Earthquake magnitudes depend on seismic history, as revealed by a neural network analysis
Neri Berman, Oleg Zlydenko, Oren Gilon, Yossi Matias, Yohai Bar-Sinai · 2026
Read Earthquake magnitudes depend on seismic history, as revealed by a neural network analysis by Neri Berman, Oleg Zlydenko, Oren Gilon, Yossi Matias, Yohai Bar-Sinai (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/pmc-13342513.txt.
Description
Neri Berman and co-authors show that past quakes carry hints about how big the next one will be in a 2026 study. Standard forecasts treat quake size as a fresh draw each time, blind to history. The team built a neural net that reads the place, time, and size of past quakes and deals out odds for the next size.
On lists from three quake zones, the net beat the standard size law by a small but steady edge. The edge held after tricks to rule out sensor quirks. Catalogs thus hold more signal than the field assumed, the team says, and hazard work can use it.
Catalog record
| CREATOR | Neri Berman, Oleg Zlydenko, Oren Gilon, Yossi Matias, Yohai Bar-Sinai |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 79 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |