Assessing environmental benefits from shared micromobility systems using machine learning algorithms and Monte Carlo simulation

Abstract

Shared micromobility systems (SMSs) are paving the way for new, more convenient travel options while also lowering transportation-related greenhouse gas (GHG) emissions. However, few studies have used real-world trip data to estimate SMSs’ environmental benefits, especially for dockless scooter-sharing services. To this end, we proposed a system to estimate the GHG emission reduction affected by SMSs. First, several machine learning (ML) algorithms were utilized to identify citizens’ travel mode choice preferences, and then the mode substituted by each shared micromobility trip was estimated. We compared the ML algorithms’ estimation results and selected those from the random forest, lightGBM, and XGBoost model for further estimating GHG reductions. Second, the Monte Carlo simulations were used to simulate the substituted mode at the trip level to improve the reliability of the final GHG reduction estimation. Finally, the environmental benefits were calculated based on the trip distances and the travel modes that were substituted. Instead of estimating a specific number, we obtained a probabilistic outcome for the environmental benefits while considering the level of uncertainty. Our results suggest that SMSs have positive environmental impacts and have the potential to facilitate the decarbonization of urban transport. According to these findings, implications and suggestions on extending SMSs’ environmental benefits are proposed.