Soil moisture sensor calibration based on the Multivariate Adaptive Regression Splines (MARSplines) model is studied in this paper. Different from the generic polynomial fitting methods, the MARSplines model is a non-parametric model, and it is able to model the complex relationship between the actual and measured soil moisture. Rao-1 algorithm is employed to tune the hyper-parameters of the calibration model and thus the performance of the proposed method is further improved. Data collected from four commercial soil moisture sensors is utilized to verify the effectiveness of the proposed method. To assess the calibration performance, the proposed model is compared with the model without using the temperature information. The numeric studies prove that it is promising to apply the proposed model for real applications.

This paper describes an individual effect of soil moisture (mg) and surface roughness (hrms) of bare soil on the back scattering coefficient (σ0) at the X-band frequency. The study contributes to the design of an efficient microwave sensor. For this purpose, experimentally observed data was utilized to provide a composite σ0 equation model accounting for individual effect in regression analysis. The experimental data are compared with Small Perturbation Method. It is observed that the X-band gives better agreement up to incidence angle 50 for HH-polarization and 60 for VV-polarization as compared to the C-band. The lower angles of incidence give better results than the higher angles for observing mg at the X-band. The multiple and partial regression analyses have also carried out for predicting the dependence of scattering coefficient (σ0) on mg and hrms more accurately. The analyses suggest that the dependence of dielectric constant (i.e., mg) is much more significant in comparison to surface roughness at lower angles of incidence for both like polarizations. The results propose the suitable angle of incidence for observing bare surface roughness and soil moisture at the X-band. All these data can be used as a reference for satellite or spaceborne sensors.