Simulating low-probability peak discharges for the Rhine basin using resampled climate modeling data

Climate change will increase winter precipitation, and in combination with earlier snowmelt it will cause a shift in peak discharge in the Rhine basin from spring to winter. This will probably lead to an increase in the frequency and magnitude of extreme floods. In this paper we aim to enhance the simulation of future low-probability flood peak events in the Rhine basin using different climate change scenarios, and downscaling methods. We use the output of a regional climate model (RCM) and a weather generator to create long, resampled time series (1000 years) of climate change scenarios as input for hydrological (daily) and hydrodynamic (hourly) modeling. We applied this approach to three parallel modeling chains, where the transformation method from different resampled RCM outputs to the hydrological model varied (delta change approach, direct output, and bias-corrected output). On the basis of numerous 1000 year model simulations, the results indicate a basin-wide increase in peak discharge in 2050 of 8%-17% for probabilities between 1/10 and 1/1250 years. Furthermore, the results show that increasing the length of the climate data series using a weather generator reduced the statistical uncertainty when estimating low-probability flood peak events from 13% to 3%. We further conclude that bias-corrected direct RCM output is to be preferred over the delta change approach because it provides insight into geographical differences in discharge projections under climate change. Also, bias-corrected RCM output can simulate changes in the variance of temperature and rainfall and in the number of precipitation days, as changes in temporal structure are expected under climate change. These added values are of major importance when identifying future problem areas due to climate change and when planning potential adaptation measures.