Fujitsu leverages AI tech in joint project to contribute to safe tsunami evacuation in Kawasaki
The International Research Institute of Disaster Science at Tohoku University, Earthquake Research Institute at the University of Tokyo, the City of Kawasaki, and Fujitsu Limited have today announced that they will conduct a field trial of AI technology for supporting tsunami evacuations in Kawasaki City on Sunday, November 17th. The four parties have been promoting their Joint Project Aiming for Tsunami Disaster Risk Reduction Using ICT in the Kawasaki Coastal Area since November 2017. The upcoming demonstration will be conducted as a continuation of this project, which most recently included a tsunami evacuation drill conducted with residents of Kawasaki in December 2018.
In the Great East Japan Earthquake on March 11, 2011, overconfidence in existing safety protocols and disaster countermeasures, in combination with insufficient communication of disaster information, partly contributed to substantial delays in evacuation. In some cases, this tragically meant that some residents did not realize that a tsunami would strike their location until it was too late, leaving them unprepared to evacuate. This project seeks to prevent this sort of miscalculation in the future through the innovative use of leading-edge ICT technologies.
To this end, Fujitsu is currently developing a smartphone application that supports the safe and timely evacuation of residents during an earthquake and tsunami disaster－the application relies on purpose-built AI technology to determine the possibility of flooding at the user's current location based on information observed every moment after an earthquake, and displaying the results of the AI on residents' smartphone screens. In this field trial, Fujitsu and its partners will examine how access to this enhanced disaster information on participants' smartphones will impact evacuation behavior. The trial will also determine whether this represents an effective means of providing information during a disaster by giving residents a chance to experience evacuation training firsthand using a prototype of the new smartphone application. Ultimately, this project aims to contribute to strengthening regional disaster prevention capabilities both in Japan and overseas, utilizing the data and knowledge obtained from this and other field trials that involve ICT-enabled disaster prevention measures.
1. Overview of AI for flooding prediction
Fujitsu Laboratories Ltd. has been the main driver in developing new AI technology that predicts the probability of flooding at given locations on land in real-time, based on tsunami waveforms observed offshore and along coastal lines in other regions leading up to when the wave makes landfall (Figure 1). In addition to tsunami warnings and evacuation advisories based on hazard maps, the smartphone app shows users the possibility of flooding in their current location based on AI predictions.
2. Overview of the newly developed evacuation app for smartphones
The Great East Japan Earthquake offers a stark example of the consequences of insufficient information in the wake of a disaster. Some residents in the area struck by the tsunami experienced delays in evacuation measures because they didn't know whether the tsunami would come to where they were when the earthquake struck. To prevent this from happening in the future, the newly developed smartphone app supports residents in making informed evacuation decisions, providing a map that shows their current location as well as safe evacuation sites in their vicinity. The app also displays the risk of flooding at the current location as predicted by AI, and the number of people who have evacuated to nearby shelters (Figure 2). In addition, to contribute to safer evacuations, the developers have included a function that lets evacuees post and share information about obstacles and other danger spots along the evacuation route, which was previously tested in December 2018.