In 2004, one of the deadliest natural disasters in human history - a tsunami that struck Asia and killed more than 200,000 people - took the majority of victims by surprise. Even a few minutes of advanced warning could have saved thousands of lives.

Despite everything scientists learned from this tsunami, there's still great fear that a similar event could strike again. And without an advanced warning system to provide locals with enough lead time, hundreds of thousands of lives could once again be lost.

Is Artificial Intelligence The Answer?

A research article released in Physics of Fluids reveals the development of an early warning system that combines "state-of-the-art acoustic technology with AI [artificial intelligence] to immediately classify earthquakes and determine potential tsunami risk."

"Tsunamis can be highly destructive events causing huge loss of life and devastating coastal areas, resulting in significant social and economic impacts as whole infrastructures are wiped out," said study co-author Usama Kadri of Cardiff University in Wales.

According to the study, audio data gathered from submerged listening devices, known as hydrophones, were used to quantify the acoustic emissions generated by 200 seismic events that transpired in the Pacific and Indian oceans.

"Our study demonstrates how to obtain fast and reliable information about the size and scale of tsunamis by monitoring acoustic-gravity waves, which travel through the water much faster than tsunami waves, enabling more time for evacuation of locations before landfall," Kadri said.

While there are warning systems in place, they rely heavily on earthquake magnitude and location. Both are important factors, but they also have the potential to result in false alarms. They lean more toward conservative than reliable.

The new advanced AI-powered machine-learning model can analyze hydrophone data within a few seconds on a standard computer.

This research study shows that AI has the potential to prevent tsunamis from causing extreme loss of life. But the new technology won't stand alone. Instead, it will be used alongside existing warning systems.