Wednesday, February 14, 2024
18.8 C
Melbourne

Federal grant to fund AI-supported wildlife recognisers

Eco Voice
Eco Voicehttps://www.ecovoice.com.au/
First published in 2003, Eco Voice is your go-to publication for sustainability news in Australia. Eco Voice prides itself as an independent news platform with a clear focus on sustainability, with articles coming from a diverse range of contributors – all levels of government, corporations, not-for-profits, community groups, small to medium sized businesses, universities, research organisations, together with input from international sources. Eco Voice values community, conservation and commerce. Eco Voice is a media partner of the prestigious Australian Banksia Sustainability Awards – The Peak Sustainability Awards.

$750k to develop and train AI to identify 120 native species

Australian Wildlife Conservancy (AWC), a global leader in conservation, has secured $750k in federal grant funding to develop and train Artificial Intelligence (AI) models to accurately recognise and identify up to 120 native species.

Funds from the Australian Government’s Innovative Biodiversity Monitoring Grants Program will be used to create open-source AI recognisers which will assist in effectively processing camera trap data collected during biodiversity surveys across Australia.

Although camera traps have revolutionised biodiversity monitoring, a single camera can collect thousands of images and ecologists will spend days, sometimes months, manually reviewing each image bank. AI has huge potential to improve the speed and cost effectiveness of camera trap image processing. However, widespread application of AI is challenging due to the number of high-quality target species images which are required across a range of habitats to accurately train the AI model.

In preparation for the AI project, AWC’s National Science Team has started collating images from the organisation’s extensive library, collected over the last 15 years from sanctuaries and project partners. Data Scientist and Software Developers in AWC’s IT team have also developed a camera trap processing and reporting pipeline and tested methods by successfully creating AI recognisers for 44 species to date.

AWC aims to develop species recognisers for 120 mammals and reptiles including the endangered Northern Bettong, the near threatened Western Quoll, the vulnerable Great Desert Skink, and the Yellow-spotted Monitor. The Species Classifier model(s) will be made available on a public open-source repository (example GitHub), along with documentation on how to use the model for animal classification, as well as documentation on AWC’s camera trap image processing pipeline, methods and tools.

Tim Allard, AWC Chief Executive Officer, welcomed the funding.

“AWC is increasingly turning to emerging technologies to improve efficiency and the quality of data collected in the field,” Allard said. “By harnessing the power of AI, these species recognisers will provide an accurate and cost-effective method for monitoring changes in biodiversity across Australia. It will also help free our ecologists to spend more time in the field, where they have the biggest impact.”

“This project represents excellent value for government investment as it builds on AWC’s existing sanctuary and data collection infrastructure, bolstered by an established network of expert ecologists familiar with the different fauna assemblages of each region. These resources cannot be replicated without millions of dollars of investment and years of effective project planning.”

For more information on AWC’s work with AI and other advanced technologies, click here.

Australian Wildlife Conservancy (AWC) is a global leader in conservation, providing hope to Australia’s wildlife with a science-informed, land management partnership model that delivers high impact results. AWC is a national leader in landscape scale conservation land management, reintroductions of threatened species and the establishment of feral predator-free areas.

 www.australianwildlife.org 

 

 

- Advertisement -
- Advertisement -
3
- Advertisement -

CONTINUE READING