Evaluation of Backscattering Models and Support Vector Machine for the Retrieval of Bare Soil Moisture from Sentinel-1 Data

Abstract

The main objective of this work was to retrieve surface soil moisture (SSM) by using scattering models and a support vector machine (SVM) technique driven by backscattering coefficients obtained from Sentinel-1 satellite images acquired over bare agricultural soil in the Tensfit basin of Morocco. Two backscattering models were selected in this study due to their wide use in inversion procedures: the theoretical integral equation model (IEM) and the semi-empirical model (Oh). To this end, the sensitivity of the SAR backscattering coefficients at V V ( σ v v ∘ ) and V H ( σ v h ∘ ) polarizations to in situ soil moisture data were analyzed first. As expected, the results showed that over bare soil the σ v v ∘ was well correlated with SSM compared to the σ v h ∘ , which showed more dispersion with correlation coefficients values (r) of about 0.84 and 0.61 for the V V and V H polarizations, respectively. Afterwards, these values of σ v v ∘ were compared to those simulated by the backscatter models. It was found that IEM driven by the measured length correlation L slightly underestimated SAR backscatter coefficients compared to the Oh model with a bias of about − 0.7 dB and − 1.2 dB and a root mean square (RMSE) of about 1.1 dB and 1.5 dB for Oh and IEM models, respectively. However, the use of an optimal value of L significantly improved the bias of IEM, which became near to zero, and the RMSE decreased to 0.9 dB. Then, a classical inversion approach of σ v v ∘ observations based on backscattering model is compared to a data driven retrieval technic (SVM). By comparing the retrieved soil moisture against ground truth measurements, it was found that results of SVM were very encouraging and were close to those obtained by IEM model. The bias and RMSE were about 0.28 vol.% and 2.77 vol.% and − 0.13 vol.% and 2.71 vol.% for SVM and IEM, respectively. However, by taking into account the difficultly of obtaining roughness parameter at large scale, it was concluded that SVM is still a useful tool to retrieve soil moisture, and therefore, can be fairly used to generate maps at such scales.

Surface Roughness Estimation in the Orog Nuur Basin (Southern Mongolia) Using Sentinel-1 SAR Time Series and Ground-Based Photogrammetry

“…At the same time, backscattering is regulated by the moisture conditions and the SAR data can be used to characterize surface roughness and (soil) moisture conditions (e.g., [26][27][28]), in turn, most of the preceding work focused on the estimation of soil moisture conditions. The relationship between surface roughness (estimated in the field by using pin profilers (e.g., [28,29]) or remote sampling techniques (e.g., [21][22][23]30,31])) and SAR backscatter of various sensors (e.g., for Sentinel-1 [28]) was investigated by using semi-empirical models (e.g., [28,32]), but was also analyzed by using empirical models (e.g., [26,29]). Thereby, most studies concentrated on applications in cultural land, especially for agricultural soils, (e.g., [16,27]) and less research was carried out for natural environments (e.g., [29,33]).…”

“…The indices considered in this study were widely used in related work to quantify surface roughness (e.g., [16,28,29]) and they were estimated in three different ways: 1D along X/Y profiles, 1D along circular profiles and 2D using a variogram analysis. The 1D and 2D estimates provided similar values and high correlation was observed.…”

“…Slight modifications of these parameters (e.g., the sill) can alter CORL values significantly, leading to different estimates (cf. [22,28,47]). This may finally explain why 2D estimates have a lower correlation with SAR data than the 1D estimates.…”

Editorial for the Special Issue “Soil Moisture Retrieval using Radar Remote Sensing Sensors”

“…Several authors [2][3][4][5][6] are developing techniques that allow SAR data to be applied to the estimation of soil moisture. They have also proposed various applications that can be used to interpret soil moisture patterns (for example irrigation mapping).…”

“…They have also proposed various applications that can be used to interpret soil moisture patterns (for example irrigation mapping). Ezzahar et al [2] studied several different surface scattering models, leading to the development of a Sentinel-1 inversion method, based on the SVM machine learning technique, which can be used to map soil moisture. Bousbih et al [3] also proposed a method based on the use of Sentinel-1 data for the estimation of soil moisture.…”