Active Source Seismic Identification and Automatic Picking of the P-wave First Arrival Using a Convolutional Neural Network
|
摘要
In seismic data processing, picking of the P-wave first arrivals takes up plenty of time and labor, and its accuracy plays a key role in imaging seismic structures. Based on the convolution neural network(CNN), we propose a new method to pick up the P-wave first arrivals automatically. Emitted from MINI28 vibroseis in the Jingdezhen seismic experiment, the vertical component of seismic waveforms recorded by EPS 32-bit portable seismometers are used for manually picking up the first arrivals(a total of 7242). Based on these arrivals, we establish the training and testing sets, including 25,290 event samples and 710,616 noise samples(length of each sample: 2 s). After 3,000 steps of training, we obtain a convergent CNN model, which can automatically classify seismic events and noise samples with high accuracy(> 99%). With the trained CNN model, we scan continuous seismic records and take the maximum output(probability of a seismic event) as the P-wave first arrival time. Compared with STA/LTA(short time average/long time average), our method shows higher precision and stronger anti-noise ability, especially with the low SNR seismic data. This CNN method is of great significance for promoting the intellectualization of seismic data processing, improving the resolution of seismic imaging, and promoting the joint inversion of active and passive sources.
In seismic data processing, picking of the P-wave first arrivals takes up plenty of time and labor, and its accuracy plays a key role in imaging seismic structures. Based on the convolution neural network(CNN), we propose a new method to pick up the P-wave first arrivals automatically. Emitted from MINI28 vibroseis in the Jingdezhen seismic experiment, the vertical component of seismic waveforms recorded by EPS 32-bit portable seismometers are used for manually picking up the first arrivals(a total of 7242). Based on these arrivals, we establish the training and testing sets, including 25,290 event samples and 710,616 noise samples(length of each sample: 2 s). After 3,000 steps of training, we obtain a convergent CNN model, which can automatically classify seismic events and noise samples with high accuracy(> 99%). With the trained CNN model, we scan continuous seismic records and take the maximum output(probability of a seismic event) as the P-wave first arrival time. Compared with STA/LTA(short time average/long time average), our method shows higher precision and stronger anti-noise ability, especially with the low SNR seismic data. This CNN method is of great significance for promoting the intellectualization of seismic data processing, improving the resolution of seismic imaging, and promoting the joint inversion of active and passive sources.
In seismic data processing, picking of the P-wave first arrivals takes up plenty of time and labor, and its accuracy plays a key role in imaging seismic structures. Based on the convolution neural network(CNN), we propose a new method to pick up the P-wave first arrivals automatically. Emitted from MINI28 vibroseis in the Jingdezhen seismic experiment, the vertical component of seismic waveforms recorded by EPS 32-bit portable seismometers are used for manually picking up the first arrivals(a total of 7242). Based on these arrivals, we establish the training and testing sets, including 25,290 event samples and 710,616 noise samples(length of each sample: 2 s). After 3,000 steps of training, we obtain a convergent CNN model, which can automatically classify seismic events and noise samples with high accuracy(> 99%). With the trained CNN model, we scan continuous seismic records and take the maximum output(probability of a seismic event) as the P-wave first arrival time. Compared with STA/LTA(short time average/long time average), our method shows higher precision and stronger anti-noise ability, especially with the low SNR seismic data. This CNN method is of great significance for promoting the intellectualization of seismic data processing, improving the resolution of seismic imaging, and promoting the joint inversion of active and passive sources.
引文
Allen R.V.Automatic earthquake recognition and timing from single trace[J].Bulletin of the Seismological Society of America,1978,68(5):1521-1532.
Bao Xuewei,Eaton D.W.Fault activation by hydraulic fracturing in western Canada[J].Science,2016,354(6318):1406-1409.
Baer M.,Kradolfer U.An automatic phase picker for local and teleseismic events[J].Bulletin of the Seismological Society of America,1987,77(4):1437-1445.
Bengio Y.Learning deep architectures for AI[J].Foundations and Trendsin Machine Learning,2009,2(1):1-127.
Brown J.R.,Beroza G.C.,Shelly D.R.An autocorrelation method to detect low frequency earthquakes within tremor[J].Geophysical Research Letters,2008,35(16):L16305,doi:10.1029/2008GL034560.
Chen Guohua,Shu Liangshu,Shu Limin,Zhang Cheng,Ouyang Yongpeng.Geological characteristics and mineralization setting of the Zhuxi tungsten(copper)polymetallic deposit in the Eastern Jiangnan Orogen[J].Science China Earth Sciences,2016,59(4):803-823.
De Vries P.M.R.,Viégas F.,Wattenberg M.,Meade B.J.Deep learning of aftershock patterns following large earthquakes[J].Nature,2018,560(7720):632-634,doi:10.1038/s41586-018-0438-y.
Gibbons S.J.,Ringdal F.The detection of low magnitude seismic events using array-based waveform correlation[J].Geophysical Journal International,2006,165(1):149-166,doi:10.1111/j.1365-246X.2006.02865.x.
Gu Jinxiang,Wang Zhenhua,Jason K.,Ma Lianyang,Shahroudy A.,Shuai Bing,Liu Ting,Wang Xingxing,Wang Li,Wang Gang,Cai Jianfei,Chen Tsuhan.Recent advances in convolutional neural networks[J].ar Xiv preprint ar Xiv:1512.07108,2015.
He Xianlong,She Tianli,Gao Feng.A new method for picking up arrival times of seismic P and S waves automatically[J].Chinese Journal of Geophysics,2016,59(7):2519-2527,doi:10.6038/cjg20160717(in Chinese with English abstract).
Hou Jinxin,Wang Baoshan.Temporal evolution of seismicity before and after the 2014 Ludian MS6.5 earthquake[J].Chinese Journal of Geophysics,2017,60(4):1446-1456(in Chinese with English abstract).
House L.Locating microearthquakes induced by hydraulic fracturing in crystalline rock[J].Geophysical Research Letters,1987,14(9):919-921,doi:10.1029/GL014i009p00919.
Jiang Ce,Wu Jianping,Fang Lihua.Earthquake detection and automatic phase picking[J].Acta Seismologica Sinica,2018,40(1):45-57,doi:10.11939/jass.20170093(in Chinese with English abstract).
Kato A.,Obara K.,Lgarashi T.,Tsuruoka H.,Nakagawa S.,Hirata N.Propagation of slow slip leading up to the2011 Mw9.0 Tohoku-Oki earthquake[J].Science,2012,335(6069):705-708,doi:10.1126/science.1215141.
Kim Y.Convolutional neural networks for sentence classification[J].ar Xiv preprint ar Xiv:1408.5882,2014.
Kingma D.P.,Ba J.Adam:a method for stochastic optimization[J].ar Xiv preprint ar Xiv:1412.6980,2014.
Le Cun Y.,Bottou L.,Bengio Y.,Haffner P.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324,doi:10.1109/5.726791.
Li Lu,Wang Baoshan,Hou Jinxin.Applications of matched filter technique in seismic data processing[J].Earthquake Research in China,2017,33(1):14-22(in Chinese with English abstract).
Liu Han,Zhang Jianzhong.STA/LTA algorithm analysis and improvement of Microseismic signal automatic detection[J].Progress in Geophysics,2014,29(4):1708-1714,doi:10.6038/pg20140429(in Chinese).
Liu Xiqiang,Zhou Huilan,Shen Ping,Ma Yanlu,Li Hong.Identification method of seismic phase in threecomponent seismograms on the basis of wavelet transform[J].Acta Seismologica Sinica,2000,22(2):125-131,doi:10.3321/j.issn:0253-3782.2000.02.002(in Chinese with English abstract).
Liu Xiqiang,Zhou Yanwen,Qu Junhao,Shi Yuyan,Li Bo.Real-time detection of regional events and automatic P-phase identification from the vertical component of a single station record[J].Acta Seismologica Sinica,2009,31(3):260-271,doi:10.3321/j.issn:0253-3782.2009.03.003(in Chinese with English abstract).
Maeda N.A method for reading and checking phase time in auto-processing system of seismic wave data[J].Zisin(Journal of the Seismological Society of Japan.2nd ser.),1985,38(3):365-379,doi:10.4294/zisin1948.38.3_365(in Japanese).
Peng Zhigang,Zhao Peng.Migration of early aftershocks following the 2004 Parkfield earthquake[J].Nature Geoscience,2009,2(12):877-881,doi:10.1038/ngeo697.
Perol T.,Gharbi M.,Denolle M.Convolutional neural network for earthquake detection and location[J].Science Advances,2018,4(2):e1700578,doi:10.1126/sciadv.1700578.
Rawat W.,Wang Zenghui.Deep convolutional neural networks for image classification:a comprehensive review[J].Neural Computation,2017,29(9):2352-2449.
Shelly D.R.,Beroza G.C.,Ide S.Non-volcanic tremor and low-frequency earthquake swarms[J].Nature,2007,446(7133):305-307,doi:10.1038/nature05666.
Shensa M.J.The deflection detector-its theory and evaluation on short-period seismic data[J].Texas Instruments,Alexandria,Virginia,1977,TR-77-03.
Sleeman R.,van Eck T.Robust automatic P-phase picking:an on-line implementation in the analysis of broadband seismogram recordings[J].Physics of The Earth and Planetary Interiors,1999,13(1/4):265-275,doi:10.1016/S0031-9201(99)00007-2.
Stevenson P.R.Microearthquakes at flathead lake,Montana:a study using automatic earthquake processing[J].Bulletin of the Seismological Society of America,1976,66(1):61-80.
Stockwell R.G.,Mansinha L.,Lowe R.P.Localization of the complex spectrum:the S transform[J].IEEETransactions on Signal Processing,1996,44(4):998-1001,doi:10.1109/78.492555.
Tan Yuyang,Yu Jing,Feng Gang,He Chuan.Arrival picking of microseismic events using the SLPEA algorithm[J].Chinese Journal of Geophysics,2016,59(1):185-196,doi:10.6038/cjg20160116(in Chinese with English abstract).
Wang Haijun,Jin Ping,Liu Guizhong,Wang Xiaoming.Accurate estimation for arrival time of seismic wave[J].Northwestern Seismological Journal,2003,25(4):298-303,doi:10.3969/j.issn.1000-0844.2003.04.003(in Chinese with English abstract).
Wang Peng,Chang Xu,Wang Yibo,Wang Luchen,Zhai Hongyu.Automatic event detection and event recovery in low SNR microseismic signals based on time-frequency sparseness[J].Chinese Journal of Geophysics,2014,57(8):2656-2665,doi:10.6038/cjg20140824(in Chinese with English abstract).
Wang Weitao,Wang Baoshan,Jiang Shengmiao,Hu Jiupeng,Zhang Yuansheng.A perspective review of seismological investigation on the crust at regional scale using the active Airgun source[J].Journal of Seismological Research,2017,40(4):514-524,doi:10.3969/j.issn.1000-0666.2017.04.002(in Chinese with English abstract).
Yu Ziye,Chu Risheng,Sheng Minhan.Pick onset time of P and S phase by deep neural network[J].Chinese Journal of Geophysics,2018,61(12):4873-4886,doi:10.6038/cjg2018L0725(in Chinese with English abstract).
Zhao Dapeng,Liu Xiqiang,Li Hong,Zhou Yanwen.Detection of regional seismic events by kurtosis method and automatic identification of direct P-wave first motion by kurtosis-AIC method[J].Journal of Seismological Research,2012,35(2):220-226,doi:10.3969/j.issn.1000-0666.2012.02.010(in Chinese with English abstract).
Zhang Miao,Wen Lianxing.An effective method for small event detection:match and locate(M&L)[J].Geophysical Journal International,2015,200(3):1523-1537,doi:10.1093/gji/ggu466.
Zhao Ming,Chen Shi,Zhang Bei,Yuen D.A.Automatic identification of aftershocks by convolutional neural networks and its application in waveform detection of China seismic network[J].Recent Developments in World Seismology,2018(8):42-43,doi:10.3969/j.issn.0253-4975.2018.08.035(in Chinese with English abstract).
Zhu Weiqiang,Beroza G.C.PhaseNet:a deep-neural-network-based seismic arrival-time picking method[J].Geophysical Journal International,2019,216(1):261-273,doi:10.1093/gji/ggy423.
Bao Xuewei,Eaton D.W.Fault activation by hydraulic fracturing in western Canada[J].Science,2016,354(6318):1406-1409.
Baer M.,Kradolfer U.An automatic phase picker for local and teleseismic events[J].Bulletin of the Seismological Society of America,1987,77(4):1437-1445.
Bengio Y.Learning deep architectures for AI[J].Foundations and Trendsin Machine Learning,2009,2(1):1-127.
Brown J.R.,Beroza G.C.,Shelly D.R.An autocorrelation method to detect low frequency earthquakes within tremor[J].Geophysical Research Letters,2008,35(16):L16305,doi:10.1029/2008GL034560.
Chen Guohua,Shu Liangshu,Shu Limin,Zhang Cheng,Ouyang Yongpeng.Geological characteristics and mineralization setting of the Zhuxi tungsten(copper)polymetallic deposit in the Eastern Jiangnan Orogen[J].Science China Earth Sciences,2016,59(4):803-823.
De Vries P.M.R.,Viégas F.,Wattenberg M.,Meade B.J.Deep learning of aftershock patterns following large earthquakes[J].Nature,2018,560(7720):632-634,doi:10.1038/s41586-018-0438-y.
Gibbons S.J.,Ringdal F.The detection of low magnitude seismic events using array-based waveform correlation[J].Geophysical Journal International,2006,165(1):149-166,doi:10.1111/j.1365-246X.2006.02865.x.
Gu Jinxiang,Wang Zhenhua,Jason K.,Ma Lianyang,Shahroudy A.,Shuai Bing,Liu Ting,Wang Xingxing,Wang Li,Wang Gang,Cai Jianfei,Chen Tsuhan.Recent advances in convolutional neural networks[J].ar Xiv preprint ar Xiv:1512.07108,2015.
He Xianlong,She Tianli,Gao Feng.A new method for picking up arrival times of seismic P and S waves automatically[J].Chinese Journal of Geophysics,2016,59(7):2519-2527,doi:10.6038/cjg20160717(in Chinese with English abstract).
Hou Jinxin,Wang Baoshan.Temporal evolution of seismicity before and after the 2014 Ludian MS6.5 earthquake[J].Chinese Journal of Geophysics,2017,60(4):1446-1456(in Chinese with English abstract).
House L.Locating microearthquakes induced by hydraulic fracturing in crystalline rock[J].Geophysical Research Letters,1987,14(9):919-921,doi:10.1029/GL014i009p00919.
Jiang Ce,Wu Jianping,Fang Lihua.Earthquake detection and automatic phase picking[J].Acta Seismologica Sinica,2018,40(1):45-57,doi:10.11939/jass.20170093(in Chinese with English abstract).
Kato A.,Obara K.,Lgarashi T.,Tsuruoka H.,Nakagawa S.,Hirata N.Propagation of slow slip leading up to the2011 Mw9.0 Tohoku-Oki earthquake[J].Science,2012,335(6069):705-708,doi:10.1126/science.1215141.
Kim Y.Convolutional neural networks for sentence classification[J].ar Xiv preprint ar Xiv:1408.5882,2014.
Kingma D.P.,Ba J.Adam:a method for stochastic optimization[J].ar Xiv preprint ar Xiv:1412.6980,2014.
Le Cun Y.,Bottou L.,Bengio Y.,Haffner P.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324,doi:10.1109/5.726791.
Li Lu,Wang Baoshan,Hou Jinxin.Applications of matched filter technique in seismic data processing[J].Earthquake Research in China,2017,33(1):14-22(in Chinese with English abstract).
Liu Han,Zhang Jianzhong.STA/LTA algorithm analysis and improvement of Microseismic signal automatic detection[J].Progress in Geophysics,2014,29(4):1708-1714,doi:10.6038/pg20140429(in Chinese).
Liu Xiqiang,Zhou Huilan,Shen Ping,Ma Yanlu,Li Hong.Identification method of seismic phase in threecomponent seismograms on the basis of wavelet transform[J].Acta Seismologica Sinica,2000,22(2):125-131,doi:10.3321/j.issn:0253-3782.2000.02.002(in Chinese with English abstract).
Liu Xiqiang,Zhou Yanwen,Qu Junhao,Shi Yuyan,Li Bo.Real-time detection of regional events and automatic P-phase identification from the vertical component of a single station record[J].Acta Seismologica Sinica,2009,31(3):260-271,doi:10.3321/j.issn:0253-3782.2009.03.003(in Chinese with English abstract).
Maeda N.A method for reading and checking phase time in auto-processing system of seismic wave data[J].Zisin(Journal of the Seismological Society of Japan.2nd ser.),1985,38(3):365-379,doi:10.4294/zisin1948.38.3_365(in Japanese).
Peng Zhigang,Zhao Peng.Migration of early aftershocks following the 2004 Parkfield earthquake[J].Nature Geoscience,2009,2(12):877-881,doi:10.1038/ngeo697.
Perol T.,Gharbi M.,Denolle M.Convolutional neural network for earthquake detection and location[J].Science Advances,2018,4(2):e1700578,doi:10.1126/sciadv.1700578.
Rawat W.,Wang Zenghui.Deep convolutional neural networks for image classification:a comprehensive review[J].Neural Computation,2017,29(9):2352-2449.
Shelly D.R.,Beroza G.C.,Ide S.Non-volcanic tremor and low-frequency earthquake swarms[J].Nature,2007,446(7133):305-307,doi:10.1038/nature05666.
Shensa M.J.The deflection detector-its theory and evaluation on short-period seismic data[J].Texas Instruments,Alexandria,Virginia,1977,TR-77-03.
Sleeman R.,van Eck T.Robust automatic P-phase picking:an on-line implementation in the analysis of broadband seismogram recordings[J].Physics of The Earth and Planetary Interiors,1999,13(1/4):265-275,doi:10.1016/S0031-9201(99)00007-2.
Stevenson P.R.Microearthquakes at flathead lake,Montana:a study using automatic earthquake processing[J].Bulletin of the Seismological Society of America,1976,66(1):61-80.
Stockwell R.G.,Mansinha L.,Lowe R.P.Localization of the complex spectrum:the S transform[J].IEEETransactions on Signal Processing,1996,44(4):998-1001,doi:10.1109/78.492555.
Tan Yuyang,Yu Jing,Feng Gang,He Chuan.Arrival picking of microseismic events using the SLPEA algorithm[J].Chinese Journal of Geophysics,2016,59(1):185-196,doi:10.6038/cjg20160116(in Chinese with English abstract).
Wang Haijun,Jin Ping,Liu Guizhong,Wang Xiaoming.Accurate estimation for arrival time of seismic wave[J].Northwestern Seismological Journal,2003,25(4):298-303,doi:10.3969/j.issn.1000-0844.2003.04.003(in Chinese with English abstract).
Wang Peng,Chang Xu,Wang Yibo,Wang Luchen,Zhai Hongyu.Automatic event detection and event recovery in low SNR microseismic signals based on time-frequency sparseness[J].Chinese Journal of Geophysics,2014,57(8):2656-2665,doi:10.6038/cjg20140824(in Chinese with English abstract).
Wang Weitao,Wang Baoshan,Jiang Shengmiao,Hu Jiupeng,Zhang Yuansheng.A perspective review of seismological investigation on the crust at regional scale using the active Airgun source[J].Journal of Seismological Research,2017,40(4):514-524,doi:10.3969/j.issn.1000-0666.2017.04.002(in Chinese with English abstract).
Yu Ziye,Chu Risheng,Sheng Minhan.Pick onset time of P and S phase by deep neural network[J].Chinese Journal of Geophysics,2018,61(12):4873-4886,doi:10.6038/cjg2018L0725(in Chinese with English abstract).
Zhao Dapeng,Liu Xiqiang,Li Hong,Zhou Yanwen.Detection of regional seismic events by kurtosis method and automatic identification of direct P-wave first motion by kurtosis-AIC method[J].Journal of Seismological Research,2012,35(2):220-226,doi:10.3969/j.issn.1000-0666.2012.02.010(in Chinese with English abstract).
Zhang Miao,Wen Lianxing.An effective method for small event detection:match and locate(M&L)[J].Geophysical Journal International,2015,200(3):1523-1537,doi:10.1093/gji/ggu466.
Zhao Ming,Chen Shi,Zhang Bei,Yuen D.A.Automatic identification of aftershocks by convolutional neural networks and its application in waveform detection of China seismic network[J].Recent Developments in World Seismology,2018(8):42-43,doi:10.3969/j.issn.0253-4975.2018.08.035(in Chinese with English abstract).
Zhu Weiqiang,Beroza G.C.PhaseNet:a deep-neural-network-based seismic arrival-time picking method[J].Geophysical Journal International,2019,216(1):261-273,doi:10.1093/gji/ggy423.