Soil moisture is a key driver of many processes in the global cycles of water, energy, and carbon. It influences hydrological and agricultural processes, runoff generation, drought development and many more. Knowledge on the spatial and temporal distribution of this parameter is essential for a number of hydrological applications as well as other geosciences like meteorology or climatology.
The EURAC soil moisture product is based on a data-driven approach , integrating several datasets using the Support Vector Regression technique . First, for the training of the data-driven model a reference is required. For this purpose the NASA SMAP Level 4 surface soil moisture product is used. Level 4 products are model-derived value-added data products of surface and root zone soil moisture and carbon net ecosystem exchange, providing 3-hourly estimates at a spatial resolution of 9 km. Information on the soil moisture status, for the retrieval, is extracted from Sentinel-1 IW imagery, with a spatial resolution of 20 m. To allow the modelling of the complex backscattering mechanisms in mountainous terrains, topographic information is required, which is integrated in the shape of the SRTM digital elevation model (30 m spatial resolution). Finally, due to the fact that the measured SAR backscatter shows no sensitivity to soil moisture over densely vegetated areas (i.e. forest), these areas are masked using the CORINE land-cover classification. Further masking is applied based on the Sentinel-1 viewing geometry.
 Pasolli et al. (2015): Estimation of Soil Moisture in Mountain Areas Using SVR Technique Applied to Multiscale Active Radar Images at C-Band. Sel. Top. Appl. Earth Obs. Remote Sens. 8(1): 262–283.
 Greifeneder et al. (2016): Using machine learning and SAR data for the upscaling of large scale modelled soil moisture in the Alps 2 Datasets and Study Area. p. 1108–1111. In 11th European Conference on Synthetic Aperture Radar, EUSAR 2016. VDE, Hamburg.