基于多粒度集成学习的地震相聚类分析技术

doi:10.3969/j.issn.0255-8297.2025.04.007

摘要/Abstract

摘要： 为了更有效地降低地质结构差异对储层预测的影响，提出了一种基于多粒度集成学习的地震相聚类分析技术。首先从粗粒度、细粒度和微粒度三个角度分别提取地震数据的不同尺度特征。粗粒度特征利用斯皮尔曼相关系数反映地层间的宏观关系；细粒度特征基于长短期记忆网络学习波形之间的细节特性；微粒度特征则基于动态时间规整距离捕捉单一波形的微观差异。在此基础上，利用自组织映射方法获得不同粒度下的聚类结果，并采用基于软配准的集成学习技术融合不同粒度下的聚类结果，有效解决了单一粒度受地质结构差异影响较大的问题。实验结果表明，所提出的多粒度集成学习算法能够更好地改善地震相聚类结果，并为不同区域的储层预测提供有效参考。

关键词: 地震相聚类分析, 多粒度, 集成学习, 动态时间规整, 自组织映射

Abstract: To mitigate the impact of geological structural variations on reservoir prediction, this study proposes a novel seismic phase clustering analysis technique based on multi-granularity ensemble learning. The technique first extracts features at three scales: coarse-grained, fine-grained, and micro-grained. Coarse-grained features are derived using the Spearman correlation coefficient to reflect the macroscopic relationships between strata. Fine-grained features are extracted via long short-term memory (LSTM) networks to capture detailed characteristics among waveforms. Micro-grained features are obtained through dynamic time warping (DTW) distances to capture the microscopic differences within individual waveforms. Subsequently, through self-organizing map methods, clustering results are obtained for each granularity. A soft alignment-based ensemble learning technique is then applied to integrate the clustering results from different granularities, effectively addressing the limitations of single-granularity approaches influenced by geological structural variations. Experimental results demonstrate that the proposed multi-granularity ensemble learning algorithm significantly enhances seismic clustering accuracy and provides a valuable reference for reservoir prediction across different regions.

Key words: seismic phase clustering analysis, multi-granularity, ensemble learning, dynamic time warping (DTW), self-organizing maps (SOM)

中图分类号:

TP18

罗红梅, 王长江, 杨培杰, 管晓燕, 周小杰, 余航. 基于多粒度集成学习的地震相聚类分析技术[J]. 应用科学学报, 2025, 43(4): 643-655.

LUO Hongmei, WANG Changjiang, YANG Peijie, GUAN Xiaoyan, ZHOU Xiaojie, YU Hang. Seismic Phase Clustering Analysis Technology Based on Multi-granularity Ensemble Learning[J]. Journal of Applied Sciences, 2025, 43(4): 643-655.

参考文献

[1] Lerat O, Nivlet P, Doligez B, et al. Construction of a stochastic geological model constrained by high-resolution 3D seismic data-application to the Girassol field, offshore Angola [C]//SPE Annual Technical Conference and Exhibition, 2007: 110422.
[2] Brown A R. Interpretation of three-dimensional seismic data [M]. Houston: Society of Exploration Geophysicists, 2011.
[3] 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 J B, Zhao P K. New progress in foreign research on seismic phase classification technology [J]. Progress in Exploration Geophysics, 2009, 32(3): 167-171. (in Chinese)
[4] 唐金炎, 杜品, 陈智雍. 地震几何属性参数在地震相识别中的应用[J]. 油气地球物理, 2011, 9(1): 34-35. Tang J Y, Du P, Chen Z Y. Application of seismic geometric attribute parameters in seismic facies identification [J]. Oil and Gas Geophysics, 2011, 9(1): 34-35. (in Chinese)
[5] 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.
[6] Jordan M I, Mitchell T M. Machine learning: trends, perspectives, and prospects [J]. Science, 2015, 349(6245): 255-260.
[7] Gao D L. Application of three-dimensional seismic texture analysis with special reference to deep-marine facies discrimination and interpretation: offshore Angola, west Africa [J]. AAPG Bulletin, 2007, 91(12): 1665-1683.
[8] Xu C, Tao D C, Xu C. A survey on multi-view learning [DB/OL]. (2013-04-20) [2023-10-24]. https://arxiv.org/abs/1304.5634.
[9] Myers L, Sirois M J. Spearman correlation coefficients, differences between [DB/OL]. (2014- 09-29) [2023-10-24]. https://doi.org/10.1002/9781118445112.stat02802.
[10] Hochreiter S, Schmidhuber J. Long short-term memory [J]. Neural Computation, 1997, 9(8): 1735-1780.
[11] Muda L, Begam M, Elamvazuthi I. Voice recognition algorithms using Mel frequency cepstral coefficient (MFCC) and dynamic time warping (DTW) techniques [DB/OL]. (2010-03-22) [2023- 10-24]. https://arxiv.org/abs/1003.4083.
[12] Kohonen T. The self-organizing map [J]. Proceedings of the IEEE, 1990, 78(9): 1464-1480.
[13] 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 X Y, Gu H M, Luo H M, et al. Intelligent identification of seismic facies based on improved deep learning method [J]. Oil Geophysical Prospecting, 2020, 55(6): 1169-1177. (in Chinese)
[14] Liu M, Jervis M, Li W, et al. Seismic facies classification using supervised convolutional neural networks and semisupervised generative adversarial networks [J]. Geophysics, 2020, 85(4): O47-O58.
[15] Yang L, Sun S Z. Seismic horizon tracking using a deep convolutional neural network [J]. Journal of Petroleum Science and Engineering, 2020, 187: 106709.
[16] 赵军才. 基于标签精炼方法的地震相深度学习预测[J]. 石油物探, 2023, 62(3): 431-441. Zhao J C. Deep learning prediction of seismic facies based on label refinement method [J]. Geophysical Prospecting for Petroleum, 2023, 62(3): 431-441. (in Chinese)
[17] 王倩楠, 王治国, 杨阳, 等. 基于多特征融合自编码器的无监督地震相分类研究[J]. 地球物理学报, 2024, 67(1): 370-378. Wang Q N, Wang Z G, Yang Y, et al. Research on unsupervised seismic facies classification based on multi-feature fusion autoencoder [J]. Chinese Journal of Geophysics, 2024, 67(1): 370- 378. (in Chinese)
[18] 硕良勋, 赵云鹤, 柴变芳. 基于半监督对抗网络的地震相识别[J]. 地球物理学进展, 2023, 38(5): 2105-2113. Shuo L X, Zhao Y H, Chai B F. Seismic phase identification based on semi-supervised adversarial network [J]. Progress in Geophysics, 2023, 38(5): 2105-2113. (in Chinese)
[19] Sahu R T, Verma M K, Ahmad I. Density-based spatial clustering of application with noise approach for regionalisation and its effect on hierarchical clustering [J]. International Journal of Hydrology Science and Technology, 2023, 16(3): 240-269.
[20] Hinneburg A, Keim D A. Optimal grid-clustering: towards breaking the curse of dimensionality in high-dimensional clustering [C]//25th International Conference on Very Large Data Bases, 1999: 506-517.
[21] 郑晓东, 李劲松, 路交通, 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. Zheng X D, Li J S, Lu J T, et al. Unsupervised seismic phase analysis technology based on SOM and PSO [J]. Chinese Journal of Geophysics, 2015, 58(9): 3412-3423. (in Chinese)
[22] 郭乃川, 王尚旭, 董春晖, 等. 地震勘探中小尺度非均匀性的描述及长波长理论[J]. 地球物理学报, 2012, 55(7): 2385-2401. Guo N C, Wang S X, Dong C H, et al. Description of small-scale heterogeneity and longwavelength theory in seismic exploration [J]. Chinese Journal of Geophysics, 2012, 55(7): 2385- 2401. (in Chinese)
[23] 杨林海. 地震波形分类及“包络解释” 技术在储层预测中的应用[J]. 中国高新科技, 2020(5): 73-75. Yang L H. Application of seismic waveform classification and “envelope interpretation” technology in reservoir prediction [J]. China High and New Technology, 2020(5): 73-75. (in Chinese)
[24] Chopra S, Marfurt K J. Seismic attributes for prospect identification and reservoir characterization [M]. Houston: Society of Exploration Geophysicists, 2007.
[25] Cohen I, Huang Y, Chen J, et al. Pearson correlation coefficient [M]. Berlin: Springer-Verlag, 2009.
[26] Kraskov A, Stögbauer H, Grassberger P. Estimating mutual information [J]. Physical review E, 2004, 69(6): 066138.
[27] Mackiewicz A, Ratajczak W. Principal components analysis (PCA) [J]. Computers & Geosciences, 1993, 19(3): 303-342.
[28] Kingma D P, Welling M. Auto-encoding variational bayes [DB/OL]. (2013-12-20) [2023-10- 24]. https://arxiv.org/abs/1312.6114.
[29] Cohen J. A coefficient of agreement for nominal scales [J]. Educational and Psychological Measurement, 1960, 20(1): 37-46.
[30] Aranganayagi S, Thangavel K. Clustering categorical data using silhouette coefficient as a relocating measure [C]//7th International Conference on Computational Intelligence and Multimedia Applications, 2007: 13-17.
[31] Kuhn H W. The Hungarian method for the assignment problem [J]. Naval Research Logistics Quarterly, 1955, 2(1/2): 83-97.