Abstract
Eddy-covariance data from five stations in the Inn Valley, Austria, are analyzed for stable conditions to determine the gap scale that separates turbulent from large-scale, non-turbulent motions. The gap scale is identified from (co)spectra calculated from different variables using both Fourier analysis and multi-resolution flux decomposition. A correlation is found between the gap scale and the mean wind speed and stability parameter z/L that is used to determine a time-varying filter time, whose performance in separating turbulent and non-turbulent motions is compared to the performance of constant filter times between 0.5 and 30 min. The impact of applying different filter times on the turbulence statistics depends on the parameter and location, with a comparatively smaller impact on the variance of the vertical wind component than on the horizontal components and the turbulent fluxes. Results indicate that a time-varying filter time based on a multi-variable fit taking both mean wind speed and stability into account and a constant filter time of 2-3 min perform best in that they remove most of the non-turbulent motions while at the same time capturing most of the turbulence. For the studied sites and conditions, a time-varying filter time does not outperform a well chosen constant filter time because of relatively small variations in the filter time predicted by the correlation with mean flow parameters.