A novel multivariable grey differential dynamic prediction model with new structures and its application to carbon emissions

The accurate prediction of carbon emissions is of great significance for countries to implement scientific and effective policies and measures. In this paper, a novel multivariable grey differential dynamic prediction model is established to analyse and forecast China’s carbon emissions. The differential term of the correlation variables is introduced to consider the influence of the rate of change of the related factors on the system. The linear correction term and grey action are introduced to increase the stability and adaptability of the model. The whitening differential equation of the model is solved by the Sadik transform, and the time response of the model is obtained. In the case study, the model used China’s carbon emissions and related data from 2004 to 2019 to calculate four cases. Its minimum simulation and prediction errors are 1.4435% and 3.1739%, respectively. Compared with the other four models, this model has better simulation and prediction accuracy, which proves the model’s effectiveness. Finally, the model forecasts China’s carbon emissions from 2020 to 2024, and some suggestions are put forwards based on the predicted results.