A team of international scientists has shown how machine learning systems can provide an early warning for earthquakes.

The researchers from Boston University, the University of Cambridge and Los Alamos National Laboratory, discovered a hidden trigger, or ‘fingerprint’, signalling an impending earthquake and developed a machine learning algorithm that could use it to predict earthquakes and save lives.

In lab-based tests the team used the techniques to detect a ‘pattern in the sound’ in the earth, once thought to be just a noise, which occurs well in advance of an earthquake.

“This is the first time that machine learning has been used to analyse acoustic data to predict when an earthquake will occur, long before it does, so that plenty of warning time can be given – it’s incredible what machine learning can do,” explained co-author Professor Sir Colin Humphreys of Cambridge’s Department of Materials Science & Metallurgy.