摘要
以甘肃预警系统运行以来记录的地震和预警系统产出结果为数据基础,对比研究地震预警系统产出震级和正式编目震级,分析震级误差分布;利用误差逆向传播神经网络对预警震级参数进行误差学习预测,得到预警震级。结果表明,对于实际震级较小的地震预警估算震级偏大,实际震级较大的地震预警估算震级偏小;使用神经网络传播算法能够模拟预测预警震级,减小预警震级与编目震级的偏差。
Based on the earthquakes recorded by Gansu early warning system since its operation and the output results of early warning system,a comparative study is conducted on the output magnitude of earthquake early warning system and the officially cataloged magnitude,and the distribution of magnitude errors is analyzed.We use the back-propagation neural network to learn and predict the warning magnitude parameters,and obtain the warning magnitude.The results indicate that for earthquakes with smaller actual magnitudes,the estimated magnitude is larger,while for earthquakes with larger magnitudes,the estimated magnitude is smaller.The neural network propagation algorithms can simulate and predict warning magnitude,and reduce the deviation between warning magnitude and cataloged magnitude.
作者
王月
张卫东
李苗
康斌龙
袁洁
WANG Yue;ZHANG Weidong;LI Miao;KANG Binlong;YUAN Jie(Gansu Earthquake Agency,450 West-Donggang Road,Lanzhou 730000)
出处
《大地测量与地球动力学》
北大核心
2025年第9期950-953,963,共5页
Journal of Geodesy and Geodynamics
基金
甘肃省地震局地震科技发展基金(2022Q11)。
关键词
地震预警
预警震级
震级估算
神经网络
earthquake early warning
warning magnitude
magnitude estimation
neural network
