Forecasting Earthquakes With AI

December 8, 2024

In 2023, researchers at the Bureau of Economic Geology won first place in an international earthquake forecasting competition, with their methods correctly predicting 70% of earthquakes a week before they happened during a seven-month trial in China. A year later, the Bulletin of the Seismological Society of America published their findings as a case study, providing details on the artificial intelligence (AI) algorithm.

Bureau seismologist Yangkang Chen is the AI’s lead developer. He and collaborators trained it to detect statistical bumps in real-time seismic data that researchers had paired with previous earthquakes. The outcome was a weekly forecast that successfully predicted 14 earthquakes within about 200 miles of where it estimated they would happen and at almost exactly the calculated strength. It missed one earthquake and gave eight false warnings.

It’s not yet known if the approach will work at other locations, but the effort is a milestone in research for AI-driven earthquake forecasting, with the bureau’s AI coming in first out of 600 designs. The researchers plan to test the AI in Texas, since the state experiences a high rate of minor-to-moderate-magnitude earthquakes. The bureau’s TexNet hosts 300 seismic stations and more than six years of continuous records, which makes the state an ideal location to verify the method.

The researchers want to integrate the system with physics-based models, which could be important where data is poor, or places where the last major earthquake happened hundreds of years before seismographs were invented. “Our future goal is to combine both physics and data-driven methods to give us something generalized, like ChatGPT, that we can apply to anywhere in the world,” Chen said.