Seismic facies analysis based on cepstrum characte-ristic parameters and spectral clustering
SANG Kaiheng1, ZHANG Fanchang1, LI Chuanhui2
1. School of Geoscience, China University of Petroleum (East China), Qingdao, Shandong 266580, China; 2. School of Geophysics and Information Technology, China University of Geosciences (Beijing), Beijing 100083, China
Abstract:Stochastic simulation, neural network, clustering and deep learning are always used to seismic facies analysis. However, stochastic simulation results are easily affected by stochastic models, and it is difficult to get accurate seismic facies division in complex geological areas. Neural network and deep learning methods have strong fault tolerance and generalization ability, but they require massive training samples and high computing costs. Classical clustering algorithms such as K-means clustering and C-fuzzy clustering can obtain ideal clustering results on simple data, but cannot achieve global optimization for non-convex data. To overcome these problems, we propose a seismic facies analysis method based on cepstrum characteristic parameters and spectral clustering. In this me-thod, seismic cepstrum characteristic parameters are calculated as input variable of spectral clustering, and then the corresponding relationship is established between seismic facies and geological body after calibrating by well data. The spectral clustering method based on graph theory transforms data clustering into graph segmentation, which achieve accurate clustering through optimal graph segmentation. And we also construct a sparse similarity matrix through optimizing the similarity matrix calculation method, by which the storage and calculation problems caused by large matrix dimensions can be solved. Therefore, spectral clustering is more suitable for 3D seismic facies division. The advantages of cepstrum characteristic parameters are as follows:on the one hand, it can reduce data dimension and computational complexity; and on the other hand, it can eliminate the influence of waveform, and improve division accuracy. The applications to model and real data show that the seismic facies divided by the proposed method are in better agreement with the paleogeomorphology than the facies division based on instantaneous seismic amplitude and multiple seismic attributes, showing clearer boundaries and better interpretability. The results are reliable data for oil exploration and reservoir evaluation.
Nivlet P.Uncertainties in seismic facies analysis for reservoir characterisation or monitoring:causes and consequences[J].Oil & Gas Science and Technology, 2007,62(2):225-235.
[2]
Abraham K J,Larry W L,Carlos T V,et al.Seismic facies identification and classification using simple statistics[J]. SPE Reservoir Evalution & Enginee-ring,2008,11(6):984-990.
[3]
Michael R,Bahk J J,Kim H S,et al.Seismic facies a-nalyses as aid in regional gas hydrate assessments,Part-I:classification analyses[J].Marine and Petro-leum Geology, 2013,47(1):248-268.
[4]
蔡涵鹏,胡浩炀,吴庆平,等.基于叠前地震纹理特征的半监督地震相分析[J].石油地球物理勘探,2020, 55(3):504-509.CAI Hanpeng,HU Haoyang,WU Qingping,et al.Semi-supervised seismic facies analysis based on pre-stack seismic texture[J].Oil Geophysical Prospecting,2020,55(3):504-509.
[5]
朱剑兵,赵培坤.国外地震相划分技术研究新进展[J]. 勘探地球物理进展,2009,32(3):167-171.ZHU Jianbing,ZHAO Peikun.Advances in seismic facies classification technology abroad[J].Progress in Exploration Geophysics,2009,32(3):167-171.
[6]
穆星.利用地震几何属性和自组织神经网络进行地震相的自动识别[J].地质科技情报,2005,24(3):109-112.MU Xing.Method of seismic facies auto-classification by the seismic geometrical attribute and the self-organizing neural network[J].Geological Science and Technology Information, 2005,24(3):109-112.
[7]
Ivan D M,Jean-Jules B,Bruce S H.A visual data-mining methodology for seismic facies analysis:Part 2:Application to 3D seismic data[J].Geophysics,2009,74(1):P1-P11.
[8]
Thierry C, Manuel P, Kostia A. Unsupervised seismic facies classification:A review and comparison of techniques and implementation[J].The Leading Edge, 2003,22(10):942-953.
[9]
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 analysis technology based on SOM and PSO[J].Chinese Journal of Geophysics,2015,58(9):3412-3423.
[10]
刘仕友,宋炜,应明雄,等.基于密度的含噪声角道集波形聚类地震相分析[J].石油物探, 2019,58(5):773-782.LIU Shiyou,SONG Wei,YING Mingxiong,et al.Seismic facies analysis for angle gathers based on DBSCAN waveform clustering[J].Geophysical Prospecting for Petroleum,2019,58(5):773-782.
[11]
Duan Y T,Zheng X D, Hu L L,et al.Seismic facies analysis based on deep convolutional embedded clustering[J]. Geophysics,2019, 84(6):IM87-IM97.
[12]
Thilo W,Indranil P,Robert L G, et al.Seismic facies analysis using machine learning[J].Geophysics,2018,83(5):O83-O95.
[13]
刘振峰,郝天珧,杨长春.沉积模型和储层随机建模[J].地球物理学进展, 2003,18(3):519-523.LIU Zhenfeng,HAO Tianyao,YANG Changchun. Sedimentation models and stochastic reservoir modeling[J]. Progress in Geophysics, 2003,18(3):519-523.
[14]
冯国庆,李允,林作华,等.应用序惯指示模拟方法模拟沉积微相[J].西南石油学院学报, 2001,23(2):1-4.FENG Guoqing, LI Yun, LIN Zuohua, et al. Application of sequential indicator simulation method to delineating sedimentary microfacies[J].Journal of Southwest Petroleum Institute, 2001,23(2):1-4.
[15]
周志华.机器学习[M].北京:清华大学出版社,2016,197-199.ZHOU Zhihua.Machine Learning[M].Tsinghua University Press, Beijing,2016,197-199.
[16]
伍育红.聚类算法综述[J].计算机科学,2015,42(Z6):491-524.WU Yuhong.General overview on clustering algorithms[J].Computer Science,2015,42(Z6):491-524.
[17]
南男,杨健,赵晶晶,等.基于谱聚类特征向量分析的模态划分方法[J].华东理工大学学报(自然科学版),2017, 43(5):669-676.NAN Nan,YANG Jian,ZHAO Jingjing,et al.Mode partitioning method based on eigenvector analysis in spectral clustering[J].Journal of East China University of Science and Technology (Natural Science Edition),2017, 43(5):669-676.
[18]
高尚兵,周静波,严云洋.一种新的基于超像素的谱聚类图像分割算法[J].南京大学学报(自然科学版),2013,49(2):169-175.GAO Shangbing,ZHOU Jingbo,YAN Yunyang. A new superpixel based spectral clustering for image segmentation[J]. Journal of Nanjing University (Na-tural Sciences), 2013, 49(2):169-175.
[19]
印兴耀,周静毅.地震属性优化方法综述[J].石油地球物理勘探,2005,40(4):482-489.YIN Xingyao, ZHOU Jingyi. Summary of optimum method of seismic attributes[J].Oil Geophysical Prospecting, 2005,40(4):482-489.
[20]
冯小英,杨延辉,左银卿,等.敏感属性与参数反演融合定量预测煤体结构[J].石油地球物理勘探,2019,54(5):1115-1122.FENG Xiaoying,YANG Yanhui,ZUO Yinqing,et al.Coal structure quantitative prediction with sensitive-attribute and parameter-inversion fusion[J]. Oil Geophysical Prospecting, 2019,54(5):1115-1122.
Sui Y H,Ma J W.A nonstationary sparse spike deconvolution with anelastic attenuation[J].Geophy-sics, 2019,84(2):R221-R234.
[23]
Du X,Li G F,Zhou Z X,et al.Band-controlled sparse deconvolution[J].Journal of Applied Geophysics,2018, 155(8):53-61.
[24]
张繁昌,何晋越,桑凯恒,等.稀疏反射系数频率域正余弦分量协同反演方法[J].石油地球物理勘探,2018, 53(4):778-783.ZHANG Fanchang,HE Jinyue,SANG Kaiheng,et al.A sparse reflectivity sine-cosine synergistic inversion method in the frequency[J].Oil Geophysical Prospecting,2018, 53(4):778-783.
[25]
Castagna J P. Spectral decomposition and high resolution reflectivity inversion[C].SEG Technical Program Expanded Abstracts,2004,23:1238-1241.
[26]
Xie T, Zheng X D, Zhang Y.Seismic facies analysis based on speech recognition feature parameters[J].Geophysics, 2017,82(3):O23-O35.
[27]
李韵.声纹识别系统中特征参数提取方法的对比分析研究[D].四川成都:成都理工大学,2016.LI Yun.The Comparison and Analysis of the Feature Extraction Algorithm of Voiceprint Recognition System[D].Chengdu University of Technology, Chengdu, Sichuan,2016.
[28]
韩纪庆,张磊,郑铁然.语音信号处理[M].北京:清华大学出版社, 2013,97-114.HAN Jiqing, ZHANG Lei, ZHENG Tieran. Processing of Speech Signal[M].Tsinghua University Press,Beijing, 2013,97-114.
[29]
Francis R B, Michael I J.Learning spectral clustering,with application to speech separation[J].Journal of Machine Learning Research,2006,7(6):1963-2001.
[30]
Shi J B,Malik J.Normalized cuts and image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(8):888-905.
[31]
钟林鹏.说话人识别系统中的语音信号处理技术研究[D].四川成都:电子科技大学,2013.ZHONG Linpeng.Studies on the Speech Signals Processing of the Speaker Recognitions System[D].University of Electronic Science and Technology of China,Chengdu, Sichuan, 2013.