-
摘要:
发展高效、高精度、普适性强的自动波形拾取算法在地震大数据时代背景下显得越来越重要.波形自动拾取算法的主要挑战来自如何适应不同区域的不同类型地震事件的分类与筛选.本文针对地震事件-噪音分类这一问题, 使用13839个汶川地震余震事件建立数据集, 应用深度学习卷积神经网络(CNN)方法进行训练, 并用8900个新的汶川余震事件作为检测数据集, 其训练和检测准确率均达到95%以上.在对连续波形的检测中, CNN方法在精度和召回率上优于STA/LTA和Fbpicker传统方法, 并能找出大量人工挑选极易遗漏的微震事件.最后, 我们应用训练好的最优模型对选自全国台网的441个台站8天的连续波形数据进行了识别、到时挑取及与参考地震目录关联, CNN检出7016段波形, 用自动挑选算法拾取到1380对P, S到时, 并与540个地震目录事件成功关联, 对1级以上事件总体识别准确率为54%, 二级以上为80%, 证明了CNN模型具有泛化能力, 初步展示了CNN在发展兼具效率、精度、普适性算法, 实时地震监测等应用上具有巨大潜力.
Abstract:The development of efficient, high-precision, and universal automatic waveform pick-up algorithm is more and more important in the background of earthquake big data.The main challenge comes from how to adapt to the classification of different types of seismic events in different regions.In this paper, according to the seismic event-noise classification problem, a convolutional neural network method was used to train the dataset based on 13839 Wenchuan earthquake aftershocks and 8900 new Wenchuan aftershock events were used as the test data set.The training and detection accuracy rates were both over 95%.In the detection of continuous waveforms, the CNN method is superior to the traditional methods of STA/LTA and Fbpicker in precision and recall rate, and can find a large number of manually selected microseismic events that are easily missed.Finally, we use the trained optimal model to identify 8-day continuous waveform data from 441 stations nationwide.CNN detects 7016 waveforms, then we pick up 1380 pairs of P and S arrival times using an automatic picking algorithm, finally the pick-ups were successfully associated with 540 earthquake catalog events.The overall recognition accuracy of events above magnitude 1 was 54% and 80% above magnitude 2, while in some areas such as Sichuan and Xinjiang the detection rate is higher.It is shown that CNN neural network has broad application prospects in the real-time earthquake detection and location.
-
Key words:
- Convolutional neural network(CNN) /
- Waveform auto-picking
-
-
图 2
数据预处理前后的训练过程
Figure 2.
Different train process before and after data preprocessing
图 3
CNN连续波形检测与专家样本示例
Figure 3.
An example of CNN continuous waveform detection and the expert selected events
图 5
对CNN识别的地震事件进行P(红线), S震相(蓝线)自动挑取
Figure 5.
P (red line) and S phase (blue line) are automatically picked up for the seismic events identified by CNN
表 1
CNN与Fbpicker、STA/LTA算法对比
Table 1.
The comparison of CNN, Fbpicker and STA/LTA algorithm
方法 Pe Re Tp Fp Fn CNN 47.9% 94.5% 1803 1960 98 STA/LTA 29% 85% 1615 3954 286 fbpicker 36% 88% 1672 2972 229 
下载: 导出CSV
表 2
全国实时流CNN事件识别结果
Table 2.
CNN events identification of the national real-time data stream
下载: 导出CSV
-
Akaike H.1974.A new look at the statistical model identification.IEEE Transactions on Automatic Control, 19(6):716-723, doi:10.1109/TAC.1974.1100705.
Akazawa T.2004.A technique for automatic detection of onset time of P-and S-Phases in strong motion records.//13th World Conference on Earthquake Engineering.Vancouver B C, Canada: International Association for Earthquake Engineering.
Allen R V.1978.Automatic earthquake recognition and timing from single traces.Bulletin of the Seismological Society of America, 68(5):1521-1532. http://gji.oxfordjournals.org/cgi/ijlink?linkType=ABST&journalCode=ssabull&resid=68/5/1521
Chen C, Holland A A.2016.PhasePApy:A robust pure python package for automatic identification of seismic phases.Seismological Research Letters, 87(6):1384-1396, doi:10.1785/0220160019.
Fang L H, Wu J P, Wang W L, et al.2015.Aftershock observation and analysis of the 2013 MS7.0 Lushan earthquake.Seismological Research Letters, 86(4):1135-1142. doi: 10.1785/0220140186
Gentili S, Michelini A.2006.Automatic picking of P and S phases using a neural tree.Journal of Seismology, 10(1) 39-63, doi:10.1007/s10950-006-2296-6.
Goodfellow I, Bengio Y, Courville A, et al.2016.Deep Learning.The MIT Press.
He K M, Zhang X Y, Ren S Q, et al.2016.Deep residual learning for image recognition.//2016 IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas, NV, USA: IEEE.
Küperkoch L, Meier T, Lee J, et al.2010.Automated determination of P-phase arrival times at regional and local distances using higher order statistics.Geophysical Journal International, 181(2):1159-1170. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=bdb37311d407b35fdf09b67cb4948951
Kong Q K, Allen R M, Schreier L, et al.2016.Myshake:A smartphone seismic network for earthquake early warning and beyond.Science Advances, 2(2):e1501055, doi:10.1126/sciadv.1501055.
Krischer L, Megies T, Barsch R, et al.2015.ObsPy:A bridge for seismology into the scientific Python ecosystem.Computational Science & Discovery, 8(1):014003, doi:10.1088/1749-4699/8/1/014003.
Krizhevsky A, Sutskever I, Hinton G E.2012.Imagenet classification with deep convolutional neural networks.//Advances in Neural Information Processing Systems, 1097-1105.
LeCun Y, Bengio Y, Hinton G.2015.Deep learning.Nature, 521(7553):436-444. doi: 10.1038/nature14539
Perol T, Gharbi M, Denolle M.2018.Convolutional neural network for earthquake detection and location.Science Advances, 4(2):e1700578, doi:10.1126/sciadv.1700578.
Ross Z E, White M C, Vernon F L, et al.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, doi:10.1785/0120150230.
Ross Z E, Meier M A, Hauksson E, et al.2018.Generalized seismic phase detection with deep learning.Bulletin of the Seismological Society of America, 108(5A):2894-2901, doi:10.1785/0120180080.
Skoumal R J, Brudzinski M R, Currie B S, et al.2014.Optimizing multi-station earthquake template matching through re-examination of the Youngstown, Ohio, sequence.Earth and Planetary Science Letters, 405:274-280. doi: 10.1016/j.epsl.2014.08.033
Sleeman R, Van Eck T.1998.Robust automatic P-phase picking:An on-line implementation in the analysis of broadband seismogram recordings.Physics of the Earth and Planetary Interiors, 113(1-4):265-275. http://www.sciencedirect.com/science/article/pii/S0031920199000072
Trnkoczy A.2012.Understanding and parameter setting of STA/LTA trigger algorithm.//Bormann P ed.New Manual of Seismological Observatory Practice 2 (NMSOP-2).Potsdam: Deutsches GeoForschungsZentrum GFZ.
Wang J, Teng T L.1995.Artificial neural network-based seismic detector.Bulletin of the Seismological Society of America, 85(1):308-319. http://d.old.wanfangdata.com.cn/NSTLQK/10.1016-j.maturitas.2010.07.008/
Withers M, Aster R, Young C, et al.1998.A comparison of select trigger algorithms for automated global seismic phase and event detection.Bulletin of the Seismological Society of America, 88(1):95-106. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=133627739c39dbce25606a48e254da77
Yoon C E, O'Reilly O, Bergen K J, et al.2015.Earthquake detection through computationally efficient similarity search.Science Advances, 1(11):e1501057, doi:10.1126/sciadv.1501057.
Zhang H, Thurber C, Rowe C.2003.Automatic P-wave arrival detection and picking with multiscale wavelet analysis for single-component recordings.Bulletin of the Seismological Society of America, 93(5):1904-1912. doi: 10.1785/0120020241
Zhao Y, Takano K.1999.An artificial neural network approach for broadband seismic phase picking.Bulletin of the Seismological Society of America, 89:670-680. http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=31e573879dc619b242165a932027a8c2
-
图(5)
表(2)
计量
- 文章访问数: 4977
- PDF下载数: 2220
- 施引文献: 0