首页|基于LSTM网络的单台仪器地震烈度预测模型

基于LSTM网络的单台仪器地震烈度预测模型

扫码查看
原文链接
  • 万方数据
  • 维普
烈度是地震预警系统的关键产出.如何实现快速预测目标场址的地震烈度是地震预警方法技术研究中的核心问题.本文提出了一种基于长短时记忆神经网络(Long Short-Term Memory,LSTM)的单台仪器地震烈度的预测模型(LSTM-I).该模型以一个台站观测到地震动参数的时间序列特征为输入,实现动态预测该台站可能遭受的最大烈度.选取了日本K-NET台网记录的102次地震的5103条强震加速度记录训练了神经网络,利用89次地震的3781条数据检验了模型的泛化能力.利用准确率、漏报率以及误报率三个评价指标评价了 LSTM-I模型的性能.结果表明,当采用P波触发后3 s的序列进行预测时,模型出现漏报的概率为46.78％,出现误报的概率为1.25％;当采用P波触发后10 s的序列进行预测时,模型出现漏报的概率大幅降低到17.6％,出现误报的概率降低到1.14％.结果表明LSTM-I模型很好把握住了时间序列中蕴含的特征.进一步基于LSTM-I模型评估了 Ⅵ度下台站所能提供的预警时间.本文模型能够提供的预警时间与P-S波到时差接近,说明LSTM-I模型具有较高的时效性.
Prediction of instrumental intensity for a single station using a LSTM neural network
Seismic intensity is a key output of earthquake early warning(EEW)system.How to quickly predict the seismic intensity at the target site is a core issue of EEW related techniques.This paper proposes a Long Short-Term Memory(LSTM)neural network-based instrumental seismic intensity prediction model(LSTM-I).The model takes the sequential features of ground motion parameters observed at a station as model input,and continuously predicts the potential maximum intensity at the station.The model was trained using 5103 strong ground motion acceleration recordings of 102 earthquakes from K-NET in Japan.The generalization of the model was tested with the 3781 recordings of 89 earthquakes.The performance of the LSTM-I model is evaluated by three metrics:precision rate,false alarm rate and missed alarm rate.The results indicate that if the first 3.0 s time series segment after the P wave onsets is employed,the probability of the missed alarm is 46.78％,and the probability of false alarm is 1.25％;While the first 10.0 s time series segment is employed,the probability of missed alarm significantly reduces to 17.6％,and the probability of false alarm reduces to 1.14％.The results verify that LSTM-I model has well captured hidden characteristic of the ground motion sequential time series.Furthermore,the lead-time at station with potential Ⅵ degree intensity is evaluated,and the lead-time is close to that of P-S wave arrival time difference,which indicates high timeliness of LSTM-I model.

Earthquake early warningTime series characteristicsLSTM neural networkInstrumental seismic intensityPrediction

李山有、王博睿、卢建旗、王傲、张海峰、谢志南、陶冬旺

展开 >

中国地震局工程力学研究所地震工程与工程振动重点实验室,哈尔滨 150080

地震灾害防治应急管理部重点实验室,哈尔滨 150080

地震预警 时间序列特征 LSTM神经网络 仪器地震烈度 预测

中国地震局工程力学研究所基本科研业务费专项资助项目国家重点研发计划项目黑龙江省自然科学基金优秀青年基金国家自然科学基金

2018B022018YFC1504004YQ2020E005U2039209

2024

10.6038/cjg2022Q0521

地球物理学报
中国地球物理学会 中国科学院地质与地球物理研究所

地球物理学报

CSTPCD北大核心
影响因子：3.703
ISSN：0001-5733
年,卷(期)：2024.67(2)
  • 24