«Automation and Informatization of the fuel and energy complex»

Modern approaches to addressing the problem of automated geological correlation

UDC: 004.032.26:519.857:551.7.02
DOI: -

Authors:

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

Keywords: geological correlation, dynamic time warping, machine-learning, deep learning

Annotation:

The authors of the article focus on analyzing automated approaches for addressing the challenge of geological correlation, which is fundamental for studying the internal structure of deposits and creating accurate geological models. The advantages and limitations of traditional approaches, such as cross-correlation and dynamic time warping (DTW) as well as their modifications are detailed. Modern neural-network solutions are considered, such as convolutional and recurrent architectures and attention mechanism; particular emphasis is placed on their integration with DTW algorithms. Additionally, the authors of the article discuss the problems related to the lack of well-labeled data, the necessity of their preliminary preparation, and challenges arising during correlation under conditions of changing layer thickness and faults. In conclusion, the authors of the article highlight the importance of creating comprehensive automated systems and software solutions for solving geological correlation challenges and emphasize the most promising areas of their further improvement.

Bibliography:

1. Rudman A.J., Lankston R.W. Stratigraphic Correlation of Well Logs by Computer Techniques // AAPG Bulletin. – 1973. – Vol. 57, Issue 3. – P. 577–588. – DOI: 10.1306/819a4306-16c5-11d7-8645000102c1865d
2. Mann C.J., Dowell Jr T.P.L. Quantitative lithostratigraphic correlation of subsurface sequences // Computers & Geosciences. – 1978. – Vol. 4, Issue 3. – P. 295–306. – DOI: 10.1016/0098-3004(78)90064-X
3. Otechestvennyy kompleks AutoCorr dlya vypolneniya korrelyatsii razrezov skvazhin v avtomaticheskom i poluavtomaticheskom rezhimakh, modelirovaniya zalezhey, podscheta zapasov UV i proektirovaniya razrabotki / I.S. Gutman, I.Yu. Balaban, G.P. Kuznetsova [i dr.] // Vestn. TsKR ROSNEDRA. – 2005. – № 2. – S. 51–62.
4. Kovalevskiy E.V., Gogonenkov G.N., Perepechkin M.V. Utochnenie geologicheskikh modeley posredstvom ispol'zovaniya avtomaticheskoy korrelyatsii skvazhin // Nedropol'zovanie XXI vek. – 2007. – № 4. – S. 28–31.
5. Le Nir I., Van Gysel N., Rossi D. Cross-Section Construction from Automated Well Log Correlation: A Dynamic Programming Approach Using Multiple Well Logs // SPWLA 39th Annual Logging Symposium, Keystone, Colorado, May 1998. – Society of Petrophysicists and Well-Log Analysts, 1998.
6. Zoraster S., Paruchuri R., Darby S. Curve Alignment for Well-to-Well Log Correlation // SPE Annual Technical Conf. and Exhibition, Houston, Texas, Sept. 26–29, 2004. – DOI: 10.2118/90471-MS
7. Grant C.W., Bashore W.M., Compton S. Rapid Reservoir Modeling with Automated Tops Correlation // Unconventional Resources Technology Conf., Houston, Texas, July 23–25, 2018. – P. 4004–4019. – DOI: 10.15530/urtec-2018-2904037
8. Burlakov N.S. Matematicheskoe, algoritmicheskoe i programmnoe obespechenie dlya identifikatsii strukturnykh ob"ektov po kompleksu raznorodnykh geologo-geofizicheskikh dannykh: dis. … kand. tekhn. nauk: 05.13.11. – M., 2014. – 243 s.
9. Razrabotka podkhodov k avtomatizirovannoy vnutriplastovoy korrelyatsii po dannym geofizicheskikh issledovaniy skvazhin s primeneniem mashinnogo obucheniya / I.D. Latypov, A.V. Markov, N.A. Evgrafov, L.R. Shagimardanova // Ekspozitsiya Neft' Gaz. – 2024. – № 4(105). – S. 47–51. – DOI: 10.24412/2076-6785-2024-4-47-51
10. Wheeler L., Hale D. Simultaneous correlation of multiple well logs // SEG Technical Program Expanded Abstracts 2014, Denver, Colorado, Oct. 26–31, 2014. – Society of Exploration Geophysicists, 2014. – P. 618–622. – DOI: 10.1190/SEGAM2014-0227.1
11. Incremental correlation of multiple well logs following geologically optimal neighbors / Wu Xinming, Shi Yunzhi, S. Fomel, Li Fangyu // 2017 SEG Int. Exposition and Annual Meeting. – Society of Exploration Geophysicists, 2017. – P. 1945–1949. – DOI: 10.1190/segam2017-17779046.1
12. Prakticheskaya realizatsiya primeneniya neyrosetevykh modeley dlya modelirovaniya slozhnykh gazotransportnykh sistem bol'shoy razmernosti / N.A. Kislenko, S.N. Pankratov, V.V. Dedkova [i dr.] // Avtomatizatsiya i informatizatsiya TEK. – 2024. – № 9(614). – S. 33–41.
13. Kanonirov A.P., Zakharov A.A. Obnaruzhenie ploskostey tektonicheskikh narusheniy metodami samokontroliruemogo obucheniya // Avtomatizatsiya i informatizatsiya TEK. – 2024. – № 11(616). – S. 83–89.
14. Luthi S.M., Bryant I.D. Well-log correlation using a back-propagation neural network // Mathematical Geology. – 1997. – Vol. 29, Issue 3. – P. 413–425. – DOI: 10.1007/BF02769643
15. Sharafutdinov T.R., Shaybakov R.A. Aprobatsiya algoritma avtokorrelyatsii dannykh geofizicheskikh issledovaniy skvazhin na primere otlozheniy achimovskoy tolshchi Pravdinskogo mestorozhdeniya // Nauch.-tekhn. vestn. OAO "NK "Rosneft'". – 2012. – № 1(26). – S. 18–22.
16. Machine-learning methods in Geoscience / H. Maniar, S. Ryali, M.S. Kulkarni, A. Abubakar // SEG Int. Exposition and Annual Meeting, Anaheim, California, USA, October 2018. – Society of Exploration Geophysicists, 2018. – P. 4638–4642. – DOI: 10.1190/SEGAM2018-2997218.1
17. Deep-Learning-Based Automated Stratigraphic Correlation / Y. Tokpanov, J. Smith, Ma Zheren [et al.] // SPE Annual Technical Conf. and Exhibition, Oct. 26–29, 2020, Virtual. – DOI: 10.2118/201459-ms
18. Automated stratigraphic correlation of well logs using Attention Based Dense Network / Yang Yang, Wang Jingyu, Li Zhuo [et al.] // Artificial Intelligence in Geosciences. – 2023. – Vol. 4. – P. 128–136. – DOI: 10.1016/j.aiig.2023.09.001
19. Automatic Well-Log Depth Shift with Multilevel Wavelet Decomposition Network and Dynamic Time Warping / Meng Fan, Fan Xiangyu, Chen Siyuan [et al.] // Geoenergy Science and Engineering. – 2024. – Vol. 246. – P. 213583. – DOI: 10.1016/j.geoen.2024.213583
20. Well Logging Stratigraphic Correlation Algorithm Based on Semantic Segmentation / Wang Cai-zhi, Wei Xing-yun, Pan Hai-xia [et al.] // Applied Geophysics. – 2024. – Vol. 21, Issue 4. – P. 650– 666. – DOI: 10.1007/s11770-024-1085-8