Abstract
The presented paper is devoted to the numerical study of the applicability of 3D inversion for fracture model reconstruction based on machine learning. In practice, geophysicists use seismic inversion for predicting reservoir properties. One-dimensional convolutional model lies in the basis of standard versions of inversion, but geology is more complex. That is why we provide implementation and investigation of the approach for 3D fracture model reconstruction based machine learning, which uses U-net neural network and 3D convolutional model. We provide numerical results for a realistic 3D synthetic fractured model from the North of Russia.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Manzocchi, T., Walsh, J.J., Bailey, W.R.: Population scaling biases in map samples of power-law fault systems. J. Struct. Geol. 31, 1612–1626 (2009)
Xu, C., Dowd, P.: A new computer code for discrete fracture network modelling. Comput. Geosci. 36, 292–301 (2010)
Ampilov, Yu.P., Barkov, A.Yu., Yakovlev, I.V., Filippova, K.E., Priezzhev, I.I.: Almost everything is about seismic inversion. Part 1. Seismic Technol. 4, 3–16 (2009)
Yakovlev, I.V., Ampilov, Yu.P., Filippova, K.E.: Almost everything is about seismic inversion. Part 2. Seismic Technol. 1, 5–15 (2011)
Russell, B. H.: Introduction to Seismic Inversion Methods. Course Notes Series, Society of Exploration Geophysicists, pp. 80–101 (1988)
Liu, E., et al.: Fracture characterization by integrating seismic-derived attributes including anisotropy and diffraction imaging with borehole fracture data in an offshore carbonate field. In: International Petroleum Technology Conference, IPTC-18533 (2015)
Shtivelman, V., Keydar, S.: Imaging shallow subsurface inhomogeneities by 3D multipath diffraction summation. First Break 23, 39–42 (2005)
De Ribet, B., Yelin, G., Serfaty, Y., Chase, D., Kelvin, R., Koren, Z.: High resolution diffraction imaging for reliable interpretation of fracture systems. First Break 35(2), 43–47 (2017)
Jin, Y., Wu, X., Chen, J., Han, Z., Hu, W.: Seismic data denoising by deep-residual networks. In: SEG Technical Program Expanded Abstracts, pp. 4593–4597 (2018)
Jia, Y., Ma, J.: What can machine learning do for seismic data processing? An interpolation application. Geophysics 82, V163–V177 (2017)
Hou, S., Messud, J.: Machine learning for seismic processing: the path to fulfilling promises. In: SEG Technical Program Expanded Abstracts, pp. 3204–3208 (2021)
Bagheri, M., Ali Riahi, M.: Modeling the facies of reservoir using seismic data with missing attributes by dissimilarity based classification. J. Earth Sci. 28(4), 703–708 (2017)
Chen, Y., Schuster, G.: Seismic inversion by Newtonian machine learning. Geophysics 85, WA185-WA200 (2020)
Pintea, S.L., Sharma, S., Vossepoel, F.C., Van Gemert, J.C., Loog, M., Verschuur, D.J.: Seismic inversion with deep learning. Comput. Geosci. 26, 351–364 (2022)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. arXiv:1505.04597v1 (2015)
Protasov, M.: High-performance implementation of 3D seismic target-oriented imaging. Commun. Comput. Inf. Sci. 1510, 125–136 (2021)
Protasov, M.I., Reshetova, G.V., Tcheverda, V.A.: Fracture detection by Gaussian beam imaging of seismic data and image spectrum analysis. Geophys. Prospect. 64(1), 68–82 (2016)
Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)
Acknowledgments
The presented research is supported and done within the scope of investigations of RSF grant 21-71-20002. We use the computational resources of Peter the Great Saint-Petersburg Polytechnic University Supercomputing Center (scc.spbstu.ru) to provide the numerical experiments and to obtain the numerical results.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Protasov, M., Kenzhin, R., Pavlovskiy, E. (2023). 3D Seismic Inversion for Fracture Model Reconstruction Based on Machine Learning. In: Voevodin, V., Sobolev, S., Yakobovskiy, M., Shagaliev, R. (eds) Supercomputing. RuSCDays 2023. Lecture Notes in Computer Science, vol 14389. Springer, Cham. https://doi.org/10.1007/978-3-031-49435-2_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-49435-2_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-49434-5
Online ISBN: 978-3-031-49435-2
eBook Packages: Computer ScienceComputer Science (R0)