Predicting the carbon dioxide emission of China using a novel augmented hypo-variance brain storm optimisation and the impulse response function
2021
Boamah, Kofi Baah | Du, Jianguo | Adu, Daniel | Mensah, Claudia Nyarko | Dauda, Lamini | Khan, Muhammad Aamir Shafique
For the past decade, the level of carbon dioxide emission in most cities in China is on the ascendancy. Yet, better prediction of environmental pollution is at the fringes of recent studies. Several erstwhile researchers have attempted predicting pollution whilst utilising approaches including the ordinary linear regressions, multivariate regressions, autoregressive integrated moving average (ARIMA), evolutionary and some conventional swarm intelligence. These conventional approaches, however, lead but to imprecise predictions owing to the inherent parameter problems characterised in those approaches. Consequently, there is the need for a better prediction of the key antecedents that affect air pollution whilst using robust techniques. This current study, therefore predicts the carbon emissions levels of China into the next decade, in response to changes in key economic variables: energy consumption, economic growth, trade, and urbanisation. This is to aid in monitoring and implementing of tailored policies and transformations in China and in similar developing and emerging economies. Our findings revealed a steadily rise in emissions as the economy grows during the initial years but decline in the ensuing forecasted period. The findings of the impulse response function, revealed that in the next decade, urbanisation, and trade (import and export) will be the major contributors of carbon dioxide emission. The proposed Brainstorm optimisation algorithms prediction model was verified and validated with actual data. Our study revealed that the Brainstorm Optimisation algorithm predicts better with less prediction error even under uncertainty information.
Show more [+] Less [-]AGROVOC Keywords
Bibliographic information
This bibliographic record has been provided by National Agricultural Library