Fujitsu develops application for tsunami forecasting system

For the past year, Fujitsu has been developing a tsunami forecasting system using supercomputers and AI to try to identify areas at risk of flooding. Fujitsu is pushing its developments further and is now developing an app that will warn users in dangerous areas to seek safety. What challenges do tsunamis present, what has Fujitsu been working on, and what other natural disaster warnings could be broadcast to user devices?

What challenges do tsunamis present?

Any coastal area near a fault line (where two tectonic plates meet) is at risk of damage from a tsunami, an undersea earthquake causing a swell of water that rushes inland lands. Unlike tidal waves (caused by tides and wind), a tsunami is a large mass of displaced water that moves inland with incredible force and can penetrate inland for many kilometers.

A convenient analogy of the difference between the two is that a tidal wave is akin to splashing in a bathtub, while a tsunami is a sudden change in water level after entering a bath. Splashing is annoying and absorbs whatever it hits, but suddenly stepping into the tub sees huge amounts of water splash out and travel extremely far away.

Thus, tsunamis are problematic as they can easily overwhelm coastal defense, have the strength to tear down buildings and trees and travel far inland, causing widespread flooding and infrastructure damage. Worse still, there are very few warnings of an incoming tsunami, because even though submarine earthquakes can be detected, it is not so easy to detect significant changes in wave height far; it is only when a tsunami approaches a shore that the severity of the wave can be observed.

Once a tsunami hits, it can be extremely difficult to alert those in the path of the tsunami and even more difficult to determine the areas most at risk. As such, the general advice where tsunamis strike is to seek high ground wherever you are, turn off all utilities, and if the wave is about to strike, grab hold of anything that is solid (like a post, tree, or concrete). pillar).

Fujitsu Announces Development of Tsunami Early Warning App

Last year, Fujitsu announced that it used a supercomputer and AI to develop a flood prediction system in hopes of providing early warning capabilities to those in vulnerable areas. Simply put, the AI ​​is trained with historical earthquake and tsunami data to predict incoming tsunami wave heights, then combines that data with realistic geological models to identify how the tsunami wave will move at inland and determine which areas are at risk of flooding.

Today, after a year of development, Fujitsu has announced that it is working on an application which it says will notify users of flooding in their area and when an impending tsunami is expected to strike. Last March, Fujitsu announced that it was able to test its flood forecasting application during a tsunami evacuation drill in Kawasaki. Selected members of the public were invited to install the app on their devices, and they were able to see the number of minutes until the tsunami hit specific areas (shaded by blue squares).

But not only does the app tell users the estimated arrival time of the tsunami, it can also alert local authorities and organizations if people have been left behind in dangerous areas. For example, a hospital for the elderly in a dangerous area may have patients who were unable to call for help, and the app would allow authorities to locate them.

Although initial trials of the app show promising results, it still faces many challenges. One is that forecasting tsunamis requires government permission to be shared with the public due to potential loss of life. As such, the app cannot be released to the public, even in beta, which means it is difficult to test the app on a large scale.

What other natural disasters could early warning apps detect?

Tsunamis are devastating but not only natural disaster that could benefit from applications and predictive modeling. An excellent use of these applications would be the prediction of the spread of forest fires; they are difficult to control and predict as they spread to any combustible material within easy reach. But they are also highly dependent on prevailing winds and will often follow the direction of the wind. As such, it may be possible to provide early warning systems that identify key wildfire prone areas and, if a wildfire is detected, determine the extent of damage that can be expected. It could then alert those in the path of the fire when it could reach them and suggest escape routes depending on the wind.

Another example of a natural disaster warning app would be tornado prediction. Although news alerts exist for tornadoes, it would be more beneficial to alert people via an app on a smartphone if they are in a predicted danger zone. Because tornadoes can strike unpredictably, giving people precious moments to prepare, whether fortifying a home or evacuating, could be vital.

Overall, natural disasters are virtually unstoppableand when they do happen, even a few moments of warning can mean the difference between life and death.

Comments are closed.