The future of earthquake forecasting
Machine-learning illuminates earthquake activity with unprecedented detail, leading to improved earthquake forecasts.
10/08/2021 By BGS Press![Figure 1. A year of seismicity in the epicentral area of the 2016 M=6.0 Amatrice earthquake (star) in Italy color coded by time of occurrence. (a) Real-time catalog, available at http://cnt.rm.ingv.it/ and (b) machine-learning catalog1 are shown for event magnitudes above their respective magnitude of completeness1,2 Mc=2.2 and Mc=0.5 (from Beroza et al., 2021).](https://www.bgs.ac.uk/wp-content/uploads/2021/07/seismicityInTheEpicentraArea.jpg)
The past five years have seen a rapidly accelerating effort in applying machine learning to seismological problems.
Now, a new generation of earthquake catalogues developed through machine learning illuminates earthquake activity with unprecedented detail, leading to improved earthquake forecasts, according to scientists at Stanford University and BGS.
Read more from Nature Communications.
![Figure 1. A year of seismicity in the epicentral area of the 2016 M=6.0 Amatrice earthquake (star) in Italy color coded by time of occurrence. (a) Real-time catalog, available at http://cnt.rm.ingv.it/ and (b) machine-learning catalog1 are shown for event magnitudes above their respective magnitude of completeness1,2 Mc=2.2 and Mc=0.5 (from Beroza et al., 2021).](https://www.bgs.ac.uk/wp-content/uploads/2021/07/seismicityInTheEpicentraArea.jpg)
A year of seismicity in the epicentral area of the 2016 M=6.0 Amatrice earthquake (star) in Italy color coded by time of occurrence.
(a) Real-time catalogue and (b) machine-learning catalogue are shown for event magnitudes above their respective magnitude of completeness, Mc=2.2 and Mc=0.5 (from Beroza et al., 2021).