基于深度嵌入网络的地震相聚类技术

doi:10.13810/j.cnki.issn.1000-7210.2022.02.002

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (1868 KB) HTML []
输出: BibTeX | EndNote (RIS)

摘要早期基于机器学习的地震相聚类分析依赖地震属性种类的选择与组合,结果具有很强的主观性,而数据驱动下的深度学习可以规避该缺陷。因此,利用深度学习技术,采用自编码网络架构,通过嵌入编码(Embedding Code)对地震数据进行抽象表示;引入聚类损失函数与重建损失函数,建立联合损失函数并优化,使学习到的地震特征既能重建地震数据,又具有较好的聚类能力。鄂尔多斯盆地A致密气探区实际应用结果表明:经过500次迭代后,嵌入编码已具有明显的聚类特征,同时能很好地恢复原始地震信号,相对误差小于5%;与均方根振幅属性相比,基于深度嵌入网络的地震相聚类技术计算的地震相图刻画河道更准确、细节更丰富;比K-Means聚类算法预测结果的井震符合率更高,可达89.3%。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	李祺鑫
	罗亚能
	马晓强
	陈诚
	祝彦贺

关键词 ：地震相分析, 卷积自编码网络, 深度学习, 特征表示

Abstract：The early seismic facies clustering based on machine learning relies on the selection and combination of seismic attributes, leading to strong subjectivity of results. Nevertheless, this defect can be overcome by data-driven deep learning. Therefore,with deep learning technology, the autoencoder network is adopted to generate embedding code that can be used for abstract representation of seismic data. The clustering loss function and the reconstruction loss function are introduced to build a combined loss function, which is then optimized so that the seismic features learned can not only be used to reconstruct seismic data but also have favorable clustering ability. The proposed method is applied to a tight gas exploration area A in Ordos Basin. The following observations are drawn from the results: After 500 iterations, the embedding code has noticeable clustering features, and the original seismic signals can be well reconstructed with a relative error of less than 5%; compared with that in the case of the root-mean-square (RMS) amplitude attribute, the seismic facies map calculated by the seismic facies clustering technology based on deep embedding network delineates channels more accurately with richer detail; compared with the K-means clustering algorithm, the proposed technology delivers a prediction result that has a higher coincidence rate between seismic data and well logging data, which can reach 89.3%.

Key words： seismic facies analysis convolutional autoencoder network deep learning feature re-presentation

收稿日期: 2021-04-12

PACS:

P631

通讯作者: 李祺鑫,北京市朝阳区太阳宫南街6号院中海油研究总院,100028。Email:lqx269@sina.com E-mail: lqx269@sina.com

作者简介: 李祺鑫,工程师,1989年生;2011年获中国海洋大学勘查技术与工程专业工学学士学位,2014年获中国石油大学(北京)地球探测与信息技术专业硕士学位;现就职于中海油研究总院,从事地震预测方面的研究。

引用本文:

李祺鑫, 罗亚能, 马晓强, 陈诚, 祝彦贺. 基于深度嵌入网络的地震相聚类技术[J]. 石油地球物理勘探, 2022, 57(2): 261-267. LI Qixin, LUO Yaneng, MA Xiaoqiang, CHEN Cheng, ZHU Yanhe. Seismic facies clustering technology based on deep embedding network. Oil Geophysical Prospecting, 2022, 57(2): 261-267.

链接本文:

http://www.ogp-cn.com/CN/10.13810/j.cnki.issn.1000-7210.2022.02.002 或 http://www.ogp-cn.com/CN/Y2022/V57/I2/261

[1]	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.
[2]	CHOPRA S,MARFURT K J.Unsupervised machine learning applications for seismic facies classification[C].SPE/AAPG/SEG Unconventional Resources Technology Conference,Colorado,USA,2019,URTEC-2019-557-MS.
[3]	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 prestack seismic texture[J].Oil Geophysical Prospecting,2020,55(3):504-509.
[4]	桑凯恒,张繁昌,李传辉.地震倒谱特征参数谱聚类地震相分析方法[J].石油地球物理勘探,2021,56(1):38-48.SANG Kaiheng,ZHANG Fanchang,LI Chuanhui.Seismic facies analysis based on cepstrum characteristic parameters and spectral clustering[J].Oil Geophysical Prospecting,2021,56(1):38-48.
[5]	Galvis I S,Villa Y,Duarte C,et al.Seismic attribute selection and clustering to detect and classify surface waves in multicomponent seismic data by using K-means algorithm[J].The Leading Edge,2017,36(3):239-248.
[6]	解滔,郑晓东,张.基于线性预测倒谱系数的地震相分析[J].地球物理学报,2016,59(11):4266-4277.XIE Tao,ZHENG Xiaodong,ZHANG Yan.Seismic facies analysis based on linear prediction cepstrum coefficients[J].Chinese Journal of Geophysics,2016,59(11):4266-4277.
[7]	ZHAO T,LI F Y,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):T163-T171.
[8]	DE MATOS M C,OSORIO P L,JOHANN P R.Unsupervised seismic facies analysis using wavelet transform and self-organizing maps[J].Geophysics,2007,72(1):P9-P21.
[9]	WRONA T,PAN I,GAWTHORPE R L,et al.Seismic facies analysis using machine learning[J].Geophysics,2018,83(5):O83-O95.
[10]	LIU Z G,CAO J X,LU Y J,et al.A seismic facies classification method based on the convolutional neural network and the probabilistic framework for seismic attributes and spatial classification[J].Interpretation,2019,7(3):SE225-SE236.
[11]	MARROQUÍN I D,BRAULT J J,HART B S.A vi-sual data-mining methodology for seismic facies analy-sis:Part 1:testing and comparison with other unsupervised clustering methods[J].Geophysics,2009,74(1):P1-P11.
[12]	MARROQUÍN I D,BRAULT J J,HART B S.A vi-sual data-mining methodology for seismic facies analy-sis:Part 2:application to 3D seismic data[J].Geophysics,2009,74(1):P13-P23.
[13]	COLÉOU T,POUPON M,AZBEl K.Unsupervised seismic facies classification:A review and comparison of techniques and implementation[J].The Leading Edge,2003,22(10):942-953.
[14]	ROSS C P,COLE D M.A comparison of popular neural network facies-classification schemes[J].The Leading Edge,2017,36(4):340-349.
[15]	MARROQUÍN I D.A knowledge-integration framework for interpreting seismic facies[J].Interpretation,2014,2(1):SA1-SA9.
[16]	BARNES A E.Redundant and useless seismic attri-butes[J].Geophysics,2007,72(3):P33-P38.
[17]	ZHAO T,LI F Y,MARFURT K J.Seismic attribute selection for unsupervised seismic facies analysis using user-guided data-adaptive weights[J].Geophy-sics,2018,83(2):O31-O44.
[18]	QI J,ZHANG B,LYU B,et al.Seismic attribute selection for machine-learning-based facies analysis[J].Geophysics,2019,85(2):O17-O35.
[19]	KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Imagenet classification with deep convolutional neural networks[C].Proceedings of the 25th International Conference on Neural Information Processing Systems,Granada,Spain,2012,1097-1105.
[20]	LECUN Y,BENGIO Y,HINTON G.Deep learning[J].Nature,2015,521(7553):436-444.
[21]	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.
[22]	ZHAO T.Seismic facies classification using different deep convolutional neural networks[C].SEG Technical Program Expanded Abstracts,2018,37:2046-2050.
[23]	DRAMSCH J S,LVTHJE M.Deep-learning seismic facies on state-of-the-art CNN architectures[C].SEG Technical Program Expanded Abstracts,2018,37:2036-2040.
[24]	QI J,LIN T F,ZHAO T,et al.Semisupervised multiattribute seismic facies analysis[J].Interpretation,2016,4(1):SB91-SB106.
[25]	QIAN F,YIN M,LIU X Y,et al.Unsupervised seismic facies analysis via deep convolutional autoencoders[J].Geophysics,2018,83(3):A39-A43.
[26]	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.
[27]	DUAN Y T,ZHENG X D,HU L L.Seismic-facies analysis based on deep-encoder clustering[C].SEG Technical Program Expanded Abstracts,2018,37:2152-2156.
[28]	XIE J Y,GIRSHICK R,FARHADI A.Unsupervised deep embedding for clustering analysis[C].Procee-dings of the 33rd International Conference on Machine Learning,New York,USA,2016,478-487.
[29]	O'Shea T,Hoydis J.An introduction to deep learning for the physical layer[J].IEEE Transactions on Cognitive Communications and Networking,2017,3(4):563-575.
[30]	罗仁泽,李阳阳.一种基于RUnet卷积神经网络的地震资料随机噪声压制方法[J].石油物探,2020,59(1):51-59.LUO Renze,LI Yangyang.Random seismic noise attenuation based on RUnet convolutional neural network[J].Geophysical Prospecting for Petroleum,2020,59(1):51-59.
[31]	VAN DER MAATEN L,HINTON G.Visualizing data using T-SNE[J].Journal of Machine Learning Research,2008,9(86):2579-2605.