3D seismic data completion method based on sparse strong feature extraction
CUI Xuepeng1,2, HUANG Handong1,2, LUO Yaneng3, CHENG Suo4, HAO Yaju5, CUI Gang6
1. State Key Laboratory of Petroleum Resources and Prospecting, China University of Petroleum(Beijing), Beijing 102249, China; 2. College of Geophysics, China University of Petroleum(Beijing), Beijing 102249, China; 3. Geophysical Research&Development Center, BGP Inc., CNPC, Zhuozhou, Hebei 072751, China; 4. Exploration and Production Research Institute, Tarim Oilfield Company, PetroChina, Korla, Xinjiang 841000, China; 5. School of Geophysics and Measurement-Control Technology, East China University of Technology, Nanchang, Jiangxi 330013, China; 6. The First Production Plant, Huabei Oilfield Company, PetroChina, Renqiu, Hebei 062552, China
Abstract:As machine learning technology for screening seismic data features of complex reservoirs develops, how to effectively collect and analyze seismic samples involved in seismic attribute optimization and reservoir inversion has currently become a hot research topic in the field of intelligent prediction based on seismic data. Existing methods mostly focus on improving model classification algorithms, which not only consume a lot of time for manual labeling in the production and collection of labels but also suffer from poor intra-class reliability and inter-class balance in the case of label imbalance. Therefore, a 3D seismic data completion method based on sparse strong feature extraction is proposed. First, sample segmentation based on majority rule (SSMR) is used to trace multi-scale and multi-label 3D seismic samples for collection and automatic labeling. Then, the improved label shuffling balance (ILSB) method is used to complete the data by a "2 + 1" sample broadening and balancing strategy, so as to improve the model training bias caused by unbalanced sample sampling. Finally, minimum L1-norm based sparse representation for feature extraction (L1-SRFE) and visual representation of the singular value decomposition results are performed. Application of the actual data shows that the predicted results of the actually drilled wells and the validation wells are in good agreement, and the method has a high accuracy of label classification.
杨旭,李永华,盖增喜.机器学习在地震学中的应用进展[J].地球与行星物理论评,2021,52(1):76-88.YANG Xu,LI Yonghua,GAI Zengxi.Machine lear-ning and its application in seismology[J].Reviews of Geophysics and Planetary Physics,2021,52(1):76-88.
[2]
DONG H,LI Y,ZHOU Z.Learning from semi-supervised weak-label data[C].Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence and Thirtieth Innovative Applications of Artificial Intelligence Conference and Eighth AAAI Symposium on Educational Advances in Artificial Intelligence,2018,2926-2933.
[3]
张,郑晓东,李劲松,等.基于SOM和PSO的非监督地震相分析技术[J].地球物理学报,2015,58(9):3412-3423.ZHANG Yan,ZHENG Xiaodong,LI Jinsong,et al.Unsupervised seismic facies analysis technology based on SOM and PSO[J].Chinese Journal of Geophysics,2015,58(9):3412-3423.
[4]
赵明,陈石,YUEN D.基于深度学习卷积神经网络的地震波形自动分类与识别[J].地球物理学报,2019,62(1):374-382.ZHAO Ming,CHEN Shi,YUEN D.Waveform classification and seismic recognition by convolution neural network[J].Chinese Journal of Geophysics,2019,62(1):374-382.
[5]
陈德武,杨午阳,魏新建,等.基于混合网络U-SegNet的地震初至自动拾取[J].石油地球物理勘探,2020,55(6):1188-1201.CHEN Dewu,YANG Wuyang,WEI Xinjian,et al.Automatic picking of seismic first arrivals based on hybrid network U-SegNet[J].Oil Geophysical Prospecting,2020,55(6):1188-1201.
[6]
PETERS B,HABER E,GRANEK J.Neural networks for geophysicists and their application to seismic data interpretation[J].The Leading Edge,2019,38(7):534-540.
[7]
王光宇,宋建国,徐飞,等.不平衡样本集随机森林岩性预测方法[J].石油地球物理勘探,2021,56(4):679-687.WANG Guangyu,SONG Jianguo,XU Fei,et al.Random forests lithology prediction method for imba-lanced data sets[J].Oil Geophysical Prospecting,2021,56(4):679-687.
[8]
WU X,LIANG L,SHI Y,et al.FaultSeg3D:using synthetic data sets to train an end-to-end convolu-tional neural network for 3D seismic fault segmentation[J].Geophysics,2019,84(3):IM35-IM45.
[9]
王静,张军华,芦凤明,等.构建三维深度监督网络的断层检测方法[J].石油地球物理勘探,2021,56(5):947-957.WANG Jing,ZHANG Junhua,LU Fengming,et al.Research on fault detection method based on 3D deeply supervised network[J].Oil Geophysical Prospecting,2021,56(5):947-957.
[10]
陈桂,刘洋.基于人工智能的断层自动识别研究进展[J].地球物理学进展,2021,36(1):119-131.CHEN Gui,LIU Yang.Research progress of automa-tic fault recognition based on artificial intelligence[J].Progress in Geophysics,2021,36(1):119-131.
[11]
陈杰,牛聪,李勇,等.基于数据驱动紧框架理论的三维地震数据去噪与重建[J].石油地球物理勘探,2020,55(4):725-732.CHEN Jie,NIU Cong,LI Yong,et al.Denoising and reconstruction of 3D seismic data on a data-driven tight frame[J].Oil Geophysical Prospecting,2020,55(4):725-732.
[12]
ZHENG Y,ZHANG Q,YUSIFOV A.Applications of supervised deep learning for seismic interpretation and inversion[J].The Leading Edge,2019,38(7):526-533.
[13]
HUANG L,DONG X,CLEE T E.A scalable deep learning platform for identifying geologic features from seismic attributes[J].The Leading Edge,2017,36(3):249-256.
[14]
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.
[15]
宗志敏,何登科,孙超.基于深度学习采用多标签的方式解释叠前地震数据[J].地球物理学进展,2022,37(3):1258-1265.ZONG Zhimin,HE Dengke,SUN Chao.Interpret pre-stack seismic data with multi-label based on deep learning[J].Progress in Geophysics,2022,37(3):1258-1265.
[16]
BHATIA K,JAIN H,KAR P,et al.Sparse local embeddings for extreme multi-label classification[C].Proceedings of the 28th International Conference on Neural Information Processing Systems,2015,730-738.
[17]
LIU M,JERVIS M,LI W,et al.Seismic facies classification using supervised convolutional neural networks and semi-supervised generative adversarial networks[J].Geophysics,2020,85(4):O47-O58.
[18]
KU B,KIM G,AHN J K,et al.Attention-based con-volutional neural network for earthquake event classification[J].IEEE Geoscience and Remote Sensing Letters,2021,18(12):2057-2061.
[19]
LIU W,ANGUELOV D,ERHAN D,et al.SSD:single shot MultiBox detector[C].Computer Vision-ECCV 2016,2016,21-37.
[20]
XU Z,CHEN Y,YANG F,et al.A post-earthquake multiple scene recognition model based on classical SSD method and transfer learning[J].ISPRS International Journal of Geo-information,2020,9(4):238.
[21]
DUBOIS M K,BOHLING G C,CHAKRABARTI S.Comparison of four approaches to a rock facies classification problem[J].Computers & Geosciences,2007,33(5):599-617.
[22]
韩明亮,邹志辉,马锐.利用反射地震资料和多尺度训练集的深度学习速度建模[J].石油地球物理勘探,2021,56(5):935-946.HAN Mingliang,ZOU Zhihui,MA Rui.Deep lear-ning-driven velocity modeling based on seismic reflection data and multi-scale training sets[J].Oil Geophysical Prospecting,2021,56(5):935-946.
[23]
董林鹭,蒋若辰,徐奴文,等.基于LMD-SVD的微震信号降噪方法研究[J].工程科学与技术,2019,51(5):126-136.DONG Linlu,JIANG Ruochen,XU Nuwen,et al.Research on microseismic signal denoising method based on LMD-SVD[J].Advanced Engineering Sciences,2019,51(5):126-136.
[24]
ZHANG K,ZUO W,CHEN Y,et al.Beyond a Gaus-sian denoiser:residual learning of deep CNN for image denoising[J].IEEE Transactions on Image Proces-sing,2017,26(7):3142-3155.
[25]
HUANG N,SHEN Z,LONG S,et al.The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J].Proceedings of the Royal Society of London,Series A:Mathematical,Physical and Engineering Sciences,1998,454(1971):903-995.
[26]
韩泉叶,王晓明,党建武.基于平均明暗熵差的人脸增强算法[J].兰州交通大学学报,2009,28(6):11-14.HAN Quanye,WANG Xiaoming,DANG Jianwu.Face enhancement alogrithm based on average bright and dark entropy difference[J].Journal of Lanzhou Jiaotong University,2009,28(6):11-14.
[27]
ZHONG Q,LI C,ZHANG Y,et al.Towards good practices for recognition & detection[C].In CVPR Workshops,2016.
[28]
陆文凯,李衍达.利用SVD分解法对任意道距道内插[J].石油地球物理勘探,1997,32(4):582-588.LU Wenkai,LI Yanda.Any-interval trace interpolation using SVD method[J].Oil Geophysical Prospecting,1997,32(4):582-588.
[29]
WRIGHT J,YANG A,GANESH A,et al.Robust face recognition via sparse representation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(2):210-227.
[30]
CANDES E J,TAO T.Decoding by linear programming[J].IEEE Transactions on Information Theory,2005,51(12):4203-4215.