Wind energy involves converting the wind’s kinetic energy into electrical energy through wind turbines, which is considered a clean energy source. Thus, accurate wind power estimation is crucial for effective wind farm planning and design. Consequently, this research focuses on predicting monthly wind power density (WPD) in Mediterranean Coastal Cities using three artificial models (radial basis neural network, multi-layer perceptron neural network, and Elman neural network), as well as two mathematical models (quadratic model, and multiple linear regression) for the first time. Case studies encompass twenty-seven cities along the eastern Mediterranean coastline. To this aim, two distinct scenarios were devised. In scenario 1, the model utilized global meteorological data (GMD) including parameters such as precipitation (PP), maximum (Tmax) and minimum (Tmin) temperatures, actual evapotranspiration (AE), wind speed at 10m elevation (WS), and solar radiation (SR) as input variables. Scenario 2 is formulated by including geographical coordinates (GC) into the GMD, aiming to assess the influence of GC on the precision of monthly WPD predictions. The results indicate that scenario 2 exhibits greater prediction accuracy in comparison to scenario 1. Additionally, it is suggested that the quadratic model is a suitable choice for capturing the complexity of interactions among WPD, climate conditions, and geographical coordinates, thereby enhancing the accuracy of WPD predictions.