English
 
Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
Add to Basket
  Local TagsRelease HistoryDetailsSummary

Released
Software

TEAM – The Transformer Earthquake Alerting Model

Authors
/persons/resource/munchmej

Münchmeyer,  J.       
2.4 Seismology, 2.0 Geophysics, Departments, GFZ Publication Database, Deutsches GeoForschungsZentrum;

/persons/resource/bindi

Bindi,  Dino       
2.6 Seismic Hazard and Risk Dynamics, 2.0 Geophysics, Departments, GFZ Publication Database, Deutsches GeoForschungsZentrum;

Leser,  Ulf
External Organizations;

/persons/resource/tilmann

Tilmann,  Frederik       
2.4 Seismology, 2.0 Geophysics, Departments, GFZ Publication Database, Deutsches GeoForschungsZentrum;

External Resource
No external resources are shared
Fulltext (restricted access)
There are currently no full texts shared for your IP range.
Fulltext (public)
There are no public fulltexts stored in PuRe
Supplementary Material (public)
There is no public supplementary material available
Citation

Münchmeyer, J., Bindi, D., Leser, U., Tilmann, F. (2021): TEAM – The Transformer Earthquake Alerting Model.
https://doi.org/10.5880/GFZ.2.4.2021.003


Cite as: https://gfzpublic.gfz.de/pubman/item/item_5007097
Abstract
TEAM, the Transformer Earthquake Alerting Model is a deep learning model for real time estimation of peak ground acceleration (TEAM), earthquake magnitude and earthquake location (TEAM-LM). This software package contains the joint implementation of both TEAM and the derivative TEAM-ML, as well as the scripts for training and evaluating these models. In addition, it contains scripts to download an early warning datasets for Japan and implementations of baseline approaches for the estimation of earthquake magnitude and peak ground acceleration. TEAM is implemented in Python.

TEAM and TEAM-ML have a variety of configuration parameters that are documented in the README. These configurations need to be provided in JSON format. In addition, multiple example configuration files are provided in the subdirectories pga_configs and magloc_configs. Please note that this implementation is intended for research purpose only. Production use is discouraged.