Decision Support for Carbon Emission Reduction Strategies in China’s Cement Industry: Prediction and Identification of Influencing Factors

Abstract

China is one of the world’s largest producers and consumers of cement, making carbon emissions in the cement industry a focal point of current research and practice. This study explores the prediction of cement consumption and its influencing factors across 31 provinces in China using the RF-MLP-LR model. The results show that the RF-MLP-LR model performs exceptionally well in predicting cement consumption, with the Mean Absolute Percentage Error (MAPE) below 10% in most provinces, indicating high prediction accuracy. Specifically, the model outperforms traditional models such as Random Forest (RF), Multi-Layer Perceptron (MLP), and Logistic Regression (LR), especially in handling complex scenarios or specific regions. The study also conducts an in-depth analysis of key factors influencing cement consumption, highlighting the significant impact of factors such as per capita GDP, per capita housing construction area, and urbanization rate. These findings provide important insights for policy formulation, aiding the transition of China’s cement industry towards low-carbon, sustainable development, and contributing positively to achieving carbon neutrality goals.