028.
     [Google Scholar]
  10. Calvert, R. (2005) Insights and methods for 4D reservoir monitoring and characterization. Houston, TX and Bunnik: Society of Exploration Geophysicists and the European Association of Geoscientists and Engineers.
     [Google Scholar]
  11. Chadwick, R., Arts, R. & Eiken, O. (2005) 4D seismic quantification of a growing CO2 plume at Sleipner, North Sea. London: Geological Society.
     [Google Scholar]
  12. Chadwick, R. & Noy, D. (2010) History‐matching flow simulations and time‐lapse seismic data from the Sleipner CO2 plume. London: Geological Society.
     [Google Scholar]
  13. Chadwick, R., Zweigel, P., Gregersen, U., Kirby, G., Holloway, S. & Johannessen, P. (2004) Geological reservoir characterization of a CO2 storage site: the Utsira Sand, Sleipner, northern North Sea. Energy, 29(9–10), 1371–1381.
     [Google Scholar]
  14. Chen, J., Schiek‐Stewart, C., Lu, L., Witte, S., Guardia, K.E, Menapace, F. et al. (2020) Machine learning method to determine salt structures from gravity data. Paper read at SPE Annual Technical Conference and Exhibition, Virtual, 26–29 October 2020.
  15. Chen, Z. (2000) Formulations and numerical methods of the black oil model in porous media. SIAM Journal on Numerical Analysis, 38(2), 489–514.
     [Google Scholar]
  16. Chen, Z., Huan, G. & Ma, Y. (2006) Computational methods for multiphase flows in porous media. Philadelphia, PA: SIAM.
     [Google Scholar]
  17. Christensen, J.M. & Olhoff, A. (2019) Emissions gap report 2019. United Nations Environment Programme.
  18. Colombo, D., Li, W., Sandoval‐Curiel, E. & McNeice, G.W. (2020) Deep‐learning electromagnetic monitoring coupled to fluid flow simulators. Geophysics, 85(4), WA1–WA12.
     [Google Scholar]
  19. Constable, S. (2010) Ten years of marine CSEM for hydrocarbon exploration. Geophysics, 75(5), 75A67–75A81.
     [Google Scholar]
  20. Crow, W., Carey, J.W., Gasda, S., Williams, D.B. & Celia, M. (2010) Wellbore integrity analysis of a natural CO2 producer. International Journal of Greenhouse Gas Control, 4(2), 186–197.
     [Google Scholar]
  21. Dadashpour, M., Landrø, M. & Kleppe, J. (2008) Nonlinear inversion for estimating reservoir parameters from time‐lapse seismic data. Journal of Geophysics and Engineering, 5(1), 54–66.
     [Google Scholar]
  22. Davis, K., Li, Y. & Batzle, M. (2008) Time‐lapse gravity monitoring: a systematic 4D approach with application to aquifer storage and recovery. Geophysics, 73(6), WA61–WA69.
     [Google Scholar]
  23. Davis, T.L., Landrø, M. & Wilson, M. (2019) Geophysics and geosequestration. Cambridge: Cambridge University Press.
     [Google Scholar]
  24. Deng, H., Bielicki, J.M., Oppenheimer, M., Fitts, J.P. & Peters, C.A. (2017) Leakage risks of geologic CO2 storage and the impacts on the global energy system and climate change mitigation. Climatic Change, 144(2), 151–163.
     [Google Scholar]
  25. Deng, H., Stauffer, P.H., Dai, Z., Jiao, Z. & Surdam, R.C. (2012) Simulation of industrial‐scale CO2 storage: multi‐scale heterogeneity and its impacts on storage capacity, injectivity and leakage. International Journal of Greenhouse Gas Control, 10, 397–418.
     [Google Scholar]
  26. Du, Z., Krahenbuhl, R., Topham, A., Lofts, J., Li, Y., Seshia, A. et al. (2021) Three‐axis borehole gravity feasibility method and its application to CO2 storage monitoring. Paper read at 82nd EAGE Annual Conference & Exhibition, October 2021. European Association of Geoscientists & Engineers, 2021(1), 1–5.
  27. Eigestad, G.T., Dahle, H.K., Hellevang, B., Riis, F., Johansen, W.T. & Øian, E. (2009) Geological modeling and simulation of CO2 injection in the Johansen formation. Computational Geosciences, 13(4), 435.
     [Google Scholar]
  28. Eslami, H., Esmaeili, A., Razaeian, M., Salari, M., Hosseini, A.N., Mobini, M. et al. (2022) Potentially toxic metal concentration, spatial distribution, and health risk assessment in drinking groundwater resources of southeast Iran. Geoscience Frontiers, 13(1), 101276.
     [Google Scholar]
  29. Furre, A.‐K., Meneguolo, R., Pinturier, L. & Bakke, K. (2020) Planning deep subsurface CO2 storage monitoring for the Norwegian full‐scale CCS project. First Break, 38(10), 55–60.
     [Google Scholar]
  30. Gasda, S.E., Nordbotten, J.M. & Celia, M.A. (2012) Application of simplified models to CO2 migration and immobilization in large‐scale geological systems. International Journal of Greenhouse Gas Control, 9, 72–84.
     [Google Scholar]
  31. Geiger, S., Matthäi, S., Niessner, J. & Helmig, R. (2009) Black‐oil simulations for three‐component, three‐phase flow in fractured porous media. SPE Journal, 14(02), 338–354.
     [Google Scholar]
  32. Gilmore, K.A., Sahu, C.K., Benham, G.P., Neufeld, J.A. & Bickle, M.J. (2022) Leakage dynamics of fault zones: experimental and analytical study with application to CO2 storage. Journal of Fluid Mechanics, 931, 31.
     [Google Scholar]
  33. Glubokovskikh, S., Pevzner, R., Gunning, J., Dance, T., Shulakova, V., Popik, D. et al. (2020) How well can time‐lapse seismic characterize a small CO2 leakage into a saline aquifer: CO2CRC Otway 2C experiment (Victoria, Australia). International Journal of Greenhouse Gas Control, 92, 102854.
     [Google Scholar]
  34. Goodfellow, I., Bengio, Y., Courville, A. & Bengio, Y. (2016) Deep learning, vol. 1. Cambridge: MIT Press.
     [Google Scholar]
  35. Goodman, A., Bromhal, G., Strazisar, B., Rodosta, T., Guthrie, W.F., Allen, D. et al. (2013) Comparison of methods for geologic storage of carbon dioxide in saline formations. International Journal of Greenhouse Gas Control, 18, 329–342.
     [Google Scholar]
  36. Guo, P. & Lyu, M.R. (2004) A pseudoinverse learning algorithm for feedforward neural networks with stacked generalization applications to software reliability growth data. Neurocomputing, 56, 101–121.
     [Google Scholar]
  37. Guo, R., Li, M., Yang, F., Xu, S., Fang, G. & Abubakar, A. (2018) Application of supervised descent method for transient EM data inversion. SEG Technical Program Expanded Abstracts 2018. Houston, TX, Society of Exploration Geophysicists. pp. 2126–2130.
  38. Hare, J.L., Ferguson, J.F., Aiken, C.L. & Brady, J.L. (1999) The 4‐D microgravity method for waterflood surveillance: a model study for the Prudhoe Bay reservoir, Alaska. Geophysics, 64(1), 78–87.
     [Google Scholar]
  39. Huang, X., Meister, L. & Workman, R. (1997) Reservoir characterization by integration of time‐lapse seismic and production data. Paper read at SPE Annual Technical Conference and Exhibition, 5–8 October 1997, San Antonio, Texas. Houston, TX, SPE.
  40. Mission Innovation . (2017) Accelerating breakthrough innovation in carbon capture, utilization, and storage. Paper read at Report of the Mission Innovation Carbon Capture, Utilization, and Storage Experts’ Workshop. Available at: https://www.energy.gov/fe/downloads/accelerating‐breakthrough‐innovationcarbon‐capture‐utilization‐and‐storage [Accessed 01 March 2019].
  41. Ivandic, M., Juhlin, C., Lueth, S., Bergmann, P., Kashubin, A., Sopher, D. et al. (2015) Geophysical monitoring at the Ketzin pilot site for CO2 storage: new insights into the plume evolution. International Journal of Greenhouse Gas Control, 32, 90–105.
     [Google Scholar]
  42. Jenkins, C., Chadwick, A. & Hovorka, S.D. (2015) The state of the art in monitoring and verification—ten years on. International Journal of Greenhouse Gas Control, 40, 312–349.
     [Google Scholar]
  43. Jeong, H., Srinivasan, S. & Bryant, S. (2013) Uncertainty quantification of CO2 plume migration using static connectivity of geologic features. Energy Procedia, 37(3), 771–779.
     [Google Scholar]
  44. Jervis, M., Bakulin, A. & Smith, R. (2018) Making time‐lapse seismic work in a complex desert environment for CO2 EOR monitoring—design and acquisition. The Leading Edge, 37(8), 598–606.
     [Google Scholar]
  45. Jessen, K., Kovscek, A.R. & Orr, F.M., Jr. (2005) Increasing CO2 storage in oil recovery. Energy Conversion and Management, 46(2), 293–311.
     [Google Scholar]
  46. Jia, B., Tsau, J.‐S. & Barati, R. (2019) A review of the current progress of CO2 injection EOR and carbon storage in shale oil reservoirs. Fuel, 236, 404–427.
     [Google Scholar]
  47. Karpatne, A., Atluri, G., Faghmous, J.H., Steinbach, M., Banerjee, A., Ganguly, A., et al. (2017) Theory‐guided data science: a new paradigm for scientific discovery from data. IEEE Transactions on Knowledge and Data Engineering, 29(10), 2318–2331.
     [Google Scholar]
  48. Krahenbuhl, R., Li, Y., Reitz, A., Wagner, S. & Konkler, J. (2016) Prudhoe Bay reservoir model: making the link between seismic and borehole data to gravity, electrical, and EM methods. SEG Technical Program Expanded Abstracts 2016. Houston, TX, Society of Exploration Geophysicists. pp. 5400–5404.
  49. Krahenbuhl, R.A. & Li, Y. (2006) Inversion of gravity data using a binary formulation. Geophysical Journal International, 167(2), 543–556.
     [Google Scholar]
  50. Krahenbuhl, R.A. & Li, Y. (2012) Time‐lapse gravity: a numerical demonstration using robust inversion and joint interpretation of 4D surface and borehole data. Geophysics, 77(2), G33–G43.
     [Google Scholar]
  51. Krahenbuhl, R.A., Martinez, C., Li, Y. & Flanagan, G. (2015) Time‐lapse monitoring of CO2 sequestration: a site investigation through integration of reservoir properties, seismic imaging, and borehole and surface gravity data. Geophysics, 80(2), WA15–WA24.
     [Google Scholar]
  52. Kuuskraa, V.A., Leewen, T.V. & Wallace, M. (2011) Improving domestic energy security and lowering CO2 emissions with 'next generation' CO2‐enhanced oil recovery (CO2‐EOR). Pittsburgh, PA, Morgantown, WV etc.: National Energy Technology Laboratory (NETL).
     [Google Scholar]
  53. LaFehr, T. (1983) Rock density from borehole gravity surveys. Geophysics, 48(3), 341–356.
     [Google Scholar]
  54. Landrø, M. (2001) Discrimination between pressure and fluid saturation changes from time‐lapse seismic data. Geophysics, 66(3), 836–844.
     [Google Scholar]
  55. Levine, J.S., Fukai, I., Soeder, D.J., Bromhal, G., Dilmore, R.M., Guthrie, G.D., et al. (2016) US DOE NETL methodology for estimating the prospective CO2 storage resource of shales at the national and regional scale. International Journal of Greenhouse Gas Control, 51, 81–94.
     [Google Scholar]
  56. Li, B. & Benson, S.M. (2015) Influence of small‐scale heterogeneity on upward CO2 plume migration in storage aquifers. Advances in Water Resources, 83, 389–404.
     [Google Scholar]
  57. Li, X. & Chouteau, M. (1998) Three‐dimensional gravity modeling in all space. Surveys in Geophysics, 19(4), 339–368.
     [Google Scholar]
  58. Li, Y. & Oldenburg, D.W. (1998) 3‐D inversion of gravity data. Geophysics, 63(1), 109–119.
     [Google Scholar]
  59. Lie, K.‐A. (2016) An introduction to reservoir simulation using MATLAB. User guide for the Matlab Reservoir Simulation Toolbox (MRST). Oslo, Norway: SINTEF ICT, Department of Applied Mathematics.
  60. Lie, K.‐A., Nilsen, H.M., Andersen, O. & Møyner, O. (2016) A simulation workflow for large‐scale CO2 storage in the Norwegian North Sea. Computational Geosciences, 20(3), 607–622.
     [Google Scholar]
  61. Little, M.G. & Jackson, R.B. (2010) Potential impacts of leakage from deep CO2 geosequestration on overlying freshwater aquifers. Environmental Science & Technology, 44(23), 9225–9232.
     [Google Scholar]
  62. Liu, M. & Grana, D. (2020) Time‐lapse seismic history matching with an iterative ensemble smoother and deep convolutional autoencoder. Geophysics, 85(1), M15–M31.
     [Google Scholar]
  63. Lofts, J., Zett, A., Clifford, P., Li, Y., Krahenbuhl, R. & Seshia, A. (2019) Three‐axis borehole gravity logging for reservoir surveillance. Paper read at SPE Middle East Oil and Gas Show and Conference, 18–21 March 2019, Manama, Bahrain. Houston, TX, SPE.
  64. Lumley, D.E. (2001) Time‐lapse seismic reservoir monitoring. Geophysics, 66(1), 50–53.
     [Google Scholar]
  65. Maag, E. & Li, Y. (2018) Discrete‐valued gravity inversion using the guided fuzzy c‐means clustering technique. Geophysics, 83(4), G59–G77.
     [Google Scholar]
  66. Mathias, S.A., Gluyas, J.G., de Miguel, G.J.G.M., Bryant, S.L. & Wilson, D. (2013) On relative permeability data uncertainty and CO2 injectivity estimation for brine aquifers. International Journal of Greenhouse Gas Control, 12, 200–212.
     [Google Scholar]
  67. Metz, B., Davidson, O. & De Coninck, H. (2005) Carbon dioxide capture and storage: special report of the intergovernmental panel on climate change. Cambridge: Cambridge University Press.
     [Google Scholar]
  68. Møller, M.F. (1993) A scaled conjugate gradient algorithm for fast supervised learning. Neural Networks, 6(4), 525–533.
     [Google Scholar]
  69. Mosher, C.R. & Farquharson, C.G. (2013) Minimum‐structure borehole gravity inversion for mineral exploration: a synthetic modeling study. Geophysics, 78(2), G25–G39.
     [Google Scholar]
  70. Mur, A., Barajas‐Olalde, C., Adams, D.C., Jin, L., He, J., Hamling, J.A. et al. (2020) Integrated simulation to seismic and seismic reservoir characterization in a CO2 EOR monitoring application. The Leading Edge, 39(9), 668–678.
     [Google Scholar]
  71. Myron, B., III, Behie, G.A. & Trangenstein, J.A. (2013) Multiphase flow in porous media: mechanics, mathematics, and numerics. vol. 34. New York, NY: Springer Science & Business Media.
     [Google Scholar]
  72. Nicol, A., Seebeck, H., Field, B., McNamara, D., Childs, C., Craig, J. & Rolland, A. (2017) Fault permeability and CO2 storage. Energy Procedia, 114, 3229–3236.
     [Google Scholar]
  73. Nind, C. & Foudilbey, N. (2022) Borehole gravity for CCS. Paper read at NSG2022 28th European Meeting of Environmental and Engineering Geophysics, September 2022. European Association of Geoscientists & Engineers.
  74. Orange, A., Key, K. & Constable, S. (2009) The feasibility of reservoir monitoring using time‐lapse marine CSEM. Geophysics, 74(2), F21–F29.
     [Google Scholar]
  75. Pandit, M., Mustafazade, A., Zhao, C., Sobreviela, G., Zou, X., Steinmann, P. et al. (2019) An ultra‐high resolution resonant MEMS accelerometer. Paper read at 2019 IEEE 32nd International Conference on Micro Electro Mechanical Systems (MEMS), 27–31 January 2019, Seoul, South Korea. IEEE.
  76. Peaceman, D.W. (2000) Fundamentals of numerical reservoir simulation. Amsterdam: Elsevier.
     [Google Scholar]
  77. Popta, J.V., Heywood, J., Adams, S. & Bostock, D. (1990) Use of borehole gravimetry for reservoir characterisation and fluid saturation monitoring. Paper read at European Petroleum Conference, 21–24 October 1990, The Hague, The Netherlands. Society of Petroleum Engineers (SPE).
  78. Price, A., Mikkelsen, G. & Hamilton, M. (2010) 3D CSEM over Frigg‐dealing with cultural noise. SEG Technical Program Expanded Abstracts 2010. Houston, TX, Society of Exploration Geophysicists. pp. 670–674.
  79. Rim, H. & Li, Y. (2015) Advantages of borehole vector gravity in density imaging. Geophysics, 80(1), G1–G13.
     [Google Scholar]
  80. Ringrose, P. (2020) How to store CO2 underground: insights from early‐mover CCS Projects. vol. 129. Cham: Springer.
     [Google Scholar]
  81. Shahin, A., Key, K., Stoffa, P. & Tatham, R. (2012) Petro‐electric modeling for CSEM reservoir characterization and monitoring. Geophysics, 77(1), E9–E20.
     [Google Scholar]
  82. Sietsma, J. & Dow, R.J. (1991) Creating artificial neural networks that generalize. Neural Networks, 4(1), 67–79.
     [Google Scholar]
  83. Sundal, A. & Hellevang, H. (2019) Using reservoir geology and petrographic observations to improve CO2 mineralization estimates: examples from the Johansen formation, North Sea, Norway. Minerals, 9(11), 671.
     [Google Scholar]
  84. Szulczewski, M.L., MacMinn, C.W., Herzog, H.J. & Juanes, R. (2012) Lifetime of carbon capture and storage as a climate‐change mitigation technology. Proceedings of the National Academy of Sciences of the United States of America, 109(14), 5185–5189.
     [Google Scholar]
  85. Thore, P. & Hubans, C. (2012) 4D seismic‐to‐well tying, a key step towards 4D inversion4D seismic‐to‐well tying. Geophysics, 77(6), R227–R238.
     [Google Scholar]
  86. van der Zwaan, B. & Smekens, K. (2009) CO2 capture and storage with leakage in an energy‐climate model. Environmental Modeling & Assessment, 14(2), 135–148.
     [Google Scholar]
  87. Wei, L. & Saaf, F. (2009) Estimate CO2 storage capacity of the Johansen formation: numerical investigations beyond the benchmarking exercise. Computational Geosciences, 13(4), 451.
     [Google Scholar]
  88. Wilkinson, M., Mouli‐Castillo, J., Morgan, P. & Eid, R. (2017) Time‐lapse gravity surveying as a monitoring tool for CO2 storage. International Journal of Greenhouse Gas Control, 60, 93–99.
     [Google Scholar]
  89. Yang, X., Chen, X. & Smith, M.M. (2022) Deep learning inversion of gravity data for detection of CO2 plumes in overlying aquifers. Journal of Applied Geophysics, 196, 104507.
     [Google Scholar]
  90. Zou, X., Thiruvenkatanathan, P. & Seshia, A.A. (2014) A seismic‐grade resonant MEMS accelerometer. Journal of Microelectromechanical Systems, 23(4), 768–770.
     [Google Scholar]
  91. Zunino, A., Ghirotto, A., Armadillo, E. & Fichtner, A. (2022) Hamiltonian Monte Carlo probabilistic joint inversion of 2D (2.75 D) gravity and magnetic data. Geophysical Research Letters, 49(20), e2022GL099789.
     [Google Scholar]
/content/journals/10.1111/1365-2478.13413
Loading
Three‐axis borehole gravity monitoring for CO2 storage using machine learning coupled to fluid flow simulator
Geophysical Prospecting 72, 767 (2024); https://doi.org/10.1111/1365-2478.13413
/content/journals/10.1111/1365-2478.13413
/content/journals/10.1111/1365-2478.13413
Loading

Data & Media loading...

  • Article Type: Research Article
Keyword(s): geophysical reservior; gravity; inversion; monitoring; time lapse

Most Cited This Month Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error