Atmospheric variables play a major role in sea level variations in the eastern central Red Sea, where the role of tides is limited to 20% or less. Extensive analysis of daily-averaged residual sea level and atmospheric variables (atmospheric pressure, air temperature, wind stress components, and evaporation rate) indicated that sea level variations in the eastern central Red Sea are mainly contributed to by the seasonal and weather-band variations in the utilized atmospheric variables. The Non-linear Auto-Regressive Network with eXogenous inputs (NARX), a type of Artificial Neural Network (ANN), was applied to investigate the role of the atmospheric variables on the sea level variations at the eastern central Red Sea. Forced by time-delayed daily-averaged observations of atmospheric variables and residual sea level, the constructed NARX-based model showed high performance in predicting the one-step-ahead residual sea level. The high performance indicated that the constructed model was able to efficiently recognize the role played by the atmospheric variables on the residual sea level variations. Further investigations, using the constructed NARX-based model, revealed the seasonal variation in the role of the atmospheric variables. The study also revealed that the role played by some of the atmospheric variables, on sea level variations, could be masked by the role of one or more of the other atmospheric variables. The obtained results clearly demonstrated that this neurocomputing (NARX) approach is effective in investigating the individual and combined role of the atmospheric variables on residual sea level variations.