运用LSTM神经网络对川滇地区的地震中期预报——回溯性预测2008年汶川M_(S)8.0地震的探索  

Application of LSTM neural network for intermediate-term earthquake prediction:retrospective prediction of 2008 Wenchuan M_(S)8.0 Earthquake

作　　者：石耀霖 李林芳 程术 SHI Yaolin;LI Linfang;CHENG Shu(Key Laboratory of Computational Geodynamics of Chinese Academy of Sciences, College of Earth and Planetary Sciences, University of Chinese Academy of Sciences,Beijing 100049, China)

机构地区：[1]中国科学院大学地球与行星科学学院中国科学院计算地球动力学重点实验室,北京100049

出　　处：《中国科学院大学学报（中英文）》2022年第1期1-12,共12页Journal of University of Chinese Academy of Sciences

基　　金：国家自然科学基金-中国地震局地震科学联合基金(U1839207);国家自然科学基金重大项目(41590865);国家重点研发计划(2018YFC1504200)资助。

摘　　要：地震预报是当代科学难题,把机器学习方法运用于地震预报探索是一个研究热点。大地震造成巨大的人员伤亡和经济损失,因此对大震的预测是地震预报的主要目标。利用1970年以来的川滇地震目录,选择16个反映地震时空强度分布特征的地震预测因子,采取滑动时空窗口方法有效地挖掘数据的隐藏信息,对川滇部分地区开展了基于长短期记忆(long short-term memory,LSTM)神经网络的为期一年的地震预报研究。结果显示,用1970—2019年地震目录的70%(时间窗口大概为1970年到2004年前后)作为训练集训练网络,对剩余的30%作为测试集(时间窗口大概为2005年前后到2019年底)进行回溯性预报检验时,实际震级落在预测震级±0.5内的准确率为70.2%,虚报率为18.7%,漏报率为11.1%,可以回溯性预测2008年汶川M_(S)8.0地震。为测试模型的稳健性,进行了扩大研究区域范围、改变大震级地震在均方差计算中的权重等测试。在这些测试中,LSTM神经网络模型依然表现良好。Earthquake prediction is a difficult problem in contemporary science,and applications of machine learning methods in the prediction have drawn intensive attention.Large earthquakes can cause huge casualties and economic losses,and are the main goals of earthquake prediction.We studies intermediate-term(one-year)earthquake prediction in Sichuan and Yunnan provinces using the earthquake catalogue since 1970 by the sliding time-space window technique and LSTM(long short-term memory)neural networks.Sixteen earthquake prediction indexes that reflect the temporal and spatial features of earthquake sequences were used in the neural network.The neural network was trained using data sets from 1970 to 2004(70%of all earthquake catalogues).Retrospective prediction tests were conducted on earthquakes after 2005,the accuracy rate(actual magnitude fell within±0.5 of the predicted magnitude)was 70.2%,over-prediction rate was 18.7%,and under-prediction rate was 11.1%.The 2008 Wenchuan M_(S)8.0 earthquake was retrospectively predicted.In order to understand the robustness of the model,we have done some tests,such as to expand the study area,change the weights of large earthquakes in calculation of the mean square error,etc.The LSTM neural network model still performed well in the tests.

关 键 词：中期地震预报 长短期记忆神经网络 地震预报因子 R值 川滇地区 

分 类 号：P315.7[天文地球—地震学] TP183[天文地球—固体地球物理学]