CaltechAUTHORS
  A Caltech Library Service

PhaseLink: A Deep Learning Approach to Seismic Phase Association

Ross, Zachary E. and Yue, Yisong and Meier, Men-Andrin and Hauksson, Egill and Heaton, Thomas H. (2019) PhaseLink: A Deep Learning Approach to Seismic Phase Association. Journal of Geophysical Research. Solid Earth, 124 (1). pp. 856-869. ISSN 2169-9313. https://resolver.caltech.edu/CaltechAUTHORS:20181213-160905447

[img] PDF - Published Version
See Usage Policy.

2580Kb
[img] PDF - Submitted Version
See Usage Policy.

2946Kb

Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20181213-160905447

Abstract

Seismic phase association is a fundamental task in seismology that pertains to linking together phase detections on different sensors that originate from a common earthquake. It is widely employed to detect earthquakes on permanent and temporary seismic networks and underlies most seismicity catalogs produced around the world. This task can be challenging because the number of sources is unknown, events frequently overlap in time, or can occur simultaneously in different parts of a network. We present PhaseLink, a framework based on recent advances in deep learning for grid‐free earthquake phase association. Our approach learns to link phases together that share a common origin and is trained entirely on millions of synthetic sequences of P and S wave arrival times generated using a 1‐D velocity model. Our approach is simple to implement for any tectonic regime, suitable for real‐time processing, and can naturally incorporate errors in arrival time picks. Rather than tuning a set of ad hoc hyperparameters to improve performance, PhaseLink can be improved by simply adding examples of problematic cases to the training data set. We demonstrate the state‐of‐the‐art performance of PhaseLink on a challenging sequence from southern California and synthesized sequences from Japan designed to test the point at which the method fails. For the examined data sets, PhaseLink can precisely associate phases to events that occur only ∼12 s apart in origin time. This approach is expected to improve the resolution of seismicity catalogs, add stability to real‐time seismic monitoring, and streamline automated processing of large seismic data sets.


Item Type:Article
Related URLs:
URLURL TypeDescription
https://doi.org/10.1029/2018JB016674DOIArticle
https://doi.org/10.7914/SN/CIRelated ItemData from the Caltech/USGS Southern California Seismic Network
https://.doi.org/10.7909/C3WD3xH1Related ItemSCEDC (2013): Southern California Earthquake Center. Caltech.Dataset.
http://arxiv.org/abs/1809.02880arXivDiscussion paper
ORCID:
AuthorORCID
Ross, Zachary E.0000-0002-6343-8400
Yue, Yisong0000-0001-9127-1989
Meier, Men-Andrin0000-0002-2949-8602
Hauksson, Egill0000-0002-6834-5051
Heaton, Thomas H.0000-0003-3363-2197
Additional Information:© 2019 American Geophysical Union. Received 8 SEP 2018; Accepted 12 JAN 2019; Accepted article online 17 JAN 2019; Published online 25 JAN 2019. This research was supported by an artificial intelligence research grant from Amazon Web Services. The authors thank Pascal Audet and an anonymous reviewer for their helpful comments that improved the manuscript. The authors were also supported by the Gordon and Betty Moore Foundation, the Swiss National Science Foundation, and the NSF Geoinformatics program. We have used waveforms data and metadata from the Caltech/USGS Southern California Seismic Network (SCSN), doi: 10.7914/SN/CI; stored at the Southern California Earthquake Data Center, doi:10.7909/C3WD3xH1. We used TensorFlow (Abadi et al., 2015) and keras (Chollet, 2015) for all deep learning computations.
Group:Seismological Laboratory
Funders:
Funding AgencyGrant Number
Amazon Web ServicesUNSPECIFIED
Gordon and Betty Moore FoundationUNSPECIFIED
Swiss National Science Foundation (SNSF)UNSPECIFIED
NSFUNSPECIFIED
Subject Keywords:phase association; deep learning; earthquake detection; earthquake monitoring
Issue or Number:1
Record Number:CaltechAUTHORS:20181213-160905447
Persistent URL:https://resolver.caltech.edu/CaltechAUTHORS:20181213-160905447
Official Citation:Ross, Z. E., Yue, Y., Meier, M.‐A., Hauksson, E., & Heaton, T. H. ( 2019). PhaseLink: A deep learning approach to seismic phase association. Journal of Geophysical Research: Solid Earth, 124, 856–869. https://doi.org/10.1029/2018JB016674
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:91845
Collection:CaltechAUTHORS
Deposited By: George Porter
Deposited On:14 Dec 2018 00:14
Last Modified:09 Mar 2020 13:19

Repository Staff Only: item control page