Forecasting CO2 Emission with Machine Learning Methods

Garip E., Oktay A. B.

International Conference on Artificial Intelligence and Data Processing (IDAP), Malatya, Turkey, 28 - 30 September 2018 identifier

  • Publication Type: Conference Paper / Full Text
  • City: Malatya
  • Country: Turkey
  • Keywords: CO2 emission, machine learning, random forest, support vector machines, ENERGY-CONSUMPTION, TURKEY
  • Yıldız Technical University Affiliated: No

Abstract

The amount of CO2 emission has significantly increased because of the increase in industrial production, usage of fossil fuels such as petroleum and coal which is a danger for global warming. The countries measure CO2 emissions and make plan for the future. In this study, Turkey's CO2 emissions are estimated using random forest and support vector machine methods. Not only time, but also attributes such as fuel consumption and population are also employed for forecasting. It has been observed that the support vector machine method produces better forecasting results.