A novel approach to forecast global CO(2) emission using Bat and Cuckoo optimization algorithms

This paper presents the application of Bat and Cuckoo optimization algorithm methods to forecast Global CO(2) emerged from energy consumption. The models are developed in two forms (linear and exponential) and used to estimate to develop Global CO2 emission model values based on the uses global oil, natural gas, coal, primary energy consumption. The available data are partly used for finding optimal, or near optimal values of weighting parameters (1980–2013) and partly for testing the models (2014–2018). The performance of methods is evaluated with mean squared error (MSE), root mean squared error (RMSE), Mean absolute error (MAE). According to the simulation results obtained, there is a good agreement between the results obtained from BA Global CO_2 emission models (BA-GCO_2) and COA Global CO_2 emission models (COA-GCO_2) but COA- exponential model outperformed the other models. The modeling approach recommended a helpful and reliable method for forecasting global climate changes and environmental decision making. • The article provides a method for forecasting and climate policy decision making. • The method presented in this article can be useful for experts, policy planners and researchers who study greenhouse gases. • The analysis obtained herein by Metaheuristic Algorithms solver can serve as a standard benchmark for other researchers to compare their analysis of the other methods using this dataset.