基于支持向量机的地震体波震相自动识别及到时自动拾取  

Automatic detection of seismic body-wave phases and determination of their arrival times based on support vector machine

作　　者：蒋一然 宁杰远[2] JIANG YiRan;NING JieYuan(State Key Laboratory of Shale Oil and Gas Enrichment Mechanisms and Effective Development,Beijing 100083, China;School of Earth and Space Sciences, Peking University, Beijing 100871, China)

机构地区：[1]页岩油气富集机理与有效开发国家重点实验室,北京100083 [2]北京大学地球与空间科学学院,北京100871

出　　处：《地球物理学报》2019年第1期361-373,共13页Chinese Journal of Geophysics

基　　金：中国石油化工股份有限公司石油勘探开发研究院开放基金项目(GSYKY-B09-33);内蒙古自治区2016年度科技重大专项"重点地区地震预测预警技术研究开发与推广示范"资助

摘　　要：面对海量地震资料,自动准确地拾取震相并确定其到时的需求非常迫切.基于支持向量机技术,本文提出了使用两个分类器SSD和SPS自动识别地震体波震相并自动拾取其到时的方法.相比于传统的自动拾取方法,本文方法能够更准确地识别震相并区分P波和S波.进一步地,我们提出了利用台阵资料辅助识别震相的方案,有效地提高了地震震相拾取的准确率.Facing massive seismic data,it is urgent to automatically detect earthquakes and determine their arrival times accurately.Based on the support vector machine technology,we developed a method by using two classifiers SSD and SPS to automatically identify seismic body-wave phases and automatically determine their arrival times.Compared with the traditional automatic phase-picking methods,our method can more accurately identify both the seismic phases from noises,and the S phases from P phases.Moreover,we employ the array strategy to further effectively improve the accuracy of phase-detection.

关 键 词：地震震相识别 人工智能 支持向量机 地震目录 

分 类 号：P315[天文地球—地震学]