Google, Harvard to use machine learning to predict earthquake aftershock locations

Christopher Davidson
September 2, 2018

The concept of employing artificial intelligent neural networks to attempt to predict aftershocks first emerged a number of years ago, during the first of Meade's two sabbaticals at Google in Cambridge.

After the procedure, they then tested how well the programme successfully predicted the aftershock locations of the remaining 25 percent of cases that hadn't been fed.

Taking on such a challenge with highly complex real-world data, however, would be a daunting task, so the pair instead asked the system to create forecasts for synthetic, highly-idealized earthquakes and then examining the predictions.

Earthquakes typically occur in sequences - an initial "mainshock" followed by a set of "aftershocks". From the data, the AI learned to determine the likely occurrence of an aftershock.

The researchers tested their neural network on 30,000 mainshock-aftershock events and found that it could predict the site of aftershocks much more accurately than the previously used model. "The previous baseline for aftershock forecasting has a precision of around three per cent across the testing data set.

Gold' becomes the first Bollywood film to release in Saudi Arabia
After Rajinikanth's hit social drama, Kaala , Reema Kagti's movie is the second film to get a release in the Gulf country. The narrative of Gold revolves around Tapan Das , who is a hockey coach living in pre-Independent India.

DeVries acknowledged that additional factors affect where aftershocks occur and that there is "much more to be done".

In October 2017, news agency PTI reported that scientists had developed an AI system to successfully predict earthquakes. Published in the Geophysical Review Letters, the study identified a hidden signal leading up to an natural disaster.

The researchers used machine-learning techniques to asses acoustic signals coming from the "fault" as it moved and searched for patterns. The methodologies involved training a neural network to deduce whether patterns existed in a database of over 131,000 so-called "mainshock-aftershock" combos where a "main" quake would be followed by an aftershock.

But sparked by a suggestion from researchers at Google, Brendan Meade, a Professor of Earth and Planetary Sciences, and Phoebe DeVries, a post-doctoral fellow working in his lab, are using artificial intelligence technology to try to get a handle on the problem. In a paper published in Science Advances, they show that it is capable of detecting 17 times more earthquakes than older methods in a fraction of the time. But while they may be easy for seismologists and other scientists to predict in a fairly accurate fashion, researchers from one of America's most prestigious institutions and one of the world's top tech companies have teamed up to create an artificial intelligence system that could predict aftershocks with much greater accuracy than ever before.

"I'm very excited for the potential for machine learning going forward with these kind of problems-it's a very important problem to go after", stated DeVries. Machine learning is able to do the work of predictive analysis by tracking patterns and analysing information to gauge whether the same possibilities could occur in the future.

Other reports by

Discuss This Article