This paper presents an advanced forecasting model designed to predict carbon dioxide (CO₂) emissions in Thailand's electricity generation sector. By integrating a multivariate gray model with the fminsearch optimization algorithm in Matlab, the study addresses the critical challenge of accurately forecasting emissions, a major contributor to climate change. The model incorporates historical data on CO₂ emissions, gross domestic product (GDP), peak electricity demand, and electricity user numbers to enhance predictive accuracy. A comparative analysis between the conventional multivariate gray model and the optimized version reveals a significant improvement in forecasting precision. The optimized model achieves Mean Absolute Percentage Error (MAPE) values of 7.74% for the training set and 1.75% for the testing set, underscoring its effectiveness. This approach offers a robust tool for policymakers and stakeholders in Thailand’s energy sector, providing actionable insights to support more informed decision-making in managing and reducing CO₂ emissions.