Capitalising on artificial intelligence to support forestry in regional Australia
Work continues on a collaborative research initiative enabling communities, universities and government to ensure the benefits of artificial intelligence (AI) are maximised in Australia’s regional areas.
The Smarter Regions Cooperative Research Centre (CRC) works with commercial partners from various sectors including forestry, agtech, mining, retail and IT.
FWPA and the University of the Sunshine Coast (USC) are working on a joint proposal outlining potential areas of focus for forestry, informed by discussions with growers and timber processors.
Optimising knowledge and knowledge transfer across the entire industry supply chain is highlighted in the proposal as a key area of priority, due to its potential to support better decision-making.
AI techniques are also identified as having the potential to uncover nonlinear relationships between the many factors impacting wood quality such as genetics, site conditions, rotations, management activities and environmental inputs.
The proposal will recommend the Smarter Regions CRC gathers and uses such insights to develop predictive models that will help ensure the implementation of short and long-term management strategies to allow regional Australia to grow the highest quality timber resource possible at a rate that will satisfy future demand.
Other key recommendations in the proposal include measures to enhance processing capabilities and optimise supply chain and logistics efficiencies to match the attributes of timber produced with the right market opportunities.
Currently, the team is awaiting the CRC to officially open its call for submissions, at which stage the joint FWPA and USC proposal will be put forward for consideration. You can find out more about the Smarter Regions CRC by clicking here.
Artificial intelligence and the supply chain
As the researchers await the call for bids from the Smarter Regions CRC, further work in the AI space has been ongoing in the background. This includes testing the application of AI for the purposes of supply chain tracking, as part of a separate FWPA-supported USC research project focused on improved information flow.
As part of this work, the team has brought in Swedish technology developed by OTMETKA — a leading company that develops solutions to simply and efficiently digitise large amounts of forestry data to create global timber traceability.
The technology being tested stamps logs with a pattern, which can then be used for information storage.
Bushfire prediction and artificial intelligence
The same research team has also been awarded an Australian Government Citizen Science Grant of almost $500,000. This funding will be used to design and implement a citizen science app for people living in bushfire prone areas, to help predict the likelihood of bushfire events and minimise their devastating effects.
The Citizen Science Grants are awarded for scientific research projects with a national impact, which engage members of the public as citizen scientists.
Citizen scientists from around the country, including people who hike, work and camp in forest areas, will therefore be encouraged to use the app to collect vital data in the form of photos and forest fuel samples.
The app, known as NOBURN — or the National Bush Fire Resilience Network — will use the data gathered and match it with satellite imagery, before training AI systems to predict the probability, severity and burn area of potential fires.
The NOBURN project should result in new knowledge to be shared with key stakeholders including fire authorities, forest professionals, landowners, key government representatives, and, most importantly, residents living in bushfire prone areas.
“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,” said Professor Mark Brown, Deputy Director of USC’s Forest Research Institute.
The USC team is working in cooperation with AI experts at the Australian Institute for Machine Learning (AIML) at the University of Adelaide.
Professor Paul Salmon, Director of USC’s Centre for Human Factors and Sociotechnical Systems, said the NOBURN app project would be a highly innovative, first-of-its-kind collaboration between experts in human factors, forestry and machine learning.
“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,” said Salmon.
“This vital information can be used to inform forest management crews ahead of possible fires about the potential fire damage, severity, and affected areas.”