Abstract：Deep learning technology has given strong impetus to the development of interpretation techno-logy for traditional seismic data, which has spawned a large number of intelligent interpretation technologies. However, limited research achievements can be applied in large-scale production. This study focuses on the industrial implementation of intelligent interpretation technologies based on deep learning for low-to-medium signal-to-noise ratio (SNR) data. Upon the development of the intelligent software development platform, an intelligent horizon interpretation and fault detection technology with strong data adaptability is formed, which plays an important role in the horizon interpretation of large-scale continuous survey data and the fine description of complex fault blocks. The efficiency of horizon interpretation by this method is increased by a factor of 9-21 compared with that of the traditional automatic interpretation techniques, and the accuracy of fault identification is significantly improved in comparison with that of classic techniques such as coherence and curvature. It can completely replace the original automatic interpretation modules and achieve the intelligent transformation of structural interpretation.
杨平, 宋强功, 詹仕凡, 陶春峰, 郭锐, 朱冬临. 基于深度学习的高效构造解释技术研发及工业化应用[J]. 石油地球物理勘探, 2022, 57(6): 1265-1275.
YANG Ping, SONG Qianggong, ZHAN Shifan, TAO Chunfeng, GUO Rui, ZHU Donglin. Research and industrial application of efficient structural interpretation technology based on deep learning. Oil Geophysical Prospecting, 2022, 57(6): 1265-1275.
吕文晶,陈劲,刘进. 第四次工业革命与人工智能创新[J]. 高等工程教育研究,2018(3): 63-70.LÜ Wenjing,CHEN Jin,LIU Jin. The fourth industrial revolution and artificial intelligence innovation[J]. Research in Higher Education of Enginee-ring,2018(3): 63-70.
[2]
中国信息通信研究院,中国人工智能产业发展联盟. 深度学习技术下的人工智能时代[J]. 大数据时代,2021(6): 56-76.CAICT,AIIA. The era of artificial intelligence under deep learning[J]. Big Data Time,2021(6): 56-76.
[3]
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.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.
[4]
杨金华,李晓光,孙乃达,等. 未来10年极具发展潜力的20项油气勘探开发新技术[J]. 石油科技论坛,2019,38(1): 38-48.YANG Jinhua,LI Xiaoguang,SUN Naida,et al. Twenty items of new technology for oil and gas exploration and development in next decade[J]. Petroleum Science and Technology Forum,2019,38(1): 38-48.
[5]
王昊,严加永,付光明,等. 深度学习在地球物理中的应用现状与前景[J]. 地球物理学进展,2020,35(2): 642-655.WANG Hao,YAN Jiayong,FU Guangming,et al. Current status and application prospect of deep learning in geophysics[J]. Progress in Geophysics,2020,35(2): 642-655.
[6]
赵改善. 石油物探智能化发展之路: 从自动化到智能化[J]. 石油物探,2019,58(6): 791-810.ZHAO Gaishan. Road to intelligent petroleum geophysical exploration: from automatic to intelligent[J]. Geophysical Prospecting for Petroleum,2019,58(6): 791-810.
[7]
YANG P,GUO R,LIU D,et al. Influence of label conditions on the effect of deep learning inversion[C]. EAGE 2020 Annual Conference & Exhibition Online,2020,1-5.
[8]
ZHU D,GUO R,LI L,et al. The weakly supervised learning method for 3D fault detection[C]. First International Meeting for Applied Geoscience & Energy Expanded Abstracts,2021,1576-1579.
[9]
于四伟,杨午阳,李海山,等. 基于深度学习的地震散射面波智能压制方法[J]. 科学通报,2021,66(18): 2343-2354.YU Siwei,YANG Wuyang,LI Haishan,et al. Scattered ground roll intelligent attenuation based on deep learning[J]. Chinese Science Bulletin,2021,66(18): 2343-2354.
[10]
张岩,李新月,王斌,等. 基于深度学习的鲁棒地震数据去噪[J]. 石油地球物理勘探,2022,57(1): 12-25.ZHANG Yan,LI Xinyue,WANG Bin,et al. Robust seismic data denoising based on deep learning[J]. Oil Geophysical Prospecting,2022,57(1): 12-25.
[11]
马国庆,王泽坤,李丽丽. 基于自注意力机制深度学习的重磁数据网格化和滤波方法[J]. 石油地球物理勘探,2022,57(1): 34-42.MA Guoqing,WANG Zekun,LI Lili. Gridding and filtering method of gravity and magnetic data based on self-attention deep learning[J]. Oil Geophysical Prospecting,2022,57(1): 34-42.
[12]
徐宗本. 人工智能的10个重大数理基础问题[J]. 中国科学: 信息科学,2021,51(12): 1967.XU Zongben. Ten fundamental problems for artificial intelligence: mathematical and physical aspects[J]. Scientia Sinica: Informationis,2021,51(12): 1967.
[13]
徐宗本,杨燕,孙剑. 求解反问题的一个新方法: 模型求解与范例学习结合[J]. 中国科学: 数学,2017,47(10): 1345-1354.XU Zongben,YANG Yan,SUN Jian. A new approach to solve inverse problems: combination of model-based solving and example-based learning[J]. Scientia Sinica: Mathematica,2017,47(10): 1345-1354.
[14]
杨平,詹仕凡,李明,等. 基于梦想云的人工智能地震解释模式研究与实践[J]. 中国石油勘探,2020,25(5): 89-96.YANG Ping,ZHAN Shifan,LI Ming,et al. Research and practice on an artificial intelligence seismic interpretation mode based on the E&P Dream Cloud[J]. China Petroleum Exploration,2020,25(5): 89-96.
[15]
陈茂山,张雷,金瑞锋,等. 适用于超大规模三维地震层位自动追踪的双尺度洪水填充方法[J]. 石油地球物理勘探,2017,52(5): 1033-1041.CHEN Maoshan,ZHANG Lei,JIN Ruifeng,et al. Double-scale flood fill approach for large-scale 3D horizon auto-tracking[J]. Oil Geophysical Prospecting,2017,52(5): 1033-1041.
[16]
LIAO Z,ZHU P,ZHANG H,et al. A method for seismic horizon tracing using deep learning with uncertain labels[C]. SEG 2021 Workshop: 4th International Workshop on Mathematical Geophysics: Traditional & Learning,Virtual,2022,41: 143-146.
[17]
WANG F,WU X,WANG H. Seismic horizon identification using semisupervised learning with virtual adversarial training[C]. First International Meeting for Applied Geoscience & Energy Expanded Abstracts,2021,1061-1065.
[18]
LOWELL J,PATON G. Application of deep learning for seismic horizon interpretation[C]. SEG Technical Program Expanded Abstracts,2018,37: 1976-1980.
[19]
董子昂. 基于条件随机场的多视图序列数据建模研究[D]. 上海: 华东师范大学,2020.DONG Ziang. Research of Multiview Sequence Data Modeling Based on Conditional Random Fields[D]. East China Normal University,Shanghai,2020.
[20]
SHEN X,WANG G,JIA Y. Multi-scale residual attention network for seismic data interpolation[C]. SEG 2021 Workshop: 4th International Workshop on Mathematical Geophysics: Traditional & Learning,Virtual,2022,41: 41-44.
[21]
杨平,李海银,胡蕾,等. 提高裂缝预测精度的解释性处理技术及其应用[J]. 石油物探,2015,54(6): 681-689.YANG Ping,LI Haiyin,HU Lei,et al. Interpretative processing techniques and their applications in improving fracture prediction accuracy[J]. Geophysical Prospecting for Petroleum,2015,54(6): 681-689.
[22]
ZHOU R,CAI Y,YU F,et al. Seismic fault detection with iterative deep learning[C]. SEG Technical Program Expanded Abstracts,2019,38: 2503-2507.
[23]
LYU F,LIU J,ZHOU J,et al. Research on buried hill fault detection method based on 3D fully convolutional neural network and transfer learning[C]. SEG 2021 Workshop: 4th International Workshop on Mathematical Geophysics: Traditional & Learning,Virtual,2022,41: 37-40.
[24]
ALOHALI R,ALZUBAIDI F,VAN KRANENDONK M,et al. Automated fault detection in the Arabian Basin[J]. Geophysics,2022,87(4): IM101-IM109.
[25]
胡广. 基于深度学习语义分割的断层识别应用研究[D]. 湖北武汉: 中国地质大学,2021.HU Guang. Application and Research on Fault Detection Based on Deep Learning Semantic Segmentation[D]. China University of Geosciences,Wuhan,Hubei,2021.
[26]
张文彪,张亚雄,段太忠,等. 塔里木盆地塔河油田托甫台区奥陶系碳酸盐岩断溶体系层次建模方法[J]. 石油与天然气地质,2022,43(1): 207-218.ZHANG Wenbiao,ZHANG Yaxiong,DUAN Taizhong,et al. Hierarchy modeling of the Ordovician fault-karst carbonate reservoir in Tuoputai area,Tahe oilfield,Tarim Basin,NW China[J]. Oil & Gas Geology,2022,43(1): 207-218.
[27]
常少英,曾溅辉,徐旭辉,等. 碳酸盐岩断溶体内部结构识别技术及应用[J]. 石油地球物理勘探,2022,57(2): 414-422.CHANG Shaoying,ZENG Jianhui,XU Xuhui,et al. Identification technology for internal structures of carbonate fault-karst and its application[J]. Oil Geophysical Prospecting,2022,57(2): 414-422.
