Abstract
This research aims to analyse the impact of economic and energy variables on carbon emissions in Germany during the period (1994–2024), within the framework of environmental economic modelling based on artificial intelligence techniques. The study is based on the hypothesis that the nature of the energy structure and the level of economic activity contribute to explaining changes in carbon dioxide emissions to varying degrees. To verify this hypothesis, an artificial neural network model was adopted to analyse the relationship between a set of independent variables represented by total energy consumption, total energy production, the proportion of renewable energy in total primary energy, GDP, and environmental taxes, and the dependent variable represented by carbon dioxide emissions. The analysis showed that total energy production and GDP are the two most influential variables in explaining changes in carbon emissions, accounting for a high percentage of the model's explanatory power. The results also showed an average effect of the renewable energy ratio. While the effect of environmental taxes was relatively limited, the effect of energy consumption appeared to be weaker than that of the other variables. The study concludes that promoting the transition to renewable energy and developing more effective environmental policies are key to reducing carbon emissions and advancing environmental sustainability.
DOI
10.33095/2227-703X.4341
Subject Area
Economics
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
First Page
13
Last Page
25
Recommended Citation
Naqee, Z. (2026). AI-Based Environmental Economic - Modeling: A Case of Germany (1994–2024). Journal of Economics and Administrative Sciences, 32(1), 13-25. https://doi.org/10.33095/2227-703X.4341
