The study addresses the challenge of bird collisions with wind turbines by developing an autonomous risk assessment method. The research uses data from the stereoscopic Bird Protection System (BPS) to anticipate potential collision threats by analysing flight parameters and distance from turbines. The danger factor depends on the flight characteristics of the identified bird species and the parameters of the wind turbine control system. The paper proposes an online quantitative risk assessment model that operates in real time, with the aim of minimising unnecessary turbine shutdowns while improving bird conservation. The model is validated through field data from bird flights. The findings suggest that adaptive management of turbine operations based on real-time bird flight data can significantly reduce collision risks without compromising energy production efficiency. The research underscores the balance between ecological considerations and the economic viability of wind energy, proposing an adaptive strategy that reduces unnecessary turbine stoppages while ensuring the safety of avian species.

With the expansion of green energy, more and more data show that wind turbines can pose a significant threat to some endangered bird species. The birds of prey are more frequently exposed to collision risk with the wind turbine blades due to their unique flight path patterns. This paper shows how data from a stereovision system can be used for an efficient classification of detected objects. A method for distinguishing endangered birds from common birds and other flying objects has been developed and tested. The research focused on the selection of a suitable feature extraction methodology. Both motion and visual features are extracted from the Bioseco BPS system and retested using a correlation-based and a wrapper-type approach with genetic algorithms (GAs). With optimal features and fine-tuned classifiers, birds can be distinguished from aeroplanes with a 98.6% recall and 97% accuracy, whereas endangered birds are delimited from common ones with 93.5% recall and 77.2% accuracy.