Aftershocks can endanger the survivors and those seeking to help them. New research from scientists at Harvard and Google suggests AI might be able to help predict the size and timing of these aftershocks and even their location. This could help direct emergency services to where they’re needed. Deep learning can help predict aftershock locations more reliably than existing models. Scientists trained a neural network to look for patterns in a database of more than 131,000 “mainshock-aftershock” events, before testing its predictions on a database of 30,000 similar pairs. The results were promising.
Aftershocks following a quake in 2016
The researchers say their deep learning model was able to make its predictions by considering a factor known as the “von Mises yield criterion,” a complex calculation used in fields like metallurgy to predict when materials will begin to break under stress. For a start, the AI model only focuses on aftershocks caused by permanent changes to the ground, known as static stress. But follow-up quakes can also be caused by rumblings in the ground that occur later, known as dynamic stress. The model is still a prototype. “We’re still a long way from actually being able to forecast [aftershocks] but I think machine learning has huge potential here,” Phoebe DeVries from Harvard said.