Analyzing Public Environmental Awareness Using Advanced Machine Learning for Sustainable Urban Transportation

Environmental awareness and sustainable transportation are critical in addressing climate change and urbanization. This research enhances understanding of environmental awareness through advanced machine learning (ML), focusing on cycling as a key component of sustainable urban mobility. Based on survey data from 550 participants in Kayseri, Türkiye, the study examines demographic, behavioral, and attitudinal factors influencing environmental awareness. Bioinspired feature selection algorithms, including genetic algorithm and particle swarm optimization, identified key predictors. Generative Adversarial Networks (GANs) generated synthetic data for underrepresented groups, improving dataset balance and reliability. Seven classification models were evaluated using 10‐fold cross‐validation. Ensemble methods, particularly CatBoost and LightGBM, achieved over 0.82 accuracy with balanced precision, recall, and F1‐score. Behavioral factors, such as reasons for choosing a bicycle and environmental expectations, were the most significant determinants. These findings can inform targeted cycling infrastructure planning, inclusive environmental campaigns, and the development of predictive tools to identify vulnerable or responsive user groups.