摘要：In June 1876, June 1910, and August 2005, northern Switzerland was severely impacted by heavy precipitation and extreme floods. Although occurring in different centuries, all three events featured very similar precipitation patterns and an extratropical storm following a cyclonic, so-called Vb (five b of the van Bebber trajectories) trajectory around the Alps. Going back in time from the recent to the historical cases, we explore the potential of dynamical downscaling of a global reanalysis product from a grid size of 220 to 3 km. We investigate sensitivities of the simulated precipitation amounts to a set of differing configurations in the regional weather model. The best-performing model configuration in the evaluation, featuring a 1 d initialization period, is then applied to assess the sensitivity of simulated precipitation totals to cyclonic moisture flux along the downscaling steps. The analyses show that cyclone fields (closed pressure contours) and tracks (minimum pressure trajectories) are well defined in the reanalysis ensemble for the 2005 and 1910 cases, while deviations from the ensemble mean increase for the 1876 case. In the downscaled ensemble, the accuracy of simulated precipitation totals is closely linked to the exact trajectory and stalling position of the cyclone, with slight shifts producing erroneous precipitation, e.g., due to a break-up of the vortex if simulated too close to the Alpine topography. Simulated precipitation totals only reach the observed ones if the simulation includes continuous moisture fluxes of >200 kg m−1 s−1 from northerly directions and high contributions of (embedded) convection. Misplacement of the vortex and concurrent uncertainties in simulating convection, in particular for the1876 case, point to limitations of downscaling from coarse input for suchcomplex weather situations and for the more distant past. On the upside,single (contrasting) members of the historical cases are well capable ofillustrating variants of Vb cyclone dynamics and features along the downscaling steps.
