New research developed in the US could help save lives before an earthquake strikes.
Marine Denolle, assistant professor of Earth and planetary sciences at Harvard, has co-authored a study that uses computer-learning algorithms to identify the small earthquakes otherwise hidden in the seismic data.
"The signals of these smaller earthquakes are buried in that background noise," she told the Harvard Gazette.
"This is really about signal detection. That's why deep-learning techniques are useful - because you can extract features from the noise."
Ms Denolle's learning algorithm is two or three orders of magnitude better at detecting earthquakes than conventional methods.
She wants to use her research to identify and locate the quakes as they happen for early warning systems - and the next step will be testing the algorithm on volcanoes.
"This is level one. We need to detect earthquakes to understand what's going on in the Earth," Ms Denolle told the Harvard Gazette.
"Looking at these smaller events might tell us something about bigger events... so this is fundamental."