Skip to main content

This AI algorithm could save lives in quake zones

An urban area devastated by an earthquake.
Faruk Tokluoğlu/Pexels
Promotional image for Tech For Change. Person standing on solar panel looking at sunset.
This story is part of Tech for Change: an ongoing series in which we shine a spotlight on positive uses of technology, and showcase how they're helping to make the world a better place.

Powerful earthquakes in urban areas can cause a shocking amount of devastation, with lives lost and buildings destroyed. Indeed, more than 60,000 people have already died in such events this year alone.

Ever since scientists discovered what causes these awful catastrophes, they’ve also been trying to predict them in a bid to save lives and reduce damage. But the way in which tectonic plates behave as pressure builds up between them makes the task of forecasting earthquakes incredibly difficult.

Recommended Videos

However, researchers at the University of Texas (UT) recently reported an exciting breakthrough that utilizes an AI-generated algorithm to predict the timing, location, and intensity of an earthquake.

Please enable Javascript to view this content

In trials that took place in China over a period of seven months, the algorithm accurately predicted 70% of earthquakes a whole week before they occurred.

It forecast 14 earthquakes within a 200-mile area of the estimated epicenter and also made a very accurate forecast regarding their intensity, a report on the university’s website said. It failed to warn of just one earthquake and gave eight false predictions.

The research team trained the AI to detect statistical bumps in real-time seismic data that the research team had paired with previous earthquakes, the report explained. Once trained, the AI monitored for signs of approaching earthquakes.

“Predicting earthquakes is the holy grail,” said Sergey Fomel, a professor at UT’s Bureau of Economic Geology and a member of the research team, adding: “What we achieved tells us that what we thought was an impossible problem is solvable in principle.”

The researchers said that by deploying the AI system in locations with effective seismic tracking networks such as California, Italy, Japan, Greece, Turkey, and Texas, it can be trained to increase its success rate and potentially improve its accuracy to within just tens of miles.

Alexandros Savvaidis, a senior research scientist who leads the bureau’s Texas Seismological Network Program, the state’s seismic network, said: “You don’t see earthquakes coming. It’s a matter of milliseconds, and the only thing you can control is how prepared you are. Even with 70%, that’s a huge result and could help minimize economic and human losses and has the potential to dramatically improve earthquake preparedness worldwide.”

Trevor Mogg
Contributing Editor
Not so many moons ago, Trevor moved from one tea-loving island nation that drives on the left (Britain) to another (Japan)…
Security robots could be coming to a school near you
Team 1st Technologies' security robot.

A number of U.S. schools are testing AI-equipped security robots designed to roam the campus around the clock looking for unwanted visitors.

School safety is an ongoing concern for staff, students, and parents, with mass shootings at the extreme end of things to be worried about.

Read more
AI-powered commentary is coming to next month’s Wimbledon
The grounds of the Wimbledon Tennis Championships.

Sports commentators who thought they were safe from the ever-expanding tentacles of generative AI should think again.

In a first for professional tennis, and possibly the entire sports world, this year’s Wimbledon Tennis Championships will deploy an AI-powered commentator for all of its video highlights.

Read more
Amazon deploys AI to summarize product reviews
Laptop on Amazon surrounded by boxes of tech gear.

Amazon has started using artificial intelligence (AI) to generate summaries of reviews for some of its listings.

The idea is that it will speed up the shopping experience for time-pressed customers who don’t want to trawl through endless reviews left by other shoppers.

Read more