Scientists are developing a new system to enhance tsunami warning and prevention capabilities with advanced algorithms. 

Scientists at Cardiff University have developed an early warning system that utilises artificial intelligence (AI) to detect tsunamis and underwater earthquakes. 

The team has combined the use of underwater microphones with AI to monitor the movement of tectonic plates in real time. This technology has enabled experts to detect over 200 earthquakes 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. [They] travel through the water much faster than tsunami waves, enabling more time for evacuation of locations before landfall,”  Dr. Usama Kadri, co-author and senior lecturer in Applied Mathematics at Cardiff University, told Sky News. 

How it works

Acoustic-gravity waves, which are sound waves that move through the deep ocean at the speed of sound, can be generated by underwater earthquakes, explosions, and landslides, all of which can cause devastating tsunamis. 

The new system combines the use of underwater microphones or hydrophones, recordings, and a “computational model” to triangulate the source of the tectonic event even thousands of kilometres away.

According to Dr. Kadri, the current setup comprises 11 hydrophones worldwide, and with 24 of them, the entire globe could be monitored. Conventional warning systems rely on waves reaching sea buoys and seismic sensors to trigger tsunami warnings, which gives little time for evacuation. 

In a situation where a few minutes can make the difference between life and death, these warning systems are not always accurate in predicting the danger posed by tsunamis.

According to Kadri, the current warning system for tsunamis does not calculate in real-time and lacks the necessary tools to measure the scale of a tsunami. Furthermore, due to the proximity of buoys to the shore, the current system often triggers too late to provide adequate warning. 

In the hypothetical case of the 2004 Sri Lanka tsunami, the team’s new system could have given people 65 minutes to evacuate, potentially saving countless lives. 

The expert, however, was surprised by the speed of the calculations, which take only about 17 seconds once the wave hits the hydrophones. The new system is designed to work alongside existing systems as a checks and balances mechanism and can classify an earthquake’s ‘slip type’ and magnitude, as well as analyse its properties to determine the actual size of the tsunami.

The team has been working with the UNESCO oceanographic commission to explore opportunities for using the technology in disaster prevention, with Portugal expressing particular interest. False alarms could have a significant financial impact, and the team’s aim is to enhance natural hazard warning systems globally.

The findings of their work were published in the Physics of Fluid on 25 April.