<![CDATA[Climate change has emerged as a pressing global issue, with carbon dioxide (CO2) emissions serving as a major contributor to global warming. In Indonesia, the expansion of industrial activities, transportation, and the reliance on fossil fuel-based energy have significantly accelerated CO2 emission levels. In this context, the need for accurate emission forecasting has become increasingly important as a basis for formulating data-driven mitigation policies. This study aims to develop a predictive model for CO2 emissions in Indonesia using a hybrid approach that combines AutoRegressive Integrated Moving Average (ARIMA) and Long Short-Term Memory (LSTM) methods. ARIMA is employed to capture linear patterns in historical time series data, while LSTM is used to model the non-linear and complex dynamics often present in environmental data. The emission data used spans from 1970 to 2023, with training and testing data separated chronologically in an 80:20 ratio. The evaluation results show that the ARIMA model alone yielded suboptimal performance (RMSE: 2342.5139, MAE: 2341.5775, MAPE: 414.77%), whereas the LSTM model significantly improved prediction accuracy (RMSE: 49.3307, MAE: 45.5498, MAPE: 7.94%). The hybrid ARIMALSTM model achieved the best results, with an RMSE of 31.5778, MAE of 25.0335, and MAPE of 4.34%. These findings indicate that the combination of both methods substantially enhances prediction performance compared to standalone models. The implications of this research are twofold: academically, it contributes to methodological development in environmental data analysis; practically, it offers valuable insights for policymakers in formulating more effective and sustainable carbon emission reduction strategies in Indonesia. ]]>
Copyrights © 2025
