Data: Decoding the Mechanisms and Predicting Provincial CO2 Emissions in China with Interpretable Machine Learning

This dataset provides provincial-level carbon emission data for China from 2011 to 2021, along with key socioeconomic and environmental variables used in machine learning-based carbon emission prediction models. The dataset was developed as part of a study aimed at improving the accuracy and interpretability of carbon emission predictions in China using multiple machine learning algorithms, SHAP (Shapley Additive exPlanations) analysis, and Structural Equation Modeling (SEM). The dataset includes key feature variables related to economic development, land use, and environmental factors, which were identified as significant drivers of carbon emissions.