基于四分量钻孔应变数据的神经网络地震活动性预测分析  

Borehole strain data based seismicity prediction analysis using a neural network

作　　者：于紫凝 李海峰[1] 景锡龙 池成全 郑海永[1] Yu Zining;Li Haifeng;Jing Xilong;Chi Chengquan;Zheng Haiyong(College of Electronic Engineering,Ocean University of China,Shandong Qingdao 266404,China;School of Information Science and Technology,Hainan Normal University,Haikou 571158,China)

机构地区：[1]中国海洋大学电子工程学院,山东青岛266404 [2]海南师范大学信息科学技术学院,海口571158

出　　处：《地震学报》2024年第2期327-339,共13页Acta Seismologica Sinica

基　　金：国家自然科学基金青年基金(42204005);山东省自然科学基金青年基金(ZR2022QF130);中央高校基本科研业务费专项(202213042);海南省自然科学基金高层次人才项目(622RC669)共同资助.

摘　　要：首先利用四分量钻孔应变数据独有的自洽特性,构建震前应变特征数据集;之后基于一维卷积神经网络框架,设计地震震级与方位的预测模型;然后通过混淆矩阵计算准确率、召回率以及F1分数,对模型预测结果进行评价与修正;最后对我国西南地区的永胜、昭通、姑咱及腾冲四个台站的钻孔应变特征分别进行训练与验证,并讨论了不同特征窗长对预测效果的影响。训练完成后的模型效果在测试集上均表现优异,四个台站对震级和方位预测的平均准确率分别可达85%和80%左右,说明四分量钻孔应变数据特征与地震的发生有着很强的相关性,通过卷积神经网络对地震前兆特征进行挖掘具有很大研究潜力,本文提出的预测策略也为未来短临地震的精确预测研究打下基础。With the development of seismological observational techniques,a number of case studies indicate that the seismogenic process of major earthquakes is often accompanied by deformation anomalies.Strain data serve as an indicator of crustal deformation,which reflects changes in subsurface stress and holds significant importance for seismology research.However,the research on the extraction of pre-earthquake anomalies from borehole strain data is currently limited to the stages of case analysis and small-sample statistical analysis.Thus,it is very meaningful to use a new technique of data mining to analyze the association between strain anomalies and earthquakes.In order to dig out more strain information and correlation information between multiple strains,according to the scholars’many analyses of the correlation between areal strains,shear strains and the self-consistent coefficients of the four-component strains,it is found that the borehole strain may reflect the preparatory process of earthquake nucleation.Therefore,this study calculates the Pearson correlation coefficients and self-consistent coefficients between these strains to finally constitute a 24-dimensional feature dataset.Subsequently,we divide earthquake events based on magnitude into three classes:no earthquake,earthquakes with 3.0≤MS<5.0,and earthquakes with MS≥5.0.Simultaneously,these earthquakes are also classified into five groups based on their orientation relative to the borehole strainmeter,form-ing an earthquake orientation dataset.Thereby,the labels for earthquake samples are generated according to these two classification criteria.Next,the study employs a one-dimensional convolutional neural network(1D-CNN)framework to develop a short-term prediction model for the magnitude and location of earth-quakes.The CNN can leverage the advantages of its convolutional layers’parameter-sharing mechanism to effectively capture local features in the data.This 1D-CNN model consists of three parts:the input layer,hidden layers,and output layer.St

关 键 词：四分量钻孔应变 卷积神经网络 震级预测 方位预测 地震前兆 

分 类 号：P315.72[天文地球—地震学]