2023, Volume 12
2022, Volume 11
2021, Volume 10
2020, Volume 9
2019, Volume 8
2018, Volume 7
2017, Volume 6
2016, Volume 5
2015, Volume 4
2014, Volume 3
2013, Volume 2
2012, Volume 1
1Exploration and Development Research Institute of PetroChina Southwest Oil and Gasfield Company, Chengdu, China
2Geological Research Center of Research Institute of BGP, Zhuozhou, China
Traditional fault interpretation mainly relies on human-machine interaction, which has low efficiency and high human uncertainty. Coherence attribute is sensitive to the discontinuity characteristics of seismic data and can effectively identify high grade faults. The coherence algorithm has undergone three innovations: cross-correlation (C1), similarity (C2), and eigenstructure (C3). In addition to coherence, attributes such as curvature, dip angle, and ant tracking have been proposed, and the likelihood attribute has developed rapidly in recent years, which can accurately reflect larger fault structures and has certain discrimination ability for small faults. However, due to the small moment and short extension length of low grade faults, they do not necessarily exhibit discontinuous characteristics at the fault location (especially for strike-slip faults), and the traditional attributes have not achieved good results in identifying small-scale faults. With the development of artificial intelligence algorithms in the field of target detection, advanced neural networks have proven to surpass traditional attributes in identifying faults from seismic data. This article takes the BD1 area of the Sichuan Basin as an example and combines fault enhancement interpretive processing such as dip scanning, structure-guided filtering, edge-preserving filtering, and frequeency filtering with artificial intelligence algorithms and transfer learning techniques for low grade fault identification research, forming a precise and reasonable artificial intelligence low grade fault identification technology process. The results show that the artificial intelligence algorithm using a large sample library can identify low grade faults that cannot be detected by traditional methods, and the fault detection results of artificial intelligence are superior to traditional attributes in terms of noise resistance, accuracy, and computational efficiency.
Low Grade Fault, Discontinuity Attribuet, Fault Enhancement, Artificial Intelligence, Large Sample Library, Transfer Learning
Chen Kang, Zhang Sheng, Zhang Xuan, Sun Desheng, Xu Xiang, et al. (2023). Artificial Intelligence Minor Fault Identification Technology and Its Application in BD1 Area. International Journal of Energy and Power Engineering, 12(4), 47-53. https://doi.org/10.11648/j.ijepe.20231204.11
Copyright © 2023 Authors retain the copyright of this article.
This article is an open access article distributed under the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
1. | Bahorich M S, Farmer S L. 3-D seismic discontinuity for faults and stratigraphic features: The coherence cube [C]. 1995. |
2. | Kurt J, Marfurt R, Lynn Kirlin, et al. 3-D seismic attributes using a semblance-based coherency algorithm [J]. Geophysics, 1998, 63 (4): 1150-1165. |
3. | Gersztenkorn A, Marfurt K J. Eigenstructure-based coherence computations as an aid to 3-D structural and stratigraphic mapping [J]. GEOPHYSICS, 1999, 64 (5): 1468-1479. |
4. | Roberts A. Curvature attributes and their application to 3D interpreted horizons [J]. First Break, 2001, 19 (2): 85-100. |
5. | Al-Dossary S, Marfurt K J. 3D volumetric multispectral estimates of reflector curvature and rotation [J]. Geophysics, 2006, 71 (5): 41-51. |
6. | Bravo L, Aldana M. Volume curvature attributes to identify subtle faults and fractures in carbonate reservoirs Cimarrona Formation, Middle Magdalena Valley Basi, Colombia [C]. SEG Denver 2010 Annual Meeting, 2010: 231-235. |
7. | Hu bing. Application of Curvature-Based Fine Interpretation Technique in Complex Fault Area [J]. Offshore Oil, 2018, 38 (01): 22-27. |
8. | Dorigo M,Maniezzo V,Colorni A.Ant system: Optimization by a colony of cooperating agents [J].IEEE Transactions on Cybernetics, 1996, 26 (1): 29-41. |
9. | Long Yuchen, Li Jun, Wang Zhizhang, Zhang Guoyin and Han Dan. Fracture identification methods and applications of integrated ant body and curvature attribute [J]. RESERVOIR EVALUATION AND DEVELOPMENT, 2017, 7 (04): 6-9+15. |
10. | Hale D. Methods to compute fault images, extract fault surfaces, and estimate fault throws from 3D seismic images [J]. Geophysics, 78 (2): O33-O43. |
11. | Pei Xiuxiu. Application of seismic maximum likelihood attribute on fault identification in Zhangchang area of Biyang sag [J]. PETROLEUM GEOLOGY AND ENGINEERING, 2020, 34 (05): 8-11. |
12. | Zhao xiaohui, Yu baoli, Cao xiaolu. Application of attribute fusion technology in the identification of micro-fractures [J]. Oil Geophysical Prospecting, 2017, 52 (S2): 164-169. |
13. | Lu wenjing, Chen jin, Liu jin.The Fourth Industrial Revolution and innovation in artificial intelligence [J]. RESEARCH IN HIGHER EDUCATION OF ENGINE ERING, 2018 (3): 63-70. |
14. | Chen Gui, Liu Yang. Research progress of automatic fault recognition based on artificial intelligence [J]. Progress in Geophysics, 2021, 36 (01): 119-131. |
15. | CAICT, Artificial intelligence Alliance. The Era of Artificial Intelligence under Deep Learning [J]. Big Data Time, 2021 (6): 56-76. |
16. | Yang ping, Song qianggong, Zhan shifan, Tao chunfeng, Guo rui, Zhu donglin. Development and industrial application of efficient structural interpretation technology based on deep learning [J]. Oil Geophysical Prospecting, 2022, 57 (06): 1265-1275+1255. |
17. | Zhuang Fuzhen, Luo ping, He qing, Shi zhongzhi. Survey on Transfer Learning Research [J]. Journal of Software, 2015, 26 (01): 26-39. |