AI erupts with revelation of 54,000 hidden earthquakes in Italy’s volcanic region

Researchers at Stanford University have used artificial intelligence to uncover four times as many earthquakes in Italy’s Campi Flegrei volcanic region than previously detected, revealing critical seismic data for an area home to 500,000 people. The AI-powered analysis identified over 54,000 earthquakes from January 2022 to March 2024—compared to the 12,000 previously tracked—and revealed two major fault lines converging beneath the town of Pozzuoli, suggesting the potential for magnitude 5 earthquakes.

Why this matters: The enhanced earthquake detection capabilities could fundamentally change how officials prepare for and respond to seismic threats in one of Europe’s most densely populated volcanic regions.

• “One of the biggest concerns in the short term in Campi Flegrei is not an eruption, but a moderate earthquake at shallow depth,” says Greg Beroza, a geophysics professor at Stanford University and the study’s co-author.
• The region has already recorded 5 earthquakes above magnitude 4 in the first 8 months of this year, indicating significantly increased seismic activity.

How the AI works: The Stanford-designed machine learning model functions similarly to how a camera lens adjusts to bring objects into focus, identifying precise earthquake locations and magnitudes from massive seismic datasets.

• The technology can pinpoint earthquake data that previous tools couldn’t extract from complex seismic information.
• When scientists have access to more accurate earthquake data, including fault locations and lengths, they can better determine the range of magnitudes for future earthquakes.

Key discoveries: The AI analysis revealed previously hidden geological structures that explain decades of seismic risk in the region.

• Two major faults were discovered converging under Pozzuoli, west of Naples.
• The model clearly mapped a ring fault system around the caldera’s edge—the depression created by volcanic eruptions 39,000 and 15,000 years ago.
• “We’ve known that this is a risky place for a long time, since the ’80s when part of the city was evacuated, and now we’re seeing for the first time the geologic structures that are responsible,” says Bill Ellsworth, co-director of the Stanford Centre for Induced and Triggered Seismicity.

What they’re saying: Italian researchers were surprised by the clarity of the newly revealed fault structures.

• “Our Italian colleagues were surprised to see the ring so clearly,” said lead study author Xing Tan, a geophysics PhD student in Beroza’s lab.
• “They expected to see something in the south where previous data had revealed scattered seismicity, but in the north, they’d never seen it so clearly.”
• “These long faults suggest that an earthquake in the magnitude 5 range is not out of the question,” Ellsworth noted.

Broader applications: The researchers believe this AI model could be deployed in other earthquake-prone volcanic regions to improve early warning systems.

• The technology could help pinpoint seismic activity locations in areas like Santorini, Greece, potentially enabling earlier evacuations and saving lives.
• Italy’s National Institute of Geophysics and Volcanology is now running the tool independently for ongoing scientific and public safety responses.

The big picture: While the AI found no evidence of upward magma migration—reducing short-term eruption concerns—the enhanced seismic monitoring provides crucial data for protecting half a million residents in an increasingly active volcanic region.

• “Seismicity could change at any time, and that may be the most important thing about this study: this capability of getting a clear view is now operational,” Beroza explains.