Single station seismic observations enable high resolution localization of tectonic tremor sources using a vision transformer
Amane Sugii, Yoshihiro Hiramatsu · 2026
Read Single station seismic observations enable high resolution localization of tectonic tremor sources using a vision transformer by Amane Sugii, Yoshihiro Hiramatsu (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13572398.txt.
Description
Amane Sugii and Yoshihiro Hiramatsu present a 2026 method for pinning down slow quakes called tectonic tremor from a single seismic station. Tremor lacks the sharp starts of normal quakes, so locating it has long needed many stations. The work asks how much place data one station's full wave record holds.
Their tool, TremorViT, reads three-part wave records with a vision transformer, a model built for images, and also reports how unsure it is. On the Nankai zone in Japan, one station gave a mean place error of 4.8 kilometres. Pooling calls from several stations cut the error to 2.5 kilometres. The tool placed 68,101 events from January to September 2016, far more than older lists held. The pattern in space and time still matched known tremor behaviour.
Catalog record
| CREATOR | Amane Sugii, Yoshihiro Hiramatsu |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 48702 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |