EGU23-2183, updated on 22 Feb 2023
https://doi.org/10.5194/egusphere-egu23-2183
EGU General Assembly 2023
© Author(s) 2023. This work is distributed under
the Creative Commons Attribution 4.0 License.

Seismic random noise attenuation in the Laplace domain using deep learning

Wansoo Ha1, Jun Hyeon Jo2, and Lydie Uwibambe3
Wansoo Ha et al.
  • 1Pukyong National University, Energy Resources Engineering, Busan, Korea, Republic of (wansooha@gmail.com)
  • 2Pukyong National University, Energy Resources Engineering, Busan, Korea, Republic of (khail2m@naver.com)
  • 3Pukyong National University, Energy Resources Engineering, Busan, Korea, Republic of (lydie.uwibambe@gmail.com)

We attenuated random noise in Laplace-domain seismic wavefields using a modified U-net. Laplace-domain wavefields can be obtained by Laplace-transforming time-domain wavefields. Due to the damping in the Laplace transform, small-amplitude noises near the first arrival signal can severely contaminate Laplace-domain wavefields. Therefore, time-domain denoising is not sufficient for seismic data processing in the Laplace domain. We trained a modified U-net in a supervised manner to generate clean wavefields from noisy wavefields. Since Laplace-domain wavefields show exponential decay with respect to offset, we used the logarithmic representation of the wavefields to train the network. Numerical examples show that the deep-learning approach can attenuate random noise better than denoising using singular value decomposition.

How to cite: Ha, W., Jo, J. H., and Uwibambe, L.: Seismic random noise attenuation in the Laplace domain using deep learning, EGU General Assembly 2023, Vienna, Austria, 24–28 Apr 2023, EGU23-2183, https://doi.org/10.5194/egusphere-egu23-2183, 2023.