A Multi-scale Indicators Carbon Emission Prediction Method Based on Decision Forests

At the 2020 United Nations General Assembly, China presented its ‘dual carbon’ plan, which aims to reach the peak of carbon emissions and achieve carbon neutrality. However, accurately estimating and forecasting carbon emissions remains a significant challenge. Traditional methods for predicting carbon emissions are often limited and inaccurate. Decision Forests has recently shown promising advancements in addressing forecasting challenges. Thus, this study developed a carbon emission prediction model based on decision forests that incorporates a multi-scale indicator system. Decision Forests was employed for data mining using multi-scale indicator information. Key indicators such as energy consumption, population, GDP, and industrial consumption play a crucial role in predicting carbon emissions and enhancing the forecast accuracy of this model. Experimental results show that the proposed model outperforms other models in forecasting carbon emissions. Finally, this study provides detailed planning for governments and businesses based on predictions.