A neural network-based method for analyzing diffracted wave velocity

Authors

TAO Junhong, College of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing 100083, ChinaFollow
ZHAO Jingtao, College of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing 100083, ChinaFollow
SHENG Tongjie, College of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China

Abstract

Background In seismic imaging, accurate velocity models are crucial for characterizing subsurface structures in a fine-scale manner. Notably, in coal mining, small-scale geological structures like faults and collapse columns are closely associated with mining accidents. These structures typically occur as diffracted waves in seismograms.Objective and Methods To effectively image these small-scale geological bodies, fine-scale velocity modeling using diffracted wave information is particularly important. Hence, this study proposed a neural network-based method for analyzing diffracted-wave velocity. First, diffracted-wave velocity spectra were generated using the gathers of diffracted waves that were separated in the common virtual source domain. Second, a gamma-ray spectrum of diffracted-wave velocity ratios was generated using the quasi-linear characteristics of diffracted waves in the migrated dip-angle domain. Finally, with the conventional reflected-wave velocity spectrum and the two diffracted-wave velocity spectra as inputs, intelligent diffracted-wave velocity modeling was performed based on a convolutional attention neural network. Results and Conclusions The tests using numerical simulation data verified that the diffracted-wave velocity analysis network can enhance the accuracy of fine-scale velocity modeling for geological bodies like stratigraphic pinch-outs and karst collapse columns. This network allows for the effective focusing of diffracted waves in the imaging profiles, thus achieving the fine-scale characterization of small- to medium-scale structures. The application of the proposed method to actual data from a coal mine further demonstrates the method's superiority over conventional methods in terms of velocity modeling efficiency and imaging accuracy. Therefore, the proposed method is more applicable to the imaging of small-scale structures under complex geologic conditions.

Keywords

diffracted wave, deep learning, velocity analysis, intelligent modeling, seismic imaging

DOI

10.12363/issn.1001-1986.24.05.0309

Recommended Citation

TAO Junhong, ZHAO Jingtao, SHENG Tongjie, et al. (2024) "A neural network-based method for analyzing diffracted wave velocity," Coal Geology & Exploration: Vol. 52: Iss. 9, Article 16.
DOI: 10.12363/issn.1001-1986.24.05.0309
Available at: https://cge.researchcommons.org/journal/vol52/iss9/16

Reference

[1] 赵惊涛，彭苏萍，陈宗南，等. 煤矿隐蔽致灾地质体地震绕射波探测方法[J]. 矿业科学学报，2022，7(1)：1−8.

ZHAO Jingtao，PENG Suping，CHEN Zongnan，et al. Seismic diffraction detection method for geological hidden disasters in coal mining[J]. Journal of Mining Science and Technology，2022，7(1)：1−8.

[2] LIU Zhenyue，BLEISTEIN N. Migration velocity analysis：Theory and an iterative algorithm[J]. Geophysics，1995，60(1)：142−153.

[3] YANG Fangshu，MA Jianwei. Deep-learning inversion：A next-generation seismic velocity model building method[J]. Geophysics，2019，84(4)：R583−R599.

[4] TANER M T，KOEHLER F. Velocity spectra—Digital computer derivation applications of velocity functions[J]. Geophysics，1969，34(6)：859−881.

[5] RATCLIFFE A，ADLER F. Accurate velocity analysis for Class II AVO events[C]//Society of Exploration Geophysicists. SEG Technical Program Expanded Abstracts 2000. 2000：232–235.

[6] SARKAR D，CASTAGNA J P，LAMB W J. AVO and velocity analysis[J]. Geophysics，2001，66(4)：1284−1293.

[7] YAN Jia，TSVANKIN I. AVO-sensitive semblance analysis for wide-azimuth data[J]. Geophysics，2008，73(2)：U1−U11.

[8] FOMEL S. Velocity analysis using AB semblance[J]. Geophysical Prospecting，2009，57(3)：311−321.

[9] 李衍达. 最大似然法速度谱估计的改进[J]. 地球物理学报，1983，26(2)：168−176.

LI Yenta. Improvement on estimation of velocity/depth spectra of maximum likelihood method[J]. Chinese Journal of Geophysics，1983，26(2)：168−176.

[10] 吕景贵，刘振彪，牛滨华，等. 一种叠加速度分析新方法[J]. 石油物探，2000，39(3)：36−42.

LYU Jinggui，LIU Zhenbiao，NIU Binhua，et al. A new approach for stack velocity analysis[J]. Geophysical Prospecting for Petroleum，2000，39(3)：36−42.

[11] 王维红，崔宝文，林春华. 加权抛物Radon变换叠加速度分析[J]. 天然气工业，2009，29(2)：42−44.

WANG Weihong，CUI Baowen，LIN Chunhua. Stock velocity analysis by weighted parabolic radon transform approach[J]. Natural Gas Industry，2009，29(2)：42−44.

[12] LUO S，HALE D. Velocity analysis using weighted semblance[J]. Geophysics，2012，77(2)：U15−U22.

[13] CHEN Yangkang，LIU Tingting，CHEN Xiaohong. Velocity analysis using similarity-weighted semblance[J]. Geophysics，2015，80(4)：A75−A82.

[14] EBRAHIMI S，KAHOO A R，CHEN Yangkang，et al. A high-resolution weighted AB semblance for dealing with amplitude-variation-with-offset phenomenon[J]. Geophysics，2017，82(2)：V85−V93.

[15] SACCHI M D. A bootstrap procedure for high-resolution velocity analysis[J]. Geophysics，1998，63(5)：1716−1725.

[16] 刘洋. 基于傅氏变换特点的一种速度分析新方法[J]. 石油地球物理勘探，1995，30(3)：329−336.

LIU Yang. A new velocity analysis method：Based on Fourier transform[J]. Oil Geophysical Prospecting，1995，30(3)：329−336.

[17] 孟阳. 椭圆展开法共炮点道集速度分析方法[D]. 中国地质大学(北京)，2011.

MENG Yang. Common shot gather velocity analysis based on the elliptic development method[D]. China University of Geosciences (Beijing)，2011.

[18] 谢俊法，孙成禹，王兴谋，等. 地震资料的多准则速度分析方法[J]. 物探与化探，2017，41(3)：513−520.

XIE Junfa，SUN Chengyu，WANG Xingmou，et al. The multi-criteria velocity analysis of seismic data[J]. Geophysical and Geochemical Exploration，2017，41(3)：513−520.

[19] ADLER F，BRANDWOOD S. Robust estimation of dense 3D stacking velocities from automated picking[C]//Society of Exploration Geophysicists. SEG Technical Program Expanded Abstracts 1999. 1999：1162–1165.

[20] ARNAUD J，RAPPIN D，DUNAND J P，et al. High density picking for accurate velocity and anisotropy determination[C]//Society of Exploration Geophysicists. SEG Technical Program Expanded Abstracts 2004. 2004：1627–1629.

[21] HARLAN W S. Constrained automatic moveout picking from semblances[EB/OL]. http://www.billharlan.com/papers/autopick.pdf，2001/2024-05-11

[22] ARAYA-POLO M，FARRIS S，FLOREZ M. Deep learning-driven velocity model building workflow[J]. The Leading Edge，2019，38(11)：872a1−872a9.

[23] ZHANG HAO，ZHU PEIMIN，GU YUAN，et al. Automatic velocity picking based on deep learning[C]//Society of Exploration Geophysicists. SEG Technical Program Expanded Abstracts 2019. San Antonio，Texas：2019：2604–2608.

[24] BISWAS R，VASSILIOU A，STROMBERG R，et al. Estimating normal moveout velocity using the recurrent neural network[J]. Interpretation，2019，7(4)：T819−T827.

[25] KAZEI V，OVCHARENKO O，ALKHALIFAH T. Velocity model building by deep learning：From general synthetics to field data application[C]//Society of Exploration Geophysicists. SEG Technical Program Expanded Abstracts 2020. 2020：1561–1565.

[26] PARK M J，SACCHI M D. Automatic velocity analysis using convolutional neural network and transfer learning[J]. Geophysics，2020，85(1)：V33−V43.

[27] SICKING C J. Diffraction semblance for velocity and structure analysis[C]//Society of Exploration Geophysicists. SEG Technical Program Expanded Abstracts 1987. 1987：424–426.

[28] BANCROFT J C，GEIGER H D. Equivalent offset CRP gathers[C]//Society of Exploration Geophysicists. SEG Technical Program Expanded Abstracts 1994. 1994：672–675.

[29] BANCROFT J C，GEIGER H D，WANG S，et al. Prestack migration by equivalent offsets and CSP gathers：An update：Vol.7[EB/OL]. https://www.crewes.org/Documents/ResearchReports/1995/1995-23.pdf，1995/2024-05-11

[30] AL-YAHYA K. Velocity analysis by iterative profile migration[J]. Geophysics，1989，54(6)：718−729.

[31] LIU Zhenyue. An analytical approach to migration velocity analysis[J]. Geophysics，1997，62(4)：1238−1249.

[32] SAVA P C，BIONDI B，ETGEN J. Wave-equation migration velocity analysis by focusing diffractions and reflections[J]. Geophysics，2005，70(3)：U19−U27.

[33] GARABITO G，DOS SANTOS SILVA J S，LIMA W. Migration velocity analysis based on focusing diffractions generated from CRS wavefront attributes：Application to real land data[J]. Geophysics，2022，87(2)：U43−U55.

[34] LANDA E，FOMEL S，RESHEF M. Separation，imaging，and velocity analysis of seismic diffractions using migrated dip-angle gathers[C]//Society of Exploration Geophysicists. SEG Technical Program Expanded Abstracts 2008. 2008：2176–2180.

[35] RESHEF M，LANDA E. Post-stack velocity analysis in the dip-angle domain using diffractions[J]. Geophysical Prospecting，2009，57(5)：811−821.

[36] ZHANG Kai，CHENG Jiubing，MA Zaitian，et al. Pre-stack time migration and velocity analysis methods with common scatter-point gathers[J]. Journal of Geophysics and Engineering，2006，3(3)：283−289.

[37] DECKER L，FOMEL S. A probabilistic approach to seismic diffraction imaging[J]. Lithosphere，2021，2021(1)：6650633.

[38] SHENG Tongjie，ZHAO Jingtao. Separation and imaging of diffractions using a dilated convolutional neural network[J]. Geophysics，2022，87(3)：S117−S127.

[39] ZHAO Jingtao，PENG Suping，DU Wenfeng，et al. Diffraction imaging method by Mahalanobis-based amplitude damping[J]. Geophysics，2016，81(6)：S399−S408.

[40] 黄建平，李振春，孔雪，等. 基于PWD的绕射波波场分离成像方法综述[J]. 地球物理学进展，2012，27(6)：2499−2510.

HUANG Jianping，LI Zhenchun，KONG Xue，et al. The review of the wave field separation method about reflection and diffraction based on the PWD[J]. Progress in Geophysics，2012，27(6)：2499−2510.

[41] LI Chuangjian，ZHAO Jingtao，PENG Suping，et al. Prestack diffraction separation in the common virtual source gather[J]. Geophysics，2021，86(2)：S113−S124.

[42] KLOKOV A，FOMEL S. Separation and imaging of seismic diffractions using migrated dip-angle gathers[J]. Geophysics，2012，77(6)：S131−S143.