Birds that nest on the ground across farmland in Europe often face a singular threat: plows and other agricultural tools. Every spring, numerous farmland breeding birds fall victim to agricultural activities, as people do not see them in time to accidentally destroy their nests.
However, science may come to the rescue in the form of drones and artificial intelligence.
A team of researchers from the University of Helsinki decided to fly a drone equipped with a thermal camera over some agricultural fields in southern Finland, then fed the resulting images to an AI algorithm designed to identify nests of Northern Lapwing (Vanellus vanellus).
During a pilot study, the researchers found that thermal vision when used at ground level was hampered by the presence of dense vegetation and objects on the road. So they decided to give the camera a bird's eye view by flying it with a drone.
The technique worked like a charm. The thermal imaging system works best on cloudy days and when the temperature is cooler. "At least at high latitudes, the temperature of these nests is typically higher than the surrounding environment," explains Andrea Santangeli, a member of the Luomus Finnish Museum of Natural History at the University of Helsinki.
The technology is far superior to human eyes, which can be a huge advantage in protecting threatened birds that are rapidly losing their habitat due to agricultural activities, Santangeli says. "We've been involved in conserving farmland birds that nest on the ground for years, and we realized how difficult it is to locate nests on the ground," he says.
Sensor-equipped drones are already in use in precision agriculture to map the spread of diseases in crops and monitor other threats to them. New artificial intelligence technology could now be used effectively in conservation efforts, such as "integrating nest detection within the precision agriculture system that relies heavily on drone sensors," the scientists explain in a study on Your results.
"The conservation community must be ready to embrace technology and work across disciplines and sectors to find efficient solutions," Santangeli emphasizes. "This is already happening, with drone technology quickly becoming popular in conservation."
The next step is to adjust the system for use in other environments to protect other threatened species. The scientists hope that soon their system will be "fully integrated into agricultural practices, so that detecting and saving nests from mechanical destruction will become a fully automated part of food production."