A method of estimating soil moisture based on the linear decomposition of mixture pixels

The objective of this study was to estimate soil moisture with soil red and nir (near-infrared) band reflectance from TM/ETM+ remotely sensed images acquired over vegetated fields. Based on linear decomposition algorithm of mixture pixel, first the soil reflectance from red–nir bands were directly and computationally derived by combining soil line equation with a developed empirical relationship between vegetation canopy and mixture pixel reflectance in red–nir spectral feature space. Then, a remote sensing image from TM with measurement data from experimental fields in Beijing, China, was used to establish the retrieval relationships between soil moisture and soil reflectance from the red and nir bands, and the results showed that the retrieval of soil moisture was better with nir band reflectance than that of red. Finally, the soil moisture retrieved method was further evaluated and validated with two images from ETM + and ground measurements from fields in Walnut Creek, America, and the analysis showed that the proposed method could be used to monitor soil moisture well, with the correlation coefficient exceeding 0.80. The preliminary results with such acceptable accuracy indicate that the method of estimating soil moisture based on the linear decomposition of mixture pixels is reasonable and suitable for being widely applied in different temporal and spatial scaled fields.