Modeling freight truck-related traffic crash hazards with uncertainties: A framework of interpretable Bayesian neural network with stochastic variational inference

Abstract

Due to the increasing demand for goods movement, externalities from freight mobility have attracted much concern among local citizens and policymakers. Freight truck-related crash is one of these externalities and impacts urban freight transportation most drastically. Previous studies have mainly focused on correlation analyses of influencing factors based on crash density/count data, but have paid little attention to the inherent uncertainties of freight truck-related crashes (FTCs) from a spatial perspective. While establishing an interpretable analysis model for freight truck-related accidents that considers uncertainties is of great significance for promoting the robust development of urban freight transportation systems. Hence, this study proposes the concept of FTC hazard (FTCH), and employs the Bayesian neural network (BNN) model based on stochastic variational inference to model uncertainty. Considering the difficulty in interpreting deep learning-based models, this study introduces the local interpretable modelagnostic explanation (LIME) model into the analysis framework to explain the results of the neural network model. This study then verifies the feasibility of the proposed analysis framework using data from California from 2011 to 2020. Results show that FTCHs can be effectively modeled by predicting confidence intervals for effects of built environment factors, in particular demographics, land use, and road network structure. Results based on LIME values indicate the spatial heterogeneity in influence mechanisms on FTCHs between areas within the metropolitan regions and alongside the freeways. These findings may help transport planners and logistic managers develop more effective measures to avoid potential negative effects brought by FTCHs in local communities.