Seasonal and spatial variations of cross-correlation matrices used by stochastic weather generators

We examine seasonal and spatial variations of stochastic-weather-generator (SWG) parameters and their impact on simulated weather sequences, Using daily weather observations from 29 stations across the contiguous United States, we estimate monthly station-specific parameters that are compared with the constant parameters that frequently are used in SWG applications. A WGEN-type SWG is then used to generate a 100 yr record of daily maximum and minimum air temperature and daily total solar radiation at each station. These sequences are compared to sequences generated with constant parameters. While the means and standard deviations of the generated sequences are in agreement, the SWG with station-specific parameters preserves relationships between variables. This is evident in both the lag-0 and lag-1 cross-correlations between generated variables and derived variables, such as diurnal temperature range. These results suggest that literature-based SWG parameters may be appropriate for applications where monthly values of the means and standard deviations of generated variables are of interest. For applications that require proper simulation of relationships between variables, station-specific parameterizations are recommended.