Deep Learning for Aviation Safety: Classifying Bird Species to Prevent Bird Strikes

Bird strikes pose a significant threat to aviation safety, often resulting in loss of life, severe aircraft damage, and substantial financial costs. Existing bird strike prevention strategies primarily rely on avian radar systems that detect and track birds in real time. A major limitation of these systems is their inability to identify bird species, an essential factor, as different species exhibit distinct flight behaviors, and altitudinal preference. To address this challenge, we propose an image-based bird classification framework using Convolutional Neural Networks (CNNs), designed to work with camera systems for autonomous visual detection. The CNN is designed to identify bird species and provide critical input to species-specific predictive models for accurate flight path prediction. We implemented and evaluated two classification architectures: the Cascade Classification Approach (CCA) and the Unified Classification Approach (UCA). CCA follows a three-stage process: it first classifies inputs as either bird or aircraft, then assigns bird instances to one of three size categories (small, medium, or large), and finally identifies the species using a size-specific classifier. In contrast to CCA, UCA uses a single CNN model to directly distinguish between aircraft and multiple bird species in one step. To benchmark our CNN-based framework, we compared its performance with three traditional machine learning classifiers: Support Vector Machine, Random Forest, and K-Nearest Neighbors. Experimental results demonstrate that the CNN significantly outperforms all baseline models in small, medium, and large bird species classifiers. Furthermore, UCA achieved slightly higher overall accuracy than CCA. These findings highlight the potential of CNN-based classification to revolutionize proactive bird strike prevention.