Towards an object-based multi-scale soil moisture product using coupled Sentinel-1 and Sentinel-2 data

Abstract

ABSTRACTWith the advent of the new generation of microwave and optical sensors with unique characteristics, the multi-sensor fusion for the soil moisture retrieval has given rise to a considerable research interest. The Sentinel satellites enable operational soil moisture mapping with moderate accuracy while providing regular temporal coverage and high spatial resolution at no cost to the users. In the meantime, working at the object level enables us to take advantage of some of the unique capabilities of this approach. This letter outlines an object-based approach for the multi-scale soil moisture retrieval by coupling the single polarization C-band synthetic aperture radar (SAR) and optical data. To fulfil this goal, a broad range of optical and texture features was extracted from the optical and single polarization mode SAR data. Subsequently, the relevant features were properly selected using the Random Forest-Recursive Feature Elimination (RF-RFE) algorithm. Then, the selected features were imported to the segmentation process to create the image objects. Afterwards, the support vector regression (SVR) technique was used to estimate the soil moisture value of the image objects and to conduct the multi-scale soil moisture retrieval with a small training database. It is observed that the proposed approach can provide multi-scale soil moisture maps with a reasonable accuracy in different applications requiring different scale requirements.