Khaberni - A small earthquake shook the city of Califatria in the state of California, USA, in the early hours of January 1, 2008.
It had a magnitude of only -0.53 on the Richter scale, weaker than the vibration of a passing truck, and nobody felt it. Despite its small size, scientists accurately detected it, thanks to artificial intelligence.
Artificial intelligence has completely transformed the field of seismology, as it is now able to detect very small earthquakes automatically and rapidly, a task that previously required human analysts and specialized equipment, according to a report published on "arstechnica" and reviewed by "Al Arabiya Business".
Kyle Bradley, one of the authors of the Earthquake Insights newsletter, said: "Adopting these technologies is like wearing glasses for the first time... suddenly you see small details you couldn’t before."
From wave analysis to deep learning
In the past, earthquake monitoring depended on human analysts reading data from vibration-measuring devices (seismometers), then traditional algorithms appeared that allowed for partial automation of this task.
But the problem has always been with small earthquakes, which get lost amid the daily noise in cities.
Here is where artificial intelligence, especially a model called Earthquake Transformer developed by researchers from Stanford University in 2020, plays a role.
This model relies on the same ideas used in image or sound recognition, but instead of analyzing pixels, it analyzes ground vibrations over time.
This model can distinguish different types of seismic waves (P and S) and pinpoint their start time with extreme accuracy.
Thanks to these models, monitoring devices are now able to detect a greater number of small earthquakes, much more than what was previously detected.
Joe Burns, a professor of geology at the University of Texas, said: "It has been a real revolution... but it is a revolution that is still ongoing."
This technology has contributed to creating accurate maps of the Earth's interior and volcanoes. In 2022, researchers from Hawaii used artificial intelligence data to confirm the existence of a hidden magma channel connecting the Mauna Loa volcano and the deep Bahala area, a discovery that had long been debated among scientists.
Earthquake prediction
Despite the huge success in monitoring and analysis, predicting earthquakes before they occur remains out of reach.
Today, artificial intelligence is used to improve understanding of seismic activity patterns, but it has not yet reached the stage of being able to determine the timing of the next earthquake accurately.
Scientists believe that this step is just the beginning, as deep learning technologies have changed the way images and speech are understood, and they may soon open the door to a new generation of early warning systems for earthquakes.
