Sentinel-1/Sentinel-2-Derived soil moisture product at plot scale (S²MP)

Loïc Lozac'H (1) , Hassan Bazzi (1) , Nicolas Baghdadi (1) , Mohammad El Hajj (1) , Mehrez Zribi (2) , Rémi Cresson (1)

1 UMR TETIS - Territoires, Environnement, Télédétection et Information Spatiale
2 CESBIO - Centre d'études spatiales de la biosphère

The objective of this paper is to present an operational approach for mapping soil moisture at high spatial resolution over agricultural areas with vegetation cover. The developed approach uses the neural network (NN) technique based on coupling Sentinel-1 radar data and Sentinel-2 optical data. The neural networks were developed and validated using synthetic and real databases. To operationally map the soil moisture, the developed NN uses the C-band SAR signal in VV polarization, SAR incidence angle, and the Normalized Differential Vegetation Index "NDVI" as the inputs. To optimize the automatic production of soil moisture maps a pipeline using the Orfeo Toolbox is implemented.

Mots clés: Orfeo Toolbox; Soil Moisture; Sentinel-1; Sentinel-2

Domaines: Environnement et Société; Sciences de l'environnement

Loïc Lozac'H, Hassan Bazzi, Nicolas Baghdadi, Mohammad El Hajj, Mehrez Zribi, et al.. Sentinel-1/Sentinel-2-Derived soil moisture product at plot scale (S²MP). IEEE Geoscience and Remote Sensing Society (M2GARSS 2020), Mar 2020, Tunis, Tunisia. ⟨10.1109/M2GARSS47143.2020.9105210⟩. ⟨hal-02631856⟩