• You are welcome to ERC!
引用本文:
【打印本页】   【HTML】   【下载PDF全文】   View/Add Comment  【EndNote】   【RefMan】   【BibTex】
过刊浏览    高级检索
本文已被:浏览 675次   下载 0  
分享到: 微信 更多
基于卷积神经网络的主动源信号识别和P波初至自动拾取
徐震, 王涛
南京大学地球科学与工程学院地球物理和动力学研究所
摘要:
在走时成像过程中,初至拾取占用了大量的人力与机时,其准确性也是地震波速结构成像的关键所在。为了满足地震资料处理高效率和高精度的需求,我们提出了一种基于卷积神经网络(CNN)自动拾取主动源P波初至到时的方法。本文利用江西景德镇实验中由可控震源车产生的地震波信号被短周期地震仪记录到的垂向道分量数据,人工拾取了7242条P波初动到时,通过预处理之后分别截取不同时窗生成25290条地震样本和710616条噪声样本(长度均为2s)。利用这些样本,训练得到一个对主动源地震信号进行自动识别的卷积神经网络。本研究将训练所得的地震分类CNN扫描连续地震记录,输出不同时间窗波形为地震信号的概率,并将概率最大处对应的时刻作为P波初动到时。测试结果显示,CNN方法对地震和噪声的检测正确率均达到了99%以上,且具有P波初至高精度的自动拾取能力(平均拾取误差:<0.10 s)。同时,与传统的短长时窗比方法(STA/LTA)相比,在对信噪比较低的记录CNN能达到更好的自动拾取效果。该方法对于促进地震资料处理工作的智能化,提高地震成像的分辨率,以及推进主动源与被动源的联合反演均具有重要意义。
关键词:  卷积神经网络  主动源信号识别  P波初至拾取  抗噪能力
DOI:
分类号:
基金项目:国家重点研发项目(2018YFC1503202-01); 国家自然科学基金应急管理项目(41842042)
Active-Source Seismic Identification and Automatic Picking of P-Wave First Arrival Using Convolutional Neural Network
Xu Zhen, Wang Tao
Institute of Geophysics and Geodynamics IGG,School of Earth Sciences and Engineering,Nanjing University,Nanjing
Abstract:
In seismic data processing, picking of P-wave first arrival takes up plenty of time and labor. And its accuracy plays a key role on imaging seismic structure. Based on convolution neural network (CNN), we propose a new method to pick up the P wave first arrivals automatically. Emitted from MINI28 vibroseis in the Jingdezhen seismic experiment, vertical component of seismic waveforms recorded by EPS 32-bit portable seismometers are used for manually picking up the first arrivals (a total of 7242). Based on these arrivals, we establish the training and testing sets, including 25290 event samples and 710616 noise samples (length of each sample: 2s). After 3000 steps of training, we obtain a convergent CNN model, which can automatically classify seismic events and noise samples with high accuracy (> 99%). With the trained CNN model, we scan continuous seismic records and take the maximum output (probability of a seismic event) as the P-wave first arrival time. Compared with STA/LTA (short time average/long time average), our method shows higher precision and stronger anti-noise ability, especially with the low SNR seismic data. This CNN method is of great significance for promoting the intellectualization of seismic data processing, improving the resolution of seismic imaging, and promoting the joint inversion of active and passive sources.
Key words:  CNN  Active-source seismic identification  first arrival picking  Anti-noise ability