This website uses cookies to improve your experience. If you continue without changing your settings, you consent to our use of cookies in accordance with our cookie policy. You can disable cookies at any time.


Automatic channel detection using deep learning


We have developed a method based on an encoder-decoder convolutional neural network for automatic channel detection in 3D seismic volumes. We use two architectures borrowed from computer vision: SegNet for image segmentation together with Bayesian SegNet for uncertainty measurement. We train the network on 3D synthetic volumes and then apply it to field data. We test the proposed approach on a 3D field data set from the Browse Basin, offshore Australia, and a 3D Parihaka seismic data in New Zealand. Applying the weights estimated from training on 3D synthetic volumes to a 3D field data set accurately identifies channel geobodies without the need for any human interpretation on seismic attributes. Our proposed method also produces uncertainty volumes to quantify the trustworthiness of the detection model.


  • Badrinarayanan, V., A. Kendall, and R. Cipolla, 2015, Segnet: A deep convolutional encoder-decoder architecture for image segmentation: CoRR, abs/1511.00561.Google Scholar
  • Claerbout, J., 2014, Geophysical image estimation by example: Scholar
  • Dumoulin, V., and F. Visin, 2016, A guide to convolution arithmetic for deep learning: CoRR, abs/1603.07285.Google Scholar
  • Fomel, S., E. Landa, and M. T. Taner, 2007, Poststack velocity analysis by separation and imaging of seismic diffractions: Geophysics, 72, no. 6, U89–U94, doi: 10.1190/1.2781533.GPYSA70016-8033AbstractWeb of ScienceGoogle Scholar
  • Gal, Y., and Z. Ghahramani, 2015a, Bayesian convolutional neural networks with Bernoulli approximate variational inference: CoRR, abs/1506.02158.Google Scholar
  • Gal, Y., and Z. Ghahramani, 2015b, Dropout as a Bayesian approximation: Representing model uncertainty in deep learning: ArXiv preprint arXiv:1506.02142.Google Scholar
  • Ghahramani, Z., 2015, Probabilistic machine learning and artificial intelligence: Nature, 521, 452–459, doi: 10.1038/nature14541.CrossrefWeb of ScienceGoogle Scholar
  • Hart, B. S., 2008, Channel detection in 3-D seismic data using sweetness: AAPG Bulletin, 92, 733–742, doi: 10.1306/02050807127.AABUD20149-1423CrossrefWeb of ScienceGoogle Scholar
  • Ioffe, S., and C. Szegedy, 2015, Batch normalization: Accelerating deep network training by reducing internal covariate shift: CoRR, abs/1502.03167.Google Scholar
  • Kendall, A., V. Badrinarayanan, and R. Cipolla, 2015, Bayesian segnet: Model uncertainty in deep convolutional encoder-decoder architectures for scene understanding: CoRR, abs/1511.02680.Google Scholar
  • Kingma, D. P., and J. Ba, 2014, Adam: A method for stochastic optimization: CoRR, abs/1412.6980.Google Scholar
  • Kington, J., 2015, Semblance, coherence, and other discontinuity attributes: The Leading Edge, 34, 1510–1512, doi: 10.1190/tle34121510.1.AbstractGoogle Scholar
  • LeCun, Y., Y. Bengio, and G. E. Hinton, 2015, Deep learning: Nature, 521, 436–444, doi: 10.1038/nature14539.CrossrefWeb of ScienceGoogle Scholar
  • Liu, J., and K. J. Marfurt, 2007, Instantaneous spectral attributes to detect channels: Geophysics, 72, no. 2, P23–P31, doi: 10.1190/1.2428268.GPYSA70016-8033AbstractWeb of ScienceGoogle Scholar
  • Long, J., E. Shelhamer, and T. Darrell, 2014, Fully convolutional networks for semantic segmentation: CoRR, abs/1411.4038.CrossrefGoogle Scholar
  • Mathewson, J., and D. Hale, 2008, Detection of channels in seismic images using the steerable pyramid: Colorado School of Mines.AbstractGoogle Scholar
  • Phillips, M., and S. Fomel, 2017, Plane-wave sobel attribute for discontinuity enhancement in seismic images: Geophysics, 82, no. 6, WB63–WB69, doi: 10.1190/geo2017-0233.1.GPYSA70016-8033AbstractWeb of ScienceGoogle Scholar
  • Wu, X., 2017, Directional structure-tensor-based coherence to detect seismic faults and channels: Geophysics, 82, no. 2, A13–A17, doi: 10.1190/geo2016-0473.1.GPYSA70016-8033AbstractWeb of ScienceGoogle Scholar