Skip to main content

Today, A.I. helps detect tiny earthquakes. Tomorrow, it might predict the big one

Earthquakes are notoriously difficult to predict. Even major quakes often occur with little warning. Meanwhile, there are many hundreds of thousands of smaller earthquakes that humans rarely ever feel but are occasionally detected on seismographs.

Now, researchers from Harvard University and the Massachusetts Institute of Technology have developed an artificial intelligence (A.I.) neural network to better help detect earthquakes of all sizes. In a recent study published in the journal Science Advances, the A.I.system was shown to be more accurate than current methods, and may help bring seismologists closer to the elusive goal of earthquake prediction.

Recommended Videos

The paper’s focus is on earthquakes in Oklahoma, a previously seismically inactive state that has become increasingly more active over the past decade due in part to the wastewater disposal practices of the fracking industry. Since Oklahomans have never really had to worry about earthquakes, the state is ill-equipped to detect and locate them.

Please enable Javascript to view this content

“One way we usually locate earthquakes is by using multiple stations and triangulation, just like GPS,” Thibaut Perol, an A.I. researcher at Harvard and one of the authors of the study, told Digital Trends. “But in that region of Oklahoma, which has only been active seismically for a short amount of time, there aren’t a lot of seismic stations that would allow you to do triangulation. What we’ve done is to allow someone to locate an earthquake using only a single station.”

The trick used by Perol and his team was to increase the sensitivity of Oklahoma’s sparse seismographs, using a convolutional neural network to filter through the noise associated with the Earth’s goings-on — from human activity like traffic to the vibrations created by wind and waves. To do this, they fed the A.I. data on regions that are seismically inactive, enabling the system to identify ambient noise that’s not the result of tremors. By being able to identify this ambient noise, the system can then better pick up on the importance stuff — i.e., earthquakes.

Perol compared this to voice-recognition software, such as Siri’s ability to recognize a command amid a bunch of background noise.

“What we’ve done is to allow someone to locate an earthquake using only a single station,” he said. “We have trained the A.I … to detect, in real time, earthquakes of whatever magnitude.”

The researchers hope to deploy this technology more widely in Oklahoma, to help seismologists detect quakes and pinpoint their cause. And by better understanding earthquakes, including their precise location and cause, they hope to someday develop a system that can predict an earthquake well before it happens.

Dyllan Furness
Former Digital Trends Contributor
Dyllan Furness is a freelance writer from Florida. He covers strange science and emerging tech for Digital Trends, focusing…
Hyundai Ioniq 5 sets world record for greatest altitude change
hyundai ioniq 5 world record altitude change mk02 detail kv

When the Guinness World Records (GWR) book was launched in 1955, the idea was to compile facts and figures that could finally settle often endless arguments in the U.K.’s many pubs.

It quickly evolved into a yearly compilation of world records, big and small, including last year's largest grilled cheese sandwich in the world.

Read more
Global EV sales expected to rise 30% in 2025, S&P Global says
ev sales up 30 percent 2025 byd sealion 7 1stbanner l

While trade wars, tariffs, and wavering subsidies are very much in the cards for the auto industry in 2025, global sales of electric vehicles (EVs) are still expected to rise substantially next year, according to S&P Global Mobility.

"2025 is shaping up to be ultra-challenging for the auto industry, as key regional demand factors limit demand potential and the new U.S. administration adds fresh uncertainty from day one," says Colin Couchman, executive director of global light vehicle forecasting for S&P Global Mobility.

Read more
Faraday Future could unveil lowest-priced EV yet at CES 2025
Faraday Future FF 91

Given existing tariffs and what’s in store from the Trump administration, you’d be forgiven for thinking the global race toward lower electric vehicle (EV) prices will not reach U.S. shores in 2025.

After all, Chinese manufacturers, who sell the least expensive EVs globally, have shelved plans to enter the U.S. market after 100% tariffs were imposed on China-made EVs in September.

Read more