Estimation of GHG Emissions in Turkey Using Energy and Economic Indicators


SÖZEN A. , Gulseven Z., ARCAKLIOĞLU E.

ENERGY SOURCES PART A-RECOVERY UTILIZATION AND ENVIRONMENTAL EFFECTS, vol.31, no.13, pp.1141-1159, 2009 (Journal Indexed in SCI) identifier identifier

  • Publication Type: Article / Article
  • Volume: 31 Issue: 13
  • Publication Date: 2009
  • Doi Number: 10.1080/15567030802089086
  • Title of Journal : ENERGY SOURCES PART A-RECOVERY UTILIZATION AND ENVIRONMENTAL EFFECTS
  • Page Numbers: pp.1141-1159

Abstract

The greenhouse gas emissions (total greenhouse gas, CO2, CO, SO2, NO2, E (emissions of non-methane volatile organic compounds)) covered by the Kyoto Protocol are weighted by their global warming potentials and aggregated to give total emissions in CO2 equivalents. The subject in this study is to obtain equations to predict the greenhouse gas emissions of Turkey using energy and economic indicators by the artificial neural network approach. In this study, three different models were used in order to train the artificial neural network. In the first of them sectoral energy consumption (Model 1), in the second of them gross domestic product (Model 2), and in the third of them gross national product (Model 3) are used input layer of the network. The greenhouse gas emissions are in the output layer for all models. The aim of using different models is to estimate the greenhouse gas emissions with high confidence to make correct investments in Turkey. The obtained equations are used to determine the future level of the greenhouse gas emissions and take measures to control the share of sectors in total emission. According to artificial neural network results, the maximum mean absolute percentage errors for Model 1 were found to be 0.147151, 0.066716, 0.181901, 0.105146, 0.124684, and 0.158157 for greenhouse gas, SO2, NO2, CO, E, and CO2, about training data with Levenberg-Marquardt algorithm by eight neurons, respectively. Similarly, for Model 2 these values were found to be 0.487212, 0.701938, 0.718754, 0.232667, 0.272346, and 0.575421, respectively. And finally, for Model 3, these values were found to be 0.126728, 0.115135, 0.069296, 0.214888, 0.080358, and 0.179481, respectively. R2 values are obtained very close to 1 for all models. The artificial neural network approach shows greater accuracy for estimating the greenhouse gas emissions.