Simulation of extreme rainfall and streamflow events in small Mediterranean watersheds with a one-way-coupled atmospheric-hydrologic modelling system

Coupled atmospheric-hydrologic systems are increasingly used as instruments for flood forecasting and water management purposes, making the performance of the hydrologic routines a key indicator of the model functionality. This study's objectives were (i) to calibrate the one-waycoupled WRF-Hydro model for simulating extreme events in Cyprus with observed precipitation and (ii) to evaluate the model performance when forced with WRF-downscaled (1 x 1 km(2)) re-analysis precipitation data (ERA-Interim). This set-up resembles a realistic modelling chain for forecasting applications and climate projections. Streamflow was modelled during extreme rainfall events that occurred in January 1989 (calibration) and November 1994 (validation) over 22 mountain watersheds. In six watersheds, Nash-Sutcliffe efficiencies (NSEs) larger than 0.5 were obtained for both events. The WRF-modelled rainfall showed an average NSE of 0.83 for January 1989 and 0.49 for November 1994. Nevertheless, hydrologic simulations of the two events with the WRF-modelled rainfall and the calibrated WRF-Hydro returned negative streamflow NSE for 13 watersheds in January 1989 and for 18 watersheds in November 1994. These results indicate that small differences in amounts or shifts in time or space of modelled rainfall, in comparison with observed precipitation, can strongly modify the hydrologic response of small watersheds to extreme events. Thus, the calibration of WRF-Hydro for small watersheds depends on the availability of observed rainfall with high temporal and spatial resolution. However, the use of modelled precipitation input data will remain important for studying the effect of future extremes on flooding and water resources.