This study examines the impact of energy consumption and urban population on carbon dioxide emissions of the forefront of green finance countries, namely, Canada, New Zealand, the United States, Norway, Denmark, Japan, the United Kingdom, Sweden, and Switzerland, and from 2008 to 2019. The machine learning method was applied in this research by using the Random Forest Regressor, Gradient Boosting, and the Lasso, Ridge, and Linear Regression. Results of Random Forest and Gradient Boosting affirm that carbon emissions are affected by non-linear relations between energy consumption, urbanization, and other control variables included in our model. Whereas Ridge, Lasso, and linear regression helped to assess the linear dependency. Additionally, our study reveals that energy consumption directly affects carbon emissions, and the urban population also has a significant effect on carbon emissions due to transportation, industrialization, and dense population, which is a major source of pollution. Technology also is found to be a significant determinant of carbon emissions since advanced and clean technology might reduce the adverse effects of industrial operations on the environment. These insights may offer crucial recommendations to reduce carbon emissions and reinforce more efforts to achieve a better and sustainable future.