摘要
Global warming is majorly caused by an increase in atmospheric temperature and carbon dioxide (CO2) emissions due to the rise in the temperature. The continued accumulation of CO2 into the atmosphere is a massive part of the climate change problem. This study aims to develop a data-driven statistical model using Africa’s fossil-fuel CO2 emissions real data to identify the significant attributable variables and their interaction that produce the carbon dioxide emissions. However, we have considered five attributable variables in our statistical modeling and they are Liquid fuels (Li), Solid fuels (So), Gas fuels (Ga), Gas flares (Gf) and Cement production. The development of the statistical model that contains the different emissions of fossil fuels and their interactions have been specified and ranked based on a percentage of their annual contributions to carbon dioxide in the atmosphere. Our proposed statistical model is compared with a different penalization method since multicollinearity among the risk factors exists and which provided excellent results according to the root mean square errors (RMSE) statistic. The results of the proposed model are compared to previous results of different countries of the world.
Global warming is majorly caused by an increase in atmospheric temperature and carbon dioxide (CO2) emissions due to the rise in the temperature. The continued accumulation of CO2 into the atmosphere is a massive part of the climate change problem. This study aims to develop a data-driven statistical model using Africa’s fossil-fuel CO2 emissions real data to identify the significant attributable variables and their interaction that produce the carbon dioxide emissions. However, we have considered five attributable variables in our statistical modeling and they are Liquid fuels (Li), Solid fuels (So), Gas fuels (Ga), Gas flares (Gf) and Cement production. The development of the statistical model that contains the different emissions of fossil fuels and their interactions have been specified and ranked based on a percentage of their annual contributions to carbon dioxide in the atmosphere. Our proposed statistical model is compared with a different penalization method since multicollinearity among the risk factors exists and which provided excellent results according to the root mean square errors (RMSE) statistic. The results of the proposed model are compared to previous results of different countries of the world.
