This study evaluates the ability of the Catchment SIMulation (CSIM) hydrologic model to describe seasonal and regional variations in river discharge over the entire Baltic Sea drainage basin (BSDB) based on 31 years of monthly simulation from 1970 through 2000. To date, the model has been successfully applied to simulate annual ﬂuxes of water from the catchments draining into the Baltic Sea.
Here, we consider spatiotemporal bias in the distribution of monthly modeling errors across the BSDB since it could potentially reduce the ﬁdelity of predictions and negatively affect the design and implementation of land-management strategies.
Within the period considered, the CSIM model accurately reproduced the annual ﬂows across the BSDB; however, it tended to underpredict the proportion of discharge during high-ﬂow periods (i.e., spring months) and overpredict during the summer low ﬂow periods. While the general over- predictions during summer periods are spread across all the subbasins of the BSDB, the underprediction during spring periods is seen largely in the northern regions.
By implementing a genetic algorithm calibration procedure and/or seasonal parameterization of subsurface water ﬂows for a subset of the catchments modeled, we demonstrate that it is possible to improve the model performance albeit at the cost of increased parameterization and potential loss of parsimony.