A novel hybrid method based on Cuckoo optimization algorithm and artificial neural network to forecast world's carbon dioxide emission

Sayyed Abdolmajid Jalaee; Alireza Shakibaei; Hossein Akbarifard; Hamid Reza Horry; Amin GhasemiNejad; Fateme Nazari Robati; Naeeme Amani Zarin; Reza Derakhshani

doi:10.1016/j.mex.2021.101310

A novel hybrid method based on Cuckoo optimization algorithm and artificial neural network to forecast world's carbon dioxide emission

MethodsX. 2021 Mar 15:8:101310. doi: 10.1016/j.mex.2021.101310. eCollection 2021.

Authors

Sayyed Abdolmajid Jalaee¹, Alireza Shakibaei¹, Hossein Akbarifard¹, Hamid Reza Horry¹, Amin GhasemiNejad¹, Fateme Nazari Robati¹, Naeeme Amani Zarin¹, Reza Derakhshani^{2

3}

Affiliations

¹ Department of Economics, Faculty of Management and Economics, Shahid Bahonar University of Kerman, Kerman, Iran.
² Department of Geology, Shahid Bahonar University of Kerman, Kerman, Iran.
³ Department of Earth Sciences, Utrecht University, Utrecht, the Netherlands.

Abstract

This paper deals with the global energy consumption to forecast future projections based on primary energy, global oil, coal and natural gas consumption using a hybrid Cuckoo optimization algorithm and information of British Petroleum Company plc and BP Amoco plc. The Artificial Neural Network (ANN) has some significant disadvantages, such as training slowly, easiness to fall into local optimal point, and sensitivity of the initial weights and bias. To overcome the shortcomings, an improved ANN structure, that is optimized by the Cuckoo Optimization Algorithm (COA), is proposed in this paper (COANN). The performance of the COANN is evaluated with Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Correlation Coefficient (CC) between the output of the model and the actual dataset. Finally, CO₂ emission in the world by 2050 is forecasted using COANN. The findings showed that COANN is a helpful and reliable tool for monitoring global warming. This proposed method will assist experts, policy planners and researchers who study greenhouse gases.•The method can be used as a potential tool for policymakers and governments to make policy on global warming monitoring and control.•The proposed method can play a key role in the global climate changes policies and can have a significant impact on the efficiency or inefficiency of government's intervention policies.

Keywords: Global climate changes; Metaheuristic method; Optimization algorithm.