Abstract
In this paper, we present a deep learning approach for very low bit rate seismic data compression. Our goal is to preserve perceptual and numerical aspects of the seismic signal whilst achieving high compression rates. The trade-off between bit rate and distortion is controlled by adjusting the loss function. 2D slices extracted from seismic 3D amplitude volumes feed the network for training two simultaneous networks, an autoencoder for latent space representation, and a probabilistic model for entropy estimation. The method benefits from the intrinsic characteristic of deep learning methods and automatically captures the most relevant features of seismic data. An approach for training different seismic surveys is also presented. To validate the method, we performed experiments in real seismic datasets, showing that the autoencoders can successfully yield compression rates up to 68:1 with an average PSNR around 40 dB.
Authors thank CAPES, FAPEMIG (grant CEX-APQ-01744-15) for the financial support, and NVIDIA for the donation of one GPU as part of the GPU Grant Program.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Averbuch, A.Z., Meyer, F., Stromberg, J., Coifman, R., Vassiliou, A.: Low bit-rate efficient compression for seismic data. IEEE Trans. Image Process. 10(12), 1801–1814 (2001). https://doi.org/10.1109/83.974565
Villasenor, J.D., Ergas, R.A., Donoho, P.L.: Seismic data compression using high-dimensional wavelet transforms. In: Proceedings of Data Compression Conference-DCC 1996, pp. 396–405. IEEE (1996)
Zhang, Y., Da Silva, C., Kumar, R., Herrmann, F., et al.: Massive 3D seismic data compression and inversion with hierarchical tucker. In: 2017 SEG International Exposition and Annual Meeting. Society of Exploration Geophysicists (2017)
Liu, Y., Xiong, Z., Lu, L., Hohl, D.: Fast SNR and rate control for JPEG XR. In: 2016 10th International Conference on Signal Processing and Communication Systems (ICSPCS), pp. 1–7. IEEE (2016)
Sullivan, G.J., Ohm, J.R., Han, W.J., Wiegand, T., et al.: Overview of the high efficiency video coding (HEVC) standard. IEEE Trans. Circuits Syst. Video Technol. 22(12), 1649–1668 (2012)
Radosavljević, M., Xiong, Z., Lu, L., Vukobratović, D.: High bit-depth image compression with application to seismic data. In: Visual Communications and Image Processing (VCIP), pp. 1–4. IEEE (2016)
Radosavljević, M., Xiong, Z., Lu, L., Hohl, D., Vukobratović, D.: HEVC-based compression of high bit-depth 3D seismic data. In: 2017 IEEE International Conference on Image Processing (ICIP), pp. 4028–4032. IEEE (2017)
Nuha, H., Mohandes, M., Liu, B.: Seismic-data compression using autoassociative neural network and restricted boltzmann machine. SEG Tech. Program Expanded Abs. 2018, 186–190 (2018)
Rippel, O., Bourdev, L.: Real-time adaptive image compression. In: International Conference on Machine Learning, pp. 2922–2930 (2017)
Mentzer, F., Agustsson, E., Tschannen, M., Timofte, R., Van Gool, L.: Conditional probability models for deep image compression. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018)
Theis, L., Shi, W., Cunningham, A., Huszár, F.: Lossy image compression with compressive autoencoders. CoRR abs/1703.00395 (2017)
Agustsson, E., et al.: Soft-to-hard vector quantization for end-to-end learning compressible representations. In: Advances in Neural Information Processing Systems, pp. 1141–1151 (2017)
Theis, L., Shi, W., Cunningham, A., Huszár, F.: Lossy image compression with compressive autoencoders. In: International Conference on Learning Representations (2017). https://openreview.net/pdf?id=rJiNwv9gg
Van Oord, A., Kalchbrenner, N., Kavukcuoglu, K.: Pixel recurrent neural networks. In: International Conference on Machine Learning, pp. 1747–1756 (2016)
Li, M., Zuo, W., Gu, S., Zhao, D., Zhang, D.: Learning convolutional networks for content-weighted image compression. arXiv preprint arXiv:1703.10553 (2017)
SEG: Open data (2019). http://wiki.seg.org/wiki/Open_data. Accessed 10 Jan 2019
Sergeev, A., Balso, M.D.: Horovod: fast and easy distributed deep learning in TensorFlow. CoRR abs/1802.05799 (2018). http://arxiv.org/abs/1802.05799
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Schiavon, A.P., Navarro, J.P., Bernardes Vieira, M., Cruz e Silva, P.M. (2019). Low Bit Rate 2D Seismic Image Compression with Deep Autoencoders. In: Misra, S., et al. Computational Science and Its Applications – ICCSA 2019. ICCSA 2019. Lecture Notes in Computer Science(), vol 11619. Springer, Cham. https://doi.org/10.1007/978-3-030-24289-3_29
Download citation
DOI: https://doi.org/10.1007/978-3-030-24289-3_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-24288-6
Online ISBN: 978-3-030-24289-3
eBook Packages: Computer ScienceComputer Science (R0)