Forecasting of transportation-related energy demand and CO2 emissions in Turkey with different machine learning algorithms


Ağbulut Ü.

Sustainable Production and Consumption, cilt.29, ss.141-157, 2022 (SCI-Expanded) identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 29
  • Basım Tarihi: 2022
  • Doi Numarası: 10.1016/j.spc.2021.10.001
  • Dergi Adı: Sustainable Production and Consumption
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Sayfa Sayıları: ss.141-157
  • Anahtar Kelimeler: Carbon footprints, CO2 emissions, Energy demand, GHG emissions, Transportation sector
  • Yıldız Teknik Üniversitesi Adresli: Hayır

Özet

Adverse impacts of the transportation sector on not only air quality but also economic growth of a country are nowadays well-noticed, particularly by developing countries. Today, the transportation sector is powered by burning the fossil-based fuels at more than 99% and approximately 6.5 million deaths annually occur due to air-pollution-related diseases worldwide. Therefore, knowledge of both energy demand and CO2 emission of a country is a very significant issue in order to revise its future energy investments and policies. In this framework, three machine learning algorithms (deep learning (DL), support vector machine (SVM), and artificial neural network (ANN)) are used to forecast the transportation-based-CO2 emission and energy demand in Turkey. The gross domestic product per capita (GDP), population, vehicle kilometer, and year are used as input parameters in the study. It is noticed that there is a very high correlation among year, economic indicators, population, vehicle kilometer, transportation-based energy demand, and CO2 emissions. To present a better comparison, the results of these algorithms are discussed with six frequently used statistical metrics (R2, RMSE, MAPE, MBE, rRMSE, and MABE). For all machine learning algorithms, R2 values are varying between 0.8639 and 0.9235, and RMSE is smaller than 5 × 106 tons for CO2 emission and 2 Mtoe for energy demand. According to the classifications in the literature, the forecast results are generally categorized as "excellent" for rRMSE metric (<10%), and “high prediction accuracy” for MAPE metric (<10%). On the other hand, with two mathematical models, future energy demand and CO2 emission arising from the transportation sector in Turkey are forecasted by the year 2050. In the results, it is forecasted that the annual growth rate for transportation-related energy demand and CO2 emission in Turkey cumulatively rise by 3.7% and 3.65%, respectively. Both energy demand and CO2 emissions from the transportation sector in Turkey will increase nearly 3.4 times higher in the year 2050 than those of today. In conclusion, the paper clearly reports that the future energy investments of the country should be revised, and various policies, regulations, norms, restrictions, legislations, and challenges on both energy consumption and emission mitigation from the transportation sector should be established by the policy-makers.