Neural phase picker trained on the Japan meteorological agency unified earthquake catalog

• Published in: Earth, planets, and space planets, and space, 2024-12, Vol.76 (1), p.150-22, Article 150
• Main Authors: Naoi, Makoto, Tamaribuchi, Koji, Shimojo, Kengo, Katoh, Shinya, Ohyanagi, Shukei
• Format: Article
• Language: English
• Subjects: 4. Seismology; analysis and interpretation of seismicity; Datasets; Deep learning; Development strategies; Earth and Environmental Science; Earth Sciences; Earthquake catalog development; Earthquake magnitude; Earthquakes; Emergency management; Emergency preparedness; Geology; Geophysics/Geodesy; Hypocenter location; Machine learning; Methods; Neural phase picker; New trends in data acquisition; Ocean bottom; Public safety; Seismic activity; Seismic response; Seismic waves; Seismological data; Seismometers; Time measurement; Waveforms
• ISSN: 1880-5981; 1343-8832; 1880-5981
• DOI: 10.1186/s40623-024-02091-8

As Japan is one of the most seismically active countries, seismic data from various institutions are shared in real time and made accessible via the Web to promote research. The Japan Meteorological Agency (JMA), in collaboration with the Ministry of Education, Culture, Sports, Science, and Technology, processes these data to compile a 'unified earthquake catalog' for use in the development of strategies for disaster prevention and public safety. Based on manual arrival-time measurements provided by the JMA, we retrained PhaseNet, the deep-learning phase picker, known as neural phase picker that has gained prominence in recent years, to promote the development of high-quality seismic catalogs in Japan. We utilized the PhaseNet architecture for our model and trained it using 6.1 million three-component seismic waveforms collected in 2014–2021. The performance of the original PhaseNet model, trained with data from California, was suboptimal when applied to routine Japanese data, particularly ocean-bottom seismometer records. Retraining the model with the JMA unified catalog and corresponding waveforms significantly enhanced its performance in picking the arrival times of regular and low-frequency earthquakes. Compared with the original PhaseNet, the dependency of the model on the type of seismic station was reduced by retraining and its performance for waveforms was improved even from stations not included in the training data set. The model performance varied with earthquake magnitude, highlighting the reliance on extensive data for small events in the training set. Compared with the conventional procedure, the model identified numerous events, particularly smaller ones with undetermined magnitudes when integrated into the routine automatic processing of the JMA. Furthermore, leveraging approximately ten times more training data than the California data set, we developed and trained PhaseNetWC, doubling the number of filter channels in each convolutional layer in comparison with those of the original PhaseNet. This modified phase picker surpassed the performance of its predecessor. The dissemination of these models is anticipated to enhance the analysis of routine observational data sets in Japan. Graphical Abstract