Machine-Learning Algorithm Predicts Laboratory Earthquakes
MIT Technology Review reported a breakthrough that raises the possibility that real earthquake prediction could be on the horizon. The team is cautious about the new technique’s utility for real earthquakes, but the work opens up new avenues of research in this area.
Bertrand Rouet-Leduc at Los Alamos National Laboratory led a team that trained a machine-learning algorithm to spot the tell-tale signs in a laboratory earthquake simulator. Using recorded acoustic emissions from experimental system that follows the Gutenberg-Richter distribution were fed into a ML algorithm.
To their astonishment, the algorithm gave accurate predictions even when an earthquake’s probability was not imminent under existing models. “We show that by listening to the acoustic signal emitted by a laboratory fault, machine learning can predict the time remaining before it fails with great accuracy,”.