Forecasting CO₂ Emissions From Industrial Processes: A Grey Model-based Approach

Abstract

- This study forecasts CO2 emissions from industrial processes in Vietnam to support climate change mitigation and sustainable development. Accurate forecasting provides valuable insights for policymakers and businesses in designing emission reduction strategies and achieving the Net Zero target by 2050. Three Grey forecasting models, namely the Gompertz Grey Model (GGM), Auto-Regressive Grey Model (ARGM (1,1)), and Nonlinear Grey Model (NGM (1,1,k,c)), were evaluated using World Bank data from 2000–2023. Forecasting performance was assessed using Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE). The results indicate that all models achieved acceptable accuracy (MAPE < 10%), with GGM outperforming the others (MAPE = 5.51%, RMSE = 2.1363). Therefore, GGM was selected to forecast CO2 emissions for 2025–2030, projecting a continued upward trend and highlighting the need for cleaner technologies and effective emission reduction policies.