This is a Jupyther Notebook (MLworkflow.ipynb) of SCOPED tutorial for machine learning catalog construction workflow.
The notebook includes code and examples to download continuous data, detect and pick phases with PhaseNet, assoicate the phases with GaMMA, locate them with HypoInverse, and relocate the events with HypoDD.
The SCOPED Container page for ML catalog construction is at https://github.com/SeisSCOPED/ml_catalog
-
Data downloaded with ObsPy Mass Downloader fuction (https://docs.obspy.org/packages/obspy.clients.fdsn.html)
-
PhaseNet for phase picking (https://github.com/AI4EPS/PhaseNet)
-
GaMMA for picks association (https://github.com/AI4EPS/GaMMA)
-
HypoInverse for single event location (https://www.usgs.gov/software/hypoinverse-earthquake-location)
-
HypoDD for double difference relocation (https://github.com/fwaldhauser/HypoDD)
-
Moritz Beyreuther, Robert Barsch, Lion Krischer, Tobias Megies, Yannik Behr and Joachim Wassermann (2010), ObsPy: A Python Toolbox for Seismology, SRL, 81(3), 530-533, doi:10.1785/gssrl.81.3.530.
-
Zhu, Weiqiang, and Gregory C. Beroza. "PhaseNet: A Deep-Neural-Network-Based Seismic Arrival Time Picking Method." arXiv preprint arXiv:1803.03211 (2018).
-
Zhu, Weiqiang et al. "Earthquake Phase Association using a Bayesian Gaussian Mixture Model." (2021)
-
Klein, Fred W. User's guide to HYPOINVERSE-2000, a Fortran program to solve for earthquake locations and magnitudes. No. 2002-171. US Geological Survey, 2002.
-
Waldhauser, Felix, and William L. Ellsworth, A double-difference earthquake location algorithm: Method and application to the northern Hayward fault, California, Bull. Seism. Soc. Am. 90, 1353-1368, 2000.