Abstract.This article presents the results of adapting the U-net convolutional neural network to solving the problem of tracing fault surfaces on 3D seismic cubes. Fault mapping is one of the stages of interpretation of the results of using the seismic methods of field geophysical work. The interpretation results are used to build structural frameworks of geological models, plan field development strategies, assess the hydrodynamic connectivity of reservoirs, plan well locations, their number, etc. The developed neural network algorithm, which uses computer vision algorithms, can significantly increase the speed of faults detection and reduce risk of skipping faults in interpretation process. The problems of using a neural network trained on a synthetic data set for solving practical problems are also considered. Methods for increasing reliability of seismic interpretation are proposed. In particular, by calculating and subsequent processing with neural network an additional volume of the coherence attribute. As a result of the study, a positive conclusion on the applicability of convolutional neural networks for solving problems of tracing fault surfaces is given.

For citation: Rusinovich V.V., Rusinovich L.E. Fault surface tracing automation using computer vision algorithms. Geosistemy perehodnykh zon = Geosystems of Transition Zones, 2023, vol. 7, no. 1, pp. 86–94. (In Russ., abstr. in Engl.).
https://doi.org/10.30730/gtrz.2023.7.1.086-094, https://www.elibrary.ru/zzuzky

Для цитирования: Русинович В.В., Русинович Л.Э. Автоматизация трассировки поверхностей разломов с помощью алгоритмов компьютерного зрения. Геосистемы переходных зон, 2023, т. 7, № 1, с. 86–94.
https://doi.org/10.30730/gtrz.2023.7.1.086-094, https://www.elibrary.ru/zzuzky

1. Pedersen S.I., Skov T., Randen T., Sonneland L. 2005. Automatic fault extraction using artificial ants. In: Iske A., Randen T. (eds) Mathematical methods and modelling in hydrocarbon exploration and production. Springer, Berlin, Heidelberg, 107–116. (Mathematics in Industry, vol. 7). https://doi.org/10.1007/3-540-26493-0_5

2. Celina C. Silva, Marcolino C.S., Lima F.D. 2005. Automatic fault extraction using ant tracking algorithm in the Marlim South Field, Campos Basin. In: SEG Technical Program Expanded Abstracts, p. 857–860. https://doi.org/10.1190/1.2148294

3. Ronneberger O., Fischer P., Brox T. 2015. U-Net: Convolutional networks for biomedical image segmentation. In: International Conference on medical image computing and computer-assisted intervention, p. 17–24. https://doi.org/10.48550/arXiv.1505.04597

4. Wu X., Liang L., Shi Yu., Fomel S. 2019. FaultSeg3D: Using synthetic data sets to train an end-to-end convolutional neural network for 3D seismic fault segmentation. Geophysics, 84(3): IM35–IM45 https://doi.org/10.1190/geo2018-0646.1

5. Ioffe S., Szegedy Ch. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd International Conference on International Conference on Machine Learning, 37: 448–456. https://doi.org/10.48550/arXiv.1502.03167

6. Kerry-3D. URL: https://wiki.seg.org/wiki/Open_data#F3_Netherlands (дата обращения 04.11.2022).

7. Kirilova А.S., Zakrevskiy K.E. 2014. Workshop of seismic interpretation in Petrel. Moscow: MAI-PRINT, 288 p. (In Russ). URL: http://www.petroportal.ru/biblioteka (accessed 04.11.2022).

8. Gersztenkorn A., Marfurt K.J. 1999. Eigenstructure-based coherence computations as an aid to 3-D structural and stratigraphic mapping. Geophysics, 64(5): 1468–1479. https://doi.org/10.1190/1.1444651

9. Druzhinin V.S., Nachapkin N.I., Osipov V.Yu. 2018. Identification and mapping of deep faults based on seismic data and their display in geophysical fields. Izvestiya UGGU = News of the Ural State Mining University, 3(51): 47–53. (In Russ.). https://doi.org/10.21440/2307-2091-2018-3-47-53