The latest in earthquake detection? Artificial intelligence
An AI in Oklahoma detected 17 times more earthquakes than recorded in the Geological Survey earthquake catalog. Image: REUTERS/Issei Kato
Get involved with our crowdsourced digital platform to deliver impact at scale
Stay up to date:
Artificial Intelligence
Detecting earthquakes
Earthquakes are a lot more common than people may think. Each year, Southern California alone experiences roughly 10,000 earthquakes, and they’re happening more frequently in the central United States, possibly due to wastewater injection.
While we may not feel a large percentage of these earthquakes, it’s important that we understand them. This knowledge could help us determine what’s causing earthquakes and possibly create tools for their prevention.
It could also help us figure out how to predict future earthquakes of all sizes, which will improve how communities respond to earthquakes.
Now, a research team led by deep learning scientist Thibaut Perol has found a way to use artificial intelligence (AI) to improve earthquake detection. Their study was published today in Science Advances.
Innovating with AI
The team named their AI system ConvNetQuake, and it’s the first neural network designed to detect and locate earthquakes. The specialized algorithm can look at ground motion measurements known as seismograms and determine whether or not the seismic activity is just “noise” or an earthquake. Historically, it been very difficult to detect very small earthquakes due to this noise, but ConvNetQuake can make the distinction.
The researchers used the seismic activity in Oklahoma to train and test ConvNetQuake. They found that their system detected 17 times more earthquakes than were recorded in the Oklahoma Geological Survey earthquake catalog.
While this particular study reveals how the system could improve earthquake detection within the central United States, ConvNetQuake could be applied beyond this region. By effectively detecting and categorizing seismic activity, it could provide important information very early on in an earthquake’s “life,” alerting communities as early as possible whether or not an earthquake is picking up steam and how severe it might be.
However, while it is superior to other earthquake detection methods, ConvNetQuake can only detect earthquakes — it can’t predict them. Still, until we can effectively predict earthquakes before they start, early detection is our best hope for preventing the devastation quakes can cause.
Don't miss any update on this topic
Create a free account and access your personalized content collection with our latest publications and analyses.
License and Republishing
World Economic Forum articles may be republished in accordance with the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International Public License, and in accordance with our Terms of Use.
The views expressed in this article are those of the author alone and not the World Economic Forum.
Related topics:
The Agenda Weekly
A weekly update of the most important issues driving the global agenda
You can unsubscribe at any time using the link in our emails. For more details, review our privacy policy.
More on Emerging TechnologiesSee all
David Elliott
October 3, 2024
Mirek Dušek
October 1, 2024
David Elliott
September 30, 2024
Eleonore Pauwels and Steven Vosloo
September 27, 2024
Pooja Chhabria and Chris Hamill-Stewart
September 27, 2024
Emma Charlton
September 27, 2024