Effects of Low-Altitude Urban Landscapes on Pilot Cognitive Load in Urban Air Mobility: An Explainable Machine Learning Approach

Whereas environmental effects on driver cognition have been extensively studied in ground transportation, research linking low-altitude visual environment characteristics to pilot cognitive load (CL) in urban air mobility (UAM) remains scarce. This study combines multimodal physiological data with explainable machine learning to elucidate how low-altitude visual environments influence pilots’ CL. First, a CL quantification framework integrating electroencephalography (EEG) and eye-tracking data is developed to capture real-time cognitive dynamics during flight. Second, multidimensional visual environment indicators are extracted from low-altitude urban landscape images captured during simulated flights using computer vision techniques. These indicators, combined with flight dynamics features, serve as input variables for constructing pilot CL prediction models via machine learning approaches. The results demonstrate that a Bayesian-optimized XGBoost model achieves superior predictive performance. Further interpretability analysis based on SHAP reveals that environmental contrast and the visibility of buildings and water bodies are key factors influencing pilot CL. Additionally, significant interaction effects are also identified among spatial morphology, color characteristics, and landscape typology, with certain landscape elements exhibiting marked variations in both importance and directional influence across different low-altitude flight scenarios. These findings inform low-altitude route optimization, urban morphological regulation, and blue-green infrastructure configuration, advancing an air-ground synergistic planning paradigm.