Forecasting of Greenhouse Gas Emissions in Serbia Using Artificial Neural Networks

Abstract

Serbia is attempting to synchronize its development with the basic assumptions of sustainable development and, consequently, data about environmental impact are necessary. The main goal of this study was to investigate and evaluate the possibility of using the artificial neural network technique for predicting the environmental indicators of sustainable development, in order to overcome the problem of incomplete data and to simulate various development scenarios and their environmental impact. Based on the results obtained, it may be concluded that an artificial neural network can be applied to model the greenhouse gas emissions as one of the environmental parameters of sustainable development.

Keywords:

• energy consumption
• neural network
• pressure indicators
• Serbia
• sustainable development

Notes

^a Share of renewable energy (%).

^b Gross Domestic Product per capita normalized to the EU 27 average.

^c Gross Energy Consumption in tonnes of oil equivalent per capita.

^d Energy intensity in kilograms of oil equivalent per 1,000 € of value produced.

^e GHG emissions/capita (CO₂pc) in tonnes of CO₂ equivalent.

^a Actual denotes the measured GHG emissions and ANN the predictions made by the model.

*Eurostat data.

**Predicted on the basis of CO₂ emission.