Combined Sentinel-1A with Sentinel-2A to Estimate Soil Moisture in Farmland

Abstract

In this article, seven filter algorithms were compared. The Lee sigma method was more suitable for estimating soil moisture (SM) than the other filtering methods under different land cover types. First, we used a combination of roughness and the dual-polarized Sentinel-1A backscattering coefficients (VV and VH) to estimate SM in bare soil areas. Second, we employed water cloud model (WCM) to remove the influence of vegetation signals on the land surface backscattering and estimate SM in vegetation-covered areas. SM was also retrieved by modified soil moisture monitoring index (MSMMI) and modified perpendicular drought index (MPDI) of Sentinel-2A images. The results show that MSMMI can more accurately monitor SM in bare soil areas, which was slightly better than synthetic aperture radar (SAR) results. The SAR backscattering coefficients after the removal of vegetation influence by WCM can more precisely estimate SM in vegetation-covered areas, which is significantly better than MSMMI and MPDI, especially in high vegetation-covered areas. Optics and SAR differ in their abilities to estimate SM under different land cover, but the powerful fitting ability of machine learning can make full use of their advantages. We employed the generalized regression neural network (GRNN), support vector regression (SVR), random forest regression (RFR), and deep neural network (DNN) algorithms to estimate SM combining Sentinel-1A with Sentinel-2A images. The estimation accuracies of SM by regression algorithms were higher than those by the semiempirical SAR and optical models. The accuracy of estimated SM by DNN was higher than that of GRNN and RFR, which were better than SVR.