TY - GEN
T1 - Deep learning for seismic template recognition
AU - Mu, Dawei
AU - Lee, En Jui
AU - Cicotti, Pietro
AU - Langer, Florin James
AU - Cui, Yifeng
AU - Qiu, Junyi
AU - Lee, Haemin Jenny
AU - Morrin, Cody
N1 - Funding Information:
The authors would like to thank Shawn Strande and the SDSC User Services Group for their resource support. This research has been partially funded by SDSC's Advanced Technology Lab, High Performance Geocomputing Lab, and by NSF research funding ACI-1450451, ACI-1548562, and Keck Foundation 005590-0000. This work used the Southern California Earthquake Center allocations including OLCF Titan supported by DOE AC05-00OR22725, NCSA Blue Waters supported by NSF OCI-0832698, and XSEDE SDSC Comet supported by NSF ACI-1548562.
Publisher Copyright:
© 2018 Association for Computing Machinery.
PY - 2018/7/22
Y1 - 2018/7/22
N2 - Detecting earthquakes is one of the most fundamental tasks in seismology. As continuous seismic recordings grow and become readily available, they offer opportunities for identifying weak seismic signals (e.g., microseismicity, nonvolcanic tremor). Mining this source of data recordings is now considered a substantial method to study various geophysical phenomena. Widely used methods, such as the template matching algorithm (TMA), use waveforms of confirmed seismic signal to slide through corresponding continuous recordings searching similarities. These methods present several weaknesses, including sensitivity to the choice of thresholds, signal-to-noise ratios (SNRs), and bias. In this work, we present a solution for seismic signal recognition using emerging deep learning techniques. We have designed a Convolutional Neural Network (CNN) that recognizes seismic signals using features extracted by multiple filter kernels. This software is designed for training with data from multiple stations and the SNRs of template waveforms. We demonstrate the accuracy of our approach using seismic waveform recordings from multiple stations during the 2016 ML 6.6 Meinong earthquake sequence in Taiwan.
AB - Detecting earthquakes is one of the most fundamental tasks in seismology. As continuous seismic recordings grow and become readily available, they offer opportunities for identifying weak seismic signals (e.g., microseismicity, nonvolcanic tremor). Mining this source of data recordings is now considered a substantial method to study various geophysical phenomena. Widely used methods, such as the template matching algorithm (TMA), use waveforms of confirmed seismic signal to slide through corresponding continuous recordings searching similarities. These methods present several weaknesses, including sensitivity to the choice of thresholds, signal-to-noise ratios (SNRs), and bias. In this work, we present a solution for seismic signal recognition using emerging deep learning techniques. We have designed a Convolutional Neural Network (CNN) that recognizes seismic signals using features extracted by multiple filter kernels. This software is designed for training with data from multiple stations and the SNRs of template waveforms. We demonstrate the accuracy of our approach using seismic waveform recordings from multiple stations during the 2016 ML 6.6 Meinong earthquake sequence in Taiwan.
UR - http://www.scopus.com/inward/record.url?scp=85051413640&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85051413640&partnerID=8YFLogxK
U2 - 10.1145/3219104.3219133
DO - 10.1145/3219104.3219133
M3 - Conference contribution
AN - SCOPUS:85051413640
SN - 9781450364461
T3 - ACM International Conference Proceeding Series
BT - Practice and Experience in Advanced Research Computing 2018
PB - Association for Computing Machinery
T2 - 2018 Practice and Experience in Advanced Research Computing Conference: Seamless Creativity, PEARC 2018
Y2 - 22 July 2017 through 26 July 2017
ER -