Towards retrieving soil hydraulic properties by hyperspectral remote sensing

In this study, we developed spectrotransfer functions (STFs) that relate soil hydraulic properties (SHPs) to spectral reflectance values to estimate hydraulic parameters of the Mualem-van Genuchten (MvG) model. We investigated the general potential of airborne as well as space-borne remote sensors to retrieve MvG hydraulic parameters of a bare soil agricultural field. Based on the ASD full spectrum (Scenario I), simple spectral signatures were generated mimicking the hyperspectral EnMAP sensor (Scenario II), and the multispectral Sentinel-2 sensor (Scenario III). A stepwise multiple linear regression method was used for each scenario to derive STFs. We further tested laboratory- and soil-map-based HYPRES and Rosetta pedotransfer functions (PTFs) to parameterize MvG parameters and thus provide soil water characteristics and hydraulic conductivity functions in the region. The best results were obtained for Scenarios I and II, with similar R2 values for shape parameters α* and n and the lognormal saturated hydraulic conductivity (Ks*). The R2 values were highest for Ks* in Scenarios I and II (0.58 and 0.57, respectively). The R2 values for α* and n were 0.30 and 0.34 in Scenario I and 0.39 and 0.31 in Scenario II, respectively. In all scenarios, the lowest R2 values were obtained for saturated water content (θs), with values around 0.10 for Scenarios I and II and almost zero in Scenario III. Compared with HYPRES and Rosetta PTFs, the spectral approach performed reasonably well in terms of predicting soil water retention characteristics and unsaturated hydraulic conductivity. These findings suggest that spectral reflectance data provide a promising indirect and quick method for large-scale parameter estimation.