Snow mass observation based on EO data and machine learning (SNOWTRANE)

The accurate monitoring of snow water equivalent (SWE) is critical to assess global water resources. More than a billion people worldwide rely on snow for the supply of drinking water. Snowmelt furthermore supports agriculture, industry, and hydropower generation, but can also cause hazards such as floods and avalanches. Snow also impacts our climate: the high albedo reflects up to 90% of the incoming solar energy back to the atmosphere, while the insulating properties reduce heat exchange with the atmosphere. Despite the importance, we still lack a basic understanding of how much snow is seasonally stored on Earth, especially in mountains where a major part of the terrestrial snow is located. Sparse in situ measurements are unable to capture the SWE variability in mountain areas. Land surface models show insufficient skill and often underestimate mountain SWE due to an under-catch of orographic precipitation. The operational global-scale passive microwave satellite retrievals are less suitable in mountainous areas, as their ~25-km resolution is too coarse to characterize the spatial variability and the measurements saturate in deep (>0.8 m) snow. Active microwave observations at Ku-band (12-18 GHz) frequency are promising, but satellite observations are lacking. The Snowtrane project aims at improving our knowledge of mountain SWE variability by developing novel satellite SWE retrievals from the Sentinel-1 mission.