基于机器学习算法的银川台阵资料自动化震相分析和定位

doi:10.12196/j.issn.1000-3274.2021.01.012

地震 ›› 2021, Vol. 41 ›› Issue (1): 153-165.doi: 10.12196/j.issn.1000-3274.2021.01.012

基于机器学习算法的银川台阵资料自动化震相分析和定位

宿君^1,2, 王未来¹, 张龙¹, 陈明飞¹

1.中国地震局地球物理研究所, 北京 100081;
2.四川省地震局, 成都 610041

收稿日期:2020-04-09 修回日期:2020-07-07 出版日期:2021-01-31 发布日期:2021-01-28
通讯作者: 王未来,副研究员。E-mail:wangwl@cea-igp.ac.cn
作者简介:宿君(1992-),女,四川凉山人,在读硕士研究生,主要从事重复地震研究。
基金资助:
国家重点研发计划项目(2018YFC1504103); 中央级公益性科研院所基本科研业务费专项(DQJB19A35)

Automatic Seismic Phase Analysis and Earthquake Location Using Yinchuan Array Datasets based on a Machine Learning Algorithm

SU Jun^1,2, WANG Wei-lai¹, ZHANG Long¹, CHEN Ming-fei¹

1. Institute of Geophysics, China Earthquake Administration, Beijing 100081, China;
2. Sichuan Earthquake Administration, Chengdu 610041, China

Received:2020-04-09 Revised:2020-07-07 Online:2021-01-31 Published:2021-01-28

摘要/Abstract

摘要： 近年来快速发展的机器学习算法显著提高了震相拾取的精度和效率。采用卷积神经网络和递归神经网络的震相识别方法对银川台阵2019年6~7月的连续波形数据进行事件检测和P、 S震相拾取, 并通过快速震相关联和事件定位得到了银川地区较全的地震目录。结果表明, 当震相数小于10时, 虽然可以检测出较多事件, 但分布呈弥散状, 与区域地震活动特征不符。进一步对震相数≥10的事件进行了人工复核。总体而言, 随着震相数量的增加, 事件的误检率逐步降低。震相数16是该地区自动检测和定位结果准确性的拐点。当震相数≥20时, 全部召回了地震目录中的13个地震事件, 二者平均定位差异4.27 km。经过人工复核, 检测到的真实地震事件为区域内地震目录中事件数量的9倍。本文使用的基于机器学习和快速震相关联和定位方法的流程可在确保准确率的基础上降低人工检测的难度, 提高地震检测的效率。

关键词: 地震检测, 震相拾取, 震相关联, 定位

Abstract: In recent years, the rapid development of machine learning algorithms have significantly improved the accuracy and efficiency of seismic phase picking. In this paper, a hybrid neural network algorithm, which comprised by convolutional neural networks (CNN) and recurrent neural networks (RNN) algorithms, is used to on continuous waveform data recorded by Yinchuan Array in June and July, 2019 for earthquake detection and phase picking. Phases from RNN are associated and located by using the Rapid Earthquake Association and Location method (REAL), and then compared with the routine catalog. The results show that when the number of seismic phases is less than 10, although more events can be detected, the distribution is diffuse, which is inconsistent with the characteristics of regional seismicity. The events with 10 or more seismic phases are manually inspected. In general, as the number of seismic phases increases, the false detection rate is lower. 16 is the critical number of seismic phases to achieve accurate phase detection and location results. When the number of seismic phases is 20 or more, 13 earthquakes in the routine catalog are all recalled. The average location offset between the relocation and routine catalog result is 4.27 km. Besides, the number of manually inspected earthquakes from the automatic procedure is 9 times of that from the routine catalog. It suggests that the procedure which combined the machine learning and REAL method is capable of reducing the difficulty and improving the accuracy and efficiency of earthquake detection.

Key words: Earthquake detection, Phase picking, Phase association, Location

中图分类号:

P315.63

宿君, 王未来, 张龙, 陈明飞. 基于机器学习算法的银川台阵资料自动化震相分析和定位[J]. 地震, 2021, 41(1): 153-165.

SU Jun, WANG Wei-lai, ZHANG Long, CHEN Ming-fei. Automatic Seismic Phase Analysis and Earthquake Location Using Yinchuan Array Datasets based on a Machine Learning Algorithm[J]. EARTHQUAKE, 2021, 41(1): 153-165.

参考文献

[1] 陈成沟, 邢成起, 胡乐银, 等. 北京及其邻区小震重定位与活动构造分析[J]. 地震, 2017, 37(3): 84-94.
CHEN Cheng-gou, XING Cheng-qi, HU Le-yin, et al. Relocation of small earthquakes and active tectonics in Beijing and its adjacent areas[J]. Earthquake, 2017, 37(3): 84-94 (in Chinese).
[2] Grigoli F, Scarabello L, Böse M, et al. Pick- and waveform-based techniques for real-time detection of induced seismicity[J]. Geophysical Journal International, 2018, 213(2): 868-884.
[3] Kao H, Shan S J. The Source-Scanning Algorithm: Mapping the distribution of seismic sources in time and space[J]. Geophysical Journal International, 2004, 157(2): 589-594.
[4] 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.
[5] Peng Z G, Zhao P. Migration of early aftershocks following the 2004 Parkfield earthquake[J]. Nature Geoscience, 2009, 2: 877-881.
[6] Pesicek J D, Child D, Artman B, et al. Picking versus stacking in a modern microearthquake location: Comparison of results from a surface passive seismic monitoring array in Oklahoma[J]. Geophysics, 2014, 79(6): KS61-KS68.
[7] Perol T, Gharbi M, Denolle M. Convolutional neural network for earthquake detection and location[J]. Science Advances, 2018, 4(2): e1700578.
[8] 邓莉, 谭毅培, 刘双庆, 等. 天津滨海爆炸事件检测与相对定位研究[J]. 地震, 2018, 38(3): 158-169.
DENG Li, TAN Yi-pei, LIU Shuang-qing, et al. Event detection and relative relocation of the massive explosions in Binhai, Tianjin[J]. Earthquake, 2018, 38(3): 185-169 (in Chinese).
[9] 闫坤, 王伟君, 王琼, 等. 北天山中段微震活动检测及其活动性和孕震构造分析[J]. 地震, 2019, 39(3): 43-60.
YAN Kun, WANG Wei-jun, WANG Qiong, et al. Discussion on the seismicity and seismogenic structure in fold-and-thrust belt of Northern Tianshan Mountains[J]. Earthquake, 2019, 39(3): 43-60 (in Chinese).
[10] Beauceé E, Frank W B, Romanenko A. Fast matched filter (FMF): An efficient seismic matched-filter search for both CPU and GPU architectures[J]. Seismological Research Letters, 2018, 89(1): 165-172.
[11] Stevenson P R. Microearthquakes at Flathead Lake, Montana: A study using automatic earthquake processing[J]. Bulletin of Seismological Society of America, 1976, 66(1): 61-80.
[12] Allen R V. Automatic earthquake recognition and timing from single traces[J]. Bulletin of Seismological Society of America, 1978, 68(5): 1521-1532.
[13] Ross Z E, Meier M A, Hauksson E. P wave arrival picking and first-motion polarity determination with deep learning[J]. Journal of Geophysical Research: Solid Earth, 2018, 123(6): 5120-5129.
[14] 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.
[15] Kong Q K, Trugman D T, Ross Z E, et al. Machine learning in seismology: Turning data into insights[J]. Seismological Research Letters, 2019, 90(1): 3-14.
[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] Yoon C E, O'Reilly O, Bergen K J, et al. Earthquake detection through computationally efficient similarity search[J]. Science Advances, 2015, 1(11): e1501057.
[18] Stewart S W. Real-time detection and location of local seismic events in central California[J]. Bulletin of Seismological Society of America, 1977, 67(2): 433-452
[19] Zhu L J, Liu E, McClellan J H. A multi-channel approach for automatic microseismic event localization using RANSAC-based arrival time event clustering (RATEC)[EB/OL]. (2017-02-15)[2020-06-20]. http:∥arxiv.org/abs/1702.01856.
[20] McBrearty I W, Delorey A A, Johnson P A. Pairwise association of seismic arrivals with convolutional neural networks[J]. Seismological Research Letters, 2019, 90(2A): 503-509.
[21] Ross Z E, Yue Y, Meier M A, et al. PhaseLink: A deep learning approach to seismic phase association[J]. Journal of Geophysical Research: Solid Earth, 2019, 124(1): 856-869.
[22] Thurber C H. Nonlinear earthquake location: Theory and example[J]. Bulletin of Seismological Society of America, 1985, 75(3): 779-790.
[23] Lomax A, Virieux J, Volant P. Probabilistic earthquake location in 3D and layered models[M]∥Thurber C H, Rabinowitz N. Dordrecht: Springer, 2000: 101-134.
[24] Zhang M, Ellsworth W L, Beroza G C. Rapid earthquake association and location[J]. Seismological Research Letters, 2019, 90(6): 2276-2284.
[25] Crotwell H P, Owens T J, Ritsema J. The TauP Toolkit: Flexible seismic travel-time and ray-path utilities[J]. Seismological Research Letters, 1999, 70(2): 154-160.
[26] Wang W L, Wu J P, Fang L H, et al. Sedimentary and crustal thicknesses and Poisson's ratios for the NE Tibetan Plateau and its adjacent regions based on dense seismic arrays[J]. Earth and Planetary Science Letters, 2017, 462: 76-85.

基于机器学习算法的银川台阵资料自动化震相分析和定位

Automatic Seismic Phase Analysis and Earthquake Location Using Yinchuan Array Datasets based on a Machine Learning Algorithm

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	左可桢, 赵翠萍. 2023年甘肃积石山6.2级地震序列精定位[J]. 地震, 2024, 44(1): 204-208.
[2]	闫坤, 王伟君, 寇华东, 叶志鹏. 2022年青海门源M_S6.9地震余震演化与地震触发[J]. 地震, 2023, 43(1): 15-32.
[3]	章宇成, 华卫. 白鹤滩水库库区基于深度学习的震相拾取与地震定位[J]. 地震, 2023, 43(1): 137-151.
[4]	钱蕊, 王亮, 张博, 杨士超, 邵媛媛. 基于tomoDd方法对盖州地区地震活动的重新定位研究[J]. 地震, 2022, 42(2): 149-160.
[5]	戴宗辉, 李冬梅, 王鹏, 郑建常, 王志才, 李霞. 2020年2月18日长清M_S4.1地震发震构造研究[J]. 地震, 2022, 42(1): 111-121.
[6]	赵策, 左可桢, 赵翠萍. 2019年6月17日四川长宁6.0级地震序列活动特征[J]. 地震, 2020, 40(3): 28-40.
[7]	司政亚, 蒋长胜, 邱宇. 重点地震监视区敏感台站的识别研究[J]. 地震, 2020, 40(2): 82-90.
[8]	刘建明, 李金, 姚远, 聂晓红, 滕海涛. 2019年1月12日新疆疏附5.1级地震序列重定位及发震构造研究[J]. 地震, 2020, 40(1): 52-61.
[9]	孟真, 宋晓东. 龙门山断裂带周缘重复地震识别及其在台网定位评价中的应用[J]. 地震, 2019, 39(3): 166-177.
[10]	申金超, 李士成, 张斌. 长岛震群b值随深度变化特征[J]. 地震, 2019, 39(2): 28-36.
[11]	张娜, 赵翠萍, 周连庆. 三峡水库区上地壳三维精细速度结构成像[J]. 地震, 2018, 38(4): 37-48.
[12]	李君, 王勤彩. 2013年松原5级震群序列精定位、震源机制解及发震构造特征[J]. 地震, 2018, 38(4): 62-73.
[13]	李春宏, 赵翠萍, 张娜, 周连庆. 白鹤滩水库库区地震本底活动特征[J]. 地震, 2018, 38(4): 94-108.
[14]	孙庆山, 李乐. 红河断裂带北段地震精定位研究[J]. 地震, 2018, 38(3): 92-102.
[15]	邓莉, 谭毅培, 刘双庆, 马婷, 卞真付, 曹井泉. 天津滨海爆炸事件检测与相对定位研究[J]. 地震, 2018, 38(3): 158-169.