Development Plan for Intelligent Geophysical Prospecting Technology of Applied Geophysical+AI

doi:10.3969/j.issn.1002-302x.2019.05.008

Abstract

Abstract: Technological innovation has become the main growth method for global petroleum industry to improve economic performance. Intelligent technology becomes a key engine for transformation of enterprises. This paper makes an indepth investigation of the present conditions for combination of current geophysical technology with artificial intelligence. It points out that the “applied geophysical + AI” intelligent geophysical prospecting is under its preliminary stage, but it was under rapid development in recent two years. The paper also comes up with the suggestions on future development of intelligent geophysical prospecting. First of all, the efforts should be focused on top design, configuration of the sharing and collaborative intelligent geophysical platform to bring about an ecological system for healthy intelligent geophysical technological development. Secondly, the development plan should be executed “step by step with the pilot spots selected”, while the CNPC intelligent geophysical system is under construction at various levels. Thirdly, it is necessary to set up the professional teams for geophysical intelligence, establish a good talents system to lay the foundation for CNPC to construct intelligent oilfields and transparent oilfields so that the company’s business development can be dominated by technology instead of capitals and resources.

摘要： 科技创新已成为全球石油工业提升效益的主要增长方式，智能化技术成为企业转型发展的核心推动力。对当前物探技术与人工智能相结合的现状做了深度调研，指出以“应用地球物理+AI”的智能物探整体处于起始阶段，近两年发展迅猛，对智能物探未来发展策略提出了建议：一是做好顶层设计，构建共享、共建的智能物探平台，形成良好的智能物探技术发展生态体系；二是采用“试点先行、逐步展开” 的发展战略，分步骤、分层次地开展中国石油智能物探体系建设，构建良好的人工智能发展技术体系；三是培养聚集物探智能化人才团队，构建良好的人才体系。为中国石油实现智能油田、透明油田，推动从资本主导、资源主导逐渐转向技术主导的业务转型奠定基础。

关键词: 人工智能, 应用地球物理+AI, 智能物探, 智能油田, 透明油田

CLC Number:

Yang Wuyang, Wei Xinjian, He Xin. Development Plan for Intelligent Geophysical Prospecting Technology of Applied Geophysical+AI[J]. Petroleum Science and Technology Forum, 2019, 38(5): 40-47.

杨午阳　魏新建　何欣. 应用地球物理+AI 的智能化物探技术发展策略[J]. 石油科技论坛, 2019, 38(5): 40-47.

References

[1] 刘伟, 闫娜. 人工智能在石油工程领域应用及影响[J]. 石油科技论坛,2018,37(4):32-40. Liu Wei, Yan Na. Application and influence of artificial intelligence in petroleum engineering area[J]. Oil Forum, 2018, 37(4): 32-40.
[2] 杨金华, 邱茂鑫. 郝红娜, 等. 智能化——油气工业发展大趋势[J]. 石油科技论坛,2016,35(6):36-42. Yang Jinhua, Qiu Maoxin, Hao Hongna, et al. Intelligence - Oil and gas industrial development trend[J]. Oil Forum, 2016, 35(6): 36-42.
[3] 曲晓强, 肖贞雄. 低油价时期全球物探行业挑战与机遇[J]. 石油科技论坛,2017,36(3):55-67. Qu Xiaoqiang, Xiao Zhenxiong. Challenges and opportunities for global geophysical prospecting industry during low oil price period[J]. Oil Forum, 2017, 36(3): 55-59.
[4] 杨金华, 李晓光, 张焕芝, 等. 油气勘探开发工程新技术发展思考[J]. 国际石油经济,2018,26(8):1-8. Yang Jinhua, Li Xiaoguang, Zhang Huanzhi, et al. Thinking on the development of new technology in oil and gas E&D engineering[J]. International Petroleum Economics,2018,26(8):1-8.
[5] 李晓阳, 韩赢. 石油地质勘探技术的创新及其发展[J]. 中国石油和化工标准与质量,2018(2):148-149. Li Xiaoyang, Han Ying. Petroleum geological exploration technological innovation and development[J]. China Petroleum and Chemical Standard and Quality,2018,38(2):148-149.
[6] 郑寿春, 林萍, 宋其, 等. 试论我国石油产业的创新机制[J]. 西南石油大学学报,2019,21(2):12-17. Zheng Shouchun, Lin Ping, Song Qi, et al. Innovation mechanism of China’s petroleum industry[J]. Journal of Southwest Petroleum University (Social Sciences Edition),2019,21(2):12-17.
[7] Dekuan Chang, Wuyang Yang, Xueshan Yong, et al. Seismic fault detection using deep learning technology[C]. SEG International Geophysical Conference, 2018: 1770-1773.
[8] Guitton A. 3D convolutional neural networks for fault interpretation[C]. 80th EAGE Conference and Exhibition 2018, 2018.
[9] Zhao T, Mukhopadhyay P. A fault detection workflow using deep learning and image processing[C]. SEG Technical Program Expanded Abstracts 2018. Society of Exploration Geophysicists, 2018: 1966-1970.
[10] Xing L, Aarre V, Theoharis T. Improving faults continuity for extraction by transfer learning based on synthetic data[C]. SEG Technical Program Expanded Abstracts 2018. Society of Exploration Geophysicists, 2018: 1961-1965.
[11] Di H, Wang Z, AlRegib G. Seismic fault detection from post-stack amplitude by convolutional neural networks[C]. 80th EAGE Conference and Exhibition 2018,2018.
[12] Wu X, Shi Y, Fomel S, et al. Convolutional neural networks for fault interpretation in seismic images[C]. SEG Technical Program Expanded Abstracts 2018. Society of Exploration Geophysicists, 2018: 1946-1950.
[13] Zhao T, Li F, Marfurt K J. Constraining self-organizing map facies analysis with stratigraphy: An approach to increase the credibility in automatic seismic facies classification [J]. Interpretation, 2017, 5(2): 163-171.
[14] Duan Y, Zheng X, Hu L. Seismic facies analysis based on deep encoder clustering[M]. SEG Technical Program Expanded Abstracts 2018. Society of Exploration Geophysicists, 2018: 2152-2156.
[15] Zhao T, Li F, Marfurt K. Automated input attribute weighting for unsupervised seismic facies analysis[C]. SEG Technical Program Expanded Abstracts 2017. Society of Exploration Geophysicists, 2017: 2122-2126.
[16] Zhang P Y, Sun J M, Jiang Y J, et al. Deep learning method for lithology identification from borehole images[C]. 79th EAGE Conference and Exhibition 2017, 2017.
[17] Emelyanova I, Pervukhina M, Clennell M, et al. Unsupervised identification of electrofacies employing machine learning[C]. 79th EAGE Conference and Exhibition 2017-Workshops, 2017.
[18] Bestagini P, Lipari V, Tubaro S. A machine learning approach to facies classification using well logs[M]. SEG Technical Program Expanded Abstracts 2017. Society of Exploration Geophysicists, 2017: 2137-2142.
[19] Wu P Y, Jain V, Kulkarni M S, et al. Machine learning-based method for automated well-log processing and interpretation[C]. SEG Technical Program Expanded Abstracts 2018. Society of Exploration Geophysicists, 2018: 2041-2045.
[20] Haishan Li, Wuyang Yang and Xueshan Yong. Deep learning for ground-roll noise attenuation. SEG International Exposition and 88th Annual Meeting, 2018:1981-1985.
[21] Chang D K, Yang W Y, Yong X S, Li H S. Generative adversarial networks for seismic data interpolation [C]//SEG 2018 Workshop: Reservoir Geophysics, Beijing, China, September, 2018. Society of Exploration Geophysicists and the Chinese Geophysical Society, 2018: 52-54.