基于自适应阈值约束的无监督聚类智能速度拾取

王迪, 袁三一, 袁焕, 曾华会, 王尚旭. 2021. 基于自适应阈值约束的无监督聚类智能速度拾取. 地球物理学报, 64(3): 1048-1060, doi: 10.6038/cjg2021O0305
引用本文: 王迪, 袁三一, 袁焕, 曾华会, 王尚旭. 2021. 基于自适应阈值约束的无监督聚类智能速度拾取. 地球物理学报, 64(3): 1048-1060, doi: 10.6038/cjg2021O0305
WANG Di, YUAN SanYi, YUAN Huan, ZENG HuaHui, WANG ShangXu. 2021. Intelligent velocity picking based on unsupervised clustering with the adaptive threshold constraint. Chinese Journal of Geophysics (in Chinese), 64(3): 1048-1060, doi: 10.6038/cjg2021O0305
Citation: WANG Di, YUAN SanYi, YUAN Huan, ZENG HuaHui, WANG ShangXu. 2021. Intelligent velocity picking based on unsupervised clustering with the adaptive threshold constraint. Chinese Journal of Geophysics (in Chinese), 64(3): 1048-1060, doi: 10.6038/cjg2021O0305

基于自适应阈值约束的无监督聚类智能速度拾取

  • 基金项目:

    国家重点研发计划(2018YFA0702504), 国家自然科学基金(41974140), 中央高校基本科研业务费专项资金(462019QNXZ03), 中国石油天然气集团有限公司-中国石油大学(北京)战略合作科技专项(ZLZX2020-03), 中国石油大学(北京)科研基金(2462020YXZZ008和2462020QZDX003)联合资助

详细信息
    作者简介:

    王迪, 女, 1996年生, 在读硕士研究生, 主要从事地震速度建模、动校正和地震解释方面的研究. E-mail: foilboil456@qq.com

    通讯作者: 袁三一, 男, 1983年生, 研究员, 博士生导师, 主要从事高分辨率地震资料处理、地震反演、智能地球物理勘探和复杂油气藏储层预测等方面的研究. E-mail: yuansy@cup.edu.cn
  • 中图分类号: P631

Intelligent velocity picking based on unsupervised clustering with the adaptive threshold constraint

More Information
  • 目前叠加速度的获取主要是通过人工拾取速度谱,存在着效率低、耗时长且易受人为因素影响的缺点.本文提出了一种基于自适应阈值约束的无监督聚类智能速度拾取方法,实现叠加速度的自动拾取,在保证速度拾取精度的同时提高拾取效率.利用时窗方法在速度谱中计算自适应阈值,从而识别出一次反射波速度能量团作为速度拾取的候选区域.然后,根据K均值方法将不同的速度能量团聚类,并将最终的聚类中心作为拾取的叠加速度.最后,依据人工拾取速度的经验,加入了离群速度点的后处理工作,以获得更光滑的速度场.模型和实际地震数据测试结果表明,本文提出的方法总体上与人工拾取叠加速度的精度相当,但明显提升了速度拾取效率,极大缓解了人工拾取负担.

  • 加载中
  • 图 1 

    一维数值模型

    Figure 1. 

    One dimensional model

    图 2 

    不同方法拾取速度比较

    Figure 2. 

    Comparison of velocities picked by different methods

    图 3 

    层速度场模型

    Figure 3. 

    Interval velocity model

    图 4 

    Marmousi模型中的单道CMP拾取结果

    Figure 4. 

    CMP gathers and the corresponding velocity curves picked by two different methods

    图 5 

    拾取的速度场与真实速度场比较

    Figure 5. 

    Comparisons of picked stacking velocity structures and the true reference

    图 6 

    Marmousi模型叠加剖面

    Figure 6. 

    Stacked sections of picked stacking velocity structures and the true reference

    图 7 

    实际数据CMP道集速度拾取及动校正结果

    Figure 7. 

    Velocity picking and NMO results of field data

    图 8 

    实际数据速度场对比

    Figure 8. 

    Comparisons of picked stacking velocity structures from field data

    图 9 

    三种方法实际数据叠加剖面

    Figure 9. 

    Stacked sections corresponding to three methods

  •  

    Ahmad A, Hashmi S. 2016. K-Harmonic means type clustering algorithm for mixed datasets. Applied Soft Computing, 48: 39-49. doi: 10.1016/j.asoc.2016.06.019

     

    Almarzoug A M, Ahmed F Y. 2012. Automatic seismic velocity picking.//87th Ann. Internat Mtg., Soc. Expi. Geophys.. Expanded Abstracts, 1-5.

     

    Araya-Polo M, Dahlke T, Frogner C, et al. 2017. Automated fault detection without seismic processing. The Leading Edge, 36(3): 208-214. doi: 10.1190/tle36030208.1

     

    Bin Waheed U, Al-Zahrani S, Hanafy S M. 2019. Machine learning algorithms for automatic velocity picking: K-means vs. DBSCAN.//89th Ann. Internat Mtg., Soc. Expi. Geophys.. Expanded Abstracts, 5110-5114.

     

    Biswas R, Vassiliou A, Stromberg R, et al. 2018. Stacking velocity estimation using recurrent neural network.//88th Ann. Internat Mtg., Soc. Expi. Geophys.. Expanded Abstracts, 2241-2245.

     

    Chen Y Q, Schuster G. 2018. Automatic semblance picking by a bottom-up clustering method.//SEG Maximizing Asset Value Through Artificial Intelligence and Machine Learning, SEG Global Meeting Abstracts, 44-48.

     

    Du Q Z, Li F, Hou B, et al. 2011. Angle-domain migration velocity analysis based on elastic-wave Kirchhoff prestack depth migration. Chinese Journal of Geophysics (in Chinese), 54(5): 1327-1339, doi:10.3969/j.issn.0001-5733.2011.05.022.

     

    Du Q Z, Guo C F, Zhao Q, et al. 2017. Vector-based elastic reverse time migration based on scalar imaging condition. Geophysics, 82(2): S111-S127. doi: 10.1190/geo2016-0146.1

     

    Fabien-Ouellet G, Sarkar R. 2020. Seismic velocity estimation: A deep recurrent neural-network approach. Geophysics, 85(1): U21-U29. doi: 10.1190/geo2018-0786.1

     

    Fomel S. 2009. Velocity analysis using AB semblance. Geophysical Prospecting, 57(3): 311-321. doi: 10.1111/j.1365-2478.2008.00741.x

     

    Galvis I S, Villa Y, Duarte C, et al. 2017. Seismic attribute selection and clustering to detect and classify surface waves in multicomponent seismic data by using k-means algorithm. The Leading Edge, 36(3): 239-248. doi: 10.1190/tle36030239.1

     

    Han D H, Zhao H Z, Yao Q L, et al. 2007. Velocity of heavy-oil sand.//77th Ann. Internat Mtg., Soc. Expi. Geophys.. Expanded Abstracts, 1619-1623.

     

    Hung C H, Chiou H M, Yang W N. 2013. Candidate groups search for K-harmonic means data clustering. Applied Mathematical Modelling, 37(24): 10123-10128. doi: 10.1016/j.apm.2013.05.052

     

    Li Q, Li Y B, Li Q C. 2019. Seismic response of anisotropic coal beds with vertical cracks. Chinese Journal of Geophysics (in Chinese), 62(1): 306-315, doi:10.6038/cjg2019M0006.

     

    Lumley D E. 1997. Monte Carlo automatic velocity picks. Stanford Exploration Project, 75(17): 1-25. http://www.mendeley.com/research/monte-carlo-automatic-velocity-picks/

     

    Ma S P, Wang Z H, Tian Y L, et al. 2010. Studies on geological meaning of seismic reflection events. Journal of Geophysics and Engineering (in Chinese), 45(3): 454-457. http://en.cnki.com.cn/Article_en/CJFDTOTAL-SYDQ201003024.htm

     

    Ma Y, Ji X, Fei T W, et al. 2018. Automatic velocity picking with convolutional neural networks.//88th Ann. Internat Mtg., Soc. Expi. Geophys.. Expanded Abstracts, 2066-2070.

     

    MacQueen J. 1967. Some methods for classification and analysis of multivariate observations. Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, 1: 281-297. http://ci.nii.ac.jp/naid/10012395366

     

    Martin G S, Wiley R, Marfurt K J. 2006. Marmousi2: an elastic upgrade for Marmousi. The Leading Edge, 25(2): 156-166. doi: 10.1190/1.2172306

     

    Meshbey V, Ragoza E, Kosloff U E, et al. 2002. Three-dimensional travel-time calculation based on Fermat's principle. Pure and Applied Geophysics, 159(7-8): 1563-1582. doi: 10.1007/s00024-002-8697-8

     

    Neidell N S, Taner M T. 1971. Semblance and other coherency measures for multichannel data. Geophysics, 36(3): 482-497. doi: 10.1190/1.1440186

     

    Park M J, Sacchi M. 2020. Automatic velocity analysis using convolutional neural network and transfer learning. Geophysics, 85(1): V33-V43. doi: 10.1190/geo2018-0870.1

     

    Ratcliffe A, Roberts G. 2003. Robust, automatic, continuous velocity Analysis.//73rd Ann. Internat Mtg., Soc. Expi. Geophys.. Expanded Abstracts, 2080-2083.

     

    Smith K. 2017. Machine learning assisted velocity autopicking.//87th Ann. Internat Mtg., Soc. Expi. Geophys.. Expanded Abstracts, 5686-5690.

     

    Song W, Ouyang Y L, Zeng Q C, et al. 2018. Unsupervised machine learning: K-means clustering velocity semblance auto-picking.//80th EAGE Annual International Meeting, Extended Abstracts, doi: https://doi.org/10.3997/2214-4609.201800919.

     

    Sun M Y, Zhang J. 2020. The near-surface velocity reversal and its detection via unsupervised machine learning. Geophysics, 85(3): U55-U63. doi: 10.1190/geo2019-0025.1

     

    Swan H W. 2001. Velocities from amplitude variations with offset. Geophysics, 66(6): 1735-1743. doi: 10.1190/1.1487115

     

    Tian Z B, Zhang Y B, Wang J Q, et al. 2016. Study on the pre-stack seismic inversion prediction method for rich coal-bed-gas reservoirs: a case in southeastern Shanxi province. Chinese Journal of Geophysics (in Chinese), 59(12): 4494-4504, doi:10.6038/cjg20161212.

     

    Toldi J L. 1989. Velocity analysis without picking. Geophysics, 54(2): 191-199. doi: 10.1190/1.1442643

     

    Xu W J, Yin J F, Wang H Z, et al. 2017. Automatic estimation of stacking velocity based on sparse inversion. Chinese Journal of Geophysics (in Chinese), 60(7): 2791-2800, doi:10.6038/cjg20170724.

     

    Yan F Y, Han D H, Yao Q L, et al. 2016. Seismic velocities of halite salt: Anisotropy, heterogeneity, dispersion, temperature, and pressure effects. Geophysics, 81(4): D293-D301. doi: 10.1190/geo2015-0476.1

     

    Yuan S Y, Wang S X, Luo Y N, et al. 2019. Impedance inversion by using the low-frequency full-waveform inversion result as an a priori model. Geophysics, 84(2): R149-R164. doi: 10.1190/geo2017-0643.1

     

    Zhang H, Zhu P M, Gu Y, et al. 2019. Automatic velocity picking based on deep learning.//89th Ann. Internat Mtg., Soc. Expi. Geophys.. Expanded Abstracts, 2604-2608.

     

    Zhang L, Claerbout J. 1990. Automatic dip-picking by non-linear optimization. Stanford Exploration Project, 67: 123-138. http://www.researchgate.net/publication/2349495_Automatic_Dip-Picking_By_Non-Linear_Optimization

     

    Zhang L. 1991. Automatic picking and its applications. Stanford Exploration Project, 70: 275-292. http://sepwww.stanford.edu/public/docs/sep70/lin2.pdf

     

    Zhang P, Lu W K, Zhang Y Q. 2015. Velocity analysis with local event slopes related probability density function. Journal of Applied Geophysics, 123: 177-187. doi: 10.1016/j.jappgeo.2015.10.010

     

    Zhang P, Lu W K. 2016. Automatic time-domain velocity estimation based on an accelerated clustering method. Geophysics, 81(4): U13-U23. doi: 10.1190/geo2015-0313.1

     

    杜启振, 李芳, 侯波等. 2011. 角度域弹性波Kirchhoff叠前深度偏移速度分析方法. 地球物理学报, 54(5): 1327-1339, doi:10.3969/j.issn.0001-5733.2011.05.022.

     

    李勤, 李永博, 李庆春. 2019. 垂向裂隙各向异性煤层地震波响应. 地球物理学报, 62(1): 306-315, doi:10.6038/cjg2019M0006.

     

    马水平, 王志宏, 田永乐等. 2010. 地震反射同相轴的地质含义. 石油地球物理勘探, 45(3): 454-457. https://www.cnki.com.cn/Article/CJFDTOTAL-SYDQ201003024.htm

     

    田忠斌, 张胤彬, 王建青等. 2016. 富含煤层气储层的叠前地震反演预测方法研究——以山西晋东南测区为例. 地球物理学报, 59(12): 4494-4504, doi:10.6038/cjg20161212.

     

    徐文君, 殷俊锋, 王华忠等. 2017. 基于稀疏反演理论的自动叠加速度反演方法. 地球物理学报, 60(7): 2791-2800, doi:10.6038/cjg20170724.

  • 加载中

(9)

计量
  • 文章访问数:  516
  • PDF下载数:  422
  • 施引文献:  0
出版历程
收稿日期:  2020-08-11
修回日期:  2021-01-03
上线日期:  2021-03-10

目录