Forecasting CO2 Emissions in Egypt Using ARIMA and LSTM models A Step Towards Sustainability

Accurate forecasting of carbon dioxide (CO₂) emissions is crucial for developing effective climate change mitigation strategies and promoting sustainable development. This study compares the performance of two widely used forecasting models ARIMA and LSTM in predicting CO₂ emissions in Egypt till 2035. Utilizing a dataset of 113 data points from 1911 to 2023, the study evaluates the models using key performance metrics, including MAE, MSE, MAPE, and R-squared (R²). The results indicate that the LSTM model outperforms ARIMA in minimizing absolute and squared errors (MAE: 2.51 vs. 3.65; MSE: 12.27 vs. 36.95) and capturing more variance in the data (R²: 0.998 vs. 0.995). However, ARIMA demonstrates better proportional accuracy, as reflected in its lower MAPE (11% vs. 18%). Both models predict a steady increase in Egypt's CO₂ emissions, with LSTM projecting a slightly faster growth rate in later years. The findings highlight the strengths and limitations of each model, offering valuable insights for policymakers and researchers aiming to design effective emissions reduction strategies. This study contributes to the growing body of literature on CO₂ emissions forecasting, particularly in the context of developing countries, and highlights the importance of selecting appropriate models based on data characteristics and forecasting objectives. This research represents a significant step towards sustainability by providing reliable tools for forecasting CO₂ emissions, which are essential for informed policy-making and environmental planning. By identifying the most effective forecasting approach, the study supports Egypt's efforts to transition to cleaner energy sources, reduce greenhouse gas emissions, and achieve its climate goals.