Integrating visual and community environments in a motorcycle crash and casualty estimation

Motorcycle crashes pose a serious problem because their probability of causing casualties is greater than that of passenger vehicle crashes. Therefore, accurately identifying the factors that influence motorcycle crashes is essential for enhancing traffic safety and public health. The aim of this study was to address three major research gaps: first, existing studies have relatively overlooked the built environment in relation to visual factors; second, existing crash prediction models have not fully reflected the differences in built environment characteristics between areas with frequent motorcycle crashes and areas with frequent casualties; and third, multidimensional analysis for variable selection is limited, and the interpretability of the models is insufficient. Therefore, this study proposes a comprehensive framework for motorcycle crash and casualty estimation. The framework uses a data cube model incorporating OLAP operations to provide deeper insights into crash influencing factors at different levels of abstraction. We also utilized the XGBoost model to predict motorcycle high crash spots and casualty risk and integrate visual factors extracted from Google Street View images and community-level urban environments into the model. SHAP techniques were used to analyze and interpret the global and local feature importance of the models. Our results revealed that the factors affecting areas with frequent motorcycle crashes and the factors that affect casualties differ. In particular, visual factors such as vegetation and the sky ratio are important for estimating casualties. We aim to provide practical guidelines for a safe environment for motorcycle crashes.