Forecasting Greenhouse Gas Emissions Based on Different Machine Learning Algorithms


Ulku I., ÜLKÜ E. E.

4th International Conference on Intelligent and Fuzzy Systems (INFUS), Bornova, Turkey, 19 - 21 July 2022, vol.505, pp.109-116 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 505
  • Doi Number: 10.1007/978-3-031-09176-6_13
  • City: Bornova
  • Country: Turkey
  • Page Numbers: pp.109-116
  • Keywords: Machine learning algorithm, Greenhouse gases, Forecasting, BUILDINGS
  • Istanbul Technical University Affiliated: No

Abstract

With the increase in greenhouse gas emissions, climate change is occurring in the atmosphere. Although the energy production for Turkey is increased at a high rate, the greenhouse gas emissions are still high currently. Problems that seem to be very complex can be predicted with different algorithms without difficulty. Due to fact that artificial intelligence is often included in the studies to evaluate the solution performance and make comparisons with the obtained solutions. In this study, machine learning algorithms are used to compare and predict greenhouse gas emissions. Carbon dioxide (CO2), nitrous oxide (N2O), methane (CH4), and fluorinated gases (F-gases) are considered direct greenhouse gases originating from the agriculture and waste sectors, energy, industrial processes, and product use, within the scope of greenhouse gas emission statistics. Compared to different machine learning methods, support vector machines can be considered an advantageous estimation method since they can generalize more details. On the other hand, the artificial neural network algorithm is one of the most commonly used machine learning algorithms in terms of classification, optimization, estimation, regression, and pattern tracking. From this point of view, this study aims to predict greenhouse gas emissions using artificial neural network algorithms and support vector machines by estimating CO2, CH4, N2O, and F-gases from greenhouse gases. The data set was obtained from the Turkish Statistical Institute and the years are included between 1990 and 2019. All analyzes were performed using MATLAB version 2019b software.