Assimilation of ground and satellite snow observations in a distributed hydrologic model for water supply forecasting

Abstract

Runoff from the Upper Colorado River Basin (UCRB) is an important water resource in the western United States. The majority of annual runoff is derived from spring snowmelt, and therefore April-July water supply volume (WSV) forecasts produced by the Colorado Basin River Forecast Center are critical to basin water management. The primary objective of this study was to evaluate the impact of snow data assimilation (DA) in a distributed hydrologic model on WSV forecasting error and skill in headwater catchments of the UCRB. To do this, a framework was built to use the Localized Ensemble transform Kalman filter to update modeled snow water equivalent (SWE) states in the Hydrology Laboratory-Research Distributed Hydrologic Model with SNOTEL SWE observations and spatially and temporally complete MODIS Snow Covered-Area and Grain size data. The DA approach was assessed by evaluating ensemble streamflow prediction forecasts over a 20-year period for 23 catchments in the UCRB. Overall, the DA approach improved water supply forecast skill in 80% of pilot basins with an average improvement in the median continuous rank probability skill score of 4%. A research-to-operations transition was facilitated by automating the implementation of the DA approach. This work demonstrates the capacity for gridded and point snow products to be used to objectively update model states in an operational forecasting setting.