东北大学学报(自然科学版) ›› 2024, Vol. 45 ›› Issue (8): 1073-1079.DOI: 10.12068/j.issn.1005-3026.2024.08.002

• 信息科学与工程 • 上一篇    下一篇

基于卷积神经网络的预警震级分段估算方法

任涛1, 刘昕靓1, 陈宏峰2, 马延路2   

  1. 1.东北大学 软件学院,辽宁 沈阳 110169
    2.中国地震台网中心,北京 100029
  • 收稿日期:2023-04-11 出版日期:2024-08-15 发布日期:2024-11-12
  • 作者简介:任 涛(1980-),男,辽宁沈阳人,东北大学教授,博士生导师.
  • 基金资助:
    国家自然科学基金资助项目(62276058);中央高校基本科研业务费专项资金资助项目(N2217003);辽宁省自然科学基金机器人国家重点实验室项目(2020-KF-12-11);星火计划公关项目(XH21042)

Segmented Estimation Method for Early Warning Magnitude Based on Convolutional Neural Network

Tao REN1, Xin-liang LIU1, Hong-feng CHEN2, Yan-lu MA2   

  1. 1.School of Software,Northeastern University,Shenyang 110169,China
    2.China Earthquake Networks Center,Beijing 100029,China. Corresponding author: LIU Xin-liang,E-mail: 1834221980@qq. com
  • Received:2023-04-11 Online:2024-08-15 Published:2024-11-12

摘要:

针对地震预警震级估算问题,提出一种基于卷积神经网络(convolutional neural network,CNN)的震级分段估算方法,该方法以单台站的P波初至后3 s时间的波形作为输入,输出结果为地震波形所属的震级区段(大地震,近震震级ML≥5.0;小地震,ML<5.0).如果波形属于大地震区段,直接发出警报;如果波形属于小地震区段,再进行具体震级的估算.对于震级区段估算,CNN模型的准确率可达98.04%.根据震级估算参数τcPd估算的小地震震级平均绝对误差(mean absolute error,MAE)分别为0.20和0.31.结果表明,预警震级分段估算方法可以准确预警大地震,减少大地震漏报率;同时使得小地震震级估算结果更为准确.

关键词: 地震预警, 震级预警, 分段估算, 卷积神经网络, 震级估算参数

Abstract:

Aiming at magnitude estimation in earthquake early warning, a segmented estimation method based on convolutional neural network (CNN) is proposed. The input is the waveform starting from the P wave onset and lasting 3 s. The output is the estimated magnitude range (local magnitude ML≥5.0 for large earthquake and ML<5.0 for small earthquake). If the waveform belongs to the large earthquake range, the alarm will be sent directly; if the waveform belongs to the small earthquake range, the specific magnitude value will be estimated. For the estimation of magnitude range, the accuracy of the CNN model can reach 98.04%. The mean absolute errors (MAE) of estimating small earthquake magnitudes based on parameters τc and Pd are 0.20 and 0.31, respectively. The results demonstrate the efficacy of the proposed segmented magnitude estimation method in accurately early warning large earthquakes and reducing the probability of missed warnings. Additionally, it enhances the precision of small earthquake magnitude estimation.

Key words: earthquake early warning, magnitude early warning, segmented estimation, convolutional neural network (CNN), magnitude estimation parameters

中图分类号: