LSTM神经网络拾取地震P波到时

doi:10.12196/j.issn.1000-3274.2023.04.005

地震 ›› 2023, Vol. 43 ›› Issue (4): 67-75.doi: 10.12196/j.issn.1000-3274.2023.04.005

LSTM神经网络拾取地震P波到时

吴为治¹, 汪小厉², 何泽平¹

1.安徽省勘查技术院, 安徽合肥 230041;
2.安徽省地震局, 安徽合肥 230031

收稿日期:2023-02-09 修回日期:2023-06-09 出版日期:2023-10-31 发布日期:2023-12-29
作者简介:吴为治(1989-), 男, 安徽无为人, 工程师, 主要从事人工智能应用研究。
基金资助:
安徽省深地钻探工程研究中心开放基金项目(2022AHSD06)

LSTM Neural Network for Automatic P Phase Picking

WU Wei-zhi¹, WANG Xiao-li², HE Ze-ping¹

1. Geological Exploration Technology Institute of Anhui Province, Hefei 230041, China;
2. Anhui Earthquake Agency, Hefei 230031, China

Received:2023-02-09 Revised:2023-06-09 Online:2023-10-31 Published:2023-12-29

摘要/Abstract

摘要： 震相到时拾取是地震学的一个基础问题, 本文针对该问题发展了地震P波到时自动拾取的LSTM神经网络方法。该方法将到时问题转化成到时标签化后的概率问题, 建立了一个4层网络模型, 利用朝鲜核爆地震垂向数据进行了模型的训练, 成功对后续核爆地震P波到时做出准确的拾取, 且该方法对一定信噪比的数据仍具有一定适应性。通过对添加不同程度噪声的随机截取的输入数据进行可靠性分析, 结果表明需要输入P波之后10 s以上的波形才能有稳定的拾取结果。该方法作为一种人工智能的方法, 为波形到时自动拾取提供了新的方法。

关键词: LSTM神经网络, 震相到时拾取, 核爆地震

Abstract: Picking up the arrival time of seismic phases is one of the fundamental problems of seismology. This study introduces a method based on LSTM neural network for automatic P phase picking. We transformed the arrival time problem into the probability problem of time redefined labeling, and a 4-layer neural network was built and trained on the North Korean nuclear earthquake vertical waveforms. The P phase arrival time of subsequent events were picked up accurately and effectively. The method shows a certain adaptability with ambient noise. Random input samples test shows that the input waveform data should be better with longer than 10 s after the P phase to get stable results. As an artificial intelligence method, LSTM neural network provides a new solution for seismic phase picking-up.

Key words: LSTM neural network, P phase picking, Nuclear explosion earthquake

中图分类号:

P315.7

吴为治, 汪小厉, 何泽平. LSTM神经网络拾取地震P波到时[J]. 地震, 2023, 43(4): 67-75.

WU Wei-zhi, WANG Xiao-li, HE Ze-ping. LSTM Neural Network for Automatic P Phase Picking[J]. EARTHQUAKE, 2023, 43(4): 67-75.

参考文献

[1] 孙印, 潘素珍, 刘明军. 天然地震识别与震相自动拾取技术进展[J]. 中国地震, 2018, 34(4): 606-620.
SUN Yin, PAN Su-zhen, LIU Ming-jun. Seismic phase identification associated with the automatic pickup technology and its application[J]. Earthquake Research in China, 2018, 34(4): 606-620 (in Chinese).
[2] Kato A, Nakagawa S. Multiple slow-slip events during a foreshock sequence of the 2014 Iquique, Chile M_W8.1 earthquake[J]. Geophysical Research Letters, 2014, 41(15): 5420-5427.
[3] 魏梦祎, 谭玉阳, 毛中华, 等. 基于波形互相关的微地震事件自动识别及初至拾取[J]. 北京大学学报(自然科学版), 2018, 54(2): 361-372.
WEI Meng-yi, TAN Yu-yang, MAO Zhong-hua, et al. Automatic microseismic event detection and arrival picking based on waveform cross-correlation[J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2018, 54(2): 361-372 (in Chinese).
[4] Allen R. Automatic earthquake recognition and timing from single traces[J]. Bulletin of the Seismological Society of America, 1978, 68(5): 1521-1532.
[5] 吴治涛, 李仕雄. STA/LTA算法拾取微地震事件P波到时对比研究[J]. 地球物理学进展, 2010, 25(5): 1577-1582.
WU Zhi-tao, LI Shi-xiong. Comparison of STA/LTA P-pickers for micro seismic monitoring[J]. Progress in Geophysics, 2010, 25(5): 1577-1582 (in Chinese).
[6] 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.
[7] 王继, 陈九辉, 刘启元, 等. 流动地震台阵观测初至震相的自动检测[J]. 地震学报, 2006, 28(1): 42-51.
WANG Ji, CHEN Jiu-hui, LIU Qi-yuan, et al. Automatic onset phase picking for portable seismic array observation[J]. Acta Seismologica Sinica, 2006, 28(1): 42-51 (in Chinese).
[8] 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).
[9] 张帆, 杨晓忠, 吴立飞, 等. 基于短时傅里叶变换和卷积神经网络的地震事件分类[J]. 地震学报, 2021, 43(4): 463-473.
ZHANG Fan, YANG Xiao-zhong, WU Li-fei, et al. Classification of seismic events based on short-time Fourier transform and convolutional neural network[J]. Acta Seismologica Sinica, 2021, 43(4): 463-473 (in Chinese).
[10] Dong L J, Tang Z, Li X B, et al. Discrimination of mining microseismic events and blasts using convolutional neural networks and original[J]. Journal of Central South University 2020, 27(10): 3078-3089.
[11] 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).
[12] Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
[13]Graves A, Schmidhuber J. Framewise phoneme classification with bidirectional LSTM and other neural network architectures[J]. Neural Networks: the Official Journal of the International Neural Network Society, 2005, 18(5-6): 602-610.
[14] Informatik F F, Schmidhuber J. LSTM can solve hard long time lag problems[C]. Advance in Neural Information Processing Systems. Denver, 1999.
[15] 王晓湘, 刘洞天, 刘南江, 等. 基于LSTM的震后通信数据异常检测分析[J]. 中国地震, 2022, 38(2): 270-279.
WANG Xiao-xiang, LIU Dong-tian, LIU Nan-jiang, et al. LSTM-based anomaly detection and analysis of post-earthquake communication data[J]. Earthquake Research in China, 2022, 38(2): 270-279 (in Chinese).
[16] 于子叶, 储日升, 盛敏汉. 深度神经网络拾取地震P和S波到时[J]. 地球物理学报, 2018, 61(12): 4873-4886.
YU Zi-ye, CHU Ri-sheng, SHENG Min-han. Pick onset time of P and S phase by deep neural network[J]. Chinese Journal of Geophysics, 2018, 61(12): 4873-4886 (in Chinese).
[17] Hayakawa Y. Effects of the chaotic noise on the performance of a neural network model[R]. Technical Report of IEICE Nlp, 1994.

LSTM神经网络拾取地震P波到时

LSTM Neural Network for Automatic P Phase Picking

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]	关兆萱, 万永革, 周明月, 王润妍, 宋泽尧, 黄少华, 顾培苑. 2024年新疆乌什M_S7.1地震发震断层产状及其动力学探讨[J]. 地震, 2024, 44(2): 1-11.
[2]	李悦, 马晗宇, 刘振辉, 王熠熙, 邵永新. 天津典型观测井渗透性变化及对玛多7.4级地震响应机理分析[J]. 地震, 2024, 44(2): 33-51.
[3]	荆涛, Boonphor Phetphouthongdy, Chansouk Sioudom, 刘洋洋, 李继庚, 康春丽, 马未宇. 基于潮汐附加构造应力的2013年灯塔M_S5.1地震射出长波辐射变化分析[J]. 地震, 2024, 44(2): 52-62.
[4]	杨彦明, 苏淑娟, 王磊. 2020年呼和浩特市和林格尔M_L4.5地震破裂方向性测定及发震构造分析[J]. 地震, 2024, 44(2): 63-85.
[5]	王婷婷, 边银菊, 任梦依, 杨千里, 侯晓琳. 地震事件分类识别软件[J]. 地震, 2024, 44(2): 104-119.
[6]	宋程, 张永仙, 夏彩韵, 毕金孟, 张小涛, 吴永加, 徐小远. 基于PI方法的华北2019年以来3次M_S≥5.0地震回溯性预测研究[J]. 地震, 2024, 44(2): 120-134.
[7]	刘俊清, 张小刚, 张宇, 蔡宏雷, 陈卓, 包秀敏. 2023年12月18日甘肃积石山M_S6.2地震多点源地震矩张量反演研究[J]. 地震, 2024, 44(2): 169-177.
[8]	黄峰, 熊仁伟, 林敬东, 赵峥, 杨攀新. 嘉黎断裂带中段流域地貌形态指数与新构造活动特征[J]. 地震, 2024, 44(1): 1-18.
[9]	舒甜甜, 罗艳, 朱音杰. 2022年四川泸定M_S6.8地震震源破裂过程及强地面运动模拟[J]. 地震, 2024, 44(1): 19-36.
[10]	吴旭, 薛兵, 李江, 朱小毅, 张兵, 黄诗. 深井地震综合观测系统授时方法设计与实现[J]. 地震, 2024, 44(1): 37-49.
[11]	薄万举, 张立成, 苏国营, 徐东卓, 赵立军. 对强震地形变监测预报方法的思考[J]. 地震, 2024, 44(1): 64-77.
[12]	岳晓媛, 李艳娥, 钟世军, 王薇, 王燕, 马梁. 唐山老震区M≥4.0地震前b值变化异常特征研究[J]. 地震, 2024, 44(1): 94-108.
[13]	贾昕晔, 白少奇, 贾彦杰, 刘芳, 娜热. 内蒙古自治区中西部Lg波衰减及场地响应特征研究[J]. 地震, 2024, 44(1): 109-117.
[14]	陈光齐, 武艳强, 夏明垚, 李志远. 2024年1月1日日本能登半岛7.6级地震: 震源特征、灾害概况与应急响应[J]. 地震, 2024, 44(1): 141-152.
[15]	杨攀新, 熊仁伟, 胡朝忠, 高原. 2023年甘肃积石山6.2级地震发震构造浅析[J]. 地震, 2024, 44(1): 153-159.