This is a transformer-based neural network to solve for the focal mechanism by combining the first-motion polarities, S/P amplitude ratios, SNRs from a set of stations.
Code will be uploaded after we publish a peer-reviewed paper.
This study is presented at SCEC meeting 2024.
Song, X., Meier, M., Ellsworth, W. L., & Beroza, G. C. (2024, 09). Transformer-based joint-station seismological analysis applied to focal-mechanism determination.. Poster Presentation at 2024 SCEC Annual Meeting.
Meier, M.-A., Lanza, F., and Martinez-Garzon, P.: A deep catalogue of 56k focal mechanisms for the 2016 Amatrice, Italy earthquake sequence, EGU General Assembly 2023, Vienna, Austria, 24–28 Apr 2023, EGU23-7167