Open Access Te Herenga Waka-Victoria University of Wellington
Browse

Parametric Testing of EQTransformer’s Performance against a High-Quality, Manually Picked Catalog for Reliable and Accurate Seismic Phase Picking

journal contribution
posted on 2024-03-21, 02:19 authored by O Pita-Sllim, Calum ChamberlainCalum Chamberlain, John TownendJohn Townend, E Warren-Smith
This study evaluates EQTransformer, a deep learning model, for earthquake detection and phase picking using seismic data from the Southern Alps, New Zealand. Using a robust, independent dataset containing more than 85,000 manual picks from 13 stations spanning almost nine years, we assess EQTransformer’s performance and limitations in a practical application scenario. We investigate key parameters such as overlap and probability threshold and their influences on detection consistency and false positives, respec-tively. EQTransformer’s probability outputs show a limited correlation with pick accuracy, emphasizing the need for careful interpretation. Our analysis of illustrative signals from three seismic networks highlights challenges of consistently picking first arrivals when reflected or refracted phases are present. We find that an overlap length of 55 s balances detection consistency and computational efficiency, and that a probability threshold of 0.1 balances detection rate and false positives. Our study thus offers insights into EQTransformer’s capabilities and limitations, highlighting the importance of parameter selection for optimal results.

History

Preferred citation

Pita-Sllim, O., Chamberlain, C. J., Townend, J. & Warren-Smith, E. (2023). Parametric Testing of EQTransformer’s Performance against a High-Quality, Manually Picked Catalog for Reliable and Accurate Seismic Phase Picking. Seismic Record, 3(4), 332-341. https://doi.org/10.1785/0320230024

Journal title

Seismic Record

Volume

3

Issue

4

Publication date

2023-10-01

Pagination

332-341

Publisher

Seismological Society of America (SSA)

Publication status

Published

Online publication date

2023-11-29

ISSN

2694-4006

eISSN

2694-4006

Language

en

Usage metrics

    Journal articles

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC