Building realistic and reliable models of the subsurface is the primary goal of seismic imaging. By employing an ensemble of convolutional neural networks (CNNs), we build velocity models directly from seismic pre-stack data and quantify model uncertainties by analyzing all ensemble results. Most attempts are made to infer models as a whole. Here, CNNs are trained to map subsets of seismic data directly into 1D vertical velocity logs. This allows us to integrate well data into the inversion and to simplify the mapping by using the regularity of active seismic acquisition geometries. The presented approach uses neighboring common midpoint gathers (CMPs) for the estimation of individual vertical velocity logs. Trained on augmentations of the Marmousi model, our CNNs allow for the inversion of sections of the Marmousi II and the Overthrust models. Once the ensemble is trained on a particular dataset, similar datasets can be inverted much faster than with conventional full-waveform inversion.


Article metrics loading...

Loading full text...

Full text loading...


  1. Araya-Polo, M., Jennings, J., Adler, A. and Dahlke, T.
    [2018] Deep-Learning Tomography.The Leading Edge, 37(1), 58–66.
    [Google Scholar]
  2. Dozat, T.
    [2016] Incorporating nesterov momentum into adam.
    [Google Scholar]
  3. Farris, S., Araya-Polo, M., Jennings, J., Clapp, B. and Biondi, B.
    [2018] Tomography: a deep learning vs full-waveform inversion comparison. In: First EAGE Workshop on High Performance Computing for Upstream in Latin America, 2018. European Association of Geoscientists & Engineers, 1–5.
    [Google Scholar]
  4. Jin, Y., Hu, W., Wu, X. and Chen, J.
    [2018] Learn low wavenumber information in FWI via deep inception based convolutional networks. In: SEG Technical Program Expanded Abstracts 2018, Society of Exploration Geophysicists, 2091–2095.
    [Google Scholar]
  5. Kazei, V. and Alkhalifah, T.
    [2019] Scattering Radiation Pattern Atlas: What anisotropic elastic properties can body waves resolve?Journal of Geophysical Research: Solid Earth, 124(3), 2781–2811.
    [Google Scholar]
  6. Kazei, V., Ovcharenko, O., Alkhalifah, T. and Simons, F.
    [2019a] Realistically Textured Random Velocity Models for Deep Learning Applications. In: 81st EAGE Conference and Exhibition 2019.
    [Google Scholar]
  7. Kazei, V., Ovcharenko, O., Plotnitskii, P., Peter, D., Zhang, X. and Alkhalifah, T.A.
    [2019b] Mapping full seismic waveforms to vertical velocity profiles by deep learning.submitted to Geophysics.
    [Google Scholar]
  8. Mora, P.
    [1989] Inversion = Migration + Tomography.Geophysics, 54(12), 1575–1586.
    [Google Scholar]
  9. Ovcharenko, O., Kazei, V., Kalita, M., Peter, D. and Alkhalifah, T.
    [2019] Deep learning for low-frequency extrapolation from multioffset seismic data.GEOPHYSICS, 84(6), R989–R1001.
    [Google Scholar]
  10. Ovcharenko, O., Kazei, V., Peter, D. and Alkhalifah, T.
    [2017] Neural Network Based Low-Frequency Data Extrapolation. In: 3rd SEG FWI Workshop: What Are We Getting.
    [Google Scholar]
  11. Röth, G. and Tarantola, A.
    [1994] Neural Networks and Inversion of Seismic Data.Journal of Geophysical Research: Solid Earth, 99(B4), 6753–6768.
    [Google Scholar]
  12. Simonyan, K. and Zisserman, A.
    [2014] Very deep convolutional networks for large-scale image recognition.arXiv preprint arXiv:1409.1556.
    [Google Scholar]
  13. Sun, H. and Demanet, L.
    [2019] Extrapolated full waveform inversion with deep learning.arXiv preprint arXiv:1909.11536.
    [Google Scholar]
  14. Zheng, Y.
    [2019] Elastic Pre-Stack Seismic Inversion in Stratified Media Using Machine Learning. In: 81st EAGE Conference and Exhibition 2019.
    [Google Scholar]

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