Australia: Bushfire ready, thanks to artificial intelligence

Source(s): Royal Melbourne Institute of Technology

During the chaos of a bushfire, people can be unpredictable. But a new artificial intelligence program developed by RMIT is helping communities plan for big evacuations.

While the program has been developed over many years of research, it was a gift from the Telematics Trust that enabled researchers to turn it into something suitable for practical application. 

Artificial Intelligence Professor and Associate Dean, Computer Science and Software Engineering, Lin Padgham, explains how it could save lives: 

Prior to the big bushfires in 2009, Australia didn’t always recommend evacuations – the policy was ‘stay and defend’.
“After people died on Black Saturday that changed, but the services knew nothing about how to evacuate people or how long it takes.

“We wanted to build a planning tool to understand how evacuations of large areas work in a situation where you need to get a lot of people out quickly.  

“The software uses a simulation where you model all the individuals and then we also model the decision making of the individuals.

“If you tell people, ‘it’s time to leave now’, they’re not going to do that while their kids are at school, or if they haven’t assembled the family, or they need to check on a close relative. 

People will never do exactly what you tell them, so you need to allow for that.

“We simulate an evacuation where we block off roads or model car accidents – to get a picture of the sort of things that can happen. You can also see the cars moving, where they’re backing up, getting into traffic jams.

“That’s been very useful to show communities why it’s important they actually plan as a community ahead of time.

“The Telematics grant has enabled us to take five years of research and actually start to turn it into something that the community and Mount Alexander Shire can really use – because research only gets you so far.

“And then of course it throws up new research questions that are based on the actual need of the users.  So we’re not just thinking about what we think the research questions are, they’re really advising out of the needs of the community.

“It’s very much informing policy at that local council level and we’re hoping to get funding to take it to the next level, so it can be used across the whole of Victoria – or even the whole of Australia.”
 

 

Explore further

Hazards Wildfire
Share this

Please note: Content is displayed as last posted by a PreventionWeb community member or editor. The views expressed therein are not necessarily those of UNDRR, PreventionWeb, or its sponsors. See our terms of use

Is this page useful?

Yes No Report an issue on this page

Thank you. If you have 2 minutes, we would benefit from additional feedback (link opens in a new window).