Monitoring of Alpine snow using satellite radiometers and artificial neural networks

The Alps represent an extremely complex environment in which snow properties suffer dramatic spatial variations that cannot easily be followed by space-borne microwave radiometers, due to their coarse spatial resolution. An improved method for monitoring the Snow Cover Extent (SCE) and the Snow Depth (SD) on alpine areas is presented here. Equivalent brightness Temperature Tbeq at an enhanced spatial resolution, corrected for the effects of orography and forest coverage, were computed from the AMSR-E measurements by using ancillary information on land use, surface temperature, and a digital elevation model (DEM). These equivalent values were used as inputs of an algorithm that merges empirical approaches and Artificial Neural Network (ANN) techniques for estimating snow properties on a global scale. The performances of the algorithm have been tested by using AMSR-E data collected during the winters between 2002 and 2011 on a test area located in the eastern part of the Italian Alps. Index Terms - AMSR-E, Brightness Temperature, Snow Depth, Snow Water Equivalent, Artificial Neural Networks.