Hybrid Methodology Using Sentinel-1/Sentinel-2 for Soil Moisture Estimation

Soil moisture is an essential parameter for a better understanding of water processes in the soil–vegetation–atmosphere continuum. Satellite synthetic aperture radar (SAR) well suited monitoring content at fine spatial resolutions on order 1 km or higher. Several methodologies are often considered inversion SAR signals: machine learning techniques, such as neural networks, empirical models and change detection methods. In this study, we propose two hybrid by improving approach with vegetation consideration combining together network algorithm. The methodology based Sentinel-1 Sentinel-2 data use numerous metrics, including vertical–vertical (VV) vertical–horizontal (VH) polarization signals, classical surface soil (SSM) index ISSM, incidence angle, normalized difference (NDVI) optical index, VH/VV ratio. Those approaches tested using situ from ISMN (International Moisture Network) observations covering different climatic contexts. results show improvement estimations algorithms, particular one, which correlation increases 54% 33% respect to that alone, respectively.