«Automation and Informatization of the fuel and energy complex»

Mathematical modeling of the borehole horizontal section based on azimuthal density logging

UDC: 004.032.26:519.857:551.7.02
DOI: -

Authors:

¹ National University of Oil and Gas "Gubkin University", Moscow, Russia

Keywords: azimuthal imaging log, image processing, computer vision, autoencoder, convolutional neural network, geophysical interpretation

Annotation:

The authors of the article present a mathematical model for the automatic extraction of structural features from azimuthal density logging images acquired during a horizontal well drilling. The model is based on a hybrid approach that combines classical computer vision algorithms with modern deep learning techniques. The classical algorithms and neural network architectures used for analyzing two-dimensional borehole data are reviewed. The proposed methodology incorporates a convolutional autoencoder trained on unlabeled data using a loss function sensitive to edge structures, enabling image reconstruction while preserving geometric specific features. A convolutional classifier trained on labeled examples is used to identify geologically significant objects. The developed system demonstrates high accuracy on data from various oil fields, robustness to noise and possibility of real-time operation under limited computational resources. The practical applicability of the method is proved in conditions of a limited amount of annotated data.

Bibliography:

1. Galkina A.V., Kanevskaya R.D. O sovremennykh podkhodakh k resheniyu zadachi avtomaticheskoy korrelyatsii geologicheskikh razrezov skvazhin // Avtomatizatsiya i informatizatsiya TEK. – 2025. – № 3(620). – S. 56–64.
2. Arsen'ev-Obraztsov S.S., Plyushch G.O. Primenenie metodov glubokogo obucheniya v aktual'nykh zadachakh obrabotki mikroKT obraztsov kerna. Segmentatsiya, vosstanovlenie i sintez tsifrovykh kernov // Avtomatizatsiya i informatizatsiya TEK. – 2023. – № 12(605). – S. 34–43. – DOI: 10.33285/2782-604X-2023-12(605)-34-43
3. Bondár I. Seismic horizon detection using image processing algorithms // Geophysical Prospecting. – 1992. – Vol. 40, Issue 7. – P. 785–800. – DOI: 10.1111/j.1365-2478.1992.tb00552.x
4. Cooper G.R.J. Geophysical Applications of the Hough Transform // South African Journal of Geology. – 2006. – Vol. 109, No. 4. – P. 555–560. – DOI: 10.2113/gssajg.109.4.555
5. Zhang Cheng-En, Pan Bao-Zhi. Feature Recognition Based on Borehole Image Processing // 2nd International Conference on Information Science and Engineering, Hangzhou, China, Dec. 04–06, 2010. – DOI: 10.1109/ICISE.2010.5690580
6. Ashraf H., Mousa W.A., Al-Dossary S. Efficient and accurate edge-preserving smoothing for 3D hexagonally sampled seismic data // Geophysical Prospecting. – 2017. – Vol. 65, Issue 3. – P. 696–710. – DOI: 10.1111/1365-2478.12447
7. Takagi T., Saitoh F. Curve detection using Delaunay triangulation based on perceptual grouping factors // Electronics and Communications in Japan. – 2012. – Vol. 95, Issue 7. – P. 19–28. – DOI: 10.1002/ecj.11388
8. Pat. WO2015053876A1, IPC G01V 1/50. Automatic dip picking from wellbore azimuthal image logs / Ye Shin-ju Chu. – Application PCT/US2014/053429; Application filed 2014–08–29; Publication 2015–04–16. – URL: https://patents.google.com/patent/WO2015053876A1
9. Azimuthal imaging of rock fractures by incorporating single borehole radar and optical data / Shen Jian, Liu Liu, Li Shaojun [et al.]. – 2024. – DOI: 10.48550/arXiv.2410.11350
10. Seismic horizon detection with neural networks / A. Koryagin, D. Mylzenova, R. Khudorozhkov, S. Tsimfer. – 2020. – DOI: 10.48550/arXiv.2001.03390
11. A Sequential Iterative Deep Learning Seismic Blind High-Resolution Inversion / Chen Hongling, Gao Jinghuai, Gao Zhaoqi [et al.] // IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. – 2021. – Vol. 14. – P. 7817–7829. – DOI: 10.1109/JSTARS.2021.3100502
12. Improving Accuracy of Automatic Fracture Detection in Borehole Images with Deep Learning and GPUs / R.A.Q. Cruz, D.C. Cacau, R.M. dos Santos [et al.] // Proceedings of the 30th SIBGRAPI Conference on Graphics, Patterns and Images, Niteroi, Brazil, Oct. 17–20, 2017. – P. 345–350. – DOI: 10.1109/SIBGRAPI.2017.52
13. Automatic Detection of Fractures Based on Optimal Path Search in Well Logging Images / Zhang Wei, Wu Tong, Li Zhipeng [et al.] // Journal of Sensors. – 2021. – Special Issue: Sensors, Signal, and Artificial Intelligent Processing. – Article ID 5577084. – DOI: 10.1155/2021/5577084
14. Automated Detection of Geological Features: Leveraging Deep Learning for Beddings and Fractures Identification in Image Logs / M.Q. Nasim, T. Maiti, N. Mosavat [et al.] // SPE Journal. – 2025. – Vol. 30, Issue 7. – DOI: 10.2118/223976-PA
15. Image Quality Assessment: From Error Visibility to Structural Similarity / Wang Zhou., A.C. Bovik, H.R. Sheikh, E.P. Simoncelli // IEEE Transactions on Image Processing. – 2004. – Vol. 13, Issue 4. – P. 600–612. – DOI: 10.1109/TIP.2003.819861
16. Sobel I., Feldman G. A 3×3 Isotropic Gradient Operator for Image Processing: Technical Report. – Stanford Artificial Intelligence Laboratory, 1968.
17. Kingma D.P., Ba J. Adam: A Method for Stochastic Optimization. – 2014. – 15 p. – DOI: 10.48550/arXiv.1412.6980
18. Otsu N. A Threshold Selection Method from Gray-Level Histograms // IEEE Transactions on Systems, Man, and Cybernetics. – 1979. – Vol. 9, Issue 1. – P. 62–66. – DOI: 10.1109/TSMC.1979.4310076
19. Canny J. A Computational Approach to Edge Detection // IEEE Transactions on Pattern Analysis and Machine Intelligence. – 1986. – Vol. 8, Issue 6. – P. 679–698. – DOI: 10.1109/TPAMI.1986.4767851
20. Suzuki S., Abe K. Topological Structural Analysis of Digitized Binary Images by Border Following // Computer Vision, Graphics, and Image Processing. – 1985. – Vol. 30, Issue 1. – P. 32–46. – DOI: 10.1016/0734-189X(85)90016-7