CO2 Emission, Energy Use, Urbanization, and Economic Growth and 2-Trilemma: A New Machine Learning Algorithm

Abstract

The study purposes to discover the association among CO2 emissions (CO2), energy use, and GDP in Pakistan. The data type is time series, with a time span of 1991–2021. The different econometric techniques structural breaks, VECM, ARDL, and D2C algorithms used along with the machine learning experiment. As well, two models were employed in this study. In model 1, Among the anticipated variables of GDP per capita, energy use per capita, and CO2 emissions, cointegration exists. Therefore, the outcomes of model 1 show that energy use per capita and CO2 emissions have a statistically significant and positive impact on GDP per capita. In mode 2, long-run associations exist along with positive and negative signs. The estimated coefficient of urbanization comes with a negative sign. The fact that urbanization is statistically significant means urbanization has effects on targeted variables such as GDP per capita. Having statistical significance, energy use per capita negatively influences GDP per capita. In the case of Pakistan, both explanatory variables have a negative association with the targeted variable. The robustness used to check the results' validity of the D2C algorithm.
Keyword- CO2 emissions, Economic Growth