Since most of the primary atmospheric pollutants are emitted inside the roughness sublayer (RSL) and consequently the first chemical reactions and dispersion occur in this layer, it is necessary to generate detailed meteorological fields inside the RSL to perform air quality modeling at high spatial resolutions. At neighborhood scale (on order of 1-km horizontal grid spacing), the meteorological fields are strongly influenced by the presence of the vegetation and building morphology of varying complexity, which requires developing more detailed treatment of the influence of canopy structures in the models and using additional morphological databases as input. The assumptions of the roughness approach, used by most of the mesoscale models, are unsatisfactory at this scale. Hence, a detailed urban and rural canopy parameterization (Dupont et al., 2003c), called DA-SM2-U, has been developed inside the Penn State/NCAR Mesoscale Model (MM5) to simulate the meteorological fields within and above the urban and rural canopies.