New technology can predict tsunami impacts in seconds

Japan is one of the most vulnerable countries to disasters weather events such as hurricanes, earthquakes and tsunamis. In 2011, the northeast region of the country was hit by a tsunami with catastrophic impacts, which claimed the lives of more than 18,000 people. Since the incident, Japan has directed efforts to prevent something similar from happening in the future.

Asian tech predicts tsunamis

New research by the RIKEN Prediction Science Laboratory has used artificial intelligence to correctly predict the impacts produced by tsunamis in less than a second. At least that's what a statement made by the institution points out.

Among the information disclosed, the leader of the work and scientist Iyan Mulia said that: "The biggest advantage of our method is the speed of predictions, which is crucial for an early warning". He also pointed out that: “Traditionally, predictions are provided after 30 minutes, which is too late, but our model can make predictions within seconds.”

To make this possible, they had to install the largest sensor network available to monitor seafloor movement. Around 150 stations at sea interconnect this network, working together to warn the team in advance about the risks of the presence of such a phenomenon.

In order for everything to work correctly, the data generated by the sensors needs to be converted into tsunami heights and spread across entire coastline, which typically involves solving complex nonlinear equations, which can take about 30 minutes on a computer common.

More than that, it does not allow people to evacuate the site in a timely manner.

This just highlights the importance of RIKEN's new artificial intelligence model. Its personnel trained the machine learning with more than 3,000 computer-generated tsunami events, which has already been tested in another 480 situations of the phenomenon and in three that actually materialized.

In this way, people get at least a 30-minute head start to evacuate risk, compared to the old weather catastrophe forecasting and warning method.

Lover of movies and series and everything that involves cinema. An active curious on the networks, always connected to information about the web.