Partial Least Squares Regression Predictive Model using QuickBird Data and Soil Reflectance Spectra Has Great Potential for Estimating Soil Salinity in Pingluo County of China

Pingluo County is located in the northern part of Ningxia Province. In recent years, salinization and secondary salinization have been a major problem in Pingluo County. Therefore, accurately extracting information on salinization such as the extent and degree of severity is vital for the dynamic monitoring of salinization and for preventing further soil deterioration.

For estimating the soil salinity of Pingluo County, a partial least squares regression (PLSR) predictive model was carried out using QuickBird data and soil reflectance spectra to. Firstly, SIDIKE Ayetiguli et al. analyzed the relationship between the sensitive bands and the spectral coverage of the commonly used optical sensors, and the contributions of vegetation indices to the estimation accuracy by comparing the estimation accuracy of model with and without vegetation indices. Then, they developed a PLSR predictive model of soil salinity using measured reflectance spectra, QuickBird data and spectral indices derived from QuickBird remote sensing imagery, including intensity within spectral bands (Int1, Int2), soil salinity indices(SI1, SI2, SI3), the brightness index (BI), the normalized difference vegetation index (NDVI) and the ratio vegetation index (RVI).

The results indicated that the sensitive bands covered several bands of each optical sensor and these sensors can be used for soil salinity estimation. The results of estimation model showed that an accurate prediction of soil salinity can be made based on the PLSR method. The PLSR model’s performance was better than that of the stepwise multiple regression (SMR) method.

The results also indicated that using spectral indices such as intensity within spectral bands (Int1, Int2), soil salinity indices (SI1, SI2, SI3), BI, NDVI and RVI as independent model variables can help to increase the accuracy of soil salinity mapping. The NDVI and RVI can help to reduce the influences of vegetation cover and soil moisture on prediction accuracy. The method developed in this study can be also applied in other arid and semi-arid areas, such as western China. The study was published in International Journal of Applied Earth Observation and Geoinformation in February 2014.