Research teams from Google+’s artificial intelligence (AI) division and Harvard University have developed an Artificial Intelligence which could predict the location of aftershocks up to one year after an earthquake.
The AI teams were trained on 199 major earthquake events, followed by over 130,000 aftershocks.
Nevertheless, it is incompetent to factor in earthquakes formed by natural disasters, such as volcanic eruption, researchers specified.
As published in VentureBeat “We found that after feeding these model stress changes into the neural network, the neural network could sort of predict aftershock locations in the testing dataset more accurately than the sort of baseline Coulomb failure stress change criterion that’s used a lot in studies of aftershock locations,” Phoebe DeVries of the Department of Earth and Planetary Sciences at Harvard University told to VentureBeat.
