Evaluation of the snow cover variation in the Canadian Regional Climate Model over eastern Canada using passive microwave satellite data

Snow cover from a 3 year (1992/93-1994/95) simulation of the Canadian Regional Climate Model (CRCM; operational version 3(.)5(.)3) driven by National Centers for Environmental Prediction analysis data over eastern Canada was evaluated using passive-microwave-derived snow cover information from the daily Special Sensor Microwave/Imager (SSM/I) data. The presence of snow on the ground was derived from 19 and 37 GHz normalized difference brightness temperature series to which a low-pass filter was applied to remove day-to-day noise, and thresholding was also applied at different levels for taking into account the variation in vegetation density. The thresholds calibrated for four density classes with surface observations show a mean residual underestimation in the SSM/I number of days with snow cover during seasonal transition of -7 days. Compared with the SSM/I-derived information, the CRCM was found to delay systematically the onset of the snow cover (typically 50 days late) and to ablate snow too quickly during the spring melt period (typically 30 days early). These systematic errors were attributed to the single-layer force-restore representation of the soil-snow layer and contributed to snow cover extent underestimations in the order of 9% relative to the total area. Copyright (C) 2004 John Wiley Sons, Ltd.