地震事件分类识别软件

doi:10.12196/j.issn.1000-3274.2024.02.007

摘要/Abstract

摘要： 非天然地震事件分类是地震监测业务部门的日常工作之一。本研究主要针对地震、爆炸和矿震的分类问题, 在地震波数据处理、特征提取和人工智能综合分类的研究基础上, 基于Qt开发框架, 结合Python、 Matlab等多种编程语言, 开发了一个具有良好的可移植性和可扩展性、具有自主知识产权的地震分类识别软件。该软件可以部署在不同操作系统上, 由七个模块组成: 地震数据导入模块、数据处理模块、特征提取模块、综合分类模块、特征分析模块、当量估算模块和结果分析模块。软件集成了多种时频特征提取技术和人工智能分类方法, 形成了较为完整的地震类型判定流程。软件内置的地震事件分类模型准确率高于90%, 适用范围较广, 已推广应用于多个地震监测部门, 并取得了较好的应用成果, 提高了对非天然地震的快速分析能力。

关键词: 非天然地震事件分类, Qt开发框架, 特征提取, 人工智能方法

Abstract: Classification of non-natural seismic events is one of the daily tasks of the seismic monitoring business. This research is mainly aimed at the classification of earthquakes, explosions and mining-induced earthquakes. On the basis of the research results of seismic wave data processing, feature extraction and artificial intelligence comprehensive classification, a seismic event recognition software (SERS) with good portability, expansibility and independent intellectual property rights is developed based on the Qt development framework and combined with Python, Matlab and other programming languages. The software can be deployed on different operating systems and consists of seven modules: seismic data import module, data processing module, feature extraction module, comprehensive classification module, feature analysis module, yield estimation module, and result analysis module. The software integrates various time-frequency feature extraction techniques and artificial intelligence classification methods, to form a comprehensive process for classifying the seismic events. The built-in classification models in the software have an accuracy rate exceeding 90% and a wide range of applications. It has been applied in a number of earthquake monitoring departments, achieved favorable outcomes and enhanced the capability for rapid analysis of non-natural earthquakes.

Key words: Classification of non-natural seismic events, Qt development framework, Feature extraction, Artificial intelligence method

中图分类号:

P315.7

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.

WANG Ting-ting, BIAN Yin-ju, REN Meng-yi, YANG Qian-li, HOU Xiao-lin. Seismic Event Recognition Software[J]. EARTHQUAKE, 2024, 44(2): 104-119.

参考文献

[1] 赵永, 刘卫红, 高艳玲. 北京地区地震、爆破和矿震的记录图识别[J]. 地震地磁观测与研究, 1995, 16(4): 48-54.
ZHAO Yong, LIU Wei-hong, GAO Yan-ling. Distinguishing earthquake, explosion and mine earthquake in Beijing area[J]. Seismological and Geomagnetic Observation and Research, 1995, 16(4): 48-54 (in Chinese).
[2]Kim W Y, Simpson D W, Richards P G. High-frequency spectra of regional phases from earthquakes and chemical explosions[J]. Bulletin of the Seismological Society of America, 1994, 84(5): 1365-1386.
[3] Koper K D, Pechmann J C, Burlacu R, et al. Magnitude-based discrimination of man-made seismic events from naturally occurring earthquakes in Utah, USA[J]. Geophysical Research Letters, 2016, 43(20): 10638-10645.
[4] Kim W Y, Simpson D W, Richards P G. Discrimination of earthquakes and explosions in the Eastern United States using regional high-frequency data[J]. Geophysical Research Letters, 1993, 20(14): 1507-1510.
[5] Esposito A M, Giudicepietro F, Scarpetta S, et al. Automatic discrimination among landslide, explosion-quake, and microtremor seismic signals at Stromboli Volcano using neural networks[J]. Bulletin of the Seismological Society of America, 2006, 96(4A): 1230-1240.
[6] Reynen A, Audet P. Supervised machine learning on a network scale: Application to seismic event classification and detection[J]. Geophysical Journal International, 2017, 210(3): 1394-1409.
[7] 任涛, 林梦楠, 陈宏峰, 等. 基于Bagging集成学习算法的地震事件性质识别分类[J]. 地球物理学报, 2019, 62(1): 383-392.
REN Tao, LIN Meng-nan, CHEN Hong-feng, et al. Seismic event classification based on bagging ensemble learning algorithm[J]. Chinese Journal of Geophysics, 2019, 62(1): 383-392 (in Chinese).
[8] Tang L L, Zhang M, Wen L X. Support vector machine classification of seismic events in the Tianshan orogenic belt[J]. Journal of Geophysical Research: Solid Earth, 2020, 125: e2019JB018132.
[9] 王婷婷, 边银菊, 杨千里, 等. 不同地区人工爆炸与天然地震记录特征及识别研究[J]. 地震学报, 2021, 43(4): 427-440.
WANG Ting-ting, BIAN Yin-ju, YANG Qian-li, et al. Research on seismic characteristics and identification of artificial explosion in different areas and natural earthquake[J]. Acta Seismologica Sinica, 2021, 43(4): 427-440 (in Chinese).
[10] 杨千里, 王婷婷, 边银菊. 基于广义S变换的地震与爆炸识别[J]. 地震学报, 2020, 42(5): 613-628.
YANG Qian-li, WANG Ting-ting, BIAN Yin-ju. Recognition of earthquakes and explosions based on generalized S transform[J]. Acta Seismologica Sinica, 2020, 42(5): 613-628 (in Chinese).
[11] Zhang Y X, Wang T T, Bian Y J, et al. Features of different types of seismic events in China’s Capital Region[J]. Earthquake Science, 2021, 34(6): 489-506.
[12] 王婷婷, 边银菊, 张博. 地震和爆破的综合识别方法研究[J]. 地球物理学进展, 2013, 28(5): 2433-2443.
WANG Ting-ting, BIAN Yin-ju, ZHANG Bo. The comprehensive identification methods between earthquakes and explosions[J]. Progress in Geophysics, 2013, 28(5): 2433-2443 (in Chinese).
[13] 隗永刚, 杨千里, 王婷婷, 等. 基于深度学习残差网络模型的地震和爆破识别[J]. 地震学报, 2019, 41(5): 646-657.
WEI Yong-gang, YANG Qian-li, WANG Ting-ting, et al. Earthquake and explosion identification based on deep learning residual network model[J]. Acta Seismologica Sinica, 2019, 41(5): 646-657 (in Chinese).
[14]Wang T, Bian Y, Zhang Y, et al. Classification of earthquakes, explosions and mining-induced earthquakes based on XGBoost algorithm[J]. Computers & Geosciences, 2023, 170: 105242.
[15] Wang T, Bian Y, Zhang Y, et al. Using artificial intelligence methods to classify different seismic events[J]. Seismological Research Letters, 2023, 94(1): 1-16.
[16] 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M_S6.4地震中的应用[J]. 地球物理学报, 2021, 64(10): 3632-3645.
LIAO Shi-rong, ZHANG Hong-cai, FAN Li-ping, et al. Development of a real-time intelligent seismic processing system and its application in the 2021 Yunnan Yangbi M_S6.4 earthquake[J]. Chinese Journal of Geophysics, 2021, 64(10): 3632-3645 (in Chinese).
[17] Renouard A, Maggi A, Grunberg M, et al. Toward false event detection and quarry blast versus earthquake discrimination in an operational setting using semiautomated machine learning[J]. Seismological Research Letters, 2021, 92(6): 3725-3742.
[18] 唐明铭. 搭建基于Qt环境的初至波拾取平台[D]. 青岛: 中国石油大学(华东), 2013.
TANG Ming-ming. Building Qt based platform for determining first arrival times[D]. Qingdao: China University of Petroleum (East China), 2013 (in Chinese).
[19] 缪雨润. 基于Qt的图形用户界面的研究与实现[D]. 南京: 东南大学, 2015.
MIAO Yu-run. Research and implementation of graphical user interface based of Qt[D]. Nanjing: Southeast University, 2015 (in Chinese).
[20] Wang T T, Bian Y J, Yang Q L, et al. Correction of P/S amplitude ratios for low-magnitude seismic events based on Bayesian kriging method[J]. Bulletin of the Seismological Society of America, 2021, 111(5): 2799-2813.
[21] Brune J N. Tectonic stress and the spectra of seismic shear waves from earthquakes[J]. Journal of Geophysical Research, 1970, 75(26): 4997-5009.
[22] Jimeénez A, Garciía J M, Romacho M D. Simultaneous inversion of source parameters and attenuation factor using genetic algorithms[J]. Bulletin of the Seismological Society of America, 2005, 95(4): 1401-1411.
[23]Douglas A. Forensic seismology and nuclear test bans[M]. Cambridge: Cambridge University Press, 2013.
[24] Baumgardt D R, Ziegler K A. Spectral evidence for source multiplicity in explosions: Application to regional discrimination of earthquakes and explosions[J]. Bulletin of the Seismological Society of America, 1988, 78(5): 1773-1795.
[25] Muller K, Mika S, Ratsch G, et al. An introduction to kernel-based learning algorithms[J]. IEEE Transactions on Neural Networks, 2001, 12(2): 181-201.
[26] 林鑫, 王向腾, 赵连锋, 等. 核试验监测的地震学研究综述[J]. 地球物理学报, 2019, 62(11): 4047-4066.
LIN Xin, WANG Xiang-teng, ZHAO Lian-feng, et al. A review of seismological research on nuclear test monitoring[J]. Chinese Journal of Geophysics, 2019, 62(11): 4047-4066 (in Chinese).
[27] Murphy J R. Types of seismic events and their source descriptions[A]//Husebye E S, Dainty A M. Monitoring a Comprehensive Test Ban Treaty[M]. Dordrecht: Kluwer Academic Publishers, 1996.
[28] Bowers D, Marshall P D, Douglas A. The level of deterrence provided by data from the SPITS seismometer array to possible violations of the comprehensive test ban in the Novaya Zemlya region[J]. Geophysical Journal International, 2001, 146(2): 425-438.
[29] Stevens J L, Murphy J R. Yield estimation from surface-wave amplitudes[J]. Pure and Applied Geophysics, 2001, 158(11): 2227-2251.
[30] Wilks S S. Mathematical statistics[M]. New York: Wiley Press, 1962.
[31] 边银菊. Fisher方法在震级比m_b/M_S判据识别爆炸中的应用研究[J]. 地震学报, 2005, 27(4): 414-422.
BIAN Yin-ju. Application of Fisher method to discriminating earthquakes and explosions using criterion m_b/M_S[J]. Acta Seismologica Sinica, 2005, 27(4): 414-422 (in Chinese).
[32] Cortes C, Vapnik V. Support-vector networks[J]. Machine Learning, 1995, 20(3): 273-297.
[33] Kortström J, Uski M, Tiira T. Automatic classification of seismic events within a regional seismograph network[J]. Computers & Geosciences, 2016, 87: 22-30.
[34] Chen T Q, Guestrin C. XGBoost: A scalable tree boosting system[C]. San Francisco: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, 2016: 785-794.
[35] Nguyen H, Bui X N, Bui H B, et al. Developing an XGBoost model to predict blast-induced peak particle velocity in an open-pit mine: A case study[J]. Acta Geophysica, 2019, 67(2): 477-490.
[36] Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
[37] Wöellmer M, Kaiser M, Eyben F, et al. LSTM-modeling of continuous emotions in an audiovisual affect recognition framework[J]. Image and Vision Computing, 2013, 31(2): 153-163.
[38] 周俊, 尹悦, 夏斌. 基于LSTM神经网络的声发射信号识别研究[J]. 计算机科学, 2021, 48(11A): 319-326.
ZHOU Jun, YIN Yue, XIA Bin. Acoustic emission signal recognition based on long short time memory neural network[J]. Computer Science, 2021, 48(11A): 319-326 (in Chinese).
[39] Jiang L, Li C. Scaling up the accuracy of decision-tree classifiers: A naive-bayes combination[J]. Journal of Computers, 2011, 6(7): 1325-1331.
[40] 董卫华, 王圣凯, 王雪元, 等. 地图线状要素眼动识别的朴素贝叶斯方法[J]. 测绘学报, 2021, 50(6): 749-756.
DONG Wei-hua, WANG Sheng-kai, WANG Xue-yuan, et al. A naive Bayesian method for eye movement recognition of map linear elements[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(6): 749-756 (in Chinese).