Which Picker Fits My Data? A Quantitative Evaluation of Deep Learning Based Seismic Pickers
Authors:
- Jannes MünchmeyerJMJannes Münchmeyer
- Jack WoollamJWJack Woollam
- Andreas RietbrockARAndreas Rietbrock
- Frederik TilmannFTFrederik Tilmann
- Dietrich LangeDLDietrich Lange
- Tobias DiehlTDTobias Diehl
- Carlo GiunchiCGCarlo Giunchi
- Florian HaslingerFHFlorian Haslinger
- Dario JozinovićDJDario Jozinović
- Alberto MicheliniAMAlberto Michelini
- Joachim SaulJSJoachim Saul
Top Cited Papers
Open Access
- 17 January 2022
- journal article
- research article
- Published by American Geophysical Union (AGU) in Journal of Geophysical Research: Solid Earth
- Vol. 127 (1)
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 PhaseNet, closely followed by EQTransformer and GPD. Furthermore, we conduct a cross‐domain study, analyzing model performance on data sets they were not trained on. We show that trained models can be transferred between regions with only mild performance degradation, but models trained on regional data do not transfer well to teleseismic data. As deep learning for detection and picking is a rapidly evolving field, we ensured extensibility of our benchmark by building our code on standardized frameworks and making it openly accessible. This allows model developers to easily evaluate new models or performance on new data sets. Furthermore, we make all trained models available through the SeisBench framework, giving end‐users an easy way to apply these models.Keywords
This publication has 21 references indexed in Scilit:
- STanford EArthquake Dataset (STEAD): A Global Data Set of Seismic Signals for AIIEEE Access, 2019
- CRED: A Deep Residual Network of Convolutional and Recurrent Units for Earthquake Signal DetectionScientific Reports, 2019
- Machine learning for data-driven discovery in solid Earth geoscienceScience, 2019
- Convolutional Neural Network for Seismic Phase Classification, Performance Demonstration over a Local Seismic NetworkSeismological Research Letters, 2019
- Machine Learning in Seismology: Turning Data into InsightsSeismological Research Letters, 2018
- Generalized Seismic Phase Detection with Deep LearningBulletin of the Seismological Society of America, 2018
- Revisiting Unreasonable Effectiveness of Data in Deep Learning Era2017
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Deep learningNature, 2015
- Automatic S-Wave Picker for Local Earthquake TomographyBulletin of the Seismological Society of America, 2009