Spatial-temporal constraints for surface soil moisture mapping using Sentinel-1 and Sentinel-2 data over agricultural regions

Surface soil moisture (SSM) information could have important applications in agricultural and regional water management. Remote sensing, particularly synthetic aperture radar (SAR), is an important technology for the estimation of spatial–temporal SSM over larger areas. Using Sentinel-1 and Sentinel-2 data, this research developed a general spatial–temporal constrained machine-learning-based method for surface soil moisture mapping over agricultural regions. Central to this method is the construction of spatial and temporal constraints and their implementation in machine-learning models. We first defined the spatial and temporal constraints for SSM estimation by investigating the spatial division of cultivated crop types and the temporal division of cumulative precipitation. Second, under the presumption that the SSM and associated variables are smoothly changing, we extracted the temporal difference variables from the multi-temporal remote sensing data. Finally, we incorporated two constraints as categorical features and temporal differences into a CatBoost-based model to improve surface soil moisture mapping. We verified the proposed model in a Spain study area with multi-temporal remote sensing observations. The experimental results after incorporating the spatial–temporal constraints demonstrate the efficacy of the proposed model for mapping surface soil moisture over agricultural regions, with significantly improved R2 = 0.7328, RMSE = 0.0451 vol, and MAE = 0.0351 vol This study also concluded that using multiple polarization in the machine-learning-based method could reliably and accurately estimate surface soil moisture.