1887

Abstract

Summary

We present an original approach to speed up seismic modeling. The approach is based on the combination of the conventional finite difference method and the machine learning technique. The approach is called the 3D Numerical Dispersion Mitigation network, or 3D NDM-net. The method allows quick but inaccurate simulation of the wavefield with further post-processing to suppress the numerical error using the machine learning. According to the numerical experiments, the approach allows speeding up seismic modeling by a factor of up to 15 in the 3D case.

Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202510371
2025-06-02
2026-02-06
Loading full text...

Full text loading...

References

  1. Anderson, J. E., V.Brytik, and G.Ayeni (2015), Numerical Temporal Dispersion Corrections For Broadband Temporal Simulation, RTM and FWI, in SEG Technical Program Expanded Abstracts 2015, edited, pp. 1096–1100.
    [Google Scholar]
  2. Gadylshin, K., D.Vishnevsky, K.Gadylshina, and V.Lisitsa [2022] Numerical dispersion mitigation neural network for seismic modeling. Geophysics, 87(3), T237–T249.
    [Google Scholar]
  3. Gadylshin, K., E.Gondyul, V.Lisitsa, K.Gadylshina, and D.Vishnevsky [2024] Mitigation of numerical dispersion in seismic data in spectral domain with neural networks. Soil Dynamics and Earthquake Engineering, 187, 109028.
    [Google Scholar]
  4. Levander, A. R. [1988] Fourth-order finite-difference P-SV seismograms. Geophysics, 53(11), 1425–1436.
    [Google Scholar]
  5. Mittet, R. [2019] Second-order time integration of the wave equation with dispersion correction procedures. Geophysics, 84(4), T221–T235.
    [Google Scholar]
  6. Virieux, J., H.Calandra, and R.-É.Plessix [2011] A review of the spectral, pseudo-spectral, finite-difference and finite-element modelling techniques for geophysical imaging. Geophysical Prospecting, 59(5), 794–813.
    [Google Scholar]
/content/papers/10.3997/2214-4609.202510371
Loading
/content/papers/10.3997/2214-4609.202510371
Loading

Data & Media loading...

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