In this research, a methodology is employed to predict local wind levels in urban areas. A semi-analytical methodology is used to calculate local wind speed in Manhattan using regional wind speed. The model up-scales the regional wind level to the urban boundary layer; it then downscales the wind level to the average building height of urban localities through two downscaling steps. A geographic information system (GIS) framework is used to extract required input for the semi-analytical method. Using the GIS information, first aerodynamic parameters of localities in Manhattan are calculated. Next, using semi-empirical methods, wind speed at the average height of buildings in each locality are estimated. The results are presented as a wind localization index map for Manhattan that can be used to calculate local wind speed at any location in the city as a function of the regional wind level. The local wind index can be used to identify the urban localities with higher local wind speeds which can be suited for harnessing wind energy on top of high-rises.