KAWASAKI—Fujitsu Ltd. is using the Fugaku supercomputer and artificial intelligence (AI) technology to develop a smartphone app that can provide real-time countdowns on when the earthquake-triggered tsunami will inundate specific areas.
In mid-March, the Tokyo-based IT giant tested its flood forecasting app during a tsunami evacuation drill at a coastal area in Kawasaki’s Kawasaki Ward.
Members of a neighborhood association and other residents who had installed the application joined in the exercise. They often looked at their smartphones as they made their way to an evacuation site at a high school.
The app on their screens displayed different colors for estimated wave arrival times and tsunami height.
The locations of the smartphone user and other participants were displayed on the map. It also showed whether people had been left behind in danger zones.
“It looks realistic because (the map) shows, for example, how many minutes are left before the tsunami hits the blue areas,” said Masayuki Suyama, 75, head of the Fujisaki neighborhood association.
Fujitsu worked with the city government of Kawasaki to test the app.
The company collaborated with Tohoku University and the University of Tokyo on tsunami flood prediction technology using the Fugaku supercomputer and an AI model.
Project members used Fugaku, one of the world’s fastest supercomputers in terms of computing speed, to run simulations of tens of thousands of scenarios. “Training data” was created to predict flooded areas based on offshore waveforms. The AI model then learned the data.
After actual earthquakes, tsunami waveform data collected by the Ministry of Lands, Infrastructure, Transport and Tourism and related organizations is entered into the computers of municipal governments and other institutions.
The trained AI model can generate flood forecasts on these computer systems and send the forecast information to smartphones in each area within seconds.
During the flood simulation phase, the AI model also incorporates data regarding terrain, buildings, and road conditions based on information provided by the Geospatial Information Authority of Japan and others. entities.
The system can provide high-resolution tsunami inundation forecasts in units of 3 by 3 meters, Fujitsu said.
After the Greater East Japan earthquake on March 11, 2011, residents of coastal areas in the Tohoku region had to rely on announcements from the Japan Meteorological Agency (JMA) for heights and arrival times. estimated tsunamis.
But the actual arrival times differed widely from place to place.
Many people died after mistakenly thinking that the tsunami hazard had ended when the estimated time of arrival had passed or the waves would not reach their location.
Japan’s tsunami observation network has since been strengthened, and supercomputer and AI capabilities have improved significantly.
Smartphones equipped with location information functions are now widely available.
“We aim to build a system that will allow everyone to escape (tsunami),” said Yusuke Oishi, 43, a Fujitsu researcher on the development team.
STILL LIMITED COVERAGE AREA
However, a number of challenges need to be overcome to put the application into practice.
Under the Meteorological Services Act, business operators must obtain permission from the government to provide tsunami forecast information.
According to the JMA, operators are prohibited from broadcasting flood forecasts to an unspecified number of people to avoid confusion caused by data that may conflict with warnings issued by the agency.
Unforeseen events and measurement errors are always a risk during natural disasters. App users could mistakenly assume that they are out of harm’s way based on the locations shown on an app’s map.
For these reasons, only those informed in advance of forecast uncertainty will receive detailed flood information via the Fujitsu app.
They include members of neighborhood associations in charge of disaster preparedness and volunteer firefighters, who will use the app to call for evacuations.
“In light of the results of the trial, we want to continue thinking about how to provide information and to whom,” a Fujitsu representative said.
The prefectural governments of Wakayama and Mie have jointly developed a tsunami flood forecasting system using an observation network set up on the seabed by the Japan Agency for Marine and Earth Science and Technology (JAMSTEC).
The two prefectures have obtained the approval of forecasting services. But their clients are limited to municipal governments along the coast and other officials.
Individual users were excluded.