Applicability and Application of Machine Learning Algorithm in Logging Interpretation

CHENG Xi; ZHOU Jun; FU Haicheng; LUO Xiongmin

doi:10.12401/j.nwg.2023029

2023 Vol. 56, No. 4

Article Contents

Article navigation > Northwestern Geology > 2023 > 56(4): 336-348

Next Article Previous Article

CHENG Xi, ZHOU Jun, FU Haicheng, LUO Xiongmin. 2023. Applicability and Application of Machine Learning Algorithm in Logging Interpretation. Northwestern Geology, 56(4): 336-348. doi: 10.12401/j.nwg.2023029

Citation:

CHENG Xi, ZHOU Jun, FU Haicheng, LUO Xiongmin. 2023. Applicability and Application of Machine Learning Algorithm in Logging Interpretation. Northwestern Geology, 56(4): 336-348. doi: 10.12401/j.nwg.2023029

Applicability and Application of Machine Learning Algorithm in Logging Interpretation

1.
College of Earth Science and Engineering, Xi’an Shiyou University, Xi’an 710065, Shaanxi, China
2.
Academician Expert Workstation, Xi’an Shiyou University, Xi’an 710065, Shaanxi, China
3.
China National Petroleum Group Logging Co. Ltd, Xi’an 710075, Shaanxi, China
4.
China National Petroleum Group Exploration and Development Research Institute, Beijing 100083, China

Received Date: 09 May 2022

Revised Date: 03 March 2023

Publish Date: 20 August 2023

Abstract

Abstract

Machine learning, especially the development of deep neural network learning algorithms, is changing the way people discover knowledge. As the oil and gas industry is shifting to unconventional oil and gas exploration and development, the evaluation and interpretation model based on limited petrophysical parameters is difficult to meet the complex lithology and structure of unconventional reservoirs, which poses a great challenge to the traditional logging evaluation technology. Oil & gas artificial Intelligence (Oil & Gas AI), based on oil and gas big data, machine learning algorithms, oil and gas application scenarios, has greatly promoted the application and development of AI technology in various professionals of oil and gas industry. According to the data–driven petrophyical knowledge discovery, and the research idea of the “data–algorithm–platform–knowledge–application scenario”, firstly we analyzed the inherent attributes, principles, quality control, hardware requirements, learning model selection, testing, and performance evaluation implementation process for the machine learning algorithm. The tree graph of the applicability of the machine learning algorithm in logging is summarized, especially the relationship between the application potential and machine learning algorithm in oil and gas logging. These applications include simulation methods for data correction, petrophysical analysis for data calibration, logging data quality control, integrated evaluation, and reservoir monitoring. The study case shows that machine learning algorithms in lithology identification and reservoir evaluation, classification, mechanics, and reservoir evaluation based on the data link across multiple physical properties of petrophysics compared with traditional well logging method, which break through the limitation of experimental conditions and physical properties and has interdisciplinary and comprehensive characterization, had obvious advantages and potentials in well logging technology.
- machine learning algorithm /
- logging big data /
- lithology identification /
- reservoir evaluation

FullText(HTML)

References

[1]	程希, 程宇雪, 程佳豪, 等. 基于机器学习与大数据技术的地球物理测井系统[J]. 西安石油大学学报(自然科学版), 2019, 06: 108-116 Google Scholar CHENG Xi, CHENG Yuxue, CHENG Jiahao, et al. Geophysical logging system based on machine learning and big data technology[J]. Journal of Xi'an Shiyou University ( Natural Science Edition) , 2019, 34( 6) : 108-116. Google Scholar
[2]	程希, 宋新爱, 李国军, 等. 数据模型与物理模拟驱动的人工智能测井[J]. 测井技术, 2021, 45(03): 233-329 doi: 10.16489/j.issn.1004-1338.2021.03.002 CrossRef Google Scholar CHENG Xi, SONG Xin’ai, LI Guojun, et al. Artificial intelligence logging driven by data modeling and physical simulation[J]. Logging Technology, 2021, 45(03): 233-329. doi: 10.16489/j.issn.1004-1338.2021.03.002 CrossRef Google Scholar
[3]	杜金虎, 时付更, 杨剑锋, 等. 中国石油上游业务信息化建设总体蓝图[J]. 中国石油勘探, 2020, 25 (5): 1-8 doi: 10.3969/j.issn.1672-7703.2020.05.001 CrossRef Google Scholar DU Jinhu, SHI Fuqing, YANG Jianfeng, et al. A general blueprint for upstream business information construction in China[J]. China Petroleum Exploration, 2020, 25 (5): 1-8. doi: 10.3969/j.issn.1672-7703.2020.05.001 CrossRef Google Scholar
[4]	韩海辉, 李健强, 易欢, 等. 遥感技术在西北地质调查中的应用及展望[J]. 西北地质, 2022, 55(3): 155-169. doi: 10.19751/j.cnki.61-1149/p.2022.03.012 CrossRef Google Scholar HAN Haihui, LI Jianqiang, YI Huan, et al. Application and Prospect of Remote Sensing Technology in Geological Survey of Northwest China[J]. Northwestern Geology, 2022, 55(3): 155-169 doi: 10.19751/j.cnki.61-1149/p.2022.03.012 CrossRef Google Scholar
[5]	刘梁, 石卫, 张晓平, 等. 基于高斯混合聚类算法的西安市人工填土空间分布研究[J]. 西北地质, 2022, 55(2): 298-304 doi: 10.19751/j.cnki.61-1149/p.2022.02.027 CrossRef Google Scholar LIU Liang, SHI Wei, ZHANG Xiaoping, et al. Research on Spatial Distribution of Artificial Fill in Xi’an Based on Gaussian Mixture Clustering Algorithm[J]. Northwestern Geology, 2022, 55(2): 298-304 doi: 10.19751/j.cnki.61-1149/p.2022.02.027 CrossRef Google Scholar
[6]	李宁, 徐彬森, 武宏亮, 等. 人工智能在测井地层评价中的应用现状及前景[J]. 石油学报, 2021, 42(4): 508-522 doi: 10.1038/s41401-020-0474-7 CrossRef Google Scholar LI Ning, XU Binsen, WU Hongliang, et al. Application status and prospects of artificialintelligence in well logging and formation evaluation[J]. Acta Petrolei Sinica, 2021, 42( 4): 508-522. doi: 10.1038/s41401-020-0474-7 CrossRef Google Scholar
[7]	李志忠, 卫征, 陈霄燕, 等. 新型对地观测技术与地球健康体检[J]. 西北地质, 2022, 55(2): 56-70. Google Scholar LI Zhizhong, WEI Zheng, CHEN Xiaoyan, et al. New Earth Observation Technology and Earth Health Examination[J]. Northwestern Geology, 2022, 55(2): 56−70. Google Scholar
[8]	罗刚, 肖立志, 史燕青, 等. 基于机器学习的致密储层流体识别方法研究[J]. 石油科学通报, 2022, 7(01): 24-33 doi: 10.3969/j.issn.2096-1693.2022.01.003 CrossRef Google Scholar LUO Gang, XIAO Lizhi, SHI Yanqing, et al. Machine learning for reservoir fluid identification with logs. Petroleum Science Bulletin, 2022, 01: 24-33. doi:10.3969/j.issn.2096-1693.2022.01.003 CrossRef Google Scholar
[9]	匡立春, 刘合, 任义丽, 等. 人工智能在石油勘探开发领域的应用现状与发展趋势[J]. 石油勘探与开发, 2021, 48 (1): 1-11 doi: 10.11698/PED.2021.01.01 CrossRef Google Scholar KUANG Lichun, LIU He, REN Yili, et al. Application and development trend of artificial intelligence in petroleum exploration and development [J]. Petroleum Exploration and Development, 2021, 48(1): 1-11. doi: 10.11698/PED.2021.01.01 CrossRef Google Scholar
[10]	赵丽莎, 史永彬, 金玮, 等. 基于梦想云的测井智能化解释应用研究[J]. 中国石油勘探, 2020, 25(5): 97-103 doi: 10.3969/j.issn.1672-7703.2020.05.013 CrossRef Google Scholar ZHAO Lisa, SHI Yongbin, JIN Wei, et al. Research on the application of intelligent interpretation of logging based on dream cloud[J]. China Petroleum Exploration, 2020, 25(5): 97-103. doi: 10.3969/j.issn.1672-7703.2020.05.013 CrossRef Google Scholar
[11]	邹文波. 人工智能研究现状及其在测井领域的应用[J]. 测井技术, 2020, 44(04): 323-328 doi: 10.16489/j.issn.1004-1338.2020.04.001 CrossRef Google Scholar ZOU Wenbo. Current status of artificial intelligence research and its application in the field of well logging[J]. Logging Technology, 2020, 44(04): 323-328. doi: 10.16489/j.issn.1004-1338.2020.04.001 CrossRef Google Scholar
[12]	Akkurt R, Miller M, Hodenfield B, et al. . Machine Learning for Well Log Normalization[C]. Society of Petroleum Engineers, 2019. Google Scholar
[13]	Gupta I, Devegowda D, Jayaram V, et al. Machine Learning Regressors and their Metrics to Predict Synthetic Sonic and Brittle Zones [C]. Unconventional Resources Technology Conference, 2019 Google Scholar
[14]	Karianne J, Paul A, Maarten V, et al. Machine learning for data-driven discovery in solid Earth geoscience[J]. Science, 2019, 363(6433): 1299. Google Scholar
[15]	Kuvichko A, Spesivtsev P, Zyuzin V, et al. Field-Scale Automatic Facies Classification Using Machine Learning Algorithms[C]. Society of Petroleum Engineers, 2019. Google Scholar
[16]	Markus R, Gustau C, Bjorn S, et al. Deep learning and process understanding for data-driven Earth system science[J]. Nature, 2019, 556(7743): 195-204. Google Scholar
[17]	Oruganti Y D, Yuan P, Inanc F, et al. Role of Machine Learning in Building Models for Gas Saturation Prediction[C]. Society of Petrophysicists and Well-Log Analysts, 2019. Google Scholar
[18]	Xu C, Misra S, Srinivasan P, Ma S. When Petrophysics Meets Big Data: What can Machine Do? [C]. Society of Petroleum Engineers, 2019. Google Scholar
[19]	Wu H H, Pan L, Ma J, et al. Enhanced Reservoir Geosteering and Geomapping from Refined Models of Ultra-Deep LWD Resistivity Inversions Using Machine-Learning Algorithms[C]. Society of Petrophysicists and Well-Log Analysts, 2019. Google Scholar