Indigenous rangers in West Arnhem use AI for wildlife monitoring

Indigenous rangers and researchers in West Arnhem, Australia, have successfully integrated artificial intelligence into the Mayh wildlife program to enhance community-based monitoring. A collaboration between Warddeken Land Management, Charles Darwin University, and the Commonwealth Scientific and Industrial Research Organisation (CSIRO) utilized the MegaDetector AI model to process camera-trap data.

The implementation resulted in an 81.4 per cent reduction in the number of images requiring manual analysis, dropping from 925,088 to 172,290. This automation shortened the total processing time from six months to two months and reduced the average fortnightly data processing time from 52.6 hours to 41.8 hours.

By reducing the burden of image processing, the technology has allowed rangers to increase their engagement in land management, focus more on species identification, and dedicate time to language documentation and community workshops. The initiative emphasizes maintaining local oversight, protecting Indigenous knowledge, and securing local employment while adopting emerging technologies.