New AI technology can predict tsunami impacts in less than a second

[ad_1]

‘The main advantage of our method is the speed of predictions, which is crucial for early warning,’ explained Iyan Mulia, project manager and scientist at RIKEN.

‘Conventional tsunami modeling predicts after 30 minutes, which is too late. But our model can predict in seconds.’

150 offshore stations

To achieve this, the coast now boasts the world’s largest network of sensors for monitoring the movement of the ocean floor. About 150 offshore stations make up this network and work together to provide early warnings in the event of a tsunami.

To work effectively, however, the data generated by the sensors must be converted into tsunami heights and extents along the coast.

This normally requires solving difficult non-linear equations, which can take around 30 minutes on a standard computer. Needless to say, this doesn’t give people enough time to evacuate.

Tsunamis are devastating natural disasters.

That’s why the RIKEN AI model is so crucial to saving lives. It allows people to have at least a half hour head start from where the tsunami will hit.

The RIKEN team trained their machine learning system using more than 3,000 computer-generated tsunami events and tested it with another 480 tsunami scenarios and three real tsunamis.

Accurate for any urgent disaster

They found that their machine learning-based model could achieve comparable accuracy with only one percent of the computational effort of conventional approaches. Now, they say their model could work for any time-sensitive natural disaster.

“The sky is the limit. You can apply this method to any type of disaster forecasting where the time constraint is very limited,” Mulia added.

[ad_2]