Earthquake Nowcasting with Deep Learning

We review previous approaches to nowcasting earthquakes and introduce new approaches based on deep learning using three distinct models based on recurrent neural networks and transformers. We discuss different choices for observables and measures presenting promising initial results for a region of...

Full description

Saved in:
Bibliographic Details
Published in:GeoHazards 2022-06, Vol.3 (2), p.199-226
Main Authors: Fox, Geoffrey Charles, Rundle, John B., Donnellan, Andrea, Feng, Bo
Format: Article
Language:English
Subjects:
Aftershocks
Deep learning
earthquake
Earthquakes
Fault lines
Localization
LSTM
Machine learning
nowcasting
Phase transitions
Southern California
Time series
transformer
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We review previous approaches to nowcasting earthquakes and introduce new approaches based on deep learning using three distinct models based on recurrent neural networks and transformers. We discuss different choices for observables and measures presenting promising initial results for a region of Southern California from 1950–2020. Earthquake activity is predicted as a function of 0.1-degree spatial bins for time periods varying from two weeks to four years. The overall quality is measured by the Nash Sutcliffe efficiency comparing the deviation of nowcast and observation with the variance over time in each spatial region. The software is available as open source together with the preprocessed data from the USGS.
ISSN:2624-795X
2624-795X
DOI:10.3390/geohazards3020011