Utilizing Artificial Intelligence for Accurate Population Predictions for Iraq Through 2030

This paper focuses on population forecasting for Iraq until 2030, using artificial intelligence techniques to align with the UN's Sustainable Development Goals (SDGs). It compares the effectiveness of recurrent neural network (RNN) and autoregressive integrated moving average (ARIMA) models by evaluating historical population data, and demographic, and socioeconomic indicators. The RNN method outperforms ARIMA, providing more accurate projections with lower root mean square error (RMSE) and higher coefficient of determination (R). The study directly contributes to various SDGs, including Goal 3 (Good Health and Wellbeing), Goal 4 (Quality Education), Goal 9 (Industry, Innovation, and Infrastructure), Goal 11 (Sustainable Cities and Communities), and Goal 17 (Partnerships for the Goals). The accurate population projections derived from this research have practical implications for healthcare planning, education resource estimation, and infrastructure development, promoting the sustainable well-being of the Iraqi population. Policymakers, urban planners, and decision-making organizations can benefit from these insights. Future research may involve incorporating additional data sources and refining forecasting models to enhance accuracy and further contribute to the achievement of the SDGs. The primary discovery in this study demonstrates that the utilization of the RNN approach yields superior results in comparison to conventional models, even in the presence of a restricted dataset or a limited number of observations.