AI & ML News

Fujitsu Develops AI Disaster Mitigation Technology to Predict River Flooding with Limited Data

Fujitsu Limited and Fujitsu Laboratories Ltd. have announced the development of a technology that draws on mathematical models built with limited data on rainfall and water levels to create flooding predictions for rivers. The solution leverages Fujitsu Human Centric AI Zinrai, a comprehensive portfolio that encompasses Fujitsu’s wide range of AI technologies and techniques, and utilizes a model that incorporates insights from hydrology to produce an AI that achieves predictions with greater precision. 

Figure 1: Summary diagram of the river water level prediction AI

The new technology proves effective even for smaller rivers with limited measurement data or for areas where water level sensors have been newly installed and have yet to accumulate sufficient data. These predictions will offer authorities a vital tool for delivering faster response times and mitigating flood damage in the event of a natural disaster, including in dispatching personnel to affected areas and supporting appropriate decision-making in issuing evacuation advisories. 

Figure 2: Example in which AI predicts water level increases during heavy rain from two days’ worth of normal period.

Fujitsu and Fujitsu Laboratories will continue to work to further perfect this technology through a field trial with local governments across Japan with the aim of delivering a commercial solution during fiscal 2019. With the development of this solution, Fujitsu demonstrates how this and other AI technologies will play an important role in bolstering its efforts to combat the effects of climate change, and contribute to the achievement of greater sustainability in society.

Related posts

IIT Bombay partners with ABB India to set up state-of-the-art electrical machines and drives lab

enterpriseitworld

Facial Recognition: Building a Robust Smart Transportation Ecosystem

enterpriseitworld

Tenable Cloud Risk Report Sounds the Alarm on Toxic Cloud Exposures

enterpriseitworld
x