There is an undisputed need to increase accuracy of snow cover estimation in regions of complex terrain, especially in areas dependent on winter snow accumulation for a substantial portion of their water supply, such as the Western United States, Central Asia, and the Andes. Presently, the most pertinent monitoring and research needs related to alpine snow cover extent (SCE) are: (1) to improve SCE monitoring by providing detailed fractional snow cover (FSC) products which perform well in temporal/spatial heterogeneous forested and/or alpine terrains; (2) to provide accurate measurements of FSC at the watershed scale for use in snow water equivalent (SWE) estimation for regional water management; (3) to provide detailed distributions of FSC in mountainous regions to investigate the temporal/spatial distribution of SCE/SWE in relation to recent climate changes; (4) to use FSC products as input for climate models at multiple scales; and (5) to estimate SCE and SWE for use in ecological studies (e.g., vegetation cover, water stress, primary production, fire, insect outbreaks, and pulses in tree demography).
To address the above our approach is based on Landsat Fractional Snow Cover (LandsatFSC), as a measure of the temporal/spatial distribution of alpine SCE. We used a fusion methodology between remotely sensed multispectral data from Landsat TM/ETM+ and Ikonos utilized at their highest respective spatial resolutions. Artificial Neural Networks (ANNs) are used to capture the multi-scale information structure of the data by means of the ANN training process, followed by the ANN extracting FSC from all available information in the Landsat images. The LandsatFSC algorithm was validated (RMSE ~ 0.09; mean error ~ 0.001–0.01 FSC) in watersheds characterized by diverse environmental factors such as: terrain, slope, exposition, vegetation cover, and wide-ranging snow cover conditions. The research results are presented for areas located in the San Juan Mountains of Colorado and the Black Hills of South Dakota, USA.