[1]张燕明,张红才,陈惠芳,等.实时智能地震处理系统在2013年福建仙游ML5.0地震序列中的应用研究[J].华南地震,2023,(04):64-74.[doi:10.13512/j.hndz.2023.04.09]
　ZHANG Yanming,ZHANG Hongcai,CHEN Huifang,et al.Application of Real-time Intelligent Seismic Processor in Xianyou ML5.0 Earthquake Sequence in Fujian Province in 2013[J].,2023,(04):64-74.[doi:10.13512/j.hndz.2023.04.09]
点击复制

实时智能地震处理系统在2013年福建仙游ML5.0地震序列中的应用研究()
分享到：

华南地震[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2023年04期
页码:
64-74
栏目:
地震科学研究
出版日期:
2023-12-30

文章信息/Info

Title:
Application of Real-time Intelligent Seismic Processor in Xianyou ML5.0 Earthquake Sequence in Fujian Province in 2013
文章编号:
1001-8662（2023）04-0064-11
作者:
张燕明1; 张红才1; 2; 陈惠芳1; 廖诗荣1
1.福建省地震局，福州 350003;2.中国地震局厦门海洋地震研究所，福建 厦门 361000
Author(s):
ZHANG Yanming1; ZHANG Hongcai1; 2; CHEN Huifang1; LIAO Shirong1
1.Fujian Earthquake Agency ， Fuzhou 350003， China;2.Institute of Xiamen Marine Seismology ， Xiamen 361000， China
关键词:
福建仙游地震; 自动编目; RISP; 深度学习
Keywords:
Xianyou earthquake sequence in Fujian; Automatic cataloging; RISP; Deep learning
分类号:
P315.78
DOI:
10.13512/j.hndz.2023.04.09
文献标志码:
A
摘要:
文中将实时智能地震处理系统（RISP）应用于福建仙游地震序列，处理了2013年8月至12月福建台网的连续波形数据。自动处理结果与人工编目结果进行了深入对比，全面评估了RISP系统对该地震序列的自动处理能力。RISP系统共产出615个地震，与人工编目匹配事件462个，对于ML≥1.0的地震，匹配率达到96.4%；漏检测事件282个，其中ML<1.0占比为94.7%；多检测事件162个，均为仙游序列地震事件。匹配事件地震参数统计结果表明：发震时刻偏差不超过1s占比99.13%；震中位置偏差小于5km占比98.69%；震源深度偏差在5km内占比91.5%；震级偏差不超过0.5占比89.54%。通过该实例测试表明：现有观测条件下，利用RISP系统可以快速产出仙游地区ML≥1.0地震序列目录，地震目录完备性高，RISP系统产出地震参数精度与人工处理结果相当，可应用于大震应急、震后趋势判定等工作。
Abstract:
In this paper， the Real-time Intelligent Seismic Processor（RISP）， an artificial intelligent（AI）based processing system was applied to the Xianyou earthquake sequence in Fujian to process the continuous waveform data of the Fujian network from August to December 2013. The automatic results were compared with the manual seismic catalogs to evaluate the processing capacities of the RISP system. During the period， a total of 615 earthquakes were processed by the system，fewer than the number of manual results. Among the automatic results， 462 events were matched with manual results， the matching rate reached 96.4% for events with ML≥1.0； 282 events were missed and 94.7% of them with ML<1.0；162 more events were detected，which were all belonged to Xianyou earthquake sequence. The statistical results of the source parameters showed that the proportion of data with the earthquake origin time deviation less than 1.0 s was 99.13%；the proportion of data with epicenter position deviation less than 5 km was 98.69%；the proportion of data with a depth deviation of the focal point less than 5 km was 91.5%； the proportion of data with a magnitude deviation less than 0.5 was 89.54%. This result shows that under the existing observation conditions，the RISP system can quickly produce catalogs of earthquake sequences with ML≥1.0， and the completeness of the earthquake catalogue is high. The accuracy of seismic parameters produced by RISP system is equivalent to that of manual processing，which can be applied to emergency response of large earthquake and post-earthquake trend determination

参考文献/References:

[1] 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.
[2] Shelly D R，Beroza G C，Ide S. Non-volcanic tremor and low-frequency earthquake swarms[J]. Nature，2007，446（7133）：305-307.
[3] Han L，Peng Z，Johnson C W，et al. Shallow microearth‐quakes near Chongqing，China triggered by the Rayleigh waves of the 2015 M7.8 Gorkha，Nepal earthquake[J].Earth and Planetary Science Letter，2017（497）：231-240.
[4] Ross Z E，Trugman D T，Hauksson E，et al. Searching for hidden earthquakes in Southern California[J]. Science，2019， 364（6442）：767-771.
[5] Peng Z，Zhao P. Migration of early aftershocks following the 2004 Parkfield earthquake[J]. Nature Geoscience，2009（2）：877-881.
[6] Yoon C E，O′Reilly O，Bergen K J，et al. Earthquake detec‐tion through computationally efficient similarity search[J]. Science Advances，2015，1（11）：e1501057. 10.1126/sciadv.1501057
[7] E. Ross Z，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.
[8] Zhu W Q，Beroza G C. PhaseNet：A deep-neural-network‐based seismic arrival-time picking method[J/OL]. Geophysi‐cal Journal International，2018[2023-05-20]. https：//api. se‐manticscholar.org/CorpusID：4957653
[9]赵明，陈石，Dave Yuen.基于深度学习卷积神经网络的地震波形自动分类与识别[J].地球物理学报，2019，62（01）：374-382.
[10] Mousavi S M，Ellsworth W L，Zhu W Q，et al. Earthquake transformer—an attentive deep-learning model for simulta‐neous earthquake detection and phase picking[J/OL].Nature Communications，2020，11（1）：39521[2023-05-20].https：//www.researchgate.net/publication/343503437_Earthquake_transformer-an_attentive_deep-learning_model_for_simul‐taneous_earthquake_detection_and_phase_picking.
[11] Zhu J，Li Z，Fang L. USTC-Pickers：a unified Set of seismic phase pickers transfer learned for China[J]. Earthquake Science，2023，36（02）：95-112.
[12] Zhang M，Liu M，Feng T，et al. LOC-FLOW：an end-to-end machine learning-based high-precision earthquake lo‐cation workflow[J/OL].Seismological Research Letters，2022 [2023-05-20]. https：//www. researchgate. net/publication/359116402_LOC-FLOW_An_End-to-End_Machine_Lea-rning-Based_High-Precision_Earthquake_Location_Work‐flow
[13] Zhu W Q，Hou A B，Yang R，et al. QuakeFlow：a scalable machine-learning-based earthquake monitoring workflow with cloud computing[J/OL]. Geophysical Journal Interna‐tional，2022[2023-05-20]. https：//api.semanticscholar.org/CorpusID：251953419
[14]廖诗荣，张红才，范莉苹，等.实时智能地震处理系统研发及其在2021年云南漾濞MS6.4地震中的应用[J].地球物理学报，2021，64（10）：3632-3645.
[15] Tamaribuchi K. Evaluation of automatic hypocenter deter‐mination in the JMA unified catalog[J/OL]. Earth ，planets& space，2018（70）：141[2023-05-20]. https：//doi. org/10.1186/s40623-018-0915-4
[16] Lomax A，Michelini A，Curtis A. Earthquake location，di‐rect，global-search methods[C]//Encyclopedia of Complexi‐ty and Systems Science. New York：Springer，2009.
[17]王祖东，杨晓鹏，尹欣欣，等．2022年1月8日青海门源MS6.9地震余震序列自动处理结果探讨[J]．地震工程学报，2022，44（2）：408-414
[18]颜利君，刘媛，廖诗荣，等. 2022年6月10日四川马尔康地震序列实时智能检测结果分析与研究[J].地震工程学报，2022，44（6）：1450-1458.
[19]苏柱金，黄文辉. MSDP软件震相自动识别技术实现[J].地震地磁观测与研究，2015，36（05）：121-127.
[20]秦双龙，李强，邱毅，等．福建仙游震群重定位及序列特征分析[J]．地震地磁观测与研究，2015，36（3）：67-71．
[21]蔡杏辉，段刚，黄其昌.福建数字遥测台网单台震级偏差研究[J]．福建地震，2006（Z2）56-60.

备注/Memo

备注/Memo:
收稿日期：2023-05-10
基金项目：地震科技星火计划（XH21026Y）
作者简介：张燕明（1993-），女，硕士，工程师，主要从事测震分析与地震自动编目方面工作。
Email：674257016@qq.com
通信作者：廖诗荣（1977-），男，正高级工程师，主要从事地震数据实时处理算法研究与软件系统研发。
E-mail：liaoshirong@fjea.gov.cn
更新日期/Last Update: 2023-12-30