Drones and deep learning produce accurate and efficient monitoring of large-scale colonies of black browed albatross and southern rockhopper penguins on Steeple Jason. Field work 2018 - 2019. Publication 2022

Photographs obtained using drones in automated flight covered entire colony areas of black browed albatross and southern rockhopper penguins on Grand and Steeple Jason over two seasons were analysed using convolutional neural networks (CNN) to detect and enumerate individuals of both species for population assessment. Results showed accuracies for detecting and counting birds at 97.66% (Black browed albatross) and 87.16% (southern rockhopper penguin), with 90% of automated counts being within 5% of manual counts from imagery, clearly demonstrating the value of these techniques for seabird monitoring in large colonies.