As the greenhouse effect intensifies, China faces pressure to manage CO2 emissions. Coal-fired power plants are a major source of CO2 in China. Traditional CO2 emission accounting methods of power plants are deficient in computational efficiency and accuracy. To solve these problems, this study proposes a novel RF-RFE-DF-Optuna (random forest–recursive feature elimination–deep forest–Optuna) framework, enabling accurate CO2 emission prediction for coal-fired power plants. The framework begins with RF-RFE for feature selection, identifying and extracting the most important features for CO2 emissions from the power plant, reducing dimensionality from 46 to just 5 crucial features. Secondly, the study used the DF model to predict CO2 emissions, combined with the Optuna framework, to enhance prediction accuracy further. The results illustrated the enhancements in model performance and showed a significant improvement with a 0.12706 increase in R2 and reductions in MSE and MAE by 81.70% and 36.88%, respectively, compared to the best performance of the traditional model. This framework improves predictive accuracy and offers a computationally efficient real-time CO2 emission monitoring solution in coal-fired power plants.
