[1](郑 周,林彬华,金 星,等.基于卷积神经网络的地震波形智能识别研究[J].世界地震工程,2023,39(02):148-157.[doi:10.19994/j.cnki.WEE.2023.0038 ]
　(ZHENG Zhou,LIN Binhua,JIN Xing,et al.Intelligent recognition of seismic waveform based on convolutional neural network[J].,2023,39(02):148-157.[doi:10.19994/j.cnki.WEE.2023.0038 ]
点击复制

基于卷积神经网络的地震波形智能识别研究
分享到：

《世界地震工程》[ISSN:/CN:]

卷:
39
期数:
2023年02期
页码:
148-157
栏目:
常规论文
出版日期:
2023-05-15

文章信息/Info

Title:
Intelligent recognition of seismic waveform based on convolutional neural network
文章编号:
1007-6069(2023)02-0148-10
作者:
(郑 周1; 2; 林彬华3; 金 星1; 2;  韦永祥 3; 丁炳火3; 陈 辉3)
1. 中国地震局工程力学研究所 中国地震局地震工程与工程振动重点实验室,黑龙江 哈尔滨 150080; 2. 地震灾害防治应急管理部重点实验室, 黑龙江 哈尔滨 150080; 3. 福建省地震局,福州 350003
Author(s):
(ZHENG Zhou1; 2;  LIN Binhua3;  JIN Xing1; 2;  WEI Yongxiang3;  DING Binghuo3;  CHEN Hui3)
1. Key Laboratory of Earthquake Engineering and Engineering Vibration, Institute of Engineering Mechanics, China Earthquake Administration, Harbin 150080, China; 2. Key Laboratory of Earthquake Disaster Mitigation, Ministry of Emergency Management,Harbin 150080, China; 3. Earthquake Administration of Fujian Province, Fuzhou 350003, China
关键词:
地震预警;  卷积神经网络;  波形分类;  异常波形;  基线校正
Keywords:
earthquake early warning;  convolution neural network;  waveform classification;  abnormal waveform;  baseline correction
分类号:
P315.31
DOI:
10.19994/j.cnki.WEE.2023.0038
文献标志码:
A
摘要:
随着世界上多个国家和地区的地震预警系统投入运行,误报和漏报等问题逐渐突显,特别是将标定以及强干扰波形误识别为大震事件,快速、精确地区分地震与其他波形是一个难题。针对于此,该研究提出了基于卷积神经网络地震波形智能识别方法。首先收集并处理了2012—2017年中国境内福建以及周边邻省共683个地震和478个爆破事件,并对这些样本筛选、截取和基线校正等预处理,共得到了27 500条三通道波形。在此基础上,构建了3 s波形输入的卷积神经网络模型(SW-CNN)。结果表明:模型对地震、噪声、爆破和异常波形的识别率分别为97.9、99、99.2和99.3%。相比于人工手动分类识别,该模型更省时和更稳定,为地震预警目前所面临的问题提供了一个新的解决方法。
Abstract:
With the operation of earthquake early warning in many countries and regions in the world, the problems of false alarm and missing alarm are gradually highlighted, In particular, calibration and strong interference signals are misidentified as large earthquake events, it is an problem to distinguish seismic waveform from other waveform quickly and accurately. For this, in this study, an intelligent recognition method of seismic waveform based on convolutional neural network is proposed. Firstly, the seismic data of Fujian, Taiwan and neighboring provinces from 2012 to 2017 were collected and processed, a total of 683 earthquakes and 478 blasting events; there samples were preprocessed by screening, interception and baseline correction, 27500 three-channel waveforms were obtained. On this basis, a convolutional neural network model(SW-CNN)was constructed by inserting three-second data records. The results show that the recognition rates of earthquake, noise, blasting, abnormal waveforms are 97.9%, 99%, 99.2%, and 99.3%, respectively. Compared with manual classification recognition, the model is more time-saving and stable for waveform classification, it provides a new solution for the problems faced by earthquake early warning at present.

参考文献/References:

[1] FANG L H, WU J P, WANG W L, et al. Aftershock observation and analysis of the 2013Ms 7.0 Lushan earthquake[J]. Seismological Research Letters, 2015, 86(4): 1135-1142.
[2] ALLEN R V. Automatic earthquake recognition and timing from single traces[J]. Bulletin of the Seismological Society of America, 1978, 68(5): 1521-1532.
[3] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2012, 60: 84-90.
[4] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. Computer Science,2014,9(4):1542-1556.
[5] 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(1): 374-382.
ZHAO Ming, CHEN Shi, YUEN D. Waveform classification and seismic recognition by convolution neural network[J]. Chinese Journal of Geophysics, 2019, 62(1): 374-382.(in Chinese)
[6] ZHANG G Y, LIN C Y, CHEN Y K. Convolutional neural networks for microseismic waveform classification and arrival picking[J]. Geophysics, 2020, 85(4): 227-240.
[7] MEN-ANDRIN M, ROSS Z E, ANSHUL R, et al. Reliable real‐time seismic signal/noise discrimination with machine learning[J]. Journal of Geophysical Research Solid Earth(JGR), 2019, 124(1): 788-800.
[8] LI Z F, MEIER M A, HAUKSSON E, et al. Machine learning seismic wave discrimination: application to earthquake early warning[J]. Geophysical Research Letters, 2018, 45(10): 4773-4779.
[9] CHEN Y K, ZHANG G Y, 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.
[10] ZHANG J Y, JIANG R C, LI B. An automatic recognition method of microseismic signals based on EEMD-SVD and ELM[J]. Computers & Geosciences, 2019, 133: 104318.
[11] 宋晋东, 余聪, 李山有. 地震预警现地PGV连续预测的最小二乘支持向量机模型[J]. 地球物理学报, 2021, 64(2): 555-568.
SONG Jindong, YU Cong, LI Shanyou. Continuous prediction of onsite PGV for earthquake early warning based on least squares support vector machine[J]. Chinese Journal of Geophysics, 2021, 64(2): 555-568.(in Chinese)
[12] SONG J D, ZHU J B, WANG Y, et al. On-site alert-level earthquake early warning using machine-learning-based prediction equations[J]. Geophysical Journal International, 2022, 231(2): 786-800.
[13] LINVILLE L, PANKOW K, DRAELOS T. Deep learning models augment analyst decisions for event discrimination[J]. Geophysical Research Letters, 2019, 46(7): 3643-3651.
[14] ZHANG H, MA C C, PAZZI V, et al. Deep convolutional neural network for microseismic signal detection and classification[J]. Pure and Applied Geophysics, 2020, 177(12): 5781-5797.
[15] LI J, HEI D W, CUI G F, et al. GAN-LSTM joint network applied to seismic array noise signal recognition[J]. Applied Sciences, 2021, 11(21): 9987.
[16] BRAS R L, ARORA N, KUSHIDA N, et al. NET-VISA from cradle to adulthood. A machine-learning tool for seismo-acoustic automatic association[J]. Pure and Applied Geophysics, 2021, 178(7): 2437-2458.
[17] LI J, WANG J, WANG X M, et al. Evaluation and comparison of the results of the NET-VISA seismic event association method based on Bayesian theory[J]. Natural Hazards, 2021, 105(2): 1521-1539.
[18] 林彬华, 金星, 陈惠芳, 等. 基于反向传播神经网络的闽台ML震级偏差分析与修正[J]. 地震学报, 2019, 41(6): 723-734.
LIN Binhua, JIN Xing, CHEN Huifang, et al. Analysis and revision of magnitude ML deviation between Fujian and Taiwan based on BP neural network[J]. Acta Seismologica Sinica, 2019, 41(6): 723-734.(in Chinese)
[19] 林彬华, 金星, 康兰池, 等. 基于卷积神经网络的地震震级测定研究[J]. 地球物理学报, 2021, 64(10): 3600-3611.
LIN Binhua, JIN Xing, KANG Lanchi, et al. The research of earthquake magnitude determination based on Convolutional Neural Networks[J]. Chinese Journal of Geophysics, 2021, 64(10): 3600-3611.(in Chinese)
[20] 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(2A): 481-490.
[21] LI Z, MEIER M A, HAUKSSON E, et al. Machine Learning Seismic Wave Discrimination: Application to Earthquake Early Warning. Geophys. Res. Lett. 2018, 45, 4773-4779.
[22] Yann Le Cun, Yoshua Bengio, Convolutional networks for images, speech, and time series, in: The Handbook of Brain Theory and Neural Networks, MIT Press, 1998: 255-258.
[23] NAGI J, DUCATELLE F, DI CARO G A, et al. Max-pooling convolutional neural networks for vision-based hand gesture recognition[C]∥2011 IEEE International Conference on Signal and Image Processing Applications(ICSIPA). Kuala Lumpur, Malaysia. IEEE, 2012: 342-347.
[24] PEROL T, GHARBI M, DENOLLE M. Convolutional neural net work for earthquake detection and location, Sci. Adv. 4, e1700578, 2018.
[25] ROSS Z, E MEIER, M-A, HAUKSSON E. P wave arrival picking and first motion polarity determination with deep learning. Journal of Geophysical Research: Solid Earth, 2018: 123, 5120-5129.
[26] ZHU W Q, BEROZA G C. PhaseNet: A deep-neural-network-based seismic arrival-time picking method[J]. Geophysical Journal International, 2019, 216(1): 261-273.
[27] LOMAX A, MICHELINI A, JOZINOVIC D. An investigation of rapid earthquake chara-cterization using single‐station waveforms and a convolutional neural network. Seismological Research Letters, 2019, 90(2A), 517-529.
[28] Lengerich, Benjamin J. Visual Explanations for Convolutional Neural Networks via Input Resampling[EB/OL]. 2017: ArXiv Pre-print ArXiv:1707.09641.

相似文献/References:

[1]孙利,钟红,林皋.高速铁路地震预警系统现状综述[J].世界地震工程,2011,(03):089.
　SUN Li,ZHONG Hong,LIN Gao.An overview of earthquake early warning systems for high speed railways and its application to Beijing-Shanghai high speed railway[J].,2011,(02):089.
[2]李纪恩,李一行,陈平.日本地震预警信息发布法律制度与实践[J].世界地震工程,2013,(03):041.
　LI Jien,LI Yihang,CHEN Ping.Legal system and practice of Japan earthquake early warning information release[J].,2013,(02):041.
[3]佘天莉,高峰,马树林.地震预警仪器研究[J].世界地震工程,2014,(04):129.
　SHE Tianli,GAO Feng,MA Shulin.Study on instruments of earthquake early warning[J].,2014,(02):129.
[4]李纪恩,贾鹏民.地震预警信息发布与传播立法若干问题探析[J].世界地震工程,2017,33(02):001.
　LI Jien,JIA Pengmin.Analysis of the legislative issues about earthquake early warning information release and dissemination[J].,2017,33(02):001.
[5]李鸿杰,曾鹏毅,黄道兴,等.一种基于位移源谱的地震预警快速震级估算方法及影响因素研究[J].世界地震工程,2017,33(04):187.
　LI Hongjie,ZENG Pengyi,HUANG Daoxing,et al.Evaluation for influence factors of a rapidly estimating earthquake magnitude algorithm for EEW: displacement source spectrum method[J].,2017,33(02):187.
[6]李鸿杰,张建经,陈逸民,等.基于2014年云南地区地震的地震预警参数与快速震级估算研究[J].世界地震工程,2018,34(02):123.
　LI Hongjie,ZHANG Jianjing,CHEN Yimin,et al.Research on earthquake early warning parameters and rapid magnitude estimation based events in Yunnan region in 2014[J].,2018,34(02):123.
[7]卢建旗,李山有.地震预警断层参数实时识别方法(FinDer)详解及其性能初步评价[J].世界地震工程,2021,(01):152.
　LU Jianqi,LI Shanyou.Detailed analysis and preliminary performance evaluation of the FinDer:A real-time finite fault rupture detector for earthquake early warning[J].,2021,(02):152.
[8]朱景宝,宋晋东,李山有.基于支持向量机的2021年2月13日日本福岛近海Mj7.3级地震震级估算[J].世界地震工程,2021,(02):074.
　ZHU Jingbao,SONG Jindong,LI Shanyou.Magnitude estimation for the February 13, 2021 Mj7.3 earthquake near the coast of Fukushima Japan based on support vector machine[J].,2021,(02):074.
[9]汪源,宋晋东,李山有.2021年2月13日日本福岛Mj7.3级地震潜在破坏区快速估计[J].世界地震工程,2021,(02):090.
　WANG Yuan,SONG Jindong,LI Shanyou.Rapid estimation of potential damage zone for the Mj7.3 Fukushima earthquake in Japan on February 13, 2021[J].,2021,(02):090.
[10]杨黎薇,邱志刚.自动捡拾P波到时综合方法的选取与探讨[J].世界地震工程,2021,(02):098.
　YANG Liwei,QIU Zhigang.Discussion on the synthetic method of automatically picking up of P wave[J].,2021,(02):098.

备注/Memo

备注/Memo:
收稿日期:2022-09-15; 修回日期:2022-11-17
基金项目:国家自然科学基金项目(42104062)资助
作者简介:郑 周(1999—),男,硕士,主要从事深度学习地震预警研究. E-mail:1224860695@qq.com

更新日期/Last Update: 1900-01-01