Forecast of Turkey's Carbon Emissions Within the Framework of the European Union’s Green Deal

Abstract

Abstract The most important of such efforts is the Paris Climate Agreement signed in 2015 and the t’s Green Deal, implemented by the European Union (EU) within the framework of this Agreement. The targets stated in Grean Deal include measures affecting not only the EU countries but also third countries with which the EU has foreign trade links. For this purpose, ın this study, the carbon emission of Turkey, which has serious commercial relations with the EU, was tried to be estimated using machine learning techniques and an estimate was made for the year 2030 on the basis of the results obtained. These results were evaluated in line with the targets of the Green Deal. The R2 value of Support Vector Regression (SVR), which is applied in the model as one of the machine learning techniques, was found to be 98.4% and it was found to have the highest predictive power. This technicque is followed by Multiple Linear Regression (MLR) with a 97.6% success rate and Artificial Neural Network (ANN) with 95.8% success rate, respectively. According to the estimates made with the most successful model, SVR, Turkey's carbon emissions are expected to be 723.97 million tons (mt) of CO2 in 2030, the target year set by the EU. This level is 42% more compared to the the target that needs be achieved given the data existing in 2019. In terms of the results obtained from the study, it is thought that the study could be an exemplary model for other countries that have commercial ties with the EU.