Identification and Prediction of Key Factors Influencing Carbon Emissions Based on the STIRPAT Model and IPNEG-BP Neural Network

With the intensification of global climate change, low-carbon development and carbon emission control have become key issues of common concern to the international community. This paper first utilizes the STIRPAT model in conjunction with ridge regression analysis to identify key indicators influencing carbon emissions. The ridge trace analysis yielded a variance inflation factor determining K=0.063, while the model’s goodness of fit, R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup>, stood at 0.941, indicating excellent model performance. The research identifies industrial carbon emissions, population size, and natural growth rate as the primary driving forces behind the increase in carbon emissions. Having established significant factors influencing carbon emissions, the study then establishes the IPNEG-BP neural network model to forecast future carbon emissions. The model predicts a decrease in carbon emissions from 32.21 million tons in 2011 to 15.27 million tons by 2035.