We are creating some awesome events for you. Kindly bear with us.

USC App to Help Citizens Predict Bushfire Severity

Researchers from the University of the Sunshine Coast (USC) have secured an Australian Government Citizen Science Grant of almost $500,000 to design and implement a citizen science app for people living in fire-prone areas to predict the likelihood of bushfires.

The app, called NOBURN (National Bush Fire Resilience Network), will be designed by citizen scientists from around the country, including people who hike, work and camp in forest areas, who will be encouraged to collect vital data in the form of photos and forest fuel samples.

The Citizen Science Grants are awarded for scientific research projects with a national impact that engage the public as citizen scientists and is part of the Inspiring Australia – Science Engagement Program.

The NOBURN project will be led by Professor Mark Brown, Deputy Director of USC’s Forest Research Institute and Professor Paul Salmon, Director of USC’s Centre for Human Factors and Sociotechnical Systems. They will be supported by USC Research Fellow Dr Sam Van Holsbeeck and artificial intelligence (AI) experts at the Australian Institute for Machine Learning (AIML) at the University of Adelaide.

The data gathered would be matched with satellite imagery and used to train AI systems to predict the probability, severity and burn area of potential bushfires.

While naturally occurring bushfires cannot be avoided, there is an opportunity with this project to predict their likelihood and implement strategies to minimise their impact on the environment, property and life.

A range of factors determines the intensity and speed of fires, including fuel load, moisture, ignition source and wind; however, the methods to predict fire events and risk are complex and not easily accessible for residents in bushfire-prone areas.

The NOBURN project will result in new knowledge being shared with key stakeholders, including fire authorities, forest professionals, landowners, key government representatives and residents living in fire-prone areas.

It was noted that before a fire, the outputs can indicate high-risk bushfire areas and support community preparation for disaster resilience.

Once there is an ignition, the AI model can quickly and more accurately predict the direction, extent, severity and boundary of the fire, allowing targeted and strategic interventions.

This vital information can be used to inform forest management crews ahead of possible fires about the potential fire damage, severity and affected areas.

This program could help enhance Australia’s resilience to bushfires and make significant contributions to the academic community working in the areas of disaster preparedness and response. Professor Javen Shi, Director of Advanced Reasoning and Learning at AIML, is the AI lead on the NOBURN project.

“We are delighted this new grant will allow us to continue our already successful collaboration with USC developing new approaches for bushfire management. In this project, the citizen science NOBURN app will give us access to more data that can be used to train the AI,” Professor Shi said.

The need for applications like the NOBURN project is obvious. The Australian government’s latest budget has committed $210 million for a new climate information service, $600 million for a new agency to promote natural disaster recovery and resilience, and $10 billion for a reinsurance fund to reduce insurance premiums in northern Australia, one report notes.

That money split is symptomatic of a general focus on the impact of natural disasters – thinking about their costs in terms of direct damage to the built environment.

According to research by Curtin University, the University of Melbourne’s Centre for Disaster Management and Public Safety, and Ghent University in Belgium, severe bushfires reduced output in the construction and transport, storage and communications sectors. Analysis showed little impact on mining, manufacturing, finance and property or agricultural output.

Send this to a friend