AI to lighten the load in the fight against bushfires
Snapping a picture on your next bushwalk could help predict and prevent devastating bushfires, thanks to an innovative new mobile phone app, NOBURN, powered by AI and developed by University of Adelaide experts. Professor Javen Shi, Director of Advanced Reasoning and Learning at the University’s Australian Institute for Machine Learning (AIML), said the app uses AI computer vision to analyse user-submitted photos of fire-prone areas to assess potential bushfire fuel loads. The submitted data is used to estimate the severity of a potential bushfire and how far it could spread.
Shi said the AI models developed for the app mimic the eyes of human experts who would ordinarily be scouring bushland for bushfire hazards. “Once we train the model, we don’t really need experts to go to the forest. We can easily have thousands of citizens — such as bushwalkers and families on camping trips — who can take photos that our AI can use to make predictions,” Shi said.
Collecting quality data from users of NOBURN could take up to 12 months, and another year for the app’s AI model to be trained on the images uploaded from rural areas. However, Shi said the point of the app is to raise awareness for the ways investment in AI can help prevent devastating losses during bushfires.
“The app alone is small, but we hope this is a catalyst to ignite people’s excitement and hope, because we lose millions of dollars every year to fires. We hope to expand this to situational awareness, like a command centre for the bushfire commanders, and they can see in real time their resource deployment, how a bushfire spreads, and we can build AI for them to interact with,” Shi said.
The researchers believe AI could even have a conversation with the commander and the firefighters, to give real-time advice and make them more aware of their surroundings in low-visibility conditions. The idea for the app was sparked after the Black Summer bushfire season of 2019–2020, which burned more than 46 million acres, destroyed more than 9000 properties, claimed 34 lives and cost farmers up to $7 billion in damages.
Shi worked alongside the University of the Sunshine Coast forestry experts Dr Sam Van Holsbeeck and Professor Mark Brown, as well as Director of the Centre for Human Factors and Sociotechnical Systems Professor Paul Salmon, to develop the NOBURN app.
“There’s a huge potential for AI to be leading that game in overall fuel-hazard assessment and again even further into bushfire prediction and simulation modelling as we’ve been attempting with AIML. It’s not just a bushfire research project; it is really like a combination of different fields of discipline coming together and doing this in a way that makes bushfire research accessible to the general public,” Van Holsbeeck said.
A team of researchers has developed a novel, more energy-efficient method for data transmission...
A recovery system developed by scientists enabled the retrieval of data from a NASA mission to...
Researchers have developed a metamaterial-based strategy to combine and transmit multiple light...