Fujitsu and Partners Leverage Fugaku Supercomputer and AI Technology to Predict Tsunami-Related Evacuations in Kawasaki City

TOKYO, March 3, 2022 – The International Institute for Research in Disaster Science (IRIDES) at Tohoku University, the Institute for Earthquake Research at the University of Tokyo, Fujitsu and the City of Kawasaki (1) today announced plans to conduct an AI field trial that is built on the world’s fastest supercomputer, Japan’s Fugaku(2), and provides high-resolution, real-time predictions of Tsunami flooding to support safe and efficient evacuations during disaster prevention drills in Kawasaki, Japan on Saturday March 12, 2022.

Figure 1: Image of the dedicated application (Japanese and English versions under development)
Figure 2: Image of the community evacuation process

During this field trial, participants from the surrounding community will be notified of the arrival time and inundation height of an expected tsunami through a special smartphone app developed by Fujitsu. The exercise aims to identify the most effective ways to use technology to help local communities share information among residents and avoid instances where people are left behind during evacuations.

This project represents the final stage of an ongoing initiative between the parties. As part of a framework agreement signed between Kawasaki City and Fujitsu in 2014 to promote the creation of sustainable communities(3), the four parties have engaged in R&D activities within the framework of the “Joint Project Aiming for Tsunami Disaster Risk Reduction Using ICT in the Kawasaki Coastal Area” since 2017. By verifying the effectiveness of information sharing among field trial participants through the app, the parties aim to further promote the practical use of mitigation methodologies. that leverage the capabilities of AI, high performance computing (HPC), and communication technologies for tsunami flood forecasting, ultimately contributing to the realization of a safer society.


Recent years have seen the development of several different technologies for real-time predictions of tsunami flooding that utilize the capabilities of high-speed supercomputers and AI. However, barriers to the practical deployment of these technologies remain, including how to share relevant information inclusively but effectively with the public, taking into account individual user differences and different levels of digital literacy.

The four parties aim to address some of these challenges by conducting a field trial to test the technology with actual residents of the community under circumstances that replicate the uncertainty of an actual disaster, including the possibility that information from prediction of the AI ​​themselves are not 100%. certain.

Overview of the field trial

Date: March 12, 2022 (Saturday) from 8:15 a.m. to 11:15 a.m. JST (held together with the comprehensive disaster prevention exercises in the Kawasaki district)

Location: Kawasaki Municipal Kawanakajima Junior High School and surrounding areas (Kawasaki Ward, Kawasaki City)

Participants: residents and members of the project

Overview: Field trial to verify evacuation effectiveness using AI(4) tsunami flood forecast data – this data will be fed to a dedicated app developed by Fujitsu, which residents and organizers will refer to in real time during an evacuation simulation. The field trial will be conducted under the supervision and guidance of Professor Fumihiko Imamura, Director of the International Research Institute for Disaster Science at Tohoku University and Professor Takashi Furumura at the Institute for Disaster Research. the University of Tokyo earthquakes.

Multiple participants informed before the field trial (including the possibility that the AI ​​forecast information is not 100% certain) will act as disaster information leaders and receive detailed information, including the estimated time of arrival and the inundation height of the tsunami. Other attendees will receive a text message on the app that the AI ​​has predicted flooding for their location.

During evacuation, disaster information officers can check the current location of participants in the same community and alert those who are behind in evacuation using the app’s messaging feature.

The field trial will be followed by an online disaster prevention course, during which participants’ evacuation actions will be reviewed.

About the app

The application has two display modes. The first is a detailed mode, in which AI-generated flood forecast data is displayed on a map in different colors corresponding to the arrival time and flood height of the incoming tsunami. The second mode is a simple display that only shows a text message warning users of a certain area of ​​the predicted tsunami flood. The app also includes a messaging feature that allows users to check the location of other community members on a map and help each other communicate and congregate safely during the evacuation. Users can additionally post and share information about points along escape routes that are believed to be damaged and difficult to pass (a feature that has been validated in previous field trials(5)) and also share information in real time on the number of people who managed to evacuate and gather in evacuation centers.

Future plans

Based on feedback from field trial participants, the four parties will further investigate methods of transmitting and using AI disaster prediction to achieve safer and more efficient community evacuation and promote the use and practical application of AI to support disaster mitigation measures. and contribute to the achievement of safer local communities.

(1) City of Kawasaki:city ​​located in Kanagawa Prefecture, Japan; Mayor: Norihiko Fukuda

(2) An AI built on the fastest supercomputer in the world, the Japanese Fugaku:This AI was built using Fugaku supercomputer computing resources provided by the RIKEN Center for Computational Science under the HPCI System Research Project (Project ID: hp210220).

(3) a framework agreement signed between Kawasaki City and Fujitsu in 2014 to foster the creation of sustainable communities:In June 2021, Kawasaki City and Fujitsu further strengthened their collaboration to promote various initiatives using state-of-the-art digital technology, focusing on the four priority themes of “health”, “safety and security”, “environment” and “work and life” that will further increase the value of communities by making them more livable.“Fujitsu and the City of Kawasaki Strengthen Cooperation to Create a Sustainable ‘City of the Future'”

(4) AI Tsunami Flood Forecast Data:Permission from the Japan Meteorological Agency (JMA) based on the Meteorological Service Law is required when the actual tsunami forecast is issued by an organization other than JMA.

(5) preliminary field tests:From 2018 to 2020, the four parties conducted experiments to achieve tsunami evacuation using smartphone apps.“Fujitsu Leverages AI Technology in Joint Project to Help Safely Evacuate Kawasaki Tsunami”“Fujitsu Optimizes Evacuation Center Management to Mitigate COVID-19 Risk with AI in Joint Field Trial in Kawasaki City”

About Fujitsu

Fujitsu is the Japanese leader in information and communication technologies (ICT) offering a complete range of technological products, solutions and services. Around 126,000 Fujitsu people support customers in more than 100 countries. We use our experience and the power of ICT to shape the future of society together with our customers. Fujitsu Limited (TSE:6702) reported consolidated revenue of 3.6 trillion yen ($34 billion) for the fiscal year ended March 31, 2021. For more information, see

Source: Fujitsu

Comments are closed.