基于波形特征向量的凝聚层次聚类地震相分析

doi:10.11720/wtyht.2020.1153

摘要
图/表
参考文献
相关文章
Metrics

全文: PDF(11214 KB) HTML
输出: BibTeX | EndNote (RIS)

摘要

常规的基于地震沉积学原理的地震相分析,主要利用地震切片技术沿目标层提取均方根振幅属性,在地震信号信噪比较低,目标层厚度薄时,容易影响地震相分析的精度和可靠性。本文从地震沉积学原理出发,沿地层切片提取地震波形特征向量,然后引入地震波形特征向量凝聚层次聚类方法(agglomerative hierarchical clustering,AHC)开展地震相划分。波形凝聚层次聚类是一种无监督的机器学习算法,与传统的地层切片地震相分析方法相比较,基于波形聚类的分析方法,通过波形特征的变化,综合考虑了地震信号的振幅、相位和频率属性特征,具有更好的抗噪能力和更高的横向分辨率。物理模型数据测试和实际资料应用都证明了该方法的稳定性和适用性,验证了本方法具有较好的沉积相特征划分能力,是一类新的岩性分析工具,具有良好的应用前景。

	服务

	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	刘仕友
	宋炜
	应明雄
	孙万元
	汪锐

关键词 ：机器学习, 凝聚层次聚类, 波形聚类, 地震相, 地震沉积学

Abstract：

Conventional seismic facies analysis based on seismic sedimentology principle mainly uses seismic slicing technology to extract RMS amplitude attributes along the target layer.When the signal-to-noise ratio of seismic signals is low and the target layer is thin,the accuracy and reliability of seismic facies analysis will be easily affected.In this study,on the basis of the principle of seismic sedimentology,the feature vectors of seismic waveforms were extracted along stratigraphic slices,and then the Agglomerative Hierarchical Clustering (AHC) method was introduced to classify seismic facies.Waveform AHC is an unsupervised machine learning algorithm.Compared with the traditional method of seismic facies analysis for stratum slices,the method based on waveform clustering considers the amplitude, phase and frequency attributes of seismic signals synthetically through the change of waveform characteristics.It has better anti-noise capability and higher horizontal resolution.The stability and applicability of this method have been proved by physical model data testing and practical data application.It has been proved that this method has a good capability of distinguishing sedimentary facies characteristics,and hence it is a new kind of reservoir facies analysis tool and has a good application prospect.

Key words： machine learning agglomerative hierarchical clustering waveform clustering seismic facing seismic sedimentology

收稿日期: 2019-03-20 出版日期: 2020-04-22

P631.4

基金资助:国家科技重大专项课题“琼东南盆地深水区大中型气田形成条件与勘探关键技术”(2016ZX05026-002)

通讯作者: 宋炜

作者简介: 刘仕友(1982-),男,高级工程师,2007年毕业于中国石油大学(华东),主要从事储层预测及烃类检测工作。Email: liushiyou@139.com

引用本文:

刘仕友, 宋炜, 应明雄, 孙万元, 汪锐. 基于波形特征向量的凝聚层次聚类地震相分析[J]. 物探与化探, 2020, 44(2): 339-349.
Shi-You LIU, Wei SONG, Ming-Xiong YING, Wan-Yuan SUN, Rui WANG. Agglomerative hierarchical clustering seismic facies analysis based on waveform eigenvector. Geophysical and Geochemical Exploration, 2020, 44(2): 339-349.

链接本文:

https://www.wutanyuhuatan.com/CN/10.11720/wtyht.2020.1153 或 https://www.wutanyuhuatan.com/CN/Y2020/V44/I2/339

Fig.1 相同数据集不同连接类型的分类结果
a—单连接;b—平均连接;c—全连接

Fig.2 相同数据集不同连接约束
a—无连接约束;b—有连接约束

Fig.3 物理模型采集尺寸及参数示意图

Fig.4 物理模型6层砂体空间分布示意图

Fig.5 砂体叠置模型垂直切面示意

Fig.6 物理模型偏移剖面及基于地震沉积学原理解释的层位

Fig.7 凝聚层次聚类输入的200个波形曲线

Fig.8 物理模型第一层砂体平面形态、均方根振幅属性及波形凝聚层次聚类结果
a—第一层“蛇形”砂体平面形态;b—沿地层切片提取的均方根振幅属性;c—波形凝聚层次聚类结果(K=7,波形向量31维);d—波形凝聚层次聚类结果(K=7,波形向量37维)

Fig.9 物理模型第二至第五层砂、泥岩空间展布及形态
a—“肠状及指状”砂体平面形态;b—“肠状”砂体和“椭圆形”泥岩平面形态;c—“哑铃状”砂体和“指状”泥岩平面形态展布;d—“菱形”砂体和“点状”泥岩平面形态展布

Fig.10 各层地层切片均方根振幅属性地震相划分
a—均方根振幅属性“肠状”砂体和“指状”砂体的平面展布;b—均方根振幅属性“肠状”砂体和“椭圆形”泥岩的平面展布;c—均方根振幅属性“哑铃状”砂体和“指状”泥岩的平面展布;d—均方根振幅属性“菱形”砂体和“点状”泥岩的平面展布

Fig.11 各层凝聚层次聚类地震相分布
a—AHC属性“肠状”砂体和“指状”砂体的平面展布;b—AHC属性“肠状”砂体和“椭圆形”泥岩的平面展布;c—AHC“哑铃状”砂体和“指状”泥岩的平面展布;d-AHC属性“菱形”砂体和“点状”泥岩的平面展布

Fig.12 目标区基于地震沉积学原理层位解释

Fig.13 T₇₀层等T₀图

Fig.14 沿T₇₀提取的叠前时间偏移数据体地层切片均方根振幅属性

Fig.15 沿T₇₀地层切片从叠前时间偏移数据体提取地震波形获得的凝聚层次聚类属性

[1]	Sloss L L . Stratigraphic models in exploration[J]. AAPG Bulletin, 1962,46(7):1040-1047.
[2]	Vail P R, Mitchum M, Thompson S , et al. Seismic stratigraphy and global changes of sea level,Part4:Global cycles of relative changes of sea level[G]//C.E.Payton,ed.Seismic stratigraphy applications to hydrocarbon exploration[J]. AAPG Memoir, 1977,26:83-97.
[3]	Zeng H L, Backus M M, Barrow K T , et al. Stratal slicing,Part I:Realistic 3-D seismic model[J]. Geophysics, 1998,63(2):502-513.
[4]	Zeng H L, Henry S C, Riola J P . Stratal slicing,Part II:Real 3-D seismic data[J]. Geophysics, 1998,63(2):514-521.
[5]	Zeng H L, Hentz T F, Wood L J . Stratal slicing of Miocene-Pliocene sediments in Vermilion Block 50-Tiger Shoal area,offshore Louisiana[J]. The Leading Edge, 2001,20(4):408-418.
[6]	Zeng H L, Ambrose W A . Seismic sedimentology and regional depositional systems in Mioceno Norte,Lake Maracaibo,Venezuela[J]. The Leading Edge, 2001,20(11):1260-269.
[7]	Zeng H L, Backus M M, Barrow K T , et al. Stratal slicing,Part I:Realistic 3-D seismic model[J]. Geophysics, 1998,63(2):502-513.
[8]	Zeng H L, Henry S C, Riola J P . Stratal slicing,PartⅡ:Realistic 3-D seismic model[J]. Geophysics, 1998,63(2):514-522.
[9]	Zeng H L, Hentz T F, Wood L J . Stratal slicing of Miocene-Plioeene sediments in Vermilion Block 50,Tiger Shoal area,offshore Louisiana[J]. The Leading Edge, 2001,20(4):408-418.
[10]	Hall B . Facies classification using machine learning[J]. The Leading Edge, 2016,36(10):906-909.
[11]	Bhattacharya S, Carr T R, Pal M . Comparison of supervised and unsupervised approaches for mudstone lithofacies classification:Case studies from the Bakken and Mahantango-Marcellus Shale,USA[J]. Journal of Natural Gas Science & Engineering, 2016,33:1119-1133
[12]	刘爱群, 陈殿远, 任科英 . 分频与波形聚类分析技术在莺歌海盆地中深层气田区的应用[J]. 地球物理学进展, 2013,28(1):338-344.
[12]	Liu A Q, Chen D Y, Ren K Y . Frequency decomposition and waveform cluster analysis techniques Yinggehai Basin gas field in the deep area of application[J]. Progress in Geophysics, 2013,28(1):338-344.
[13]	白博, 舒梦珵, 康洪全 , 等. 基于伪阻抗体波形聚类的贝克灰岩储层预测方法[J]. 物探化探计算技术, 2015,37(6):724-727.
[13]	Bai B, Shu M C, Kang H Q , et al. Coquina reservoir prediction method of seismic pseudo-impedance waveform clustering[J]. Computing Techniques for Geophysical and Geochemical Exploration, 2015,37(6):724-727.
[14]	李辉, 罗波, 何雄涛 , 等. 基于地震波形聚类储集砂体边界识别与预测[J]. 工程地球物理学报, 2017,14(5):573-577.
[14]	Li H, Luo B, He X T , et al. Boundary identification and prediction of sand body based on seismic waveform[J]. Chinese Journal of Engineering Geophysics, 2017,14(5):573-577.
[15]	徐海, 都小芳, 高君 , 等. 基于波形聚类的沉积微相定量解释技术研究[J]. 石油物探, 2018,57(5):744-755.
[15]	Xu H, Du X F, Gao J , et al. Quantitative interpretation of sedimentary microfaacies based on waveform clustering:a case study of X oilfield,Middle East[J]. Geophysical Prospecting for Petroleum, 2018,57(5):744-755.
[16]	张艳, 张春雷, 高世臣 . 基于SOM和HSV染色技术的致密砂岩储层地震相分析[J]. 天然气地球科学, 2018,29(2):259-267.
[16]	Zhang Y, Zhang C L, Gao S C . Seismic facies analysis of tight sandstone reservoir based on SOM and HSV color techniqu[J]. Natural Gas Geoscience, 2018,29(2):259-267.
[17]	罗浩然, 尹成, 丁峰 , 等. 概率神经网络的平滑参数分析及在地震属性分析中的应用[J]. 石油物探, 2017,56(4):551-558.
[17]	Luo H R, Yin C, Ding F , et al. The smoothing parameter analysis of probabilistic neural network and its application[J]. Geophysical Prospecting for Petroleum, 2017,56(4):551-558.
[18]	魏艳, 尹成, 丁峰 , 等. 地震多属性综合分析的应用研究[J]. 石油物探, 2007,46(1):42-47.
[18]	Wei Y, Yin C, Ding F , et al. Synthetic analysis of seismic multi-attribute and its application[J]. Geophysical Prospecting for Petroleum, 2007,46(1):42-47.

[1]	王丹, 贾跃玮, 魏水建, 郑文波. 新场须四段叠后裂缝综合预测[J]. 物探与化探, 2014, 38(5): 1038-1044.
[2]	谢会文, 许永忠, 郑多明, 王兴军, 苗青, 徐亚, 汤浩哲. 火成岩速度反演及三维速度场建立的关键技术及效果分析[J]. 物探与化探, 2013, 37(6): 1071-1079.
[3]	陈殿远, 陈志宏, 刘仕友, 陈雪菲. 地震频率域信息在涠西南地区勘探中的应用[J]. 物探与化探, 2013, 37(3): 467-472.
[4]	祁雪梅, 董守华. 地震相技术在煤层气勘探中的应用[J]. 物探与化探, 2012, 36(2): 170-173，179.
[5]	隋俊杰, 阎建国, 朱强. 层序地层格架下的地震相分析技术及其应用[J]. 物探与化探, 2012, 36(2): 228-233.
[6]	崔大尉, 王一, 田庆路, 刘最亮, 齐振洪. 利用地震属性解释煤层冲刷带[J]. 物探与化探, 2011, 35(2): 234-237.
[7]	胡伟光, 蒲勇, 易小林, 肖伟, 尤思科, 赵卓男. 川东北元坝地区生物礁识别[J]. 物探与化探, 2010, 34(5): 635-642.
[8]	张明学, 刘淑芬. 乌尔逊凹陷南部大磨拐河组地震相[J]. 物探与化探, 2009, 33(6): 638-641.
[9]	冯兴强, 杨珍, 张忠民. 塔河油田泥盆系东河塘组地震相研究[J]. 物探与化探, 2009, 33(5): 552-556.

Viewed

Full text

Abstract

Cited

Shared

Discussed