8000 GitHub - xhsongstanford/FocoNet: 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.
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

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.

Notifications You must be signed in to change notification settings

xhsongstanford/FocoNet

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 

Repository files navigation

FocoNet

FocoNet

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.

FocoNet structure and the workflow to deterine a focal mechanism:

FOCONETnew

This study is presented at SCEC meeting 2024.

Citation:

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.

References:

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

About

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.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published
0