实时智能地震处理系统研发及其在2021年云南漾濞<i>M</i><sub>S</sub>6.4地震中的应用

doi:10.6038/cjg2021O0532

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (10632 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract This paper introduces a real-time seismic processing system based on artificial intelligence. The system uses the deep learning method to detect earthquakes. It includes earthquake detection, phase arrival picking, association, earthquake location and magnitude measurement. It can process continuous seismic waveform data and dense seismic sequences in real time and off-line modes. The obtained earthquake catalog shows significant improvement in location accuracy, completeness and consistency compared to manually determined catalog. For the 2021 Yangbi M_S6.4 earthquake sequence in Yunnan Province, the system can produce earthquake catalog within 2~4 minutes after the earthquake. The number of detected earthquakes is 2~3 times more than those of obtained from manual processing. The location accuracy is equivalent to the results of manual processing. The uncertainty of the estimated magnitudes is small and the lower limit of magnitude can reach~M_L0.0. The system can be used not only for regional seismic network, but also for real-time data process of seismic network with different purposes, such as dense seismic observations in reservoir, mining and volcano areas. Based on the outputs of the system, we can further calculate the change of b-value, analyze the temporal and spatial evolution characteristics of earthquakes, and carry out real-time precise earthquake sequence relocation, to provide important data for earthquake emergency, earthquake prediction and related scientific research. The system is of great significance to optimize the automatic processing flowchart of seismic data and improve the automation level of seismic cataloging in China.

Key words： Automatic processing Deep learning Earthquake detection Earthquake cataloging Yangbi earthquake

Received: 26 July 2021

PACS:

P315

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	LIAO ShiRong
	ZHANG HongCai
	FAN LiPing
	LI BoRen
	HUANG LingZhu
	FANG LiHua
	QIN Min

URL:

http://www.geophy.cn//EN/10.6038/cjg2021O0532 OR http://www.geophy.cn//EN/Y2021/V64/I10/3632

Chai C, Maceira M, H J Santos-Villalobos, et al. 2020. Using a Deep Neural Network and Transfer Learning to Bridge Scales for Seismic Phase Picking. Geophysical Research Letters, 47(16), doi:10.1029/2020GL088651.
China Earthquake Administration. 2017. DB/T 66-2016 Specification for earthquake cataloguing (in Chinese). Beijing:Standards Press of China.
Dai G H, Miao C L, Zhai L Y. 2019. Unified earthquake cataloging of China seismographic network. Earthquake Research in China (in Chinese), 35(1):192-203, doi:10.3969/j.issn.1001-4683.2019.01.018.
Fang L H, Wu J P, Wang W L, et al. 2013. Relocation of the mainshock and aftershock sequences of M_S7.0 Sichuan Lushan earthquake. Chinese Science Bulletin, 58(28-29):3451-3459, doi:10.1007/s11434-013-6000-2.
Fang L H, Wu Z L, Song K. 2017. Seism Olympics. Seismological Research Letters, 88(6):1429-1430.
Fang L H, Wu J P, Su J R, et al. 2018. Relocation of mainshock and aftershock sequence of the M_S7.0 Sichuan Jiuzhaigou earthquake. Chinese Science Bulletin (in Chinese), 63(7):649-662, doi:10.1360/N972017-01184.
Hanka W, Saul J, Weber B, et al. 2010. Real-time earthquake monitoring for tsunami warning in the Indian Ocean and beyond. Natural Hazards and Earth System Sciences, 10(12):2611-2622, doi:10.5194/nhess-10-2611-2010.
Huang W H, Kang Y, Su Z J, et al. 2016a. The design and implementation of unified national cataloging system. Seismological and Geomagnetic Observation and Research (in Chinese), 37(4):170-175, doi:10.3969/j.issn.1003-3246.2016.04.031.
Huang W H, Shen Y S, Lv Z Y, et al. 2016b. Evaluating the results of the earthquake very fast report system. South China Journal of Seismology (in Chinese), 36(4):1-7, doi:10.13512/j.hndz.2016.04.001.
Jiang C S, Wu Z L, Yin F L, et al. 2015. Stability of early-estimation sequence parameters for continuous forecast of the aftershock rate:A case study of the 2014 Ludian, Yunnan M_S6.5 earthquake. Chinese Journal of Geophysics (in Chinese), 58(11):4163-4173, doi:10.6038/cjg20151123.
Jiang Y R, Ning J Y. 2019. Automatic detection of seismic body-wave phases and determination of their arrival times based on support vector machine. Chinese Journal of Geophysics (in Chinese), 62(1):361-373, doi: 10.6038/cjg2019M0442.
Jin X, Ma Q, Li S Y. 2004. Real-time simulation of ground displacement and acceleration using digital velocity record. Earthquake Engineering and Engineering Vibration (in Chinese), 24(6):9-14, 38, doi: 10.13197/j.eeev.2004.06.002.
Jin X, Liao S R, Chen F W. 2007. The test running of real-time earthquake information system for province-level seismic network. Seismological and Geomagnetic Observation and Research (in Chinese), 28(1):64-72, doi: 10.3969/j.issn.1003-3246.2007.01.011.
Johnson C E, Bittenbinder A, Bogaert B, et al. 1995. Earthworm:A flexible approach to seismic network processing. IRIS Newsletter, 14(2):1-4.
Kanamori H, Maechling P, Hauksson E. 1999. Continuous monitoring of ground-motion parameters. Bulletin of the Seismological Society of America, 89(1):311-316, doi:10.1785/BSSA0890010311.
Kennett B L N. 2005. Seismological tables:ak135. Canberra, Australia:Research School of Earth Sciences, Australian National University, 1-289.
Klein F. 2002. User's guide to HYPOINVERSE-2000, a Fortran program to solve for earthquake locations and magnitudes. US Geological Survey. Open-File Rept. 02-171, 123, doi:10.13140/2.1.4859.3602.
Kong Q K, Trugman D T, Ross Z E, et al. 2019. Machine learning in seismology:Turning data into insights. Seismological Research Letters, 90(1):3-14, doi:10.1785/0220180259.
Lei X L, Wang Z W, Ma S L, He C R. 2021. A preliminary study on the characteristics and mechanism of the May 2021 M_S 6.4, Yangbi earthquake sequence, Yunnan, China. Acta Seismologica Sinica, 43(3):1-24. doi: 10.11939/jass.20210100.
Li S Y. 2018. Approaching the Earthquake Early Warning.Overview of Disaster Prevention, (2):14-23. doi:CNKI:SUN:FZBL.0.2018-02-010.
Li Y Q, Wang D, Xu S H, et al. 2019. Thrust and conjugate strike-slip faults in the 17 June 2018 MJMA 6.1 (Mw 5.5) Osaka, Japan, earthquake sequence. Seismological Research Letters, 90(6):2132-2141, doi: 10.1785/0220190122.
Liang J H. 2009. Research and application of methods for rapid processing of seismic data[Master's thesis] (in Chinese). Beijing:Institute of Geophysics, China Earthquake Administration, 37-42.
Liu M, Zhang M, Zhu W Q, et al. 2020. Rapid characterization of the July 2019 Ridgecrest, California, earthquake sequence from raw seismic data using machine-learning phase picker. Geophysical Research Letters, 47(4): e2019GL086189, doi:10.1029/2019GL086189.
Lomax A, Michelini A, Curtis A. 2008. Earthquake Location, Direct, Global-Search Methods. Springer New York, doi:10.1007/978-0-387-30440-3_150.
Lomax A, Satriano C, Vassallo M. 2012. Automatic picker developments and optimization:filter Picker-a robust, broadband picker for real-time seismic monitoring and earthquake early warning. Seismological Research Letters, 83 (3):531-540, doi:10.1785/gssrl.83.3.531.
Long F, Qi Y P, Yi G X, et al. 2021. Relocation of the M_S6.4 Yangbi earthquake sequence on May 21, 2021 in Yunnan Province and its seismogenic structure analysis. Chinese Journal of Geophysics (in Chinese), 64(8):2631-2646, doi:10.6038/cjg2021O0526.
Mousavi S M, Ellsworth W L, Zhu W Q, et al. 2020. Earthquake transformer-an attentive deep-learning model for simultaneous earthquake detection and phase picking. Nature Communications, 11(1):3952, doi:10.1038/s41467-020-17591-w.
Park Y, Mousavi S M, Zhu W, Ellsworth W L, &Beroza G C. 2020. Machine learning-based analysis of the Guy-Greenbrier, Arkansas earthquakes:A tale of two sequences. Geophysical Research Letters, 47, e2020GL087032. https://doi.org/10.1029/2020GL087032.
Patton J M, Guy M R, Benz H M, et al. 2016. Hydra-The National Earthquake Information Center's 24/7 seismic monitoring, analysis, catalog production, quality analysis, and special studies tool suite. Reston, VA:U.S. Geological Survey, doi:10.3133/ofr20161128.
Pero T, Gharbi M, Denolle M. 2018. Convolutional neural network for earthquake detection and location. Science Advances, 4(10):e1700578, doi:10.1126/sciadv.1700578.
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.
Scafidi D, Spallarossa D, Ferretti G, et al. 2019. A Complete Automatic Procedure to Compile Reliable Seismic Catalogs and Travel-Time and Strong-Motion Parameters Datasets. Seismological Research Letters, 90(3). doi: 10.1785/0220180257.
Schweitzer J. 2001. HYPOSAT-An enhanced routine to locate seismic events. Pure and Applied Geophysics, 158(1):277-289, doi:10.1007/PL00001160.
Spallarossa D, Cattaneo M, Scafidi D, et al. 2020. An automatically generated high-resolution earthquake catalogue for the 2016-2017 Central Italy seismic sequence, including P and S phase arrival times. Geophysical Journal International, 225, 555-571, doi:10.1093/gji/ggaa604.
Su J B, Liu M, Zhang Y P, et al. 2021. High resolution earthquake catalog building for the 21 May 2021 Yangbi, Yunnan, M_S6.4 earthquake sequence using deep-learning phase picker. Chinese Journal of Geophysics (in Chinese), 64(8):2647-2656, doi:10.6038/cjg2021O0530.
Tamaribuchi K. 2018. Evaluation of automatic hypocenter determination in the JMA unified catalog. Earth Planets and Space, 70(1), doi:10.1186/s40623-018-0915-4.
Tan Y J, Waldhauser F, Ellsworth W L, et al. 2021. Machine-learning-based high-resolution earthquake catalog reveals how complex fault structures were activated during the 2016-2017 central Italy sequence. The Seismic Record, 1(1):11-19, doi:10.1785/0320210001.
Thurber C, Roecker S, Zhang H, et al. 2004. Fine-scale structure of the San Andreas fault zone and location of the SAFOD target earthquakes. Geophysical Research Letters, 31(12):L12S02, doi:10.1029/2003GL019398.
Wang D, Hutko A R. 2018. Relative relocations of the North Korean nuclear tests from 2006 to 2017 using the Hi-Net array in Japan. Geophysical Research Letters, 45(15):7481-7487, doi:10.1029/2018GL078653.
Wang J, Xiao Z W, Liu C, et al. 2019. Deep learning for picking seismic arrival times. Journal of Geophysical Research:Solid Earth, 124(7):6612-6624, doi:10.1029/2019JB017536.
Wang R J, Schmandt B, Zhang M, et al. 2020. Injection-Induced earthquakes on complex fault zones of the Raton basin illuminated by machine-learning phase picker and dense nodal array. Geophysical Research Letters, 47 (14):e2020GL088168, doi:10.1029/2020GL088168.
Wessel P, Luis J F, Uieda L, et al. 2019. The generic mapping tools version 6. Geochemistry, Geophysics, Geosystems, 20(11):5556-5564, doi:10.1029/2019GC008515.
Wu J P, Yang T, Wang W L, et al. 2013. Three dimensional P-wave velocity structure around Xiaojiang fault system and its tectonic implications. Chinese Journal of Geophysics (in Chinese), 56(7):2257-2267, doi: 10.6038/cjg20130713.
Xiao Z W, Wang J, Liu C, et al. 2021. Siamese earthquake transformer:a pair-input deep-learning model for earthquake detection and phase picking on a seismic array. Journal of Geophysical Research:Solid Earth, 126(5): e2020JB021444, doi:10.1029/2020JB021444.
Yang T, Li B R, Fang L H, Su Y J, Zhong Y S, Yang J Q, Qin M, Xu Y J. 2021. Relocation of the foreshocks and aftershocks of the 2021 M_S6.4 Yangbi earthquake sequence, Yunnan, China. Journal of Earth Science. https://doi.org/10.1007/s12583-021-1527-7.
Yang Z G, Liu J, Zhang X M, Deng W Z, Du G B and Wu X Y. 2021. A preliminary report of the Yangbi, Yunnan, M_S6.4 earthquake of May 21, 2021. Earth Planet. Phys., 5(4), 1-3. http://doi.org/10.26464/epp2021036.
Yeck W L, Patton J M, Johnson C E, et al. 2019. GLASS3:A Standalone Multiscale Seismic Detection Associator. Bulletin of the Seismological Society of America. 109(4), doi:10.1785/0120180308.
Yi G X, Wen X Z, Xin H, et al. 2013. Stress state and major-earthquake risk on the southern segment of the Longmen Shan fault zone. Chinese Journal of Geophysics (in Chinese), 56(4):1112-1120, doi:10.6038/cjg20130407.
Yu Z Y, Chu R S, Sheng M H, et al. 2020. A new deep neural network for phase picking with balanced speed and accuracy. Acta Seismologica Sinica (in Chinese), 42(3):269-282, doi:10.11939/jass.20190154.
Zhang H J, Thurber C H. 2003. Double-difference tomography:the method and its application to the Hayward fault, California. Bulletin of the Seismological Society of America, 93(5):1875-1889, doi:10.1785/0120020190.
Zhang M, Ellsworth W L, Beroza G C. 2019. Rapid earthquake association and location. Seismological Research Letters, 90(6):2276-2284, doi:10.1785/0220190052.
Zhang Y, Xu L S, Chen Y T. 2015. Rupture process of the 2015 Nepal M_W7.9 earthquake:Fast inversion and preliminary joint inversion. Chinese Journal of Geophysics (in Chinese), 58(5):1804-1811, doi: 10.6038/cjg20150530.
Zhao M, Chen S, Fang L H, et al. 2019. Earthquake phase arrival auto-picking based on U-shaped convolutional neural network. Chinese Journal of Geophysics (in Chinese), 62(8):3034-3042, doi:10.6038/cjg2019M0495.
Zhao M, Tang L, Chen S, et al. 2021. Machine learning based automatic foreshock catalog building for the 2019M_S6.0 Changning, Sichuan earthquake. Chinese Journal of Geophysics (in Chinese), 64(1):54-66, doi:10.6038/cjg2021O0271.
Zhou B W, Fan L P, Zhang L, et al. 2020. Earthquake detection using convolutional neural network and its optimization.Acta Seismologica Sinica (in Chinese), 42(6):669-683, doi:10.11939/jass.20200045.
Zhu L J, Peng Z G, Mcclellan J, et al. 2019. Deep learning for seismic phase detection and picking in the aftershock zone of 2008 M_W7.9 Wenchuan earthquake. Physics of the Earth and Planetary Interiors, 293: 106261, doi:10.1016/j.pepi.2019.05.004.
Zhu W Q, Beroza G C. 2019. PhaseNet:a deep-neural-network-based seismic arrival-time picking method. Geophysical Journal International, 216(1):261-273, doi:10.1093/gji/ggy423.
附中文参考文献
代光辉, 苗春兰, 翟璐媛. 2019. 中国测震台网统一地震编目. 中国地震, 35(1):192-203, doi:10.3969/j.issn.1001-4683.2019.01.018.
房立华, 吴建平, 苏金蓉等. 2018. 四川九寨沟M_S7.0地震主震及其余震序列精定位. 科学通报, 63(7):649-662, doi:10.1360/N972017-01184.
黄文辉, 康英, 苏柱金等. 2016a. 全国统一编目系统设计与实现. 地震地磁观测与研究, 37(4):170-175, doi:10.3969/j.issn.1003-3246.2016.04.031.
黄文辉, 沈玉松, 吕作勇等. 2016b. 地震超快速报系统试运行结果评估. 华南地震, 36(4):1-7, doi:10.13512/j.hndz.2016.04.001.
蒋长胜, 吴忠良, 尹凤玲等. 2015. 余震的序列参数稳定性和余震短期发生率预测效能的连续评估以2014年云南鲁甸6.5级地震为例. 地球物理学报, 58(11):4163-4173, doi:10.6038/cjg20151123.
蒋一然, 宁杰远. 2019. 基于支持向量机的地震体波震相自动识别及到时自动拾取. 地球物理学报, 62(1):361-373, doi:10.6038/cjg2019M0442.
金星, 马强, 李山有. 2004. 利用数字化速度记录实时仿真位移与加速度时程. 地震工程与工程振动, 24(6):9-14, 38, doi:10.13197/j.eeev.2004.06.002.
金星, 廖诗荣, 陈绯雯. 2007. 区域数字地震台网实时速报系统研究. 地震地磁观测与研究, 28(1):64-72, doi:10.3969/j.issn.1003-3246.2007.01.011.
雷兴林, 王志伟, 马胜利等. 2021. 关于2021年5月滇西漾濞M_S6.4地震序列特征及成因的初步研究. 地震学报, 43(3):1-24, doi:10.11939/jass.20210100.
李山有. 2018. 走近地震预警. 防灾博览, (2):14-23. doi:CNKI:SUN:FZBL.0.2018-02-010.
梁建宏. 2009. 地震快速处理方法研究与应用[硕士论文]. 北京:中国地震局地球物理研究所, 37-42.
龙锋, 祁玉萍, 易桂喜等. 2021. 2021年5月21日云南漾濞M_S6.4地震序列重新定位与发震构造分析. 地球物理学报, 64(8):2631-2646, doi:10.6038/cjg2021O0526.
苏金波, 刘敏, 张云鹏等. 2021. 基于深度学习构建2021年5月21日云南漾濞M_S6.4地震序列高分辨率地震目录. 地球物理学报, 64(8):2647-2646, doi:10.6038/cjg2021O0530.
吴建平, 杨婷, 王未来等. 2013. 小江断裂带周边地区三维P波速度结构及其构造意义. 地球物理学报, 56(7):2257-2267, doi:10.6038/cjg20130713.
易桂喜, 闻学泽, 辛华等. 2013. 龙门山断裂带南段应力状态与强震危险性研究. 地球物理学报, 56(4):1112-1120, doi:10.6038/cjg20130407.
于子叶, 储日升, 盛敏汉等. 2020. 兼顾速度和精度的深度神经网络震相拾取. 地震学报, 42(3):269-282, doi:10.11939/jass.20190154.
张勇, 许力生, 陈运泰. 2015. 2015年尼泊尔M_W7.9地震破裂过程:快速反演与初步联合反演. 地球物理学报, 58(5):1804-1811, doi:10.6038/cjg20150530.
赵明, 陈石, 房立华等. 2019. 基于U形卷积神经网络的震相识别与到时拾取方法研究. 地球物理学报, 62(8):3034-3042, doi:10.6038/cjg2019M0495.
赵明, 唐淋, 陈石等. 2021. 基于深度学习到时拾取自动构建长宁地震前震目录. 地球物理学报, 64(1):54-66, doi:10.6038/cjg2021O0271.
中国地震局. 2017. DB/T 66-2016 地震编目规范. 北京:中国标准出版社.
周本伟, 范莉苹, 张龙等. 2020. 利用卷积神经网络检测地震的方法与优化. 地震学报, 42(6):669-683, doi:10.11939/jass.20200045.