KIT | KIT-Bibliothek | Impressum | Datenschutz

Which Picker Fits My Data? A Quantitative Evaluation of Deep Learning Based Seismic Pickers

Münchmeyer, J. ; Woollam, J. 1; Rietbrock, A. 1; Tilmann, F.; Lange, D.; Bornstein, T.; Diehl, T.; Giunchi, C.; Haslinger, F.; Jozinović, D.; Michelini, A.; Saul, J.; Soto, H.
1 Geophysikalisches Institut (GPI), Karlsruher Institut für Technologie (KIT)

Abstract:

Seismic event detection and phase picking are the base of many seismological workflows. In recent years, several publications demonstrated that deep learning approaches significantly outperform classical approaches, achieving human-like performance under certain circumstances. However, as studies differ in the datasets and evaluation tasks, it is unclear how the different approaches compare to each other. Furthermore, there are no systematic studies about model performance in cross-domain scenarios, that is, when applied to data with different characteristics. Here, we address these questions by conducting a large-scale benchmark. We compare six previously published deep learning models on eight data sets covering local to teleseismic distances and on three tasks: event detection, phase identification and onset time picking. Furthermore, we compare the results to a classical Baer-Kradolfer picker. Overall, we observe the best performance for EQTransformer, GPD and PhaseNet, with a small advantage for EQTransformer on teleseismic data. Furthermore, we conduct a cross-domain study, analyzing model performance on data sets they were not trained on. ... mehr


Verlagsausgabe §
DOI: 10.5445/IR/1000143103
Veröffentlicht am 07.07.2022
Originalveröffentlichung
DOI: 10.1029/2021JB023499
Scopus
Zitationen: 58
Web of Science
Zitationen: 50
Dimensions
Zitationen: 75
Cover der Publikation
Zugehörige Institution(en) am KIT Geophysikalisches Institut (GPI)
Publikationstyp Zeitschriftenaufsatz
Publikationsjahr 2022
Sprache Englisch
Identifikator ISSN: 2169-9313, 0148-0227, 2156-2202, 2169-9356
KITopen-ID: 1000143103
Erschienen in Journal of Geophysical Research: Solid Earth
Verlag John Wiley and Sons
Band 127
Heft 1
Seiten Art-Nr e2021JB023499
Vorab online veröffentlicht am 06.01.2022
Nachgewiesen in Web of Science
Dimensions
Scopus
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page