A hybrid algorithm for carbon dioxide emissions forecasting based on improved lion swarm optimizer

Global warming is a hot topic of climate change, and its negative impact on oceans, ecology, and human health has become an indisputable fact. As a major cause of global warming, carbon dioxide emissions forecasting has attracted increasingly attention. However, previous studies only focused on forecasting accuracy and neglected stability. To solve this problem, this paper proposes a novel hybrid algorithm, which combines lion swarm optimizer and genetic algorithm to optimize the traditional least squares support vector machine model. The carbon dioxide emissions data of developed countries, developing countries and the world from 1965 to 2017 are taken as the research objects. The performance test of the new algorithm shows that it has higher stability and accuracy. In addition, the forecasting results of the new algorithm are compared with the other eight algorithms, it shows that the novel hybrid algorithm has stronger global optimization ability, faster convergence speed, and higher accuracy, and has a medium calculation speed. Regarding the forecast of carbon dioxide emissions, compared with other five models (such as back-propagation neural network and least squares support vector machine), the mean absolute error of the new model (in the test set) decreased by 30.68-163.35 MT, and the mean absolute percentage error decreased by 0.726%-1.878%. Finally, the new model is utilized to forecast carbon dioxide emissions in various countries from 2018 to 2025. (C) 2019 Elsevier Ltd. All rights reserved.