Earthquake-predicting tool driven by AI shows 70 per cent accuracy, new research reveals

An AI-driven tool was 70 per cent accurate in predicting earthquakes a week before they happened during a seven-month trial in China, scientists report.

The outcome was a weekly forecast in which the AI successfully predicted 14 earthquakes within about 200 miles, or 320 kilometres, of where it estimated they would happen and at almost exactly the calculated strength, the researchers at The University of Texas (UT) at Austin, US, said.

The AI-tool, however, missed one earthquake and gave eight false warnings, they reported.

The AI was trained to detect statistical bumps in real-time seismic data that researchers had paired with previous earthquakes, they said, adding that the method follows a relatively simple machine learning approach. Their study is published in the journal Bulletin of the Seismological Society of America.

The AI was given a set of statistical features based on the team's knowledge of earthquake physics, then told to train itself on a five-year database of seismic recordings.

Once trained, the AI gave its forecast by listening for signs of incoming earthquakes among the background rumblings in the Earth, the researchers said in their study.

While it is not yet known if the same approach will work at other locations, but the researchers are confident that in places with robust seismic tracking networks such as California, Italy, Japan, Greece, Turkey and Texas, the AI could improve its success rate and narrow its predictions to within a few tens of miles.

The findings of this study, however, are a milestone in research for AI-driven earthquake forecasting, the researchers said.

"Predicting earthquakes is the holy grail," said Sergey Fomel, a professor in UT's Bureau of Economic Geology and a member of the research team. "We're not yet close to making predictions for anywhere in the world, but what we achieved tells us that what we thought was an impossible problem is solvable in principle. You don't see earthquakes coming," said Alexandros Savvaidis, a senior research scientist who leads the bureau's Texas Seismological Network Program (TexNet) - the state's seismic network.

"It's a matter of milliseconds, and the only thing you can control is how prepared you are. Even with 70 per cent, that's a huge result and could help minimise economic and human losses and has the potential to dramatically improve earthquake preparedness worldwide," said Savvaidis.

The trial was part of an international competition held in China in which the UT-developed AI came first out of 600 other designs. UT's entry was led by bureau seismologist and the AI's lead developer, Yangkang Chen.

"Our future goal is to combine both physics and data-driven methods to give us something generalised, like chatGPT, that we can apply to anywhere in the world," said Chen.