Portal de Periódicos da CAPES

Convolutional Neural Network for Seismic Phase Classification, Performance Demonstration over a Local Seismic Network

2019; Seismological Society of America; Volume: 90; Issue: 2A Linguagem: Inglês

10.1785/0220180312

1938-2057

Jack Woollam, Andreas Rietbrock, Ángel Bueno, Silvio De Angelis,

Seismic Waves and Analysis

Research Article| January 16, 2019 Convolutional Neural Network for Seismic Phase Classification, Performance Demonstration over a Local Seismic Network Jack Woollam; Jack Woollam aUniversity of Liverpool, Jane Herdman Building, 4 Brownlow Street, Liverpool L69 3GP, United Kingdom, Jack.Woollam@liverpool.ac.uk, S.De-Angelis@liverpool.ac.uk Search for other works by this author on: GSW Google Scholar Andreas Rietbrock; Andreas Rietbrock bGeophysical Institute (GPI), Karlsruhe Institute of Technology, Hertzstraße 16, 76187 Karlsruhe, Germany, andreas.rietbrock@kit.edu Search for other works by this author on: GSW Google Scholar Angel Bueno; Angel Bueno cDepartment of Signal Theory, Telematics and Communications, University of Granada, Calle Periodista Daniel Saucedo Aranda, 18014 Granada, Spain, angelbueno@ugr.es Search for other works by this author on: GSW Google Scholar Silvio De Angelis Silvio De Angelis aUniversity of Liverpool, Jane Herdman Building, 4 Brownlow Street, Liverpool L69 3GP, United Kingdom, Jack.Woollam@liverpool.ac.uk, S.De-Angelis@liverpool.ac.uk Search for other works by this author on: GSW Google Scholar Author and Article Information Jack Woollam aUniversity of Liverpool, Jane Herdman Building, 4 Brownlow Street, Liverpool L69 3GP, United Kingdom, Jack.Woollam@liverpool.ac.uk, S.De-Angelis@liverpool.ac.uk Andreas Rietbrock bGeophysical Institute (GPI), Karlsruhe Institute of Technology, Hertzstraße 16, 76187 Karlsruhe, Germany, andreas.rietbrock@kit.edu Angel Bueno cDepartment of Signal Theory, Telematics and Communications, University of Granada, Calle Periodista Daniel Saucedo Aranda, 18014 Granada, Spain, angelbueno@ugr.es Silvio De Angelis aUniversity of Liverpool, Jane Herdman Building, 4 Brownlow Street, Liverpool L69 3GP, United Kingdom, Jack.Woollam@liverpool.ac.uk, S.De-Angelis@liverpool.ac.uk Publisher: Seismological Society of America First Online: 16 Jan 2019 Online Issn: 1938-2057 Print Issn: 0895-0695 © Seismological Society of America Seismological Research Letters (2019) 90 (2A): 491–502. https://doi.org/10.1785/0220180312 Article history First Online: 16 Jan 2019 Cite View This Citation Add to Citation Manager Share Icon Share Facebook Twitter LinkedIn MailTo Tools Icon Tools Get Permissions Search Site Citation Jack Woollam, Andreas Rietbrock, Angel Bueno, Silvio De Angelis; Convolutional Neural Network for Seismic Phase Classification, Performance Demonstration over a Local Seismic Network. Seismological Research Letters 2019;; 90 (2A): 491–502. doi: https://doi.org/10.1785/0220180312 Download citation file: Ris (Zotero) Refmanager EasyBib Bookends Mendeley Papers EndNote RefWorks BibTex toolbar search Search Dropdown Menu toolbar search search input Search input auto suggest filter your search All ContentBy SocietySeismological Research Letters Search Advanced Search ABSTRACT Over the past two decades, the amount of available seismic data has increased significantly, fueling the need for automatic processing to use the vast amount of information contained in such data sets. Detecting seismicity in temporary aftershock networks is one important example that has become a huge challenge because of the high seismicity rate and dense station coverage. Additionally, the need for highly accurate earthquake locations to distinguish between different competing physical processes during the postseismic period demands even more accurate arrival‐time estimates of seismic phase. Here, we present a convolutional neural network (CNN) for classifying seismic phase onsets for local seismic networks. The CNN is trained on a small dataset for deep‐learning purposes (411 events) detected throughout northern Chile, typical for a temporary aftershock network. In the absence of extensive training data, we demonstrate that a CNN‐based automatic phase picker can still improve performance in classifying seismic phases, which matches or exceeds that of historic methods. The trained network is tested against an optimized short‐term average/long‐term average (STA/LTA) based method (Rietbrock et al., 2012) in classifying phase onsets for a separate dataset of 3878 events throughout the same region. Based on station travel‐time residuals, the CNN outperforms the STA/LTA approach and achieves location residual distribution close to the ones obtained by manual inspection. You do not have access to this content, please speak to your institutional administrator if you feel you should have access.