Identification of Karst caves in seismic data based on deep convolutional neural network
YAN Xingyu1,2, LI Zongjie3, GU Hanming1,2, CHEN Benchi4, DENG Guangxiao3, LIU Jun3
1. Institute of Geophysics&Geomatics, China University of Geosciences(Wuhan), Wuhan, Hubei 430074, China; 2. Hubei Subsurface Multiscale Image Key Laboratory, Wuhan, Hubei 430074, China; 3. Research Institute of Exploration and Development, Northwest Oilfield Branch Co., SINOPEC, Urumqi, Xinjiang 830011, China; 4. Oil Field Department of Science and Technology Ministry, SINOPEC, Beijing 100728, China
Abstract:Karst cave identification is significant for the exploration and development of fracture-cavity oil and gas reservoirs. Conventional identification methods are multi-solution and inefficient. Therefore, a deep learning method with strong feature learning and generalization capabilities is introduced into Karst cave identification. However, it is still a challenging task to identify Karst caves by deep learning due to the complex response characteristics of Karst caves to the seismic wavefield, the small sizes of anomalies, and the difficulties in obtaining training samples. Faced with this pro-blem, we propose a "two-step" deep learning me-thod for identifying Karst caves in seismic data. Spe-cifically, the U-Net model is used to identify the "bead-shaped" anomalous reflection on the seismic section. Then, according to the identification results of the "bead-shaped" anomalies, seismic data are cropped into small patches and input into the deep residual network to implement the prediction of the actual Karst cave profile. Considering the difficulties in obtaining training data for actual Karst cave prediction, we propose implementing wave equation forward modeling to generate seismic Karst cave data with accurate labels. The application of field seismic data shows that the me-thod is accurate in Karst cave identification, has strong noise resistance, and can greatly save the cost of manual interpretation.
闫星宇, 李宗杰, 顾汉明, 陈本池, 邓光校, 刘军. 基于深度卷积神经网络的地震数据溶洞识别[J]. 石油地球物理勘探, 2022, 57(1): 1-11.
YAN Xingyu, LI Zongjie, GU Hanming, CHEN Benchi, DENG Guangxiao, LIU Jun. Identification of Karst caves in seismic data based on deep convolutional neural network. Oil Geophysical Prospecting, 2022, 57(1): 1-11.
韩剑发,程汉列,施英,等.塔中缝洞型碳酸盐岩储层连通性分析及应用[J].科学技术与工程,2016,16(5):147-153.HAN Jianfa,CHENG Hanlie,SHI Ying,et al. Connectivity analysis and application of fracture cave carbonate reservoir in Tazhong[J].Science Technology and Engineering,2016,16(5):147-153.
[2]
崔泽飞,熊晓军,龚思宇,等.碳酸盐岩裂缝储层精细建模及其数值模拟[J].科学技术与工程,2017,17(26):177-180.CUI Zefei,XIONG Xiaojun,GONG Siyu,et al.Carbonate fractured reservoir modeling and its numerical simulation[J].Science Technology and Engineering,2017,17(26):177-180.
[3]
曲寿利,朱生旺,赵群,等.碳酸盐岩空洞型储集体地震反射特征分析[J].地球物理学报,2012, 55(6):2053-2061.QU Shouli,ZHU Shengwang,ZHAO Qun,et al.Analysis of seismic reflection characters for carbonate Karst reservoir[J].Chinese Journal of Geophysics,2012,55(6):2053-2061.
[4]
马灵伟,顾汉明,李宗杰,等.正演模拟碳酸盐岩缝洞型储层反射特征[J].石油地球物理勘探,2015,50(2):290-297.MA Lingwei,GU Hanming,LI Zongjie,et al.Simulation of carbonate fracture-cavern reservoir reflection characteristics with forward modeling[J].Oil Geophysical Prospecting,2015,50(2):290-297.
[5]
任海洋.基于深度学习方法的溶洞体识别及定量计算[D].四川成都:电子科技大学,2019.
[6]
王保才,刘军,马灵伟,等.塔中顺南地区奥陶系缝洞型储层地震响应特征正演模拟分析[J].石油物探,2014,53(3):344-350.WANG Baocai,LIU Jun,MA Lingwei,et al.Forward modeling for seismic response characteristics of the fracture-cavity Ordovician reservoir in Shunnan area of central Tarim Basin[J].Geophysical Prospecting for Petroleum,2014,53(3):344-350.
[7]
王立华,魏建新,狄帮让.溶洞物理模型地震响应及其属性分析[J].石油地球物理勘探,2008,43(3):291-296.WANG Lihua,WEI Jianxin,DI Bangrang.Seismic response of Karst cave physical model and analysis of its attributes[J].Oil Geophysical Prospecting,2008,43(3):291-296.
[8]
张军华,刘振,刘炳杨,等.强屏蔽层下弱反射储层特征分析及识别方法[J].特种油气藏,2012,19(1):23-26.ZHANG Junhua,LIU Zhen,LIU Bingyang,et al.Analysis and identification of reservoir characteristics of weak reflectors under strong shielding layer[J].Special Oil & Gas Reservoirs,2012,19(1):23-26.
[9]
赵裕辉,胡建中,鲁新便,等.碳酸盐岩缝洞型储集体识别与体积估算[J].石油地球物理勘探,2010,45(5):720-724.ZHAO Yuhui,HU Jianzhong,LU Xinbian,et al.Identification of carbonate fractured-vuggy reservoir and volume estimation[J].Oil Geophysical Prospecting,2010,45(5):720-724.
[10]
奚先,黄江清.基于卷积神经网络的地震偏移剖面中散射体的定位和成像[J].地球物理学报,2020, 63(2):687-714.XI Xian, HUANG Jiangqing.Location and imaging of scatterers in seismic migration profiles based on convolution neural network[J].Chinese Journal of Geophysics,2020,63(2):687-714.
[11]
WU X,SHI Y,FOMEL S,et al.Convolutional neural networks for fault interpretation in seismic images[C].SEG Technical Program Expanded Abstracts,2018,37:1946-1950.
[12]
SHI Y,WU X,FOMEL S.Automatic salt-body classification using deep-convolutional neural network[C].SEG Technical Program Expanded Abstracts,2018,37:1971-1975.
[13]
ALAUDAH Y,ALFARRAJ M.Structure label prediction using similarity-based retrieval and weakly supervised label mapping[J].Geophysics,2019,84(1):V67-V79.
[14]
王天云,韩小锋,许海红,等.无监督神经网络地震属性聚类方法在沉积相研究中的应用[J].石油地球物理勘探,2021,56(2):372-379.WANG Tianyun,HAN Xiaofeng,XU Haihong,et al.Study on sedimentary facies based on unsupervised neural network seismic attribute clustering[J].Oil Geophysical Prospecting,2021,56(2):372-379.
[15]
DI H,LI Z,MANIAR H,et al.Seismic stratigraphy interpretation via deep convolutional neural networks[C].SEG Technical Program Expanded Abstracts,2019,38:2358-2362.
[16]
PETERS B,GRANEK J,HABER E.Multiresolution neural networks for tracking seismic horizons from few training images[J].Interpretation,2019,7(3):SE201-SE213.
[17]
WU X,YAN S,QI J,et al.Deep learning for characterizing paleokarst collapse features in 3-d seismic ima-ges[C].SEG Technical Program Expanded Abstracts,2020,39:1454-1459.
[18]
朱剑兵,王兴谋,冯德永,等.基于双向循环神经网络的河流相储层预测方法及应用[J].石油物探,2020,59(2):250-257.ZHU Jianbing,WANG Xingmou,FENG Deyong,et al.Predicting fluvial reservoirs using seismic data based on a Bi-recurrent neural network[J].Geophysical Prospecting for Petroleum,2020,59(2):250-257.
[19]
闫星宇,顾汉明,罗红梅,等.基于改进深度学习方法的地震相智能识别[J].石油地球物理勘探,2020,55(6):1169-1177.YAN Xingyu, GU Hanming, LUO Hongmei, et al.Intelligent seismic facies classification based on an improved deep learning method[J].Oil Geophysical Prospecting,2020,55(6):1169-1177.
[20]
LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[C].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2015,3431-3440.
[21]
RONNEBERGER O,FISCHER P,BROX T.U-Net:Convolutional networks for biomedical image segmentation[C].International Conference on Medical Image Computing and Computer-Assisted Intervention,Springer,Cham,2015,234-241.
[22]
HE K,ZHANG X,REN S,et al.Deep residual lear-ning for image recognition[C].Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2016,770-778.
[23]
KINGMA D P,BA J.Adam:A method for stochastic optimization[C].The 3rd International Conference on Learning Representations,2015.http://arxiv.org/abs/1412.6980.