• ISSN 1003-3238
  • CN 10-1702/P

利用深度学习进行P波到时拾取和初动极性判定

Z. E. Ross M. -A. Meier E. Hauksson 王凌 高翔 于辰飞 张瑞青

引用本文:
Citation:

利用深度学习进行P波到时拾取和初动极性判定

  • 摘要: 地震震源位置和震源机制解的确定需要精确的P波到时和初动极性信息。由于这些参数的自动化算法的精度比人工识别的要低,因而在处理大数据时是存在一定问题的。本文通过训练卷积神经网络来获取P波到时和初动极性信息,该方法直接对波形记录进行学习,而不是特征提取。我们利用南加州地区1 820万条手动拾取的波形记录,来训练卷积神经网络。1 200万条无关联波形记录的交叉验证显示,自动与人工拾取之间的差异的标准差为0.023s。以人工识别的初动极性做参考,分类器拾取的精度为95%。同时,在不影响质量的前提下,与人工识别相比,分类器拾取的极性数量更多,从而获得的震源机制解数量几乎翻倍。经过训练的卷积神经网络具有很好的精度,这表明它们可以与地震专家一样好,甚至更好。
  • [1]

    Allam,A.A.,& Ben-Zion,Y.(2012).Seismic velocity structures in the southern California plate-boundary environment from double-difference tomography.Geophysical Journal Internatio-nal,190(2),1181-1196.https://doi.org/10.1111/j.1365-246X.2012.05544.x
    [2]

    Allen,R.(1982).Automatic phase pickers:Their present use and future prospects.Bulletin of the Seismological Society of America,72(6B),S225-S242.
    [3]

    Allen,R.M.,& Kanamori,H.(2003).The potential for earthquake early warning in Southern California.Science,300(5620),786-789.https://doi.org/10.1126/science.1080912
    [4]

    Baer,M.,& Kradolfer,U.(1987).An automatic phase picker for local and teleseismic events.Bulletin of the Seismological Society of America,77(4),1437-1445.
    [5]

    Baillard,C.,Crawford,W.C.,Ballu,V.,Hibert,C.,& Mangeney,A.(2014).An automatic kurtosis-based P- and S-phase picker designed for local seismic networks.Bulletin of the Seismological Society of America,104(1),394-409.https://doi.org/10.1785/0120120347
    [6]

    Chen,C.,& Holland,A.A.(2016).PhasePApy:A robust pure Python package for automatic identification of seismic phases.Seismological Re-search Letters,87(6),1384-1396.https://doi.org/10.1785/0220160019
    [7]

    Chen,Y.(2018).Automatic microseismic event picking via unsupervised machine learning.Geophysical Journal International,212(1),88-102.https://doi.org/10.1093/gji/ggx420
    [8]

    Di Stefano,R.,Aldersons,F.,Kissling,E.,Baccheschi,P.,Chiarabba,C.,& Giardini,D.(2006).Automatic seismic phase picking and consistent observation error assessment:application to the Italian seismicity.Geophysical Journal International,165(1),121-134.
    [9]

    Diehl,T.,Deichmann,N.,Kissling,E.,& Husen,S.(2009).Automatic S-wave picker for local earthquake tomography.Bulletin of the Seismological Society of America,99(3),1906-1920.https://doi.org/10.1785/0120080019
    [10]

    Gentili,S.,& Michelini,A.(2006).Automatic picking of P and S phases using a neural tree.Journal of Seismology,10(1),39-63.https://doi.org/10.1007/s10950-006-2296-6
    [11]

    Girshick,R.,Donahue,J.,Darrell,T.,& Malik,J.(2014).Rich feature hierarchies for accurate object detection and semantic segmentation.In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition(pp.580-587).Washington,DC:IEEE Computer Society.
    [12]

    Hammer,C.,Beyreuther,M.,& Ohrnberger,M.(2012).A seismic-event spotting system for volcano fast-response systems.Bulletin of the Seismological Society of America,102(3),948-960.https://doi.org/10.1785/0120110167
    [13]

    Hardebeck,J.L.,& Shearer,P.M.(2002).A new method for determining first-motion focal me-chanisms.Bulletin of the Seismological Society of America,92(6),2264-2276.https://doi.org/10.1785/0120010200
    [14]

    Heaton,T.H.(1985).A model for a seismic compu-terized alert network.Science,228(4702),987-990.https://doi.org/10.1126/science.228.4702.987
    [15]

    Hildyard,M.W.,Nippress,S.E.J.,& Rietbrock,A.(2008).Event detection and phase picking using a time-domain estimate of predominate period Tpd.Bulletin of the Seismological Society of America,98(6),3025-3032.https://doi.org/10.1785/0120070272
    [16]

    Huber,P.J.(1964).Robust estimation of a location parameter.The Annals of Mathematical Statistics,35(1),73-101.https://doi.org/10.1214/aoms/1177703732
    [17]

    LeCun,Y.,Bottou,L.,Bengio,Y.,& Haffner,P.(1998).Gradient-based learning applied to document recognition.Proceedings of the IEEE,86(11),2278-2324.https://doi.org/10.1109/5.726791
    [18]

    LeCun,Y.,Bengio,Y.,& Hinton,G.(2015).Deep learning.Nature,521(7553),436-444.https://doi.org/10.1038/nature14539
    [19]

    Mousavi,S.M.,Horton,S.P.,Langston,C.A.,& Samei,B.(2016).Seismic features and automatic discrimination of deep and shallow induced-microearthquakes using neural network and logi-stic regression.Geophysical Journal International,207(1),29-46.https://doi.org/10.1093/gji/ggw258
    [20]

    Nair,V.,& Hinton,G.E.(2010).Rectified linear units improve restricted boltzmann machines.In Proceedings of the 27th International Conference on Machine Learning(ICML-10)(pp.807-814).Haifa,Israel.
    [21]

    Nippress,S.E.J.,Rietbrock,A.,& Heath,A.E.(2010).Optimized automatic pickers:Applica-tion to the ANCORP data set.Geophysical Journal International,181(2),911-925.https://doi.org/10.1111/j.1365-246X.2010.04531.x
    [22]

    Perol,T.,Gharbi,M.,& Denolle,M.(2018).Convolutional neural network for earthquake detection and location.Science Advances,4(2),e1700578.https://doi.org/10.1126/sciadv.1700578
    [23]

    Pugh,D.J.,White,R.S.,& Christie,P.A.F.(2016).Automatic Bayesian polarity determination.Geophysical Journal International,206(1),275-291.https://doi.org/10.1093/gji/ggw146
    [24]

    Ross,Z.E.,Rollins,C.,Cochran,E.S.,Hauksson,E.,Avouac,J.-P.,& Ben-Zion,Y.(2017).Aftersho-cks driven by afterslip and fluid pressure swee-ping through a fault-fracture mesh.Geophysical Research Letters,44,8260-8267.https://doi.org/10.1002/2017GL074634
    [25]

    Ross,Z.E.,White,M.C.,Vernon,F.L.,& Ben-Zion,Y.(2016).An improved algorithm for real-time S-wave picking with application to the(augmented)ANZA network in Southern California.Bulletin of the Seismological Society of America,106(5),2013-2022.https://doi.org/10.1785/0120150230
    [26]

    Saragiotis,C.D.,Hadjileontiadis,L.J.,& Panas,S.M.(2002).PAI-S/K:A robust automatic seismic P phase arrival identification scheme.IEEE Tran-sactions on Geoscience and Remote Sensing,40(6),1395-1404.https://doi.org/10.1109/TGRS.2002.800438
    [27]

    Satriano,C.,Wu,Y.-M.,Zollo,A.,& Kanamori,H.(2011).Earthquake early warning:Concepts,methods and physical grounds.Soil Dynamics and Earthquake Engineering,31(2),106-118.https://doi.org/10.1016/j.soildyn.2010.07.007
    [28]

    Shelly,D.R.,Moran,S.C.,& Thelen,W.A.(2013).Evidence for fluid-triggered slip in the 2009 Mount Rainier,Washington earthquake swarm.Geophysical Research Letters,40,1506-1512.https://doi.org/10.1002/grl.50354
    [29]

    Skoumal,R.J.,Brudzinski,M.R.,& Currie,B.S.(2015).Earthquakes induced by hydraulic fracturing in Poland Township,Ohio earthquakes induced by hydraulic fracturing in Poland Township,Ohio.Bulletin of the Seismological Society of America,105(1),189-197.https://doi.org/10.1785/0120140168
    [30]

    Sleeman,R.,& van Eck,T.(1999).Robust automatic P-phase picking:An on-line implementation in the analysis of broadband seismogram recor-dings.Physics of the Earth and Planetary Interiors,113(1-4),265-275.https://doi.org/10.1016/S0031-9201(99)00007-2
    [31]

    Southern California Earthquake Data Center(2013).Southern California Earthquake Data Center.California Institute of Technology,Dataset.https://doi.org/10.7909/C3WD3xH1
    [32]

    Szegedy,C.,Liu,W.,Jia,Y.,Sermanet,P.,Reed,S.,Anguelov,D.,et al.(2015).Going deeper with convolutions.In Proceedings of the IEEE Conference on Computer Vision and Pattern Re-cognition(pp.1-9).Boston,MA.
    [33]

    Wang,J.,& Teng,T.(1997).Identification and picking of S phase using an artificial neural network.Bulletin of the Seismological Society of America,87(5),1140-1149.
    [34]

    Yang,W.,Hauksson,E.,& Shearer,P.M.(2012).Computing a large refined catalog of focal mechanisms for Southern California(1981-2010):Temporal stability of the style of faul-ting.Bulletin of the Seismological Society of America,102(3),1179-1194.https://doi.org/10.1785/0120110311
    [35]

    Yoon,C.E.,O'Reilly,O.,Bergen,K.J.,& Beroza,G.C.(2015).Earthquake detection through computationally efficient similarity search.Science Advances,1(11),e1501057.https://doi.org/10.1126/sciadv.1501057
    [36]

    Zeiler,M.D.,& Fergus,R.(2014).Visualizing and understanding convolutional networks.In Computer Vision-ECCV 2014(pp.818-833).Cham,Switzerland:Springer.https://doi.org/10.1007/978-3-319-10590-1_53
  • [1] Y. K. Chen李帛珊唐丽华孙燕萍吕春来 . 通过无监督机器学习自动拾取微震事件. 地球与行星物理论评, 2019, 50(5): 411-432. doi: 10.16738/j.cnki.issn.1003-3238.201905002
    [2] I. KurzonF. L. VernonA. RosenbergerY. Ben-Zion刘长生李万金赵谊吴何珍 . 利用奇异值分解方法实时自动检测P波和S波. 地球与行星物理论评, 2017, 48(4): 291-307. doi: 10.16738/j.cnki.issn.1003-3238.201704002
    [3] X. LiuD. P. Zhao张晓曼赵小艳 . 利用地方震、远震走时和面波数据联合反演日本俯冲带P波和S波层析成像. 地球与行星物理论评, 2019, 50(1): 35-63. doi: 10.16738/j.cnki.issn.1003-3238.201901003
    [4] Fenglin NiuJuan Li李娟吴何珍 . 利用P波质点运动估计“中国数字地震观测网络”地震计方位角. 地球与行星物理论评, 2015, 46(5-6): 454-469. doi: 10.16738/j.cnki.issn.1003-3238.2015Z1006
    [5] E. Z. NaeiniK. Prindle汪忠德朱晓丹赵明 . 机器学习和向机器学习. 地球与行星物理论评, 2019, 50(5): 442-452. doi: 10.16738/j.cnki.issn.1003-3238.201905004
    [6] 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. 地球与行星物理论评, 2012, 43(4): 47-61.
    [7] J. H. GrawS. E. HansenC. A. LangstonB. A. YoungA. MostafanejadY. Park李翠平唐茂云张天中 . 去除冰层对P波响应的影响来计算地壳和上地幔波速结构:以南极洲地震研究为例. 地球与行星物理论评, 2018, 49(4): 352-368. doi: 10.16738/j.cnkii.ssn.1003-3238.201804004
    [8] E. KozlovskayaT. JanikJ. YliniemiG. KaratayevM. Grad薛彬阮爱国吕春来 . 由EUROBRIDGE'97地震剖面的P波与S波速度模型和重力数据得到的岩石层上部密度-速度关系. 地球与行星物理论评, 2012, 43(2): 33-48.
    [9] R. D. CostleyG. Galan-ComasC. K. KirkendallJ. E. SimmsK. K. HathawayM. W. ParkerS. A. KetchamE. W. SmithW. R. FolksT. W. MilburnH. M. Wadman李帛珊吕春来 . 利用同时光纤分布式声传感和垂直检波器的面波频谱分析. 地球与行星物理论评, 2019, 50(6): 573-586. doi: 10.16738/j.cnkii.ssn.1003-3238.201906007
    [10] R. E. AnthonyA. T. RinglerD. C. Wilson刘天龙王乔孙艺梅孙宏志燕云吕春来 . 利用局部地球重力测量进行绝对地震仪灵敏度校准的改进. 地球与行星物理论评, 2019, 50(4): 390-400. doi: 10.16738/j.cnki.issn.1003-3238.201904008
    [11] 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. 地球与行星物理论评, 2016, 47(3): 222-233. doi: 10.16738/j.cnki.issn.1003-3238.201603004
    [12] Martyn UnsworthStéphane Rondenay郭春玲刘雁冰郭春玲陈小斌裴顺平吴何珍吕春来 . 利用地球物理方法描绘地壳和岩石层地幔流体的分布. 地球与行星物理论评, 2015, 46(5-6): 355-403. doi: 10.16738/j.cnki.issn.1003-3238.2015Z1001
    [13] J. K. CrossJ. RobergeD. A. Jerram于红梅吕春来 . 利用气孔大小分布和玻璃地球化学研究约束墨西哥波波卡特佩特火山脱气过程. 地球与行星物理论评, 2014, 45(1-2): 94-116.
    [14] Y. M. WenZ. L. GuoC. J. XuG. Y. XuC. Song郭泽龙温扬茂 . 利用高频和低频GPS观测资料研究2018年MW7.9阿拉斯加科迪亚克地震的同震和震后形变. 地球与行星物理论评, 2020, 51(4): 376-388.
    [15] Xuewei BaoXiaoxiao SunMingjie XuDavid W. EatonXiaodong SongLiangshu WangZhifeng DingNing MiHua LiDayong YuZhouchuan HuangPan Wang孙晓晓鲍学伟徐鸣洁朱玉萍 . 通过接收函数和瑞利波联合反演揭示青藏高原东南缘两个壳内低速通道. 地球与行星物理论评, 2016, 47(4): 329-343. doi: 10.16738/j.cnki.issn.1003-3238.201604005
    [16] Shunta NodaShunroku YamamotoWilliam L. Ellsworth张立文吕春来 . 根据高频振幅峰值的到时快速估算地震震级. 地球与行星物理论评, 2017, 48(3): 234-247. doi: 10.16738/j.cnki.issn.1003-3238.201703004
    [17] B. FryerG. SiddiqiL. Laloui孙春仙叶学沈红会 . 注入诱发地震:利用高应力路径储层和温度诱发应力预处理降低诱发地震风险的策略. 地球与行星物理论评, 2020, 51(5): 509-525.
    [18] Franjo ŠumanovacEndre HegedüsJasna OreškovićSaša KolarAttila C. KovácsDarko DudjakIstván J. Kovács王林蔡辉腾李永华 . 利用被动源地震实验和接收函数分析确定迪纳拉山脉北部和潘诺尼亚盆地西南部交界处地壳结构. 地球与行星物理论评, 2017, 48(1): 74-96. doi: 10.16738/j.cnki.issn.1003-3238.201701006
    [19] C. E. YoonO. O'ReillyK. J. BergenG. C. Beroza李万金朱玉萍 . 通过计算高效的相似性搜索进行地震检测. 地球与行星物理论评, 2017, 48(6): 496-516. doi: 10.16738/j.cnki.issn.1003-3238.201706003
    [20] Xiaofeng LiangYun ChenXiaobo TianYongshun John ChenJames NiAndrea GallegosSimon L. KlempererMinling WangTao XuChangqing SunShaokun SiHaiqiang LanJiwen Teng左思成梁晓峰朱玉萍 . 基于体波有限频层析成像的青藏高原南部和中部下方印度大陆岩石层俯冲和撕裂的三维图像. 地球与行星物理论评, 2016, 47(6): 521-542. doi: 10.16738/j.cnki.issn.1003-3238.201606005
  • 加载中
计量
  • 文章访问数:  317
  • HTML全文浏览量:  166
  • PDF下载量:  48
  • 被引次数: 0
出版历程

利用深度学习进行P波到时拾取和初动极性判定

摘要: 地震震源位置和震源机制解的确定需要精确的P波到时和初动极性信息。由于这些参数的自动化算法的精度比人工识别的要低,因而在处理大数据时是存在一定问题的。本文通过训练卷积神经网络来获取P波到时和初动极性信息,该方法直接对波形记录进行学习,而不是特征提取。我们利用南加州地区1 820万条手动拾取的波形记录,来训练卷积神经网络。1 200万条无关联波形记录的交叉验证显示,自动与人工拾取之间的差异的标准差为0.023s。以人工识别的初动极性做参考,分类器拾取的精度为95%。同时,在不影响质量的前提下,与人工识别相比,分类器拾取的极性数量更多,从而获得的震源机制解数量几乎翻倍。经过训练的卷积神经网络具有很好的精度,这表明它们可以与地震专家一样好,甚至更好。

English Abstract

参考文献 (36)

目录

    /

    返回文章
    返回