<![CDATA[Carbon Dioxide (CO₂) emissions are a primary driver of global climate change, with the energy sector being the dominant contributor. Southeast Asia, experiencing rapid economic growth, faces significant increases in CO₂ emissions due to high energy consumption. This study proposes a hybrid Autoregressive Integrated Moving Average (ARIMA)-XGBoost approach to predict CO₂ emissions in Association of Southeast Asian Nations (ASEAN) countries from 2023 to 2035, overcoming limitations of traditional linear models by combining machine learning (XGBoost) and time-series analysis ARIMA. Results demonstrate high accuracy (R² = 0.98) with the identification of key factors, including Gross Domestic Product (GDP), population, and total greenhouse gas (GHG) emissions. For instance, Indonesia's emissions are predicted to rise from 841.84 MtCO₂ (2023) to 2197.36 MtCO₂ (2035), while Brunei's emissions decrease from 10.86 MtCO₂ to 9.57 MtCO₂. Residual analysis and k-fold cross-validation confirm model robustness. These findings underscore the need for differentiated policies, such as renewable energy transitions in high-growth emission countries (Indonesia, Philippines) and regulatory strengthening in stable-trend nations (Brunei, Laos). The study provides methodological contributions to data-driven emission forecasting and evidence-based policy recommendations for the Association of Southeast Asian Nations (ASEAN) climate change mitigation.]]>
Copyrights © 2025
