Examining Determinants of Transport-Related Carbon Dioxide Emissions by Novel Super Learner Algorithm

Combating carbon dioxide (CO₂) emissions across sectors becomes inevitable due to negative impacts. The transport sector takes place among the most important sectors. Accordingly, the study examines transport-related CO₂ (TCO₂) emissions in the top four emitting countries (namely, the United States, Canada, Saudi Arabia, & Australia) by considering six explanatory variables, using data from 1990/Q1 to 2020/Q4, and performing an artificial intelligence approach. The outcomes show fresh insights that (i) super learner (SL) algorithm overwhelms other machine-learning algorithms in terms of model performance; (ii) energy intensity has an increasing impact on TCO₂ emissions, whereas others (e.g., financial development, income, globalization, oil use, & urbanization) have a mixed impact across countries; (iii) the influential variables have some critical thresholds, where the power of impacts differentiate across these limits. Hence, the SL algorithm presents robust outcomes for TCO₂ emissions. Accordingly, a set of policy endeavors for the countries examined are also discussed.