1887
  1. Home
  2. A-Z Publications
  3. Geophysical Prospecting
  4. Volume 72, Issue 1
  5. Article
Volume 72 Number 1
  • E-ISSN: 1365-2478

Abstract

Abstract

Multiphysics inversion exploits different types of geophysical data that often complement each other and aims to improve overall imaging resolution and reduce uncertainties in geophysical interpretation. Despite the advantages, traditional multiphysics inversion is challenging because it requires a large amount of computational time and intensive human interactions for preprocessing data and finding trade‐off parameters. These issues make it nearly impossible for traditional multiphysics inversion to be applied as a real‐time monitoring tool for geological carbon storage. In this paper, we present a deep learning (DL) multiphysics network for imaging CO saturation in real time. The multiphysics network consists of three encoders for analysing seismic, electromagnetic and gravity data and shares one decoder for combining imaging capabilities of the different geophysical data for better predicting CO saturation. The network is trained on pairs of CO label models and multiphysics data so that it can directly image CO saturation. We use the bootstrap aggregating method to enhance the imaging accuracy and estimate uncertainties associated with CO saturation images. Using realistic CO label models and multiphysics data derived from the Kimberlina CO storage model, we evaluate the performance of the deep learning multiphysics network and compare its imaging results to those from the deep learning single‐physics networks. Our modelling experiments show that the deep learning multiphysics network for seismic, electromagnetic, and gravity data not only improves the imaging accuracy but also reduces uncertainties associated with CO saturation images. Our results also suggest that the deep learning multiphysics network for the non‐seismic data (i.e., electromagnetic and gravity) can be used as an effective low‐cost monitoring tool in between regular seismic monitoring.

© 2024 European Association of Geoscientists & Engineers. Published 2022. This article is a U.S. Government work and is in the public domain in the USA.
Loading

Article metrics loading...

/content/journals/10.1111/1365-2478.13257
2023-12-18
2025-05-24

  • From This Site

    /content/journals/10.1111/1365-2478.13257
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C. et al. (2015) TensorFlow: large‐scale machine learning on heterogeneous systems.
  2. Ajo‐Franklin, J.B., Peterson, J., Doetsch, J. & Daley, T.M. (2013) High‐resolution characterization of a CO2 plume using crosswell seismic tomography: Cranfield, MS, USA. International Journal of Greenhouse Gas Control, 18, 497–509.
     [Google Scholar]
  3. Alford, R.M., Kelly, K.R. & Boore, D.M. (1974) Accuracy of finite‐difference modeling of the acoustic wave equation. Geophysics, 39(6), 834–842.
     [Google Scholar]
  4. Alnes, H., Eiken, O., Nooner, S., Sasagawa, G., Stenvold, T. & Zumberge, M. (2011) Results from Sleipner gravity monitoring: updated density and temperature distribution of the CO2 plume. Energy Procedia, 4, 5504–5511.
     [Google Scholar]
  5. Alumbaugh, D., Commer, M., Crandall, D., Gasperikova, E., Harbert, W., Li, Y. et al. (2021) Development of a Multi‐Scale Synthetic Data Set for the Testing of Subsurface CO2 Storage Monitoring Strategies. AGU Meeting.
  6. Araya‐Polo, M., Jennings, J., Adler, A. & Dahlke, T. (2018) Deep‐learning tomography. The Leading Edge, 37(1), 58–66.
     [Google Scholar]
  7. Arts, R., Eiken, O., Chadwick, A., Zweigel, P., Van der Meer, L. & Zinszner, B. (2003) Monitoring of CO2 injected at Sleipner using time lapse seismic data. In: Greenhouse Gas Control Technologies—6th International Conference, pp. 347–352. Pergamon.
  8. Benson, S.M. & Cole, D.R. (2008) CO2 sequestration in deep sedimentary formations. Elements, 4(5), 325–331.
     [Google Scholar]
  9. Chadwick, A., Williams, G., Delepine, N., Clochard, V., Labat, K., Sturton, S. et al. (2010) Quantitative analysis of time‐lapse seismic monitoring data at the Sleipner CO2 storage operation. The Leading Edge, 29(2), 170–177.
     [Google Scholar]
  10. Chollet, F. (2017) Deep learning with Python. New York: Simon and Schuster.
     [Google Scholar]
  11. Chollet, F. (2018) Keras: the python deep learning library. Astrophysics Source Code Library.
  12. 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]
  13. Commer, M. & Newman, G.A. (2008) New advances in three‐dimensional controlled‐source electromagnetic inversion. Geophysical Journal International, 172(2), 513–535.
     [Google Scholar]
  14. Davis, T.L., Landrø, M. & Wilson, M. (Eds.) (2019) Geophysics and geosequestration. Cambridge, UK: Cambridge University Press.
     [Google Scholar]
  15. Eiken, O., Stenvold, T., Zumberge, M., Alnes, H. & Sasagawa, G. (2008) Gravimetric monitoring of gas production from the Troll field. Geophysics, 73(6), WA149–WA154.
     [Google Scholar]
  16. Fichtner, A. (2010) Full seismic waveform modelling and inversion. Berlin: Springer Science & Business Media.
     [Google Scholar]
  17. Friedman, J., Hastie, T. & Tibshirani, R. (2006) The elements of statistical learning. Berlin: Springer.
     [Google Scholar]
  18. Gasperikova, E., Appriou, D., Bonneville, A., Feng, Z., Huang, L., Gao, K. et al. (2022) Sensitivity of geophysical techniques for monitoring secondary CO2 storage plumes. International Journal of Greenhouse Gas Control, 114, 103585.
     [Google Scholar]
  19. Gasperikova, E. & Hoversten, G.M. (2006) A feasibility study of nonseismic geophysical methods for monitoring geologic CO2 sequestration. The Leading Edge, 25(10), 1282–1288.
     [Google Scholar]
  20. Gasperikova, E. & Li, Y. (2021) Time‐lapse electromagnetic and gravity methods in carbon storage monitoring. The Leading Edge, 40(6), 442–446.
     [Google Scholar]
  21. Goodfellow, I., Bengio, Y. & Courville, A. (2016) Deep learning. Cambridge, MA: MIT Press.
     [Google Scholar]
  22. Guo, R., Yao, H.M., Li, M., Ng, M.K.P., Jiang, L. & Abubakar, A. (2020) Joint inversion of audio‐magnetotelluric and seismic travel time data with deep learning constraint. IEEE Transactions on Geoscience and Remote Sensing, 59(9), 7982–7995.
     [Google Scholar]
  23. Harbert, W., Daley, T.M., Bromhal, G., Sullivan, C. & Huang, L. (2016) Progress in monitoring strategies for risk reduction in geologic CO2 storage. International Journal of Greenhouse Gas Control, 51, 260–275.
     [Google Scholar]
  24. Hu, Y., Wei, X., Wu, X., Sun, J., Chen, J., Chen, J. & Huang, Y. (2021) Deep learning‐enhanced multiphysics joint inversion. In First International Meeting for Applied Geoscience & Energy. Houston, TX: Society of Exploration Geophysicists, pp. 1721–1725.
     [Google Scholar]
  25. James, G., Witten, D., Hastie, T. & Tibshirani, R. (2021) An introduction to statistical learning. Berlin: Springer.
     [Google Scholar]
  26. 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]
  27. Kaur, H., Zhong, Z., Sun, A. & Fomel, S. (2021) Time‐lapse seismic data inversion for estimating reservoir parameters using deep learning. Interpretation, 10(1), 1–91.
     [Google Scholar]
  28. Kim, J., Xue, Z. & Matsuoka, T. (2010) Experimental study on CO2 monitoring and saturation with combined P‐wave velocity and resistivity. SPE‐130284‐MS; In: International Oil and Gas Conference and Exhibition in China. OnePetro.
  29. Kingma, D.P. & Ba, J. (2015) Adam: A method for stochastic optimization. In: Third International Conference on Learning Representations. Conference Track Proceedings.
  30. Lazaratos, S.K. & Marion, B.P. (1997) Crosswell seismic imaging of reservoir changes caused by CO2 injection. The Leading Edge, 16(9), 1300–1308.
     [Google Scholar]
  31. Li, D., Peng, S., Huang, X., Guo, Y., Lu, Y. & Cui, X. (2021) Time‐lapse full waveform inversion based on curvelet transform: case study of CO2 storage monitoring. International Journal of Greenhouse Gas Control, 110, 103417.
     [Google Scholar]
  32. Li, Y. & Yang, D. (2021) Electrical imaging of hydraulic fracturing fluid using steel‐cased wells and a deep‐learning method. Geophysics, 86(4), E315–E332.
     [Google Scholar]
  33. Mansoor, K., BuscheckT., YangX., CarrollS. & ChenX. (2018), LLNL Kimberlina 1.2 NUFT Simulations. Available at: https://edx.netl.doe.gov/dataset/llnl‐kimberlina‐1‐2‐nuft‐simulations‐june‐2018. https://doi.org/10.18141/1603336 [Accessed 16 August 2022].
  34. Mavko, G., Mukerji, T. & Dvorkin, J. (2020) The rock physics handbook. Cambridge, UK: Cambridge University Press.
     [Google Scholar]
  35. Metz, B., Davidson, O., De Coninck, H.C., Loos, M. & Meyer, L. (2005) IPCC special report on carbon dioxide capture and storage. Cambridge, UK: Cambridge University Press.
     [Google Scholar]
  36. Moczo, P., RobertssonJ.O. & EisnerL. (2007) The finite‐difference time‐domain method for modeling of seismic wave propagation. Advances in Geophysics, 48, 421–516.
     [Google Scholar]
  37. Oh, S., Noh, K., Seol, S.J. & Byun, J. (2020) Cooperative deep learning inversion of controlled‐source electromagnetic data for salt delineation. Geophysics, 85(4), E121–E137.
     [Google Scholar]
  38. Pruess, K., Oldenburg, C.M. & Moridis, G.J. (1999) TOUGH2 user's guide version 2 (No. LBNL‐43134). Berkeley, CA: Lawrence Berkeley National Lab.
     [Google Scholar]
  39. Puzyrev, V. (2019) Deep learning electromagnetic inversion with convolutional neural networks. Geophysical Journal International, 218(2), 817–832.
     [Google Scholar]
  40. Queißer, M. & Singh, S.C. (2013) Full waveform inversion in the time lapse mode applied to CO2 storage at Sleipner. Geophysical Prospecting, 61(3), 537–555.
     [Google Scholar]
  41. Ribeiro, A.H. & Schön, T.B. (2021) How convolutional neural networks deal with aliasing. In: ICASSP 2021‐2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Piscataway, NJ: IEEE, pp. 2755–2759.
  42. Rim, H. & Li, Y. (2015) Advantages of borehole vector gravity in density imaging. Geophysics, 80(1), G1–G13.
     [Google Scholar]
  43. Ringrose, P. (2020) How to store CO2 underground: Insights from early‐mover CCS projects. Berlin: Springer.
     [Google Scholar]
  44. Ronneberger, O., Fischer, P. & Brox, T. (2015) U‐net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W., & Frangi, A. (Eds.) International Conference on Medical Image Computing and Computer‐Assisted Intervention. Lecture Notes in Computer Science, vol 9351. Cham: Springer, pp. 234–241.
     [Google Scholar]
  45. Rutqvist, J. (2012) The geomechanics of CO2 storage in deep sedimentary formations. Geotechnical and Geological Engineering, 30(3), 525–551.
     [Google Scholar]
  46. Shin, C. & Cha, Y.H. (2009) Waveform inversion in the Laplace—Fourier domain. Geophysical Journal International, 177(3), 1067–1079.
     [Google Scholar]
  47. Sun, Y., Denel, B., Daril, N., Evano, L., Williamson, P. & Araya‐Polo, M. (2020) Deep learning joint inversion of seismic and electromagnetic data for salt reconstruction. In SEG Technical Program Expanded Abstracts. Houston, TX: Society of Exploration Geophysicists, pp. 550–554.
     [Google Scholar]
  48. Um, E.S., Alumbaugh, D., Lin, Y. & Feng, S. (2022) Real time deep learning inversion of seismic full waveform data for CO2 saturation and uncertainty in geological carbon storage monitoring. Geophysical Prospecting, Advance online publication. https://doi.org/10.1111/1365‐2478.13197
     [Google Scholar]
  49. Um, E.S., Commer, M. & Newman, G.A. (2014) A strategy for coupled 3D imaging of large‐scale seismic and electromagnetic data sets: application to subsalt imaging. Geophysics, 79(3), ID1‐ID13.
     [Google Scholar]
  50. Um, E.S., Kim, J. & Wilt, M. (2020) 3D borehole‐to‐surface and surface electromagnetic modeling and inversion in the presence of steel infrastructure. Geophysics, 85(5), E139–E152.
     [Google Scholar]
  51. Vasco, D.W., Daley, T.M. & Bakulin, A. (2014) Utilizing the onset of time‐lapse changes: a robust basis for reservoir monitoring and characterization. Geophysical Journal International, 197(1), 542–556.
     [Google Scholar]
  52. Virieux, J. & Operto, S. (2009) An overview of full‐waveform inversion in exploration geophysics. Geophysics, 74(6), WCC1–WCC26.
     [Google Scholar]
  53. Wainwright, H.M., Finsterle, S., Zhou, Q. & Birkholzer, J.T. (2013) Modeling the performance of large‐scale CO2 storage systems: a comparison of different sensitivity analysis methods. International Journal of Greenhouse Gas Control, 17, 189–205.
     [Google Scholar]
  54. Wang, Z., Harbert, W.P., Dilmore, R.M. & Huang, L. (2018) Modeling of time‐lapse seismic monitoring using CO2 leakage simulations for a model CO2 storage site with realistic geology: application in assessment of early leak‐detection capabilities. International Journal of Greenhouse Gas Control, 76, 39–52.
     [Google Scholar]
  55. Wu, Y. & Lin, Y. (2019) InversionNet: an efficient and accurate data‐driven full waveform inversion. IEEE Transactions on Computational Imaging, 6, 419–433.
     [Google Scholar]
  56. Yang, F. & Ma, J. (2019) Deep‐learning inversion: a next‐generation seismic velocity model building method. Geophysics, 84(4), R583–R599.
     [Google Scholar]
  57. Yang, X., Buscheck, T.A., Mansoor, K., Wang, Z., Gao, K., Huang, L. et al. (2019) Assessment of geophysical monitoring methods for detection of brine and CO2 leakage in drinking water aquifers. International Journal of Greenhouse Gas Control, 90, 102803.
     [Google Scholar]
  58. 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]
  59. Zeng, Q., Feng, S., Wohlberg, B. & Lin, Y. (2021) InversionNet3D: efficient and scalable learning for 3D full waveform inversion. IEEE Transactions on Geoscience and Remote Sensing, 60, 4506816.
     [Google Scholar]
  60. Zhang, Z. & Lin, Y. (2020) Data‐driven seismic waveform inversion: a study on the robustness and generalization. IEEE Transactions on Geoscience and Remote Sensing, 58(10), 6900–6913.
     [Google Scholar]
  61. Zhang, Z.D. & Alkhalifah, T. (2019) Regularized elastic full‐waveform inversion using deep learning. Geophysics, 84(5), R741–R751.
     [Google Scholar]
  62. Zhou, Q. & Birkholzer, J.T. (2011) On scale and magnitude of pressure build‐up induced by large‐scale geologic storage of CO2. Greenhouse Gases: Science and Technology, 1(1), 11–20.
     [Google Scholar]
  63. Zoback, M.D. & Gorelick, S.M. (2012) Earthquake triggering and large‐scale geologic storage of carbon dioxide. Proceedings of the National Academy of Sciences, 109(26), 10164–10168.
     [Google Scholar]
/content/journals/10.1111/1365-2478.13257
Loading
Deep learning multiphysics network for imaging CO2 saturation and estimating uncertainty in geological carbon storage
Geophysical Prospecting 72, 183 (2023); https://doi.org/10.1111/1365-2478.13257
/content/journals/10.1111/1365-2478.13257
/content/journals/10.1111/1365-2478.13257
Loading

Data & Media loading...

  • Article Type: Research Article
Keyword(s): electromagnetics; full waveform; gravity; inversion and monitoring

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