Seismic P-Wave First-Arrival Picking Model Based on Spatiotemporal Attention Mechanism

doi:10.3778/j.issn.1002-8331.2109-0428

Abstract

Abstract: Aiming at the problems of low accuracy and poor robustness of the existing earthquake first-arrival picking algorithm, a seismic P-wave arrival picking network based on deep learning is designed. This network is encoder-decoder structure, which can identify seismic signal sequence point by point. The encoder uses multi-scale feature extractor for feature extraction and fusion of input data to improve feature utilization ratio. The multi-scale residual structure is used to deeply mine the hidden feature information in the data to improve the nonlinear fitting ability of the model. Then, the spatiotemporal attention mechanism is added to the decoder to improve the network’s perception of the first-arrival features. Finally, a deep coding feature fusion module is proposed to effectively avoid the pollution of feature sequence while ensuring the integrity of features. The experimental results show that under the three error thresholds of 0.1 s, 0.2 s and 0.3 s, the picking hit rate of the proposed network are 75.04%, 94.6% and 97.37%, respectively, the mean absolute error and mean square error are 0.092 s and 0.036. Compared with the existing traditional and deep learning first-arrival picking methods, it has higher P-wave first-arrival picking accuracy.

Key words: phase arrive picking, deep learning, sequence processing, spatiotemporal attention, feature fusion

摘要： 针对现有地震到时拾取算法精度较低、鲁棒性较差等问题，设计了一种基于深度学习的地震P波到时拾取网络，该网络为编解码结构，可实现地震波形序列的逐点预测。网络编码器对输入数据进行多尺度特征提取与融合，提高特征利用率；利用多尺度残差结构深度挖掘数据中隐藏特征信息，提升模型非线性拟合能力；在解码网络中加入时空注意力机制，提高网络对到时特征的感知能力；提出深层编码特征融合模块，在保证特征完整性的同时有效避免融合特征过程中出现的特征序列污染问题。实验结果表明，提出的网络在0.1?s、0.2?s、0.3?s三个误差阈值下，拾取命中率分别为75.04%、94.6%、97.37%，平均绝对误差和均方误差为0.092?s、0.036，相比现有传统方法与深度学习到时拾取方法，具有更高的P波到时拾取精度。

关键词: 震相到时拾取, 深度学习, 序列处理, 时空注意力, 特征融合

LI Yu, HAN Xiaohong, ZHANG Ling, ZHANG Haixuan, LI Gang. Seismic P-Wave First-Arrival Picking Model Based on Spatiotemporal Attention Mechanism[J]. Computer Engineering and Applications, 2023, 59(6): 113-124.

李宇, 韩晓红, 张玲, 张海轩, 李钢. 融合时空注意力机制的P波到时拾取网络[J]. 计算机工程与应用, 2023, 59(6): 113-124.

References

[1] 代光辉，苗春兰，翟璐媛.中国测震台网统一地震编目[J].中国地震，2019，35（1）：192-203.
DAI G H，MIAO C L，ZHAI L Y.Unified earthquake cataloging of China seismiographic network[J].Earthquake Research in China，2019，35（1）：192-203.
[2] ALLEN R V.Automatic earthquake recognition and timing from single traces[J].Bulletin of the Seismological Society of America，1978，68（5）：1521-1532.
[3] AKAIKE H T.A new look at the statistical model identification[J].IEEE Transactions on Automatic Control，1974，19（6）：716-723.
[4] PEROL T，GHARBI M，DENOLLE M.Convolutional neural network for earthquake detection and location[J].Science Advances，2018，4（2）：e1700578.
[5] ZHU W，BEROZA G C.PhaseNet：a deep-neural-network-based seismic arrival-time picking method[J].Geophysical Journal International，2018（1）：1.
[6] 李力，张建国，李盛乐.余震自动识别技术研究进展[J].地震研究，2018，41（1）：1-13.
LI L，ZHANG J G，LI S L.Developments of research on automatic aftershock recognition technology[J].Earthquake Research，2018，41（1）：1-13.
[7] BAER M，KRADOLFER U.An automatic phase picker for local and teleseismic events[J].Bulletin of the Seismological Society of America，1987，77（4）：1437-1445.
[8] 李晓锐，张娜，姚林鹏，等.ObsPy包中的地震事件触发和震相拾取算法梳理[J].山西地震，2020（3）：42-46.
LI X R，ZHANG N，YAO L P，et al.Sorting of seismic event triggering and seismic phase picking algorithms in ObsPy package[J].Earthquake Research in Shanxi，2020（3）：42-46.
[9] AKAZAWA T.A technique for automatic detection of onset time of P and S phases in strong motion records[C]//13th World Conference on Earthquake Engineering，Vancouver，B C，Canada，2004.
[10] ZHANG J，TANG Y，LI H.STA/LTA fractal dimension algorithm of detecting the P-wave arrival[J].Bulletin of the Seismological Society of America，2017，108（1）：230-237.
[11] DAI H，MACBETH C.The application of back-propagation neural network to automatic picking seismic arrivals from single-component recordings[J].Journal of Geophysical Research Solid Earth，1997，102（B7）：15105-15113.
[12] 王俊，杨驰，詹小艳，等.P波初至到时自动拾取技术研究[J].地震研究，2018，41（1）：38-45.
WANG J，YANG C，ZHAN X Y，et al.Research on automatic picking up technique of P-wave first arrival time[J].Journal of Seismological Research，2018，41（1）：38-45.
[13] CHAI C，MACEIRA M，SANTOS‐VILLALOBOS H J，et al.Using a deep neural network and transfer learning to bridge scales for seismic phase picking[J].Geophysical Research Letters，2020，47（16）.
[14] ZACHARY E R，MEIER M A，HAUKSSON E.P wave arrival picking and first‐motion polarity determination with deep learning[J].Journal of Geophysical Research Solid Earth，2018，123（6）：5120-5129.
[15] 赵明，唐淋，陈石，等.基于深度学习到时拾取自动构建长宁地震前震目录[J].地球物理学报，2021，64（1）：54-66.
ZHAO M，TANG L，CHEN S，et al.Machine learning based automatic foreshock catalog building for the 2019 MS6.0 Changning，Sichuan earthquake[J].Chinese Journal of Geophysics，2021，64（1）：54-66.
[16] 蔡振宇，盖增喜.人工智能在拾取地震P波初至中的应用——以汶川地震余震序列为例[J].北京大学学报（自然科学版），2019，55（3）：451-460.
CAI Z Y，GAI Z X.Using artificial intelligence to pick P-wave first-arrival of the microseisms：taking the after-shock sequence of Wenchuan earthquake as an example[J].Journal of Peking University（Natural Science Edition），2019，55（3）：451-460.
[17] 赵明，陈石，房立华，等.基于U形卷积神经网络的震相识别与到时拾取方法研究[J].地球物理学报，2019，62（8）：3034-3042.
ZHAO M，CHEN S，FANG L H，et al.Earthquake phase arrival auto-picking based on U-shaped convolutional neural network[J].Chinese Journal of Geophysics，2019，62（8）：3034-3042.
[18] MOUSAVI S M，ELLSWORTH W L，ZHU W，et al.Earthquake transformer—an attentive deep-learning model for simulta-neous earthquake detection and phase picking[J].Nature Communications，2020，11（1）：3952.
[19] SZEGEDY C，IOFFE S，VANHOUCKE V，et al.Inception-v4，In-ception-ResNet and the impact of residual connections on learning[J].arXiv：1602.07261，2016.
[20] 周凡，朴燕，秦晓伟.基于密集模块与特征融合的SSD目标检测算法[J].计算机工程与应用，2020，56（16）：105-111.
ZHOU F，PIAO Y，QIN X W.SSD target detection algorithm based on dense module and feature fusion[J].Computer Engineering and Applications，2020，56（16）：105-111.
[21] HUANG G，LIU Z，LAURENS V，et al.Densely connected convolutional networks[J].arXiv：1608.06993v2，2016.
[22] HE K，ZHANG X，REN S，et al.Deep residual learning for image recognition[C]//2016 IEEE Conference Computer Vision and Pattern Recognition，2016：770-778.
[23] SIMONYAN K，ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[J].arXiv：1409.1556，2014.
[24] LIU Z，CAO Y，WANG Y，et al.Computer vision-based concrete crack detection using U-net fully convolutional networks[J].Automation in Construction，2019，104（8）：129-139.
[25] 任欢，王旭光.注意力机制综述[J].计算机应用，2021，41（z1）：1-6.
REN H，WANG X G.Review of attention mechanism[J].Journal of Computer Applications，2021，41（z1）：1-6.
[26] 张宇倩，李国辉，雷军，等.FF-CAM：基于通道注意机制前后端融合的人群计数[J].计算机学报，2021，44（2）：304-317.
ZHANG Y Q，LI G H，LEI J，et al.FF-CAM：crowd counting based on frontend-backend fusion through channel-attention mechanism[J].Chinese Journal of Computers，2021，44（2）：304-317.
[27] 王玲，王家沛，王鹏，等.融合注意力机制的孪生网络目标跟踪算法研究[J].计算机工程与应用，2021，57（8）：169-174.
WANG L，WANG J P，WANG P，et al.Siamese network tracking algorithms for hierarchical fusion of attention mechanism[J].Computer Engineering and Applications，2021，57（8）：169-174.
[28] BRECKPOT R，MARZEC M K.ObsPy：a Python toolbox for seismology[J].Seismological Research Letters，2010，81（3）：530-533.
[29] HOCHREITER S，SCHMIDHUBER J.Long short-term memory[J].Neural Computation，1997，9（8）：1735-1780.
[30] 王国栋，芦天亮，尹浩然，等.基于CNN-BiLSTM的恶意代码家族检测技术[J].计算机工程与应用，2020，56（24）：72-77.
WANG G D，LU T L，YIN H R，et al.Malicious code family detection technology based on CNN-BiLSTM[J].Computer Engineering and Applications，2020，56（24）：72-77.
[31] CHO K，MERRIENBOER B V，GULCEHRE C，et al.Learning phrase representations using RNN encoder-decoder for statistical machine translation[J].arXiv：1406.1078，2014.