• ISSN 1003-3238
  • CN 11-2368/P

通过无监督机器学习自动拾取微震事件

Y. K. Chen 李帛珊 唐丽华 孙燕萍 吕春来

引用本文:
Citation:

通过无监督机器学习自动拾取微震事件

  • 基金项目:

    新疆维吾尔自治区自然科学基金项目(2017D01A66)资助

  • 摘要: 高效的波至拾取在微震和地震数据处理及成像过程中起到重要作用。广泛使用的基于波至拾取算法的短期平均和长期平均比(STA/LTA),对中强度随机环境噪声的敏感程度较低。为了使最先进的波至拾取方法奏效,首先需要对微震数据进行预处理,例如,消除足量的噪声,再由波至拾取法进行分析。为了解决微震或地震事件波至拾取的噪声问题,利用机器学习技术帮助识别微震或地震数据中的地震波形。由于受监督机器学习算法对大量设计好的训练数据具有依赖性,本文利用无监督机器学习算法将时间样本分为两组,即波形点和非波形点。已证明模糊聚类算法可以运用于微震拾取。一组复杂程度不同的合成、真实微震和地震数据集表明,即使在中强背景噪声情况下,该方法在拾取微震事件方面比最先进的STA/LTA方法表现得更稳健。
  • [1]

    Allen,R.V.,1978.Automatic earthquake recognition and timing from single traces,Bull.seism.Soc.Am.,68(5),1521-1532.
    [2]

    Arrowsmith,S.J.& Eisner,L.,2006.A technique for identifying microseismic multiplets and application to the Valhall field,North Sea,Geophys.J.Int.,71(2),V31-V40.
    [3]

    Bezdek,J.C.,1981.Pattern Recognition with Fuzzy Objective Function Algoritms,Plenum Press.
    [4]

    Bogiatzis,P.& Ishii,M.,2015.Continuous wavelet decomposition algorithms for automatic detec-tion of compressional-and shear-wave arrival times,Bull.seism.Soc.Am.,105(3),1628-1641.
    [5]

    Candès,E.J.,Demanet,L.,Donoho,D.L.& Ying,L.,2006.Fast discrete curvelet transforms,Multiscale Model.Simul.,5,861-899.
    [6]

    Chen,Y.,2016.Dip-separated structural filtering using seislet thresholding and adaptive empirical mode decomposition based dip filter,Geophys.J.Int.,206(1),457-469.
    [7]

    Chen,Y.,2017.Fast dictionary learning for noise attenuation of multidimensional seismic data,Geophys.J.Int.,209,21-31.
    [8]

    Chen,Y.& Fomel,S.,2015.Random noise attenu-ation using local signaland-noise orthogonalization,Geophysics,80,WD1-WD9.
    [9]

    Chen,Y.,Fomel,S.& Hu,J.,2014.Iterative deb-lending of simultaneous-source seismic data using seislet-domain shaping regularization,Geo-physics,79,V179-V189.
    [10]

    Chen,Y.,Zhang,D.,Huang,W.& Chen,W.,2016a.An open-source matlab code package for improved rank-reduction 3D seismic data denois-ing and reconstruction,Comput.Geosci.,95,59-66.
    [11]

    Chen,Y.,Zhang,D.,Jin,Z.,Chen,X.,Zu,S.,Huang,W.& Gan,S.,2016b.Simultaneous denoising and reconstruction of 5D seismic data via dam-ped rank-reduction method,Geophys.J.Int.,206,1695-1717.
    [12]

    Chen,Y.,Zhou,Y.,Chen,W.,Zu,S.,Huang,W.& Zhang,D.,2017.Empirical low rank decomposition for seismic noise attenuation,IEEE Trans.Geosci.Remote Sen.,55(8),4696-4711.
    [13]

    Coppens,F.,1985.First arrival picking on common-offset trace collections for automatic estimation of static corrections,Geophys.Prospect.,33(8),1212-1231.
    [14]

    Dunn,J.C.,1973.A fuzzy relative of the isodata process and its use in detecting compact well-separated clusters,J.Cybern.,3,32-57.
    [15]

    Eisner,L.,Fischer,T.& Calvez,J.H.L.,2006.Detection of repeated hydraulic fracturing out-of-zone growth by microseismic monitoring,Leading Edge,25,548-554.
    [16]

    Elad,M.& Aharon,M.,2006.Image denoising via sparse and redundant representations over learn-ed dictionaries,IEEE Trans.Image Process.,15(12),3736-3745.
    [17]

    Fomel,S.,2013.Seismic data decomposition into spectral components using regularized nonstationary autoregression,Geophysics,78,O69-O76.
    [18]

    Forghani-Arani,F.,Willis,M.,Haines,S.S.,Batzle,M.,Behura,J.& Davidson,M.,2013.An effec-tive noise-suppression technique for surface microseismic data,Geophysics,78(6),KS85-KS95.
    [19]

    Gan,S.,Wang,S.,Chen,Y.& Chen,X.,2016a.Simul-taneous-source separation using iterative seis-let-frame thresholding,IEEE Geosci.Remote Sen.Lett.,13,197-201.
    [20]

    Gan,S.,Wang,S.,Chen,Y.,Chen,X.& Xiang,K.,2016b.Separation of simultaneous sources using a structural-oriented median filter in the flatten-ed dimension,Comput.Geosci.,86,46-54.
    [21]

    Gelchinsky,B.& Shtivelman,V.,1983.Automatic picking of first arrivals and parameterization of traveltime curves,Geophys.Prospect.,31,915-928.
    [22]

    Gibbons,S.J.& Ringdal,F.,2006.The detection of low magnitude seismic events using array-based waveform correlation,Geophys.J.Int.,165(1),149-166.
    [23]

    Gibbons,S.J.,Ringdal,F.& Kvaerna,T.,2006.Detection and characterization of seismic phases using continuous spectral estimation on inco-herent and partially coherent arrays,Geophys.J.Int.,172(1),405-421.
    [24]

    Gilles,J.,2013.Empirical wavelet transform,IEEE Trans.Signal Process.,61,3999-4010.
    [25]

    Gómez,J.L.& Velis,D.R.,2016.A simple method inspired by empirical mode decomposition for denoising seismic data,Geophysics,81(6),V403-V413.
    [26]

    Han,J.& van der Baan,M.,2015.Microseismic and seismic denoising via ensemble empirical mode decomposition and adaptive thresholding,Geophysics,80(6),KS69-KS80.
    [27]

    Hatherly,P.,1982.A computer method for determining seismic first arrival times,Geophysics,47,1431-1436.
    [28]

    Huang,N.E.,Shen,Z.,Long,S.R.,Wu,M.C.,Shih,H.H.,Zheng,Q.,Yen,N.-C.,Tung,C.C.& Liu,H.H.,1998.The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis,Proc.R.Soc.A,454,903-995.
    [29]

    Huang,W.,Wang,R.,Chen,Y.,Li,H.& Gan,S.,2016.Damped multichannel singular spectrum analysis for 3D random noise attenuation,Geophysics,81(4),V261-V270.
    [30]

    Huang,W.,Wang,R.,Chen,X.& Chen,Y.,2017a.Double least squares projections method for signal estimation,IEEE Trans.Geosci.Remote Sen.,55(7),4111-4129.
    [31]

    Huang,W.,Wang,R.,Li,H.& Chen,Y.,2017b.Unveiling the signals from extremely noisy microseismic data for high-resolution hydraulic fracturing monitoring,Sci.Rep.,7,11996,doi:10.1038/s41598-017-09711-2.
    [32]

    Huang,W.,Wang,R.,Yuan,Y.,Gan,S.& Chen,Y.,2017c.Signal extraction using randomized-order multichannel singular spectrum analysis,Geophysics,82(2),V59-V74.
    [33]

    Huang,W.,Wang,R.,Zhang,D.,Zhou,Y.,Yang,W.& Chen,Y.,2017d.Mathematical morphological filtering for linear noise attenuation of seismic data,Geophysics,82(6),V369-V384.
    [34]

    Huang,W.,Wang,R.,Zu,S.&Chen,Y.,2017e.Low-frequency noise attenuation in seismic and microseismic data using mathematical morphologi-cal filtering,Geophys.J.Int.,211,1318-1340.
    [35]

    Kalkan,E.,2016.An automatic p-phase arrival-time picker,Bull.seism.Soc.Am.,106(3),doi:10.1785/0120150111.
    [36]

    Leonard,M.,2000.Comparison of manual and automatic onset time picking,Bull.seism.Soc.Am.,90(6),1384-1390.
    [37]

    Li,H.,Wang,R.,Cao,S.,Chen,Y.& Huang,W.,2016a.A method for low-frequency noise suppression based on mathematical morphology in microseismic monitoring,Geophysics,81,V159-V167.
    [38]

    Li,H.,Wang,R.,Cao,S.,Chen,Y.,Tian,N.& Chen,X.,2016b.Weak signal detection using multiscale morphology in microseismic monitoring,J.Appl.Geophys.,133,39-49.
    [39]

    Liu,G.& Chen,X.,2013.Noncausal f-x-y regu-larized nonstationary prediction filtering for random noise attenuation on 3D seismic data,J.Appl.Geophys.,93,60-66.
    [40]

    Liu,G.,Chen,X.,Du,J.& Wu,K.,2012.Random noise attenuation using f-x regularized nonstationary autoregression,Geophysics,77,V61-V69.
    [41]

    Liu,W.,Cao,S.& He,Y.,2015.Ground roll attenu-ation using variational mode decomposition,in 77th Annual International Conference and Exhibition,EAGE,Extended Abstracts.
    [42]

    Liu,W.,Cao,S.& Chen,Y.,2016a.Seismic time-frequency analysis via empirical wavelet trans-form,IEEE Geosci.Remote Sens.Lett.,13,28-32.
    [43]

    Liu,W.,Cao,S.& Chen,Y.,2016b.Applications of variational mode decomposition in seismic time-frequency analysis,Geophysics,81,V365-V378.
    [44]

    Liu,W.,Cao,S.,Wang,Z.,Kong,X.& Chen,Y.,2017.Spectral decomposition for hydrocarbon detection based on VMD and teager-kaiser energy,IEEE Geosci.Remote Sens.Lett.,14(4),539-543.
    [45]

    Maxwell,S.C.,Rutledge,J.,Jones,R.& Fehler,M.,2010.Petroleum reservoir characterization using downhole microseismic monitoring,Geophysi-cs,75(5),75A129-75A137.
    [46]

    Michelet,S.& Toksöz,M.N.,2007.Fracture mapping in the Soultz-sousforets geothermal field using microearthquake locations,J.geoph-ys.Res.,112,B07315,doi:10.1029/2006JB 004442.
    [47]

    Mousavi,S.M.& Langston,C.A.,2016a.Hybrid seismic denoising using higher-order statistics and improved wavelet block thresholding,Bull.seism.Soc.Am.,106(4),1380-1393.
    [48]

    Mousavi,S.M.&Langston,C.A.,2016b.Adaptive noise estimation and suppression for improving microseismic event detection,J.Appl.Geo-phys.,132,116-124.
    [49]

    Mousavi,S.M.&Langston,C.A.,2016c.Fast and novel microseismic detection using time-freque-ncy analysis,in 86th Annual International Meeting,SEG,Expanded Abstracts,pp.2632-2636.
    [50]

    Mousavi,S.M.& Langston,C.A.,2017.Automatic noise-removal/signal-removal based on general cross-validation thresholding in synchrosquee-zed domain and its application on earthquake data,Geophysics,82(4),V211-V227.
    [51]

    Mousavi,S.M.,Langston,C.A.& Horton,S.P.,2016.Automatic microseismic denoising and onset detection using the synchrosqueezed continuous wavelet transform,Geophysics,81(4),V341-V355.
    [52]

    Murat,M.E.& Rudman,A.J.,1992.Automated first arrival picking:A neural network approach,Geophys.Prospect.,40(6),587-604.
    [53]

    Rodriguez,I.V.,Bonar,D.& Sacchi,M.,2012.Microseismic data denoising using a 3c group sparsity constrained time-frequency transform,Geophy-sics,77(2),V21-V29.
    [54]

    Sabbione,J.I.& Sacchi,M.D.,2015.Radon transform-based microseismic event detection and signal-to-noise ratio enhancement,J.Appl.Geophys.,113,51-63.
    [55]

    Sabbione,J.I.& Velis,D.,2010.Automatic first-breaks picking:New strategies and algorithms,Geophysics,75(4),V67-V76.
    [56]

    Senkaya,M.& Karsli,H.,2014.A semi-automatic approach to identify first arrival time:the cross-correlation technique(CCT),Earth Sci.Res.J.,18(2),107-113.
    [57]

    Shearer,P.M.,1991a.Imaging global body wave phases by stacking long period seismograms,J.geophys.Res.,96(B12),20535-20324.
    [58]

    Shearer,P.M.,1991b.Constraints on upper mantle discontinuities from observations of long period reflected and converted phases,J.geophys.Res.,96(B11),18147-18182.
    [59]

    Siahsar,M.A.N.,Abolghasemi,V.& Chen,Y.,2017a.Simultaneous denoising and interpolation of 2d seismic data using data-driven non-negative dictionary learning,Signal Process.,141,309-321.
    [60]

    Siahsar,M.A.N.,Gholtashi,S.,Kahoo,A.R.,Chen,W.& Chen,Y.,2017b.Data-driven multi-task sparse dictionary learning for noise attenuation of 3D seismic data,Geophysics,82(6),V385-V396.
    [61]

    Siahsar,M.A.N.,Gholtashi,S.,Olyaei,E.,Chen,W.& Chen,Y.,2017c.Simultaneous denoising and interpolation of 3D seismic data via damped data-driven optimal singular value shrinkage,IEEE Geosci.Remote Sens.Lett.,14(7),1086-1090.
    [62]

    Song,F.& Toksöz,M.N.,2011.Full-waveform based complete moment tensor inversion and source parameter estimation from downhole microseismic data for hydrofracture monitoring,Geophysics,76(6),WC103-WC116.
    [63]

    Song,F.,Kuleli,H.S.,Toksöz,M.N.,Ay,E.&Zhang,H.,2010.An improved method for hydrofracture-induced microseismic event detection and phase picking,Geophysics,75(6),A47-A52.
    [64]

    Vaezi,Y.&Van der Baan,M.,2015.Comparison of the STA/LTA and power spectral density methods for microseismic event detection,Geophys.J.Int.,203(3),1896-1908.
    [65]

    Vautard,R.,Yiou,P.&Ghil,M.,1992.Singular-spectrum analysis:A toolkit for short,noisy chaotic signals,Phys.D,58(1),95-126.
    [66]

    Velis,D.,Sabbione,J.I.& Sacchi,M.D.,2015.Fast and automatic microseismic phase-arrival detection and denoising by pattern recognition and reduced-rank filtering,Geophysics,80(6),WC25-WC38.
    [67]

    Wang,Y.,Zhou,H.,Zu,S.,Mao,W.& Chen,Y.,2017.Three-operator proximal splitting scheme for 3D seismic data reconstruction,IEEE Geo-sci.Remote Sens.Lett.,14,1830-1834.
    [68]

    Withers,M.,Aster,R.,Young,C.,Beiriger,J.,Harris,M.,Moore,S.& Trujillo,J.,1998.A comparison of select trigger algorithms for automated global seismic phase and event detection,Bull.seism.Soc.Am.,88(1),95-106.
    [69]

    Wu,G.,Fomel,S.& Chen,Y.,2017.Data-driven time-frequency analysis of seismic data using non-stationary prony method,Geophys.Prospect.,doi:10.1111/1365-2478.12530.
    [70]

    Wu,Z.& Huang,N.E.,2009.Ensemble empirical mode decomposition:A noise-assisted data analy-sis method,Adv.Adapt.Data Anal.,1,1-41.
    [71]

    Xie,J.,Chen,W.,Zhang,D.,Zu,S.& Chen,Y.,2017.Application of principal component analysis in weighted stacking of seismic data,IEEE Geo-sci.Remote Sens.Lett.,14(8),1213-1217.
    [72]

    Xue,Y.,Chang,F.,Zhang,D.& Chen,Y.,2016a.Simultaneous sources separation via an iterative rank-increasing method,IEEE Geosci.Remote Sens.Lett.,13(12),1915-1919.
    [73]

    Xue,Z.,Chen,Y.,Fomel,S.& Sun,J.,2016b.Seismic imaging of incomplete data and simultaneous-source data using least-squares reverse time migration with shaping regularization,Geophy-sics,81,S11-S20.
    [74]

    Yang,P.,Yin,X.& Zhang,G.,2006.Seismic data analysis based on fuzzy clustering,in20068th International Conference on Signal Processing,doi:10.1109/ICOSP.2006.346109.
    [75]

    Zhang,H.,Thurber,C.& Rowe,C.,2003.Automatic p-wave arrival detection and picking with multiscale wavelet analysis for single-component recordings,Bull.seism.Soc.Am.,93(5),1904-1912.
    [76]

    Zhang,D.,Chen,Y.,Huang,W.& Gan,S.,2016.Multi-step damped multichannel singular spectrum analysis for simultaneous reconstruction and denoising of 3D seismic data,J.Geophys.Eng.,13,704-720.
    [77]

    Zhang,D.,Zhou,Y.,Chen,H.,Chen,W.,Zu,S.& Chen,Y.,2017.Hybrid rank-sparsity constraint model for simultaneous reconstruction and denoising of 3D seismic data,Geophysics,82(5),V351-V367.
    [78]

    Zhou,Y.,Shi,C.,Chen,H.,Xie,J.,Wu,G.& Chen,Y.,2017.Spike-like blending noise attenuation using structural low-rank decomposition,IEEE Geosci.Remote Sens.Lett.,14(9),1633-1637.
    [79]

    Zu,S.,Zhou,H.,Chen,Y.,Qu,S.,Zou,X.,Chen,H.& Liu,R.,2016.A periodically varying code for improving deblending of simultaneous sources in marine acquisition,Geophysics,81(3),V213-V225.
    [80]

    Zu,S.,Zhou,H.,Mao,W.,Zhang,D.,Li,C.,Pan,X.& Chen,Y.,2017.Iterative deblending of simultaneous-source data using a coherency-pass shaping operator,Geophys.J.Int.,211(1),541-557.
  • [1] V. VavryukD. Kühn赵仲和吕春来 . 波形矩张量反演的时间一频率两步法. 世界地震译丛, 2012, 43(6): 28-48.
    [2] Rizheng HeXuefeng ShangChunquan YuHaijiang ZhangRobert D. Van der Hilst李万金郑雪刚田宝峰 . 通过接收函数分析得到的中国大陆莫霍面深度和VP/VS比的统一图. 世界地震译丛, 2016, 47(3): 222-233. doi: 10.16738/j.cnki.issn.1003-3238.201603004
    [3] Lion KrischerTobias MegiesRobert BarschMoritz BeyreutherThomas LecocqCorentin CaudronJoachim Wassermann韩雪君马延路鲁来玉 . ObsPy:将地震学引入科学Python生态系统的桥梁. 世界地震译丛, 2016, 47(4): 344-358. doi: 10.16738/j.cnki.issn.1003-3238.201604006
    [4] Z. E. RossY. Ben-Zion高研李万金刘长生朱玉萍 . 断层带围陷波的自动识别算法. 世界地震译丛, 2017, 48(4): 349-366. doi: 10.16738/j.cnki.issn.1003-3238.201704005
    [5] I. LiorA. Ziv杨国栋曾文浩田野常利军 . 地震动加速度与震源参数之间的关系:理论与观测. 世界地震译丛, 2018, 49(6): 582-591. doi: 10.16738/j.cnkii.ssn.1003-3238.201806005
    [6] N. Deichmann杨国栋曾文浩许忠淮 . 观测到的小震与大震之间ML/MW标度突然改变的理论基础. 世界地震译丛, 2019, 50(1): 1-20. doi: 10.16738/j.cnki.issn.1003-3238.201901001
    [7] I. IervolinoM. GiorgioB. Polidoro赵爱平李守勇吕春来 . 基于序列的地震危险性概率分析. 世界地震译丛, 2014, 45(3): 33-40.
    [8] O. S. Boyd李晶吕春来 . 包括前震和余震的不含时间的地震危险性概率分析. 世界地震译丛, 2013, 44(4): 37-47.
    [9] Y. L. LiB. S. WangR. Z. HeH. W. ZhengJ. Y. YanY. Li李娱兰郑洪伟贺日政 . 青藏高原中部中小地震的精定位、震源机制及构造背景分析. 世界地震译丛, 2019, 50(3): 212-230. doi: 10.16738/j.cnki.issn.1003-3238.201903002
    [10] Ruijia WangYu Jeffrey GuRyan SchultzAhyi KimGail Atkinson邹长桥朱玉萍 . 加拿大艾伯塔省福克斯克里克附近潜在水压致裂诱发地震的震源分析. 世界地震译丛, 2017, 48(3): 191-203. doi: 10.16738/j.cnki.issn.1003-3238.201703001
    [11] Jeanne L. Hardebeck靳志同万永革李一琼 . 俯冲带的应力方向和俯冲带大型逆断层的强度. 世界地震译丛, 2016, 47(3): 255-260. doi: 10.16738/j.cnki.issn.1003-3238.201603007
    [12] 中原恒贾丽华李君顾娜白玲 . 利用地震波干涉法探求衰减结构的理论背景. 世界地震译丛, 2014, 45(1-2): 43-50.
    [13] P. ShearerR. Bürgmann赵雯佳吕春来 . 从2004年苏门答腊-安达曼巨型逆冲断层破裂得到的经验教训. 世界地震译丛, 2012, 43(1): 1-23.
    [14] P. S. EarleS. RostP. M. ShearerC. Thomas林秀娜曲保安吕春来 . 近距离观测的散射P'P'波. 世界地震译丛, 2012, 43(4): 47-61.
    [15] T. Dean朱维吴何珍 . 伪随机扫描在可控震源探测中的应用. 世界地震译丛, 2016, 47(1): 64-90. doi: 10.16738/j.cnki.issn.1003-3238.201601005
    [16] Vince Cronin李万金李永华吕春来 . 地质学家震源机制解入门. 世界地震译丛, 2015, 46(1): 66-83.
    [17] Haiying GaoD. A. SchmidtR. J. Weldon II翟璐媛吕春来 . 慢滑动事件震源参数的标度关系. 世界地震译丛, 2013, 44(5-6): 13-23.
    [18] V. Vavryčuk高熹微宋程万永革吕春来 . 根据震源机制迭代联合反演应力和断层取向. 世界地震译丛, 2014, 45(4): 21-33.
    [19] Y. Y. Kagan刘双庆赵仲和 . 双力偶震源的三维旋转. 世界地震译丛, 2019, 50(6): 549-555. doi: 10.16738/j.cnkii.ssn.1003-3238.201906005
    [20] Q. K. KongR. M. AllenL. Schreier康涛冯继威邹立晔 . MyShake:全球智能手机地震台网的初步观测结果. 世界地震译丛, 2018, 49(1): 19-27. doi: 10.16738/j.cnki.issn.1003-3238.201801002
  • 加载中
计量
  • 文章访问数:  209
  • HTML全文浏览量:  80
  • PDF下载量:  18
  • 被引次数: 0
出版历程

通过无监督机器学习自动拾取微震事件

基金项目:  新疆维吾尔自治区自然科学基金项目(2017D01A66)资助

摘要: 高效的波至拾取在微震和地震数据处理及成像过程中起到重要作用。广泛使用的基于波至拾取算法的短期平均和长期平均比(STA/LTA),对中强度随机环境噪声的敏感程度较低。为了使最先进的波至拾取方法奏效,首先需要对微震数据进行预处理,例如,消除足量的噪声,再由波至拾取法进行分析。为了解决微震或地震事件波至拾取的噪声问题,利用机器学习技术帮助识别微震或地震数据中的地震波形。由于受监督机器学习算法对大量设计好的训练数据具有依赖性,本文利用无监督机器学习算法将时间样本分为两组,即波形点和非波形点。已证明模糊聚类算法可以运用于微震拾取。一组复杂程度不同的合成、真实微震和地震数据集表明,即使在中强背景噪声情况下,该方法在拾取微震事件方面比最先进的STA/LTA方法表现得更稳健。

English Abstract

参考文献 (80)

目录

    /

    返回文章
    返回