1887

Abstract

Summary

In this paper, we present a deep learning approach for lossy compression of 3D post-stack seismic data. The network is feed with two-dimensional 32-bits slices from the original volume, training at the same time two autoencoders, one for latent space representation, and other for entropy estimation. The bitrate of the compressed volume is controlled by hyper-parameter tuning. The method benefits from the intrinsic characteristic of deep learning methods and automatically captures the most relevant features of the data. It presents impressive results in data reconstruction with high PSNR values at low bitrates. High compression rates (up to 45:1) are obtained, training specialized networks for single datasets. We validate the results using different raw datasets (without any pre-conditioning) from SEG Open Data repository.

Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.201901620
2019-06-03
2020-06-05
Loading full text...

Full text loading...

References

  1. Agustsson, E., Mentzer, F., Tschannen, M., Cavigelli, L., Timofte, R.
    , Benini, L. and Van Gool, L. [2017] Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations.
    [Google Scholar]
  2. Averbuch, A.Z., Meyer, F., Stromberg, J.., Coifman, R. and Vassiliou, A
    . [2001] Low bit-rate efficient compression for seismic data. IEEE Transactions on Image Processing, 10(12), 1801–1814.
    [Google Scholar]
  3. Li, M., Zuo, W., Gu, S., Zhao, D. and Zhang, D.
    [2017] Learning Convolutional Networks for Content-weighted Image Compression. arXiv preprint arXiv:1703.10553.
    [Google Scholar]
  4. Mentzer, F., Agustsson, E., Tschannen, M., Timofte, R. and Van Gool, L
    . [2018] Conditional Probability Models for Deep Image Compression. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR).
    [Google Scholar]
  5. SEG
    [2019] Open data. http://wiki.seg.org/wiki/Open data.Accessed: 2019-01-10.
  6. Theis, L., Shi, W., Cunningham, A. and Huszár, F
    . [2017] Lossy Image Compression with Compressive Autoencoders. In: International Conference on Learning Representations.
    [Google Scholar]
  7. Van Oord, A., Kalchbrenner, N. and Kavukcuoglu, K
    . [2016] Pixel Recurrent Neural Networks. In: International Conference on Machine Learning. 1747–1756.
    [Google Scholar]
  8. Zhang, Y., Da Silva, C., Kumar, R. and Herrmann, F.
    [2017] Massive 3D seismic data compression and inversion with hierarchical Tucker.
    [Google Scholar]
http://instance.metastore.ingenta.com/content/papers/10.3997/2214-4609.201901620
Loading
/content/papers/10.3997/2214-4609.201901620
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