Estimation of carbon dioxide emissions from the cement industry in Beijing-Tianjin-Hebei using neural networks

Abstract

This study develops a method to predict carbon dioxide (CO ₂) emissions from the cement industry in the Beijing-Tianjin-Hebei region using artificial intelligence-based neural networks. By analyzing data from the National Bureau of Statistics and the China Statistical Yearbook (2010–2021), we calculated CO ₂ emissions generated by fossil fuel combustion during cement production. The neural network model achieved robust predictive performance with a root mean square error (RMSE) of 0.05, a mean absolute error (MAE) of 2,640,769 tons, and a coefficient of determination (R ²) of 0.9620. These results demonstrate the model’s effectiveness in identifying emission trends and supporting real-time strategies to mitigate CO ₂ emissions. Future research could expand this approach to other high-emission industries, providing valuable tools for global carbon reduction efforts.