Elaboração da interpretação automática de fraturas nos perfis de imagem utilizando a Inteligência Artificial
DOI:
https://doi.org/10.21712/lajer.2023.v10.n2.p13-22Keywords:
Artificial Intelligence, Machine Learning, Oil and Gas, Fractures, Automatic Interpretation, Image Processing, Support Vector Machine (SVM)Abstract
Artificial Intelligence (AI) is a data processing approach that uses information analysis, pattern detection and predictions with little human intervention. The field of AI encompasses several subsets, with emphasis on machine learning (ML), which has great potential in the oil and gas industry, especially in data analysis and interpretation. ML algorithms such as Support Vector Machine (SVM), Artificial Neural Networks (ANN), Deep Learning (DL) and Genetic Algorithms (GA) have been successfully applied in the oil industry. The petroleum industry faces significant technological challenges, given its complexity. Geological formation analysis through logging is crucial to improve the assessment of rock formations, minimize damage and reduce costs when drilling wells. Furthermore, the identification of natural and induced fractures is fundamental to understanding reservoirs, especially non-disruptive ones. The study of fractures can be divided into qualitative and quantitative aspects, which involves the identification and detailed analysis of fractures in reservoirs. AI, especially ML, can be applied to analyze the geometry, orientation, density and complexity of fractures, classifying them into different types such as induced and natural fractures. The objective of this study is to automate the interpretation of flaws in image profiles through the use of Artificial Intelligence, improving the efficiency, accuracy and speed of this procedure. The Python programming language and the Jupyter Notebook tool were used to develop the AI program. Data and images were collected, which were processed and analyzed using libraries such as OpenCV, Numpy and Sklearn.svm. The results obtained demonstrate the effectiveness of AI in identifying fractures in different types of image profiles, including acoustic images, resistivity images, and other logging tools. Artificial Intelligence was able to accurately identify natural fractures, low-amplitude fractures, internal fractures and other geological events. However, the success of AI depends on the quality and quantity of training data, and challenges such as geological complexity and image resolution still need to be overcome. The application of AI in the automatic interpretation of fractures in images in the petroleum industry offers significant improvements in the efficiency and speed of the process, contributing to the understanding of the characteristics of rock formations.
Downloads
References
Adams, JT e Dart, C (1998) “The appearance of potential sealing faults on borehole images,” Geological Society special publication, 147(1), pp. 71–86. doi: 10.1144/gsl.sp.1998.147.01.05 DOI: https://doi.org/10.1144/GSL.SP.1998.147.01.05
Ali, JK. (1994) “Neural networks: A new tool for the petroleum industry?,” in All Days. SPE. DOI: https://doi.org/10.2118/27561-MS
Alizadeh, M, Movahed, Z e Junin, RB (no date) In-situ stress analysis using image logs, Tsijournals.com. Available at: https://www.tsijournals.com/articles/insitu-stress-analysis-using-image-logs.pdf (Acesso em: 26 de setembro de 2023).
Ameen, MS, MacPherson, K, Al-Marhoon, MI, e Rahim, Z (2012). Diverse fracture properties and their impact on performance in conventional and tight-gas reservoirs, Saudi Arabia: The Unayzah, South Haradh case study. AAPG Bulletin, 96(3), 459–492. https://doi.org/10.1306/06011110148 (Acesso em: 27 de setembro de2023). DOI: https://doi.org/10.1306/06011110148
Brekke, H, MacEachern, JA, Roenitz, T, e Dastgard, SE (2017). The use of microresistivity image logs for facies interpretations: An example in point-bar deposits of the McMurray Formation, Alberta, Canada. AAPG Bulletin, 101(05), 655–682. doi:10.1306/08241616014 DOI: https://doi.org/10.1306/08241616014
Cuddy, S (2021) “The benefits and dangers of using artificial intelligence in petrophysics,” Artificial Intelligence in Geosciences, 2, pp. 1–10. doi: 10.1016/j.aiig.2021.04.001. DOI: https://doi.org/10.1016/j.aiig.2021.04.001
Donselaar, ME. e Schmidt, JM (2005) “Integration of outcrop and borehole image logs for high‐resolution facies interpretation: example from a fluvial fan in the Ebro Basin, Spain,” Sedimentology, 52(5), pp. 1021–1042. doi: 10.1111/j.1365-3091.2005.00737.x DOI: https://doi.org/10.1111/j.1365-3091.2005.00737.x
Donselaar, ME e Schmidt, JM (2010) “The application of borehole image logs to fluvial facies interpretation,” in Dipmeter and Borehole Image Log Technology. American Association of Petroleum Geologists, pp. 1–22. doi: https://doi.org/10.1306/13181283M923415 DOI: https://doi.org/10.1306/13181283M923415
Fatah, TYA (2020) “Análise de zonas de fraturas através de perfis de imagem em poços do pré-sal da Bacia de Santos.” Available at: https://oasisbr.ibict.br/vufind/Record/UFF-2_576d4b9b9c807be6630881af06ed96ca (Acesso em: 27 de setembro de 2023).
Félix, FA, Nascimento, ES do e Borba, C (2013) “Perfis de imagem de poços de petróleo”, Caderno de Graduação - Ciências Exatas e Tecnológicas - UNIT - SERGIPE, 1(2), p. 61–78. Disponível em: https://periodicos.set.edu.br/cadernoexatas/article/view/525 (Acesso em: 27 de setembro de 2023).
Folkestad, A, Veselovsky, Z e Roberts, P (2012) “Utilising borehole image logs to interpret delta to estuarine system: A case study of the subsurface Lower Jurassic Cook Formation in the Norwegian northern North Sea,” Marine and petroleum geology, 29(1), pp. 255–275. doi: 10.1016/j.marpetgeo.2011.07.008. DOI: https://doi.org/10.1016/j.marpetgeo.2011.07.008
Hanga, K M. e Kovalchuk, Y (2019) “Machine learning and multi-agent systems in oil and gas industry applications: A survey,” Computer science review, 34(100191), p. 100191. doi: 10.1016/j.cosrev.2019.08.002 DOI: https://doi.org/10.1016/j.cosrev.2019.08.002
Ja'fari, A, Kadkhodaie-Ilkhchi, A, Sharghi, Y, e Ghanavati, K (2012) Fracture density estimation from petrophysical log data using the adaptive neuro-fuzzy inference system. Journal of Geophysics and Engineering, 9(1), 105-114. doi: https://doi.org/10.1088/1742-2132/9/1/013 DOI: https://doi.org/10.1088/1742-2132/9/1/013
Roedel Júnior, J (2014). Aplicação dos Perfis de Imagem na Indústria do Petróleo. SILO of research documents. Available at: https://silo.tips/download/aplicaao-dos-perfis-de-imagem-na-industria-do-petroleo (Acesso em: 27 de setembro de 2023).
Lagraba, JOP, Hansen, SM, Spalburg, M, e Helmy, M (2010). Borehole image tool design, value of information, and tool selection. Dipmeter and borehole image log technology, 92, 15-38. doi: https://doi.org/10.1306/13181275M923403 DOI: https://doi.org/10.1306/13181275M923403
Lai, J, Wang, G, Fan, Z, Wang, Z, Chen, J, Zhou, Z, e Xiao, C (2017). Fracture detection in oil-based drilling mud using a combination of borehole image and sonic logs. Marine and Petroleum Geology, 84, 195-214. doi: https://doi.org/10.1016/j.marpetgeo.2017.03.035 DOI: https://doi.org/10.1016/j.marpetgeo.2017.03.035
Lechner, JP. e Zangl, G (2005) “Treating uncertainties in reservoir performance prediction with neural networks,” in All Days. SPE, p. SPE-94357-MS. DOI: https://doi.org/10.2118/94357-MS
Li, H, Yu, H, Cao, N, Tian, H, e Cheng, S (2021) “Applications of artificial intelligence in oil and gas development,” Archives of Computational Methods in Engineering. State of the Art Reviews, 28(3), pp. 937–949. doi: 10.1007/s11831-020-09402-8 DOI: https://doi.org/10.1007/s11831-020-09402-8
Liu, H (2017) Principles and applications of well logging. Berlin, Heidelberg: Springer Berlin Heidelberg.
Liu, J, Ding, W, Wang, R, Yin, S, Yang, H, e Gu, Y (2017) “Simulation of paleotectonic stress fields and quantitative prediction of multi-period fractures in shale reservoirs: A case study of the Niutitang Formation in the Lower Cambrian in the Cen’gong block, South China,” Marine and petroleum geology, 84, pp. 289–310. doi: 10.1016/j.marpetgeo.2017.04.004 DOI: https://doi.org/10.1016/j.marpetgeo.2017.04.004
Lyu, W, Zeng, L, Liu, Z, Liu, G, e Zu, K. (2016) “Fracture responses of conventional logs in tight-oil sandstones: A case study of the Upper Triassic Yanchang Formation in southwest Ordos Basin, China,” AAPG bulletin, 100(09), pp. 1399–1417. doi: 10.1306/04041615129 DOI: https://doi.org/10.1306/04041615129
Lyu, W, Zeng, L, Zhang, B, Miao, F, Lyu, P, e Dong, S (2017) “Influence of natural fractures on gas accumulation in the Upper Triassic tight gas sandstones in the northwestern Sichuan Basin, China,” Marine and petroleum geology, 83, pp. 60–72. doi: 10.1016/j.marpetgeo.2017.03.004 DOI: https://doi.org/10.1016/j.marpetgeo.2017.03.004
Muniz, MC e Bosence, DWJ (2015) “Pre-salt microbialites from the Campos Basin (offshore Brazil): image log facies, facies model and cyclicity in lacustrine carbonates,” Geological Society special publication, 418(1), pp. 221–242. doi: 10.1144/sp418.10 DOI: https://doi.org/10.1144/SP418.10
Paes, M da R (2016) “Aplicação do sistema LWD em poços horizontais.” Available at: https://app.uff.br/riuff;/handle/1/1438 (Acesso em: 27 de setembro de 2023).
Prioul, R, Donald, A, Koepsell, R, Marzouki, ZE, e Bratton, T (2007) “Forward modeling of fracture-induced sonic anisotropy using a combination of borehole image and sonic logs,” Geophysics, 72(4), pp. E135–E147. doi: 10.1190/1.2734546 DOI: https://doi.org/10.1190/1.2734546
Support vector machine (SVM) explained (no date) Mathworks.com. Available at: https://www.mathworks.com/discovery/support-vector-machine.html (Acesso em: 28 de outubro de 2023).
Tokhmchi, B, Memarian, H e Rezaee, MR (2010) “Estimation of the fracture density in fractured zones using petrophysical logs,” Journal of petroleum science & engineering, 72(1–2), pp. 206–213. doi: 10.1016/j.petrol.2010.03.018 DOI: https://doi.org/10.1016/j.petrol.2010.03.018
Wennberg, OP, Ramalho, FDO, Mafia, MV, Lapponi, F, Chandler, AS, Cartesio, LG, e Hunt, DW (2023) “The characteristics of natural open fractures in acoustic borehole image logs from the pre-salt Barra Velha formation, Santos Basin, Brazil,” Journal of structural geology, 167(104794), p. 104794. doi: 10.1016/j.jsg.2023.104794 DOI: https://doi.org/10.1016/j.jsg.2023.104794
Wilson, ME, Lewis, D, Holland, D, Hombo, L, e Goldberg, A. (2013) “Development of a Papua New Guinean onshore carbonate reservoir: A comparative borehole image (FMI) and petrographic evaluation,” Marine and petroleum geology, 44, pp. 164–195. doi: 10.1016/j.marpetgeo.2013.02.018 DOI: https://doi.org/10.1016/j.marpetgeo.2013.02.018
Xu, C, Cronin, TP, McGinness, TE, e Steer, B (2009) “Middle Atokan sediment gravity flows in the Red Oak field, Arkoma Basin, Oklahoma: A sedimentary analysis using electrical borehole images and wireline logs,” AAPG bulletin, 93(1), pp. 1–29. doi: 10.1306/09030808054 DOI: https://doi.org/10.1306/09030808054
Zeng, L (2010) “Microfracturing in the Upper Triassic Sichuan Basin tight-gas sandstones: Tectonic, overpressure, and diagenetic origins,” AAPG bulletin, 94(12), pp. 1811–1825. doi: 10.1306/06301009191 DOI: https://doi.org/10.1306/06301009191
Zoback, MD (2007) Reservoir Geomechanics. Cambridge University Press, New York, 3-55. DOI: https://doi.org/10.1017/CBO9780511586477
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 Latin American Journal of Energy Research
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
O autor, no ato da submissão do artigo, transfere o direito autoral ao periódico.
