基于深度学习的地震检测模型在区域台网的泛化性研究

doi:10.12196/j.issn.1000-3274.2021.01.013

地震 ›› 2021, Vol. 41 ›› Issue (1): 166-179.doi: 10.12196/j.issn.1000-3274.2021.01.013

基于深度学习的地震检测模型在区域台网的泛化性研究

赵明^1,2, 陈石^1,2

1.中国地震局地球物理研究所, 北京 100081;
2.北京白家疃国家地球科学野外观测研究站, 北京 100095

收稿日期:2020-07-23 修回日期:2020-11-18 出版日期:2021-01-31 发布日期:2021-01-28
作者简介:赵明(1984-),男,湖北仙桃人,助理研究员,主要从事地震学和机器学习方法的研究。
基金资助:
国家自然科学基金青年基金资助项目(41804047); 中国地震局地球物理研究所基本科研业务专项(DQJB19A0114); 科技部重点研发专项项目(2018YFC0603502)

The Generalization Ability Research of Deep Learning Algorithm in Seismic Phase Detection of Regional Seismic Network

ZHAO Ming^1,2, CHEN Shi^1,2

1. Institute of Geophysics, China Earthquake Administration, Beijing 100081, China;
2. Beijing Baijiatuan Earth Science National Observation and Research Station, Beijing 100095, China

Received:2020-07-23 Revised:2020-11-18 Online:2021-01-31 Published:2021-01-28

摘要/Abstract

摘要： 将识别地震的深度学习算法PhaseNet应用于四川台网和首都圈台网, 对该模型的泛化能力进行了测试和评估。首先利用2010年1月至2018年10月首都圈台网199个地震台站记录的29328个事件(M_L0~M_L4)所对应的126761段事件波形, 以及 2019年4—9月四川及邻省部分台网227个地震台站记录的16595个事件(M_L0~M_L6.0)所对应的120233段事件波形分别建立了SC和CA测试数据集, 并用预训练好的PhaseNet模型进行P、 S震相自动识别和到时拾取, 并将拾取结果与人工拾取结果在不同误差阈值下进行对比。测试结果表明, PhaseNet在两个数据集上具有良好的震相检测能力(误差阈值为0.5 s), 其P、 S震相检测的F₁值都超过0.75, 具有比较稳定的准确拾取P波到时能力(误差阈值0.1 s), 其检测F₁值均超过0.6, 而S波到时拾取的F₁值分别为0.33(SC)和0.53(CA)。进一步分析了测试结果与震中距、震级、信噪比、台站所处地域之间的关系, 为下一步继续训练更优化的模型指明了方向。研究结果表明, PhaseNet算法在区域台网地震自动检测和到时拾取方面有很大的应用潜力和提升空间, 可以为区域台网的自动编目工作提供辅助。

关键词: PhaseNet, 泛化性, 到时拾取, 震相检测

Abstract: We applied PhaseNet, a deep learning seismic phase detection and arrival time picking algorithm to the data from the Sichuan Network and the Capital Region Network and tested its generalization ability. Based on 126761 event waveforms corresponding to 29328 events (M_L0~M_L4) recorded by 199 seismic stations in the Capital Region Network from January 2010 to October 2018, and 120233 event waveforms corresponding to 16595 events (M_L0~M_L6) recorded by 227 seismic stations in Sichuan and neighboring provinces from April to September 2019, we established SC and CA test datasets, and used the pre-trained PhaseNet model for automatically detecting P、 S phases and picking up arrival time. The test shows that PhaseNet has good seismic phase detection capability, the F₁ value of P and S detection exceeds 0.75 (threshold value is 0.5 s), and has a relatively stable and accurate ability to pick up P arrival time (threshold value 0.1 s), where the F₁ value exceed 0.6 on both datasets, and the F₁ values for S phase picking are 0.33 (SC) and 0.53 (CA). We further analyzed the relationship between the test results and the epicentral distance, magnitude, signal-to-noise ratio, and the location of the station, which not only defined the scope of the current PhaseNet model, but also indicated the direction for the next step to continue training more optimized models. The above results show that the PhaseNet algorithm have great application potential in the automatic seismic phases detection of regional networks and can currently provide assistance for the automatic cataloging work.

Key words: PhaseNet, Generalization ability, Arrival time picking, Phase detection

中图分类号:

P315.7

赵明, 陈石. 基于深度学习的地震检测模型在区域台网的泛化性研究[J]. 地震, 2021, 41(1): 166-179.

ZHAO Ming, CHEN Shi. The Generalization Ability Research of Deep Learning Algorithm in Seismic Phase Detection of Regional Seismic Network[J]. EARTHQUAKE, 2021, 41(1): 166-179.

参考文献

[1] Allen R V. Automatic earthquake recognition and timing from single traces[J]. Bulletin of the Seismological Society of America, 1978, 68: 1521-1532.
[2] Chen Y, Zhang G, Bai M, et al. Automatic waveform classification and arrival picking based on convolutional neural network[J]. Earth and Space Science, 2019, 6(7): 1244-1261.
[3] Akaike H. A new look at the statistical model identification[J]. IEEE transactions on automatic control, 1974, 19(6): 716-723.
[4] 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, 113(1-4): 265-275.
[5] Saragiotis C D, Hadjileontiadis L J, Panas S M. PAI-S/k: A robust automatic seismic P phase arrival identification scheme[J]. IEEE Transactions on Geoscience and Remote Sensing, 2002, 40(6): 1395-1404.
[6] Küperkoch L, Meier T, Brüstle A, et al. Automated determination of S-phase arrival times using autoregressive prediction: Application to local and regional distances[J]. Geophysical Journal International, 2012, 188(2): 687-702.
[7] Küperkoch L, Meier T, Lee J, et al. Automated determination of P-phase arrival times at regional and local distances using higher order statistics[J]. Geophysical Journal International, 2010, 181(2): 1159-1170.
[8] Akazawa T. A technique for automatic detection of onset time of P-and S-phases in strong motion records[C]∥Proc. of the 13th World Conf. on Earthquake Engineering. 2004.
[9] Zhu L J, Peng Z G, McClellan J, et al. Deep learning for seismic phase detection and picking in the aftershock zone of 2008 M_W7.9 Wenchuan earthquake[J]. Physics of the Earth and Planetary Interiors, 2019, 293: 106261.
[10] Zhou Y J, Yue H, Kong Q K, et al. Hybrid event detection and phase-picking algorithm using convolutional and recurrent neural networks[J]. Seismological Research Letters, 2019, 90(3): 1079-1087.
[11] Dokht R M H, Kao H, Visser R, et al. Seismic event and phase detection using time-frequency representation and convolutional neural networks[J]. Seismological Research Letters, 2019, 90(3): 481-490.
[12] 赵明, 陈石, 房立华, 等. 基于U形卷积神经网络的震相识别与到时拾取方法研究[J]. 地球物理学报, 2019, 62(8): 3034-3042.
ZHAO Ming, CHEN Shi, FANG Li-hua, et al. Earthquake phase arrival auto-picking based on u-shaped convolutional neural network[J]. Chinese Journal of Geophysics, 2019, 62(8): 3034-3042 (in Chinese).
[13] 李健, 王晓明, 张英海, 等. 基于深度卷积神经网络的地震震相拾取方法研究[J]. 地球物理学报, 2020, 63(4): 1591-1606.
LI Jian, WANG Xiao-ming, ZHANG Ying-hai et al. Research on the seismic phase picking method based on the deep convolution neural network[J]. Chinese Journal of Geophysics, 2020, 63(4): 1591-1606 (in Chinese).
[14] Zhu W Q, Beroza G C. Phasenet: A deep-neural-network-based seismic arrival-time picking method[J]. Geophysical Journal International, 2018, 216(1): 261-273.
[15] Ross Z E, Meier M A, Hauksson E, et al. Generalized seismic phase detection with deep learning[J]. Bulletin of the Seismological Society of America, 2018, 108(5A): 2894-2901.
[16] Wang J, Xiao Z W, Liu C, et al. Deep learning for picking seismic arrival times[J]. Journal of Geophysical Research: Solid Earth, 2019, 124(7): 6612-6624.
[17] 谢卓娟, 吕悦军, 方怡, 等. 京津冀地区的地震活动性研究[J]. 地球物理学进展, 2019, 34(3): 961-968.
XIE Zhuo-juan, LÜ Yue-jun, FANG Yi, et al. Research on the seismic activity of the Beijing-Tianjin-Hebei region[J]. Progress in Geophysics, 2019, 34(3): 961-968 (in Chinese).

基于深度学习的地震检测模型在区域台网的泛化性研究

The Generalization Ability Research of Deep Learning Algorithm in Seismic Phase Detection of Regional Seismic Network

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价