Supporting offshore wind growth: Automating data analysis in digital aerial surveys to enhance wildlife protection and survey efficiency

With Europe projected to install 260 GW of new wind power between 2024 and 2030, much of it offshore, efficient Environmental Impact Assessments (EIAs) are essential. Regulations require 24 monthly aerial digital surveys before development, with continued monitoring during and after construction. This generates massive volumes of ecological data. We present an automated system that drastically reduces the time required for the most labour-intensive task: screening imagery to identify objects or individuals for further species classification. The process is reduced from several months to the 4-hour survey duration. In a 15-month case study (with one month excluded for testing), the system achieved 97.9 % accuracy, outperforming manual screening (68.75 %), and eliminated 99.13 % of frames from requiring manual review. Avian detection matched manual performance but remained limited by current survey conditions and image resolution. Critically, we found that the commonly assumed 2 cm ground sampling distance (GSD) was inconsistent across survey frames, with no part of any image achieving 2 cm/px, due to camera angles and aircraft configuration. This reduces classification confidence and highlights a need for improved data standards and transparency. As the first study to directly examine these assumptions using raw data, our results demonstrate that survey resolution is insufficient for consistent species identification, and that manual screening may miss up to 30 % of individuals. These findings underscore the importance of questioning inherited data assumptions and improving survey methodologies before such outputs are used to inform policy or conservation action. • Automated screening reduces data processing time from months to hours, enabling the review of all collected data instead of just half, thereby increasing windfarm survey coverage from approximately 10% to 20%. • The model achieves 97.9% accuracy, significantly outperforming commercial screeners at 68.75%, and eliminates 99.13% of frames from review for mammalian species. • Manual screening misses up to 30% of individuals in survey datasets, with up to 70% of species miscounted in individual frames. • The stated 2 cm Ground Sample Distance (GSD) is inaccurate, undermining classification confidence and providing insufficient resolution for reliable species-level classifications in many cases. • Findings emphasize the need for improved survey methodologies, higher resolution imaging, and greater transparency in Offshore Wind Environmental Impact Assessments.