Automatic earthquake detection and phase picking in Muong Te, Lai Chau region: an application of machine learning in observational seismology in Vietnam

Abstract

We applied the automatic detection and picking of P- and S-wave to one-year continuous raw seismic data from 17 seismic stations in the Muong Te area, northwestern Vietnam. The deep learning picker, Earthquake Transformer, has performed automatic picking of P- and S-waves, and phase association, then we located the earthquakes using Hypoinverse and NonLinLoc programs. The newly derived catalog consisted of 893 events, which is significantly higher than the number of events in the manual catalog. From this new catalog, we can observe more earthquakes related to the Muong Te ML 4.9 earthquake on June 16, 2020, and the earthquake activity in other faults such as the Dien Bien Phu and Muong Nhe faults. The extended catalog can further study the seismogenesis and the seismic velocity structure of the crust beneath northwestern Vietnam.