Scientists use drones, satellites and AI to monitor Antarctica’s tiniest organisms

ANTARCTICA, CANADA GLACIER, MCMURDO DRY VALLEYS, AUSTRALIA (UNIVERSITY OF WOLLONGONG), 30 SEPTEMBER 2026 —

A team led by the University of Wollongong (UOW) has unveiled a new geospatial artificial‑intelligence framework that will allow scientists to monitor Antarctica’s smallest ecosystems from anywhere in the world.

The new approach is significant because Antarctica’s mosses, lichens and cyanobacteria grow in tiny, fragmented patches that are difficult to track over time. “We’re only beginning to understand the role that many of Antarctica’s least‑studied species play in its ecosystems,” said Dr. Narmilan Amarasingam, the study’s lead author.

“Long‑term monitoring is how we find out, and it’s essential if we want to protect Antarctica’s biodiversity as a whole, not just the parts people already know and love.”

The framework was developed under the Australian Research Council’s Securing Antarctica’s Environmental Future (SAEF) program and was tested over seven years at Canada Glacier in the McMurdo Dry Valleys. This ice‑free polar desert is one of the most biologically productive areas in Antarctica, making it an ideal test site for the new method.

“The new approach allowed us to capture a consistent and comprehensive picture of the ecosystem and terrain, from centimetre‑sized patches to landscape‑level patterns,” Amarasingam said.

The system works by first collecting detailed field observations of moss and lichen communities. These observations are used to train AI models that interpret drone‑based imagery, which in turn informs satellite‑scale monitoring. “We can observe this ecological detail in the field and with drones, but these approaches cover relatively small areas,” Amarasingam explained. “Satellites, on the other hand, can repeatedly observe much larger landscapes, but at a much coarser spatial scale.

Our idea was to connect these different scales, using detailed field observations to inform drone‑based mapping, and then using those drone‑derived observations to support satellite‑scale monitoring.”

The ability to track vegetation across multiple years will help scientists separate short‑term variation from longer‑term change as Antarctica’s environment is reshaped by global warming. The framework could provide large‑scale data to support decision‑making, biodiversity modelling and environmental management strategies. “The aim is not to replace fieldwork,” Amarasingam said. “Field observations remain essential because they provide the biological understanding needed to interpret what we see remotely.

Instead, approaches like this can help us make those valuable field observations work much harder by extending them across areas that are difficult, expensive and logistically challenging to revisit.”

The study’s findings are published in the ISPRS Journal of Photogrammetry and Remote Sensing (2026), DOI: 10.1016/j.isprsjprs.2026.09.016. The research demonstrates that a multi‑sensor, multi‑temporal GeoAI framework can resolve ecological scale mismatch in Antarctica, enabling consistent monitoring of vegetation from centimetre‑scale patches to landscape‑level patterns. The authors note that field observations remain essential for interpreting remote measurements, but the new approach can extend the reach of those observations across difficult terrain.

The development of this framework represents a major step forward for Antarctic research, providing a tool that can be used by scientists worldwide to monitor the continent’s most vulnerable ecosystems. The ability to generate long‑term, high‑resolution maps of Antarctic vegetation will support efforts to protect and manage the region’s biodiversity in the face of rapid environmental change.

Related: Dr. Narmilan Amarasingam