Application of convolutional neural networks for search and determination of physical characteristics of inhomogeneities in geological media from seismic data
https://doi.org/10.25587/SVFU.2023.87.50.008
Abstract
With the use of convolutional neural networks, we solve inverse problems of exploration seismology to determine the spatial position and physical characteristics of geological fractures, such as the proportion of excess surface and the nature of saturation. The training and validation sets were formed using numerical modeling by the grid-characteristic method on unstructured meshes in the two-dimensional case. The continuum mechanics equations were used, while the fractures were specified discretely in the integration domain; this approach made it possible to obtain the most detailed patterns of wave responses.
About the Authors
M. V. Muratov
Moscow Institute of Physics and Technology
Russian Federation
Russian Federation
Maxim V. Muratov
9 Institutsky Lane, 141700 Dolgoprudny
D. S. Konov
Moscow Institute of Physics and Technology
Russian Federation
Russian Federation
Denis S. Konov
9 Institutsky Lane, 141700 Dolgoprudny
D. I. Petrov
Moscow Institute of Physics and Technology
Russian Federation
Russian Federation
Dmitry I. Petrov
9 Institutsky Lane, 141700 Dolgoprudny
I. B. Petrov
Moscow Institute of Physics and Technology
Russian Federation
Russian Federation
Igor B. Petrov
9 Institutsky Lane, 141700 Dolgoprudny
References
1. Claerbout J. F., “Coarse grid calculations of waves in inhomogeneous media with application to delineation of complicated seismic structure,” Geophys., 36, No. 3, 407–418 (1970).
2. Etgen J., Gray S., and Zhang Y., “An overview of depth imaging in exploration geophysics,” Geophys., 74, WCA5–WCA17 (2009).
3. Jiao K., Huang W., Vigh D., Kapoor J., Coates R., Starr E. W., and Cheng X., “Elastic migration for improving salt and subsalt imaging and inversion,” SEG Tech. Program Expanded Abstr., 1–5 (2012).
4. Luo Y., Tromp J., Denel B., and Calandra H., “3D coupled acoustic-elastic migration with topography and bathymetry based on spectral-element and adjoint methods,” Geophys., 78, No. 4, S193–S202 (2013).
5. Muratov M. V., Petrov D. I., Ryazanov V. V., and Biryukov V. A., “Machine learning application to solving inverse problems in fractures layer seismic surveys,” Russ. J. Cybern., 3, No. 1, 8–13 (2022).
6. Muratov M. V., Petrov D. I., and Biryukov V. A., “The solution of fractures detection problems by methods of machine learning,” in: Smart Modelling for Engineering Systems, Springer, Singapore (2021) (Smart Innov. Syst. Technol.; V. 215).
7. Zhang C., Frogner C., Araya-Polo M., and Hohl D., “Machine-learning based automated fault detection in seismic traces,” EAGE Conf. Exhib. (2014).
8. Araya-Polo M., Dahlke T., Frogner C., Zhang C., Poggio T., and Hohl D., “Automated fault detection without seismic processing,” The Leading Edge, 36, No. 3, 208–214 (2017).
9. Wu Y., Lin Y., Zhou Zh., and Delorey A., “Seismic-net: a deep densely connected neural network to detect seismic events,” arXiv:1802.02241 (2018).
10. Menga M., Chua Y. J., Woutersonb E., and Ong C. P. K., “Ultrasonic signal classification and imaging system for composite materials via deep convolutional neural networks,” Neurocomput., 257, 128–135 (2017).
11. Kondaurov V. I. and Fortov V. I., Fundamentals of Thermomechanics of Condensed Matter [in Russian], MIPT, Moscow (2002).
12. Chelnokov F. B., “Numerical simulation of deformation dynamic processes in media with a complex structure [in Russian], Diss. Kand. Fiz.-Mat. Nauk, MIPT, Moscow (2005).
13. Magomedov K. M. and Kholodov A. S., Grid-Characteristic Numerical Methods [in Russian], Nauka, Moscow (1988).
14. Golubev V. I., Shevchenko A. V., Khokhlov N. I., and Nikitin I. S., “Numerical investigation of compact grid-characteristic schemes for acoustic problems,” J. Phys., Conf. Ser., 1902, No. 1, 012110 (2021).
15. Petrov I. B., Tormasov A. G., and Kholodov A. S., “On the use of hybrid grid-characteristic schemes for the numerical solution of three-dimensional problems in the dynamics of a deformable solid,” USSR Comput. Math. Math. Phys., 30, No. 4, 191–196 (1990).
16. Favorskaya A. V., Breus A. V., and Galitskii B. V., “Application of the grid-characteristic method to the seismic isolation model,” Smart Innov. Syst. Technol., 133, 167–181 (2019).
17. Kozlov Ye. A., Models of the Medium in Exploration Seismology [in Russian], GERS, Tver (2006).
18. Leviant V. B., Petrov I. B., and Kvasov I. Ye., “Numerical modeling of wave response from subvertical macrofractures, probable fluid-conducting channels [in Russian],” Tekhnologii Seismorazvedki, 4, 41–61 (2011).
19. Petrov I. B. and Muratov M. V., “The application of grid-characteristic method in solution of fractured formations exploration seismology direct problems (review article),” Mat. Model., 31, No. 4, 33–56 (2019).
20. Karaev N. A., Leviant V. B., Petrov I. B., Karaev N. A., Karaev G. N., and Muratov M. V., “Estimation by methods of mathematical and physical modeling of the possibility of using converted scattered waves for direct detection and characterization of macrofracture systems [in Russian],” Tekhnologii seismorazvedki, 1, 22–36 (2015).
21. Muratov M. V., Stognii P. V., Petrov I. B., Anisimov A. A., and Karaev N. A., “The study of dynamical processes in problems of mesofracture layers exploration seismology by methods of mathematical and physical simulation,” RENSIT, 13, No. 1, 71–78 (2021).
22. Ioffe S. and Szegedy Ch., “Batch normalization: accelerating deep network training by reducing internal covariate shift,” Proc. 32nd Int. Conf. Machine Learning, 37, 448–456 (2015).
23. Paszke A., Gross S., and Massa F., “PyTorch: an imperative style, high-performance deep learning library,” Proc. 33rd Conf. Neural Information Processing Systems (NeurIPS 2019), Vancouver (2019).
24. Paszke A., Gross S., and Chintala S., “Automatic differentiation in PyTorch,” Proc. 31st Conf. Neural Information Processing Systems (NIPS 2017), Long Beach, CA (2017).
Review
For citations:
Muratov M.V., Konov D.S., Petrov D.I., Petrov I.B. Application of convolutional neural networks for search and determination of physical characteristics of inhomogeneities in geological media from seismic data. Mathematical notes of NEFU. 2023;30(1):101-113. (In Russ.) https://doi.org/10.25587/SVFU.2023.87.50.008
Views:
8
JATS XML
Email this article 