Improved forecasting of carbon dioxide emissions using a hybrid SSA ARIMA model based on annual time series data in Bahrain

Forecasting carbon dioxide (CO₂) emissions has become crucial for attaining environmental sustainability, especially in Bahrain, which uses a lot of fossil fuels. Therefore, there is need for more accurate modeling tools that are suited to Bahrain emission pattern, particularly in light of the increasing environmental pressure and dearth of previous studies. Accordingly, we proposed a hybrid forecasting model that combines Singular Spectrum Analysis (SSA) and the Auto Regressive Integrated Moving Average (ARIMA) method. This hybrid model decomposes the annual CO₂ emissions time series into trend, periodic, and noise components using SSA, then applies ARIMA individually to each component. As a result, the study makes use of World Bank annual CO₂ emission data for three different time periods: 1990-2018, 2000-2018, and 2003-2018. The model performance was evaluated using standard error metrics-Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE). To assess whether the observed improvements were statistically significant, the Diebold-Mariano (DM) test was also applied, a widely used method for comparing the predictive accuracy of competing models. In addition, forecast evaluation metrics such as Theil's U-statistic and out-of-sample forecast plots with confidence intervals were also used to strengthen the assessment of the models. Results show that the SSA-ARIMA hybrid model significantly outperforms the conventional ARIMA model. For instance, during the 2014-2018 period, the hybrid model achieved lower MAPE values (1.12%, 0.91%, and 1.40%) compared to ARIMA (2.14%, 1.69%, and 1.41%) across the respective time frames. These results demonstrated the hybrid SSA-ARIMA model's potential as a reliable tool for Bahrain's emissions forecasting.