应用人工神经元网络方法自动检测地震事件

英文篇名：An automatic seismic event detection method based on artificial neural network
中文刊名：地震地磁观测与研究
英文刊名：Seismological and Geomagnetic Observation and Research
作者：王继 ; 陈九辉
英文作者：Wang Ji and Chen Jiuhui(State Key Laboratory of Earthquake Dynamics ; Institute of Geology ; China Earthquake Administration ; Beijing 100029 ; China)
中文关键词：流动台阵 ; 人工神经元网络 ; 功率谱 ; 事件检测
英文关键词：portable seismic array ; artificial neural network power spectra ; detect seismic
出版日期：2008-06-25
机构：中国地震局地质研究所地震动力学国家重点实验室,中国地震局地质研究所地震动力学国家重点实验室,
年：2008
期：03
出版单位：地震地磁观测与研究

摘要

利用人工神经元网络方法,提出了一种从连续的地震数据中检测出地震事件的方法。该方法分两步,首先,低阈值的STA/LTA算法从连续的波形中检测出类似地震事件;其次利用神经元网络方法,区分事件是地震事件还是噪声事件。通过对数据检测结果比较,找出了适合地震检测的神经元网络训练方法和神经元传递函数。在对天山流动台阵其中两个台的检测结果表明,在连续约两个月数据中,39RLS台检测出地震75个,30RNA台检测出地震95个,证明该方法对地震事件检测来说是一种有效的方法。
An automatic seismic event detection method based on artificial neural network(ANN)is presented in this paper.The algorithm is divided into two steps:firstly all possible events are extracted by a loosely confined STA/LTA algorithm from continuous waveforms,and then seismic events are distinguished from them by an ANN based algorithm.Optimal transfer function and number of nodes in hidden layers is found out by comparing the detecting results of several hundreds of sample events.Tested by the Tian Mountain portable seismic array records,75 and 95 earthquake events are detected for the station 39RLS and 30RNA respectively in a period of 2 months,which shows that the method presented in this paper is an effective method for seismic events detection.

引文

飞思科技产品研发中心.2004.MATLAB6.5辅助神经网络分析与设计(第一版)[M].北京:电子工业出版社
    李慧婷,黄文辉,等.2000.应用人工神经网络方法识别近震与远震[J].华南地震,20(4):71～75
    邱宏茂,范万春,孙煌.2004.基于能量分布特征的地震事件自动识别[J].核电子学与探测技术,24(6):698～701
    Simon Haykina著.叶世伟,史忠植译.2004.神经网络原理(第二版)[M].北京:机械工业出版社
    Dai Hengcheng.1995.Colin MacBenAutomatic picking of seismic arrivals in local earthquake data using an artificial neuralnetwork[J].Geophys Jour Int,120,758～774
    Wang Jin,Taliang Teng.1995.Artificial neural network-based seismic detector[J].Bull SeismSoc Amer,85(1):308～319
    Zhao Yue,Kiyoshi Takano.1999.An Artificial Neural Network Approach for Broadband Seismic Phase Picking[J].BSSA,89(3):670～680