On a lonely wind turbine in the North Sea, a gull flaps past a camera just before dawn. Minutes later, a tiny songbird darts through the dark, invisible to the human eye—but not to the 16 thermal cameras watching every angle, day and night. At Hollandse Kust Zuid, off the coast of the Netherlands, this quiet moment is part of a breakthrough. For nearly a year, these cameras—paired with artificial intelligence—have been tracking birds around an offshore wind turbine, capturing something scientists have long struggled to see: actual bird movements at sea, and possible collisions.
Offshore wind energy is key to fighting climate change, but it comes with risks for wildlife. Millions of birds, including small songbirds and bats, cross the North Sea each spring and fall, often flying at night. Until now, we could only guess how many might hit turbines. On land, researchers can find remains, but at sea, bodies vanish in waves and currents. So estimates were based on models, not real data. That’s why this pilot project matters. Led by energy company Vattenfall, with technology from Wildlife Imaging Systems (WIS) and analysis by Wageningen University & Research (WUR), the study tested whether thermal cameras and AI could work in harsh, salty, windy offshore conditions—and they did.
Over almost 12 months, the system recorded 22 possible collisions. Two were confirmed, one was highly probable, and the rest are under review. These numbers aren’t about blame or danger—they’re about knowledge. For the first time, scientists have observational evidence of what happens when birds meet offshore turbines. The cameras detected everything from large gulls to tiny warblers, even insects, offering a full picture of nighttime activity during migration seasons.
"Until now, estimates of offshore bird collisions were mainly based on theoretical models," says Jesper Kyed Larsen, bioscience expert at Vattenfall. "At sea, it is extremely difficult to verify fatalities because there are no remains to recover. This study demonstrates how we can get the empirical data needed to improve collision estimates and secure efficient mitigation measures."
The goal isn’t to stop wind farms—it’s to make them safer. By understanding when and where collisions happen, developers can adjust turbine placement, lighting, or operation during peak migration. The next phase will expand monitoring across more turbines and conditions, fine-tuning both technology and conservation strategies. As offshore wind grows—from the North Sea to the coasts of Asia and America—this kind of smart, precise science will help protect both clean energy goals and the birds that share the skies.