Travel Behavior, Built Environment, and Decarbonization

Globally, transportation sector accounts for 15% of greenhouse gas (GHG) emissions and 24% of carbon dioxide (CO2) emissions. Due to more people buying and using cars, the share of CO2 emissions from the transportation sector is growing by a large amount every day. This has negative effects on the environment and public health that need to be fixed with well-informed solutions. One of the potential solutions to reduce CO2 emissions and fuel consumption from the transportation sector is sustainable urbanism. This solution deals with strategies to re-plan cities through changing their built environment by increasing the compactness of the cities through high-density and mixed-use development, which will encourage the use of sustainable travel modes (i.e., walking and bicycling), reduce travel demand for motorized modes, and consequently, help to develop a smart, clean, and environment friendly transportation system. Therefore, it is necessary to understand the impact of built environment on travel behavior and CO2 emissions, specially in context of developing country. The research:

• Examined the direct and indirect effects of the built environment on commuting-related mode choice behavior in Dhaka, Bangladesh, using an integrated framework of Structural Equation Modeling (SEM) and discrete choice model, considering commute distance and car ownership as mediating variables.

• Explored the non-linear and interaction effects of the built environment on commuting-related mode choice behavior using three machine learning algorithms: Support Vector Machines (SVM), Random Forest (RF), and Gradient Boosting Decision Trees (GBDT).

• Investigated the direct and indirect effects of the built environment on commuting-related carbon dioxide emissions using SEM, considering car ownership as a mediating variable.