Missouri AI drones track waterfowl with 90% accuracy

Missouri’s Department of Conservation is testing a new AI-powered drone system to monitor waterfowl populations, achieving over 90% accuracy in bird identification while avoiding the disturbance caused by traditional helicopter and plane surveys. The technology allows for more frequent, cost-effective monitoring between major survey efforts, providing conservation managers with real-time data for habitat management and hunting plans.

Why this matters: Traditional waterfowl monitoring relies on disruptive aerial surveys or limited ground counts that can miss birds in dense areas, making it difficult to track migration patterns and population changes accurately.

How it works: The AI system processes drone-captured images to automatically identify and count waterfowl species across state and federal wildlife refuges.

• Unlike crewed aircraft, drones showed no measurable change in waterfowl behavior, allowing for undisturbed monitoring of resting and refueling birds during migration.
• The AI models can analyze thousands of images within hours, enabling same-day analyses for water-level management, habitat restoration, and hunting plans.
• The system also processes camera-trap photos, automatically identifying species like deer and raccoons, potentially saving staff thousands of hours.

What they’re saying: Reid Viegut, Missouri’s migratory game bird coordinator, emphasized the importance of minimizing disturbance on refuges.

• “We really try and minimize the amount of disturbance on the refuges, so that the waterfowl have a safe place to rest and refuel when they come into the state on their migrations,” Viegut explained.
• “Some of these areas have large numbers of birds on small areas. And so they can just be sometimes they’re hard to see and hard to really get a good count on them.”

The big picture: Yi Shang, a University of Missouri researcher, noted that the goal isn’t to replace biologists but to modernize conservation efforts with scalable technology.

• The project creates “a playbook the department can scale [with] predictable battery needs, coverage estimates, and repeatable image quality that make ad-hoc ‘opportunity flights’ feasible between larger aerial efforts.”

What’s next: The department hopes to operationalize the technology within the next few years, potentially expanding its use to map invasive plants, monitor wetland habitats, and analyze river ecosystems.