Evaluation of urban transportation carbon footprint − Artificial intelligence based solution

Abstract

This research uses three machine learning algorithms to predict transport-related CO₂ emissions, considering transport-related factors and socioeconomic aspects. We analyze the top 30 countries that produce the highest transport-related global CO₂ emissions, split evenly between Tier 1 and 2. Tier 1 comprises the five leading nations that produce 61% of the world’s CO₂ emissions, while Tier 2 comprises the subsequent twenty-five nations that produce 35% of the global CO₂ emissions. We assess the efficacy of our model by using four statistical measures (R2, MAE, rRMSE, and MAPE) in a four-fold cross-validation procedure. The Gradient-Boosted Regression (GBR) machine learning model, which incorporates a combination of economic and transportation factors, outperforms the other two machine learning approaches (Support Vector Machine and Ordinary Less Square). Our findings indicate that among Tier 1 and Tier 2 countries, socioeconomic factors like population and GDP are more influential on the models than transportation-related factors.