Carbon dioxide emissions prediction of five Middle Eastern countries using artificial neural networks

Mohammad Hossein Ahmadi, Hamidreza Jashnani, Kwok Wing Chau, Ravinder Kumar, Marc A. Rosen

Research output: Journal article publicationJournal articleAcademic researchpeer-review

19 Citations (Scopus)


Greenhouse gas (GHG) emissions contribute considerably to global warming and climate change. Since energy systems notably influence GHG emissions, such emissions can be modeled at the national level based on the energy sources utilized by a country. Economic activity also affects GHG emissions. In this work, an Artificial Neural Network (ANN) approach, Group Method of Data Handling (GMDH), is used for determining emissions of carbon dioxide, the most significant GHG, on the basis of shares of various energy sources used as primary energy supply and GDP as an indicator of economic activity. Five countries are considered as case studies: Iran, Kuwait, Qatar, Saudi Arabia, and United Arab Emirates (UAE). Comparing the results achieved by the developed model and actual quantities shows that the ANN model has acceptable accuracy for predicting CO2 emissions. The average absolute relative error and the R-squared values of the GMDH model are 2.3% and 0.9998, respectively. These values demonstrate the precision of the model in forecasting emissions of CO2.

Original languageEnglish
JournalEnergy Sources, Part A: Recovery, Utilization and Environmental Effects
Publication statusAccepted/In press - 1 Jan 2019


  • Artificial Neural Network
  • carbon dioxide emission
  • GMDH
  • greenhouse gases
  • Middle Eastern countries

ASJC Scopus subject areas

  • Renewable Energy, Sustainability and the Environment
  • Nuclear Energy and Engineering
  • Fuel Technology
  • Energy Engineering and Power Technology


Dive into the research topics of 'Carbon dioxide emissions prediction of five Middle Eastern countries using artificial neural networks'. Together they form a unique fingerprint.

Cite this