SYDNEY, July 30 (Xinhua) -- Australian researchers have developed a remote sensing system that maps Antarctica's mosses and lichens, its only vegetation and ecosystem health indicators, more efficiently and accurately.
The team used Uncrewed Aerial Vehicle-mounted hyperspectral cameras, precise Global Navigation Satellite System Real-Time Kinematic navigation, and high-resolution RGB (red-green-blue) imaging to monitor fragile vegetation non-invasively, according to a statement released Tuesday by Australia's Queensland University of Technology (QUT).
Juan Sandino, a researcher from QUT's School of Electrical Engineering & Robotics, described mosses and lichens as Antarctica's green "stress barometers," essential for biogeochemical cycles, soil insulation, and biodiversity support.
"They drive nutrient cycles and underpin Antarctica's ecosystems, yet they are the first to suffer from warming, extreme weather and human trampling. Keeping track of their health is vital but extremely difficult in sub-zero field conditions," Sandino said.
The system uses six specialized spectral indices for polar plants, enabling artificial intelligence models to classify mosses and lichens.
The researchers compared 12 different AI models for labeling the vegetation, and the best options reached about 99 percent accuracy while staying consistent in rigorous tests.
"This new integrated system surpasses conventional digital images (red-green-blue, or RGB) and also the satellite-based Normalised Different Vegetation Index that is being used to assess vegetation health and density," said Sandino.
This approach allows rapid, cost-effective surveys at multiple scales, and a simplified eight-wavelength version makes it accessible with smaller drones and cheaper sensors, said Felipe Gonzalez, a professor from QUT's School of Electrical Engineering and Robotics. Enditem