Geologic interpretation of large seismic stacked or migrated seismic images can be a time-consuming task for seismic interpreters. Neural network based semantic segmentation provides fast and automatic interpretations, provided a sufficient number of example interpretations are available. Networks that map from image-to-image emerged recently as powerful tools for automatic segmentation, but standard implementations require fully interpreted examples. Generating training labels for large images manually is time consuming. We introduce a partial loss-function and labeling strategies such that networks can learn from partially interpreted seismic images. This strategy requires only a small number of annotated pixels per seismic image. Tests on seismic images and interpretation information from the Sea of Ireland show that we obtain high-quality predicted interpretations from a small number of large seismic images. The combination of a partial-loss function, a multi-resolution network that explicitly takes small and large-scale geological features into account, and new labeling strategies make neural networks a more practical tool for automatic seismic interpretation.


Article metrics loading...

Loading full text...

Full text loading...


  1. Alaudah, Y., Gao, S. and AlRegib, G.
    [2018] Learning to label seismic structures with deconvolution networks and weak labels. In: SEG Technical Program Expanded Abstracts 2018. 2121–2125.
    [Google Scholar]
  2. Di, H.
    [2018] Developing a seismic pattern interpretation network (SpiNet) for automated seismic interpretation. arXiv preprint arXiv:1810.08517.
    [Google Scholar]
  3. Harrigan, E., Kroh, J.R, Sandham, W.A and Durrani, T.S
    [1992] Seismic horizon picking using an artificial neural network. In: Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing, 3. 105–108 vol. 3.
    [Google Scholar]
  4. Meldahl, P., Heggland, R., Bril, B. and de Groot, P.
    [2001] Identifying faults and gas chimneys using multiattributes and neural networks. The Leading Edge, 20(5), 474–482.
    [Google Scholar]
  5. Peters, B., Granek, J. and Haber, E.
    [2018] Multi-resolution neural networks for tracking seismic horizons from few training images. arXiv preprint arXiv:1812.11092.
    [Google Scholar]
  6. Ronneberger, O., Fischer, P. and Brox, T.
    [2015] U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention, 234–241.
    [Google Scholar]
  7. Shi, Y., Wu, X. and Fomel, S.
    [2018] Automatic salt-body classification using deep-convolutional neural network. In: SEG Technical Program Expanded Abstracts2018. 1971–1975.
    [Google Scholar]
  8. Tingdahl, K.M and De Rooij, M.
    [2005] Semi-automatic detection of faults in 3D seismic data. Geophysical Prospecting, 53(4), 533–542.
    [Google Scholar]
  9. Veezhinathan, J., Kemp, F. and Threet, J.
    [1993] A Hybrid of Neural Net and Branch and Bound Techniques for Seismic Horizon Tracking. In: Proceedings of the 1993 ACM/SIGAPP Symposium on Applied Computing: States of the Art and Practice, SAC '93. ACM, New York, NY, USA, 173–178.
    [Google Scholar]
  10. Waldeland, A.U, Jensen, A.C, Gelius, L.J and Solberg, A.H.S.
    [2018] Convolutional neural networks for automated seismic interpretation. The Leading Edge, 37(7), 529–537.
    [Google Scholar]
  11. Wu, H. and Zhang, B.
    [2018] A deep convolutional encoder-decoder neural network in assisting seismic horizon tracking. arXiv preprint arXiv:1804.06814.
    [Google Scholar]
  12. Zhao, T.
    [2018] Seismic facies classification using different deep convolutional neural networks. In: SEG Technical Program Expanded Abstracts 2018. 2046–2050.
    [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