DOI: https://doi.org/10.26089/NumMet.v26r431

Acceleration of numerical simulation of seismic data for monitoring the burial of CO₂ using a neural network

Authors

  • Elena A. Gondyul
  • Vadim V. Lisitsa
  • Dmitry M. Vishnevsky

Keywords:

seismic monitoring
greenhouse gases
filtration of two-phase flow
neural network

Abstract

Seismic monitoring of greenhouse gases accumulations and injection in reservoir is critical for evaluating the safety and efficiency of injection and preventing leakage. Small changes in reservoir properties caused by fluid displacement lead to changes in seismic attributes. At the same time, modelling of seismic wavefield propagation is resource-consuming due to the need to solve the problem for a series of seismogeological models of the medium corresponding to different stages of fluid injection. The paper presents an algorithm for seismic modelling using a finite-difference method and a neural network to suppress numerical errors in seismograms when applied to the problem of seismic monitoring of greenhouse gas disposal. The algorithm speeds up calculations up to 4 times due to the application of the neural network to rapidly calculated seismograms using a coarse computational grid.


Downloads

Published

2025-11-17

Issue

Vol. 26 (2025): Issue 4.

Section

Methods and algorithms of computational mathematics and their applications

Authors

Elena A. Gondyul

Sobolev Institute of Mathematics of SB RAS

• Junior Researcher

Vadim V. Lisitsa

Sobolev Institute of Mathematics of SB RAS

• Head of Laboratory

Dmitry M. Vishnevsky

Sobolev Institute of Mathematics of SB RAS

• Senior Researcher

References

  1. J. Paffenholz, “Introduction to this special section: The role of advanced modeling in enhanced carbon storage, “ The Leading Edge. 40 (6). 408-412 (2021).
    doi 10.1190/tle40060408.1
  2. R. Pevzner, M. Urosevic, E. Caspari, R. J. Galvin, M. Madadi, T. Dance, V. Shulakova, B. Gurevich, V. Tcheverda., Y. Cinar, “Feasibility of time-lapse seismic methodology for monitoring the injection of small quantities of co2 into a saline formation, co2crc otway project, “ Energy Procedia. 37, 4336-4343 (2023).
    doi 10.1016/j.egypro.2013.06.336
  3. Z. Wang, W. P. Harbert, R. M. Dilmore, L. Huang, “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 capa- bilities, “ International Journal of Greenhouse Gas Control. 76, 39-52 (2018).
    doi 10.1016/j.ijggc.2018.06.011
  4. M. Ivandic, P. Bergmann, J. Kummerow, F. Huang, C. Juhlin, S. Lueth, “Monitoring CO2 saturation using time‐lapse amplitude versus offset analysis of 3D seismic data from the Ketzin CO2 storage pilot site, Germany, “ Geophysical Prospecting. 66 (8). 1568-1585 (2018).
    doi 10.1111/1365-2478.12666
  5. J. Virieux, “P-sv wave propagation in heterogeneous media: Velocity-stress finite-difference method, “ Geophysics. 51 (4). 889-901 (1986).
    doi 10.1190/1.1442147
  6. A. R Levander, “Fourth-order finite-difference p-sv seismograms, “ Geophysics. 53 (11).1425-1436 (1988).
    doi 10.1190/1.1442422
  7. E. H. Saenger, N. Gold, S. A. Shapiro, “Modeling the propagation of the elastic waves using a modified finite-difference grid, “ Wave Motion. 31. 77-92 (2000).
    doi 10.1016/S0165-2125(99)00023-2
  8. V. Lisitsa and D. Vishnevskiy, “Lebedev scheme for the numerical simulation of wave propagation in 3d anisotropic elasticity, “ Geophysical Prospecting. 58 (4). 619-635 (2010).
    doi 10.1111/j.1365-2478.2009.00862.x
  9. V. Lisitsa, V. Tcheverda, D. Vishnevsky, “Numerical simulation of seismic waves in models with anisotropic formations: coupling virieux and lebedev finite-difference schemes, “ Computational Geosciences. 16 (4). 1135-1152 (2012).
    doi 10.1007/s10596-012-9308-0
  10. A. Idesman and D. Pham, “Finite element modeling of linear elastodynamics problems with explicit time-integration methods and linear elements with the reduced dispersion error, “ Computer Methods in Applied Mechanics and Engineering. 271. 86-108 (2014).
    doi 10.1016/j.cma.2013.12.002
  11. M. Dumbser and M. Kaser, “An arbitrary high-order discontinuous galerkin method for elastic waves on unstructured meshes - ii. the three-dimensional isotropic case, “ Geophysical Journal International. 167 (1), 319-336 (2006).
    doi 10.1111/j.1365-246X.2006.03120.x
  12. V. Lisitsa, V. Tcheverda, C. Botter, “Combination of the discontinuous galerkin method with finite differences for simulation of seismic wave propagation, “ Journal of Computational Physics. 311. 142-157 (2016).
    doi 10.1016/j.jcp.2016.02.005
  13. D. Komatitsch and J. P. Vilotte, “The spectral element method; an efficient tool to simulate the seismic response of 2d and 3d geological structures, “ Bulletin of the Seismological Society of America. 88 (2). 368-392 (1988).
    doi 10.1785/BSSA0880020368
  14. J. Tromp, D. Komatitsch, Q. Liu, “Spectral-element and adjoint methods in seismology, “ Commun. Comput. Phys. 3 (1). 1-32 (2008).
    https://www.geophysik.uni-muenchen.de/ igel/EGU2007/Material/Tromp/CiCP-06-077.pdf . Cited October 23, 2025.
  15. S. Anyosa, S. Bunting, J. Eidsvik, A. Romdhane, P. Bergmo, “Assessing the value of seismic monitoring of CO2 storage using simulations and statistical analysis, “ International Journal of Greenhouse Gas Control. 105. 103219 (2021).
    doi 10.1016/j.ijggc.2020.103219
  16. G. Wen, Z. Li, K. Azizzadenesheli, A. Anandkumar, S. M. Benson, “U-FNO—an enhanced fourier neural operator-based deep-learning model for multiphase flow, “ Advances in Water Resources. 163, 104180 (2022).
    doi 10.1016/j.advwatres.2022.104180
  17. Z. Yin, A. Siahkoohi, M. Louboutin, F. J. Herrmann, “Learned coupled inversion for carbon sequestration monitoring and forecasting with fourier neural operators, “ in Second International Meeting for Applied Geoscience & Energy, Houston, Texas, August 28, 2022 (Society of Exploration Geophysicists, 2022), pp. 467-472.
    doi 10.1190/image2022-3722848.1
  18. L. Bei, E. L. Yunyue, “Neural Network-Based CO2 Interpretation From 4D Sleipner Seismic Images, “ Journal of Geophysical Research: Solid Earth. 126 (12). e2021JB022524 (2021).
    doi 10.1029/2021JB022524
  19. H. Sheng, X. Wu, X. Sun, L. Wu, “Deep learning for characterizing co2 migration in time-lapse seismic images, “ Fuel. 336, 126806 (2023).
    doi 10.1016/j.fuel.2022.126806
  20. P. Shokouhi, V. Kumar, S. Prathipati, S. A. Hosseini, C. L. Giles, D. Kifer, “Physics-informed deep learning for prediction of CO2 storage site response, “ Journal of Contaminant Hydrology. 241. 103835 (2021).
    doi 10.1016/j.jconhyd.2021.103835
  21. G. Wen, C. Hay, S. M. Benson, “CCSNet: A deep learning modeling suite for CO2 storage, “ Advances in Water Resources. 155. 104009 (2021).
    doi 10.1016/j.advwatres.2021.104009
  22. K. Gadylshin, V. Lisitsa, K. Gadylshina, D. Vishnevsky, “Frequency domain numerical dispersion mitigation network, “ in Computational Science and Its Applications (ICCSA 2023), Athens, Greece, July 3-6, 2023 (Lecture Notes in Computer Science, 2023), pp. 31-41.
    doi 10.1007/978-3-031-37111-0_3
  23. E. Gondyul, V. Lisitsa, K. Gadylshin, D. Vishnevsky, “Numerical dispersion mitigation neural network with the model-based training dataset optimization, “ in Computational Science and Its Applications (ICCSA 2023), Athens, Greece, July 3-6, 2023 (Lecture Notes in Computer Science, 2023), pp. 19-30.
    doi 10.1007/978-3-031-37111-0_2
  24. P. Isola, J. Zhu, T. Zhou, A. A. Efros, “Image-to-image translation with conditional adversarial networks, “ in IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017), Honolulu, USA July 21-26, 2017 (IEEE, 2017), pp. 5967-5976.
    doi 10.1109/CVPR.2017.632
  25. J. W. Sheldon, B. Zondek, W. T. Cardwell, “One-dimensional, incompressible, non-capillary, two-phase fluid flow in a porous medium, “ Trans. SPE AIME. 216. 290-296 (1959).
    doi 10.2118/978-G
  26. Jr. J. Douglas, D. W. Peaceman, Jr. H. H. Rachford, “A method for calculating multi-dimensional immiscible displacement, “ Trans. SPE AIME. 216. 297-306 (1959).
    doi 10.2118/1327-G
  27. R. C. MacDonald, “Methods for Numerical Simulation of Water and Gas Coning, “ Society of Petroleum Engineers Journal. 10 (4), 425-436 (1970).
    doi 10.2118/2796-PA
  28. G. W. Thomas and D. H. Thurnau, “Reservoir Simulation Using an Adaptive Implicit Method, “ Society of Petroleum Engineers Journal. 23 (24). 759-768 (1983).
    doi 10.2118/10120-PA
  29. W. F. Murphy, L. M. Schwartz, B. Hornby, “Interpretation physics of VP and VS in sedimentary rocks, “ in Trans. SPWLA 32nd Ann. Logging Symp, Midland, Texas, June 16-–19, 1991 ,
    https://onepetro.org/SPWLAALS/proceedings-abstract/SPWLA-1991/SPWLA-1991/SPWLA-1991-FF/18997 . Cited October 23, 2025.
  30. Z. Chen, G. Huan, Y. Ma, Computational Methods for Multiphase Flows in Porous Media , (Society for Industrial and Applied Mathematics, 2006).
    doi 10.1137/1.9780898718942
  31. Yu. M. Laevsky, P. E. Popov, A. A. Kalinkin, “ Modeling of Two-Phase Fluid Filtration by a Mixed Method of Finite Elements, “ Mat. Model. 3. 74-90 (2010).
    https://www.mathnet.ru/links/d005d54746cd4b0d4878f90d6c121b63/mm_2950_refs_eng.pdf . Cited October 23, 2025.
  32. J. Virieux and R. Madariaga, “Dynamic faulting studied by a finite difference method, “ Bulletin of the Seismological Society of America. 72 (2). 345-369 (1982).
    doi 10.1785/BSSA0720020345
  33. K. Gadylshin, D. Vishnevsky, K. Gadylshina, V. Lisitsa, “Numerical dispersion mitigation neural network for seismic modeling, “ Geophysics. 87 (32). T237-T249 (2022).
    doi 10.1190/geo2021-0242.1
  34. E. Gondyul, V. Lisitsa, K. Gadylshin, D. Vishnevsky, “Numerical dispersion mitigation neural network with velocity model correction, “ Computers & Geosciences. 196. 105806 (2025).
    doi 10.1016/j.cageo.2024.105806

License

Copyright (c) 2025 Е. А. Гондюл, В. В. Лисица, Д. М. Вишневский

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.