Forecasting urban carbon emissions using an Adaboost-STIRPAT model

Solving outstanding environmental issues, reducing carbon emissions, and promoting green development are necessary ways to achieve carbon neutrality and carbon peak goals. It is also an important issue faced by society today. This paper uses the Kaya identity combined with the logarithmic mean Divisia index (LMDI) decomposition method to analyze the factors affecting carbon emissions, and uses the Pearson correlation coefficient to screen out eight highly correlated features to construct an extended STIRPAT model. In order to further improve the accuracy of the model in predicting carbon emissions, this paper introduces the Adaboost algorithm from machine learning to enhance the STIRPAT model. Finally, scenario analysis is used to predict and analyze carbon emissions in Shandong Province from 2020 to 2050. The results show that: 1) The main factors affecting urban carbon emissions from 1998 to 2019 are economic growth effects, followed by energy structure effects and energy consumption effects. 2) Under three different development scenarios, Shandong Province can achieve carbon peak between 2030-2035, but there are differences in peaking time and peak values.