https://doi.org/10.26089/NumMet.v27r443

Numerical dispersion mitigation in 3D seismic data using neural network

Authors

  • Elena A. Gondyul
  • Dmitry M. Vishnevsky
  • Kirill G. Gadylshin
  • Vadim V. Lisitsa

Keywords:

neural network
numerical dispersion
seismic modeling

Abstract

Seismic modelling is one of the most time-consuming and resource-intensive parts of modern seismic data processing procedures. To obtain an accurate solution, a fine computational grid must be used. A natural way to reduce computational costs is to use a coarser grid; however, this leads to a significant increase in numerical errors, primarily numerical dispersion. This paper presents an approach to accelerating seismic modelling and suppressing numerical dispersion in the modelling results using machine learning methods. In the first stage, the entire dataset, consisting of thousands of seismograms, is computed on a coarse computational grid. Then, for a small number of sources, seismograms are computed on a fine computational grid to form a training dataset. Subsequently, a neural network is trained to reconstruct a solution free of numerical dispersion based on the simulation results obtained on the coarse grid. It is shown that using only 2–4% of the total number of sources to form the training sample halves the error whilst accelerating the simulation of seismic wavefields in a three-dimensional domain by more than a factor of six.


Downloads

Published

2026-11-13

Issue

Vol. 27 (2026): 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

Dmitry M. Vishnevsky

Sobolev Institute of Mathematics of SB RAS

• Researcher

Kirill G. Gadylshin

Sobolev Institute of Mathematics of SB RAS

• Senior Researcher

Vadim V. Lisitsa

Sobolev Institute of Mathematics of SB RAS

• Head of Laboratory

References

  1. T. Manning, D. Ablyazina, and J. Quigley, “The nimble node – Million-channel land recording systems have arrived,” The Leading Edge 38 (9), 706–714 (2019).
    doi 10.1190/tle38090706.1
  2. J. Virieux, S. Operto, H. Ben-Hadj-Ali, et al., “Seismic wave modeling for seismic imaging,” The Leading Edge 28 (5), 538–544 (2009).
    doi 10.1190/1.3124928
  3. J. Virieux, H. Calandra, and R.-E. Plessix, “A review of the spectral, pseudo-spectral, finite-difference and finite-element modelling techniques for geophysical imaging,” Geophysical Prospecting 59 (5), 794–813 (2011).
    doi 10.1111/j.1365-2478.2011.00967.x
  4. 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
  5. P. Moczo, J. Kristek, and M. Galis, itThe Finite-Difference Modelling of Earthquake Motions: Waves and Ruptures (Cambridge University Press, Cambridge, 2014).
    doi 10.1017/S0016756814000600
  6. E. H. Saenger, N. Gold, and S. A. Shapiro, “Modeling the propagation of elastic waves using a modified finite-difference grid,” Wave Motion 31 (1), 77–92 (2000).
    doi 10.1016/S0165-2125(99)00023-2
  7. 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
  8. J. E. Castillo and R. D. Grone, “A Matrix Analysis Approach to Higher-Order Approximations for Divergence and Gradients Satisfying a Global Conservation Law,” SIAM Journal on Matrix Analysis and Applications 25 (1), 128–142 (2003).
    doi 10.1137/S0895479801398025
  9. J. de la Puente, M. Ferrer, M. Hanzich, et al., “Mimetic seismic wave modeling including topography on deformed staggered grids,” Geophysics 79 (3), T125–T141 (2014).
    doi 10.1190/geo2013-0371.1
  10. J. Shragge and B. Tapley, “Solving the tensorial 3D acoustic wave equation: A mimetic finite-difference time-domain approach,” Geophysics 82 (4), T183–T196 (2017).
    doi 10.1190/geo2016-0691.1
  11. D. Belousov and V. Lisitsa, “Mimetic finite differences for boundaries misaligned with grid nodes,” Journal of Computational and Applied Mathematics 428, Article Number 115185 (2023).
    doi 10.1016/j.cam.2023.115185
  12. L. Dovgilovich and I. Sofronov, “High-accuracy finite-difference schemes for solving elastodynamic problems in curvilinear coordinates within multiblock approach,” Applied Numerical Mathematics 93, 176–194 (2015).
    doi 10.1016/j.apnum.2014.06.005
  13. O. O’Reilly, T. Lundquist, E. M. Dunham, and J. Nordström, “Energy stable and high-order-accurate finite difference methods on staggered grids,” Journal of Computational Physics 346, 572–589 (2017).
    doi 10.1016/j.jcp.2017.06.030
  14. O. O’Reilly and N. A. Petersson, “Energy conservative SBP discretizations of the acoustic wave equation in covariant form on staggered curvilinear grids,” Journal of Computational Physics 411, Article Number 109386 (2020).
    doi 10.1016/j.jcp.2020.109386
  15. M. Dumbser and M. Käser, “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
  16. M. Käser, M. Dumbser, J. de la Puente, and H. Igel, “An arbitrary high-order Discontinuous Galerkin method for elastic waves on unstructured meshes – III. Viscoelastic attenuation,” Geophysical Journal International 168 (1), 224–242 (2007).
    doi 10.1111/j.1365-246X.2006.03193.x
  17. V. Lisitsa, V. Tcheverda, and 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
  18. M. Galis, P. Moczo, and J. Kristek, “A 3-D hybrid finite-difference–finite-element viscoelastic modelling of seismic wave motion,” Geophysical Journal International 175 (1), 153–184 (2008).
    doi 10.1111/j.1365-246X.2008.03866.x
  19. 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 (1998).
    doi 10.1785/BSSA0880020368
  20. M. Xia, H. Zhou, H. Chen, et al., “A rectangular-grid lattice spring model for modeling elastic waves in Poisson’s solids,” Geophysics 83 (2), T69–T86 (2018).
    doi 10.1190/geo2016-0414.1
  21. B. F. Soysal and Y. Arici, “The use of discrete element models for the seismic assessment of concrete gravity dams,” Structures 70, Article Number 107831 (2024).
    doi 10.1016/j.istruc.2024.107831
  22. R. Wang, S. Li, Y. Liu, et al., “Peridynamics-based large-deformation simulations for near-fault landslides considering soil uncertainty,” Computers and Geotechnics 168, Article Number 106128 (2024).
    doi 10.1016/j.compgeo.2024.106128
  23. T. N. Hoang, T. T. Nguyen, T. V. Nguyen, et al., “SPH simulation of earthquake-induced liquefaction and large deformation behaviour of granular materials using SANISAND constitutive model,” Computers and Geotechnics 174, Article Number 106617 (2024).
    doi 10.1016/j.compgeo.2024.106617
  24. C. Jiang, H. Zhou, M. Xia, et al., “Stability conditions of multiple-relaxation-time lattice Boltzmann model for seismic wavefield modeling,” Journal of Applied Geophysics 204, Article Number 104742 (2022).
    doi 10.1016/j.jappgeo.2022.104742
  25. M. Ainsworth, “Discrete Dispersion Relation for hp-Version Finite Element Approximation at High Wave Number,” SIAM Journal on Numerical Analysis 42 (2), 553–575 (2004).
    doi 10.1137/S0036142903423460
  26. M. Ainsworth, P. Monk, and W. Muniz, “Dispersive and Dissipative Properties of Discontinuous Galerkin Finite Element Methods for the Second-Order Wave Equation,” Journal of Scientific Computing 27 (1), 5–40 (2006).
    doi 10.1007/s10915-005-9044-x
  27. M. Ainsworth, “Dispersive and dissipative behaviour of high order discontinuous Galerkin finite element methods,” Journal of Computational Physics 198 (1), 106–130 (2004).
    doi 10.1016/j.jcp.2004.01.004
  28. V. Lisitsa, “Dispersion analysis of discontinuous Galerkin method on triangular mesh for elastic wave equation,” Applied Mathematical Modelling 40 (7–8), 5077–5095 (2016).
    doi 10.1016/j.apm.2015.12.039
  29. O. P. Stoyanovskaya, V. V. Lisitsa, S. A. Anoshin, et al., “Dispersion analysis of SPH as a way to understand its order of approximation,” Journal of Computational and Applied Mathematics 438, Article Number 115495 (2024).
    doi 10.1016/j.cam.2023.115495
  30. M. Ainsworth and H. A. Wajid, “Dispersive and Dissipative Behavior of the Spectral Element Method,” SIAM Journal on Numerical Analysis 47 (5), 3910–3937 (2009).
    doi 10.1137/080724976
  31. J. E. Anderson, V. Brytik, and G. Ayeni, “Numerical Temporal Dispersion Corrections for Broadband Temporal Simulation, RTM and FWI,” in SEG International Exposition and Annual Meeting, New Orleans, Louisiana, October 18–23, 2015(SEG Technical Program Expanded Abstracts, 2015), pp. 1096–1100.
    doi 10.1190/segam2015-5817144.1
  32. R. Mittet, “Second-order time integration of the wave equation with dispersion correction procedures,” Geophysics 84 (4), T221–T235 (2019).
    doi 10.1190/geo2018-0770.1
  33. E. F. M. Koene, J. O. A. Robertsson, F. Broggini, and F. Andersson, “Eliminating time dispersion from seismic wave modeling,” Geophysical Journal International 213 (1), 169–180 (2018).
    doi 10.1093/gji/ggx563
  34. W. A. Mulder, “Temporal dispersion correction for wave-propagation modelling with a series approach,” Geophysical Prospecting 72 (2), 301–314 (2024).
    doi 10.1111/1365-2478.13411
  35. H. Kaur, S. Fomel, and N. Pham, “Seismic ground-roll noise attenuation using deep learning,” Geophysical Prospecting 68 (7), 2064–2077 (2020).
    doi 10.1111/1365-2478.12985
  36. S. Yu, J. Ma, and W. Wang, “Deep learning for denoising,” Geophysics 84 (6), V333–V350 (2019).
    doi 10.1190/geo2018-0668.1
  37. F. Yang and J. Ma, “Deep-learning inversion: A next-generation seismic velocity model building method,” Geophysics 84 (4), R583–R599 (2019).
    doi 10.1190/geo2018-0249.1
  38. W. Zhu, Y. Sheng, and Y. Sun, Wave-dynamics simulation using deep neural networks. Tech. rep.(Stanford University, 2017).
    doi 10.13140/RG.2.2.21994.77764
  39. Y. Xiang, Z. Wang, Z. Song, et al., “SeismicTransformer: An attention-based deep learning method for the simulation of seismic wavefields,” Computers & Geosciences 190, Article Number 105629 (2024).
    doi 10.1016/j.cageo.2024.105629
  40. K. Gadylshin, D. Vishnevsky, K. Gadylshina, and V. Lisitsa, “Numerical dispersion mitigation neural network for seismic modeling,” Geophysics 87 (3), T237–T249 (2022).
    doi 10.1190/geo2021-0242.1
  41. K. Gadylshin, E. Gondyul, V. Lisitsa, et al., “Mitigation of numerical dispersion in seismic data in spectral domain with neural networks,” Soil Dynamics and Earthquake Engineering 187, Article Number 109028 (2024).
    doi 10.1016/j.soildyn.2024.109028
  42. F. Collino and C. Tsogka, “Application of the perfectly matched layer absorbing layer model to the linear elastodynamic problem in anisotropic heterogeneous media,” Geophysics 66 (1), 294–307 (2001).
    doi 10.1190/1.1444908
  43. D. Komatitsch and R. Martin, “An unsplit convolutional perfectly matched layer improved at grazing incidence for the seismic wave equation,” Geophysics 72 (5), SM155–SM167 (2007).
    doi 10.1190/1.2757586
  44. V. Lisitsa, “Optimal Discretization of PML for Elasticity Problems,” Electronic Transactions on Numerical Analysis 30, 258–277 (2008).
    https://ftp.gwdg.de/pub/misc/EMIS/journals/ETNA/vol.30.2008/pp258-277.dir/pp258-277.pdf Cited October 24, 2026.
  45. A. R. Levander, “Fourth-order finite-difference P-SV seismograms,” Geophysics 53 (11), 1425–1436 (1988).
    doi 10.1190/1.1442422
  46. G. Cohen, Méthodes numériques d’ordre élevé pour les ondes en régime transitoire(INRIA, 1994).
  47. P. Moczo, J. Kristek, M. Galis, et al., “3-D finite-difference, finite-element, discontinuous-Galerkin and spectral-element schemes analysed for their accuracy with respect to P-wave to S-wave speed ratio,” Geophysical Journal International 187 (3), 1645–1667 (2011).
    doi 10.1111/j.1365-246X.2011.05221.x
  48. V. Kostin, V. Lisitsa, G. Reshetova, and V. Tcheverda, “Local time-space mesh refinement for simulation of elastic wave propagation in multi-scale media,” Journal of Computational Physics 281, 669–689 (2015).
    doi 10.1016/j.jcp.2014.10.047
  49. K. Gadylshin, V. Lisitsa, D. Vishnevsky, and K. Gadylshina, “Hausdorff-distance-based training dataset construction for numerical dispersion mitigation neural network,” Computers & Geosciences 180, Article Number 105438 (2023).
    doi 10.1016/j.cageo.2023.105438
  50. E. A. Gondyul, V. A. Dubrovina, V. V. Lisitsa, and D. M. Vishnevsky, “Neural seismic modeling – using of modeling data for migration,” Geophysics No 2, 17–22 (2026).
    doi 10.34926/geo.2026.37.16.003
  51. E. Gondyul, V. Lisitsa, K. Gadylshin, and D. Vishnevsky, “Numerical dispersion mitigation neural network with velocity model correction,” Computers & Geosciences 196, Article Number 105806 (2025).
    doi 10.1016/j.cageo.2024.105806

License

Copyright (c) 2026 Е. А. Гондюл, Д. М. Вишневский, К. Г. Гадыльшин, В. В. Лисица

Creative Commons License

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