Evaluation of two observation operator schemes for wind profiler radar data assimilation and its impacts on short-term forecasting

The assimilation of wind profiler (profiler) observations has the potential of improving the model initial condition of dynamical field with its high spatial and temporal wind field information. In this study, the impacts of two kinds of wind observation operators, i.e., eastward and northward velocities (u and v; uv_scheme) and wind speed and direction (spd and dir; sd_scheme), on analyses and forecasts are discussed to determine the optimal observation operator for profiler data assimilation. To compare the performance of the two observation operators on profiler data assimilation, we carry out a series of single wind tests and a two-week period cycling assimilation and forecasting experiments. The single wind tests show that the adjustment of the two observation operators to the analyses of wind can be significantly different with large innovation (OMB) of dir. The uv_scheme adjusts the corresponding model variables by ingesting profiler information of u and v winds, so that the analyzed spd is indirectly affected by the observed dir. By contrast, the changes in observed dir will not affect the analyzed spd in sd_scheme, as the observed spd and dir are independently assimilated. The case diagnoses illustrate that the sd_scheme generates the best analysis of wind in RMSE when validating against either the profiler or the pilot observations. The improved analysis of winds in turn leads to better wind forecasts and precipitation prediction, confirming the advantage of sd_scheme. Results from the cycling experiments further demonstrate that, compared with the uv_scheme, the sd_scheme shows decent improvements in wind forecasts, thus leading to better precipitation forecast skills.