Seismic Facies Analysis Based on Spectral Clustering with Waveform Characteristic Vector
-
摘要:
本文提出一种基于地震沉积学原理沿层提取地震波形特征向量，并以谱聚类（spectral clustering）分析进行地震相划分的方法。谱聚类能够处理非线性的数据结构和高维数据的聚类问题，但其相似度矩阵的构建和谱分解的计算较为复杂，需要较高的计算资源和时间成本。为提高谱聚类算法的效率和可扩展性，本文提出将Mini-batch K-means算法与谱聚类算法结合起来的MKSC算法，在提高谱聚类算法精度的同时大大降低谱聚类空间的复杂度。经过对数值模拟、地球物理模型数据和实际地震资料的处理分析，证明该方法在沉积相划分、沉积相特征识别方面的效果明显，是一种具有良好应用前景的新型沉积特征分析工具。
Abstract:Based on the principle of seismic sedimentology, the feature vectors of seismic waveforms are extracted along stratum slices, and spectral clustering analysis is introduced to classify seismic facies. Spectral clustering is an unsupervised machine learning algorithm. Its essence is to simplify the expression of high-dimensional seismic data in the form of feature vectors, which belongs to the process of dimensionality reduction. Considering the traces with specific time windows in the seismic work area as nodes of the graph and the similarity between traces as the weight of the edges, a graph model can be constructed. Spectral clustering must determine the best segmentation method to complete the segmentation of the graph, so that different types of sedimentary characteristics can be distinguished. Physical model and actual data processing and analysis demonstrate that this method is capable of dividing sedimentary facies characteristics and is a new kind of facies analysis tool for reservoir classification, which has good application prospects.
-
-
![]()
图 1 无向图及其邻接矩阵特征向量
Figure 1. Feature vectors of the undirected graph and its adjacency matrix
![]()
图 2 相同数据集不同聚类方式分类结果
Figure 2. Classification results of the same dataset by different clustering methods
![]()
图 3 物理模型的采集尺寸及参数示意图
Figure 3. Schematic of the acquisition size and parameters of the physical model
![]()
图 6 物理模型偏移剖面及基于地震沉积学原理解释的层位
Figure 6. Migration section of the physical model and horizon interpretation based on the seismic sedimentology principle
![]()
图 8 物理模型第2至第5层砂、泥岩空间展布及形态
Figure 8. Spatial distribution and morphology of sand and mudstone in the second to fifth layers of the physical model
![]()
图 9 为各层的地层切片均方根振幅地震相
Figure 9. Slices of root mean square amplitude seismic phase of stratums
![]()
图 10 各层MKSC 聚类地震相分布
Figure 10. MKSC clustering seismic facies distribution of stratums
![]()
图 11 目标区基于地震沉积学原理解释的层位
Figure 11. Horizon interpretation based on seismic sedimentological principles in the target area
![]()
图 14 分流河道中心部位不同水动力条件下的相变示意图
Figure 14. Schematic diagram of phase transition in the central part of distributary channel under different hydrodynamic conditions
![]()
图 16 H3c段MKSC聚类属性平面图和沉积相平面图
Figure 16. MKSC clustering attribute plan and sedimentary facies plan of H3c
![]()
图 17 H3b段MKSC聚类属性平面图和沉积相平面图
Figure 17. MKSC clustering attribute plan and sedimentary facies plan of H3b
表 1 不同聚类分析算法计算效率比较
Table 1 Comparison of the computational efficiency of different clustering analysis algorithms
算法类型 Mini-batch K-means Spectral clustering MKSC 计算时间/s 0.17 0.21 0.17+0.09 
下载: 导出CSV
-
[1] ZENG H, BACKUS M M, BARROW T K, et al. Stratal slicing, Part I: Realistic 3-D seismic model[J]. Geophysics, 1998, 63(2): 502−513. doi: 10.1190/1.1444351
[2] ZENG H, HENRY C S, RIOLA P J. Strata slicing; Part II, Real 3-D seismic data[J]. Geophysics, 1998, 63(2): 514−521. doi: 10.1190/1.1444352
[3] ZENG H, HENTZ F T, WOOD J L. Stratal slicing of Miocene-Pliocene sediments in vermilion block 50-Tiger Shoal Area, offshore Louisiana[J]. The Leading Edge, 2012, 20(4): 408−418.
[4] ZENG H, AMBROSE A W, VILLALTA E. Seismic sedimentology and regional depositional systems in Mioceno Norte, Lake Maracaibo, Venezuela[J]. The Leading Edge, 2001, 20(11): 260−269.
[5] BHATTACHARYA S, CARR R T, 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 and Engineering, 2016, 33: 1119−1133. doi: 10.1016/j.jngse.2016.04.055
[6] 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. 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): 0338-0344. (in Chinese).
[7] 白博, 舒梦珵, 康洪全, 等. 基于伪阻抗体波形聚类的贝壳灰岩储层预测方法[J]. 物探化探计算技术, 2015, 37(6): 724-727. 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. (in Chinese).
[8] 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. 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. (in Chinese).
[9] 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−以中东地区 X油田为例[J]. 石油物探, 2018,57(5): 744−755. doi: 10.3969/j.issn.1000-1441.2018.05.014 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. (in Chinese). doi: 10.3969/j.issn.1000-1441.2018.05.014
[10] 刘仕友, 宋炜, 应明雄, 等. 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. DOI: 10.11720/wtyht.2020.1153. LIU S Y, SONG W, YING M X, et al. Agglomerative hierarchical clustering seismic facies analysis based on waveform eigenvector[J]. Geophysical and Geochemical Exploration, 2020, 44(2): 339−349. DOI: 10.11720/wtyht.2020.1153. (in Chinese).
[11] 杨随心, 耿修瑞, 杨炜暾, 等. 一种基于谱聚类算法的高光谱遥感图像分类方法[J]. 中国科学院大学学报, 2019,36(2): 267−274. doi: 10.7523/j.issn.2095-6134.2019.02.015 YANG S X, GENG X R, YANG W T, et al. A method of hyperspectral remote sensing image classification based on spectral clustering[J]. Journal of University of Chinese Academy of Sciences, 2019, 36(2): 267−274. (in Chinese). doi: 10.7523/j.issn.2095-6134.2019.02.015
[12] NG A Y, JORDAN M I, WEISS Y. On spectral clustering: Analysis and an algorithm[J]. Advances in Neural Information Processing Systems, 2001, 14: 849−856.
-
期刊类型引用(5)
1. 孙红全，潘小磊. 多层螺旋CT联合磁共振成像对胸腰椎压缩性骨折的诊断价值研究. 黑龙江医药科学. 2025(02): 154-156 . 
百度学术
2. 燕林. 急慢性椎体骨折患者常规胸腹部CT图像特征分析. 影像研究与医学应用. 2024(07): 60-62 . 百度学术
3. 尚晓情，陈英敏，刘向，高慧敏，贾秀川，暴云锋. 双能CT虚拟去钙技术在“臀坐式”骶尾椎急性损伤诊断中的价值. CT理论与应用研究. 2024(06): 725-732 . 本站查看
4. 李微，王毅，周宇，韩雪，王丹. 单源双能量CT虚拟去钙成像对脊柱压缩性骨折骨髓水肿的诊断价值研究. 中国医学装备. 2024(12): 61-65 . 百度学术
5. 马欢，罗嗣频，傅菲，邓欣，万业达. 应用能谱CT分析退行性腰椎皮质羟基磷灰石和钙含量. 中国医疗设备. 2021(10): 96-99 . 百度学术
其他类型引用(2)
计量
- 文章访问数: 206
- HTML全文浏览量: 103
- PDF下载量: 50
- 被引次数: 7
