A partial least square regression method to quantitatively retrieve soilsalinity using hyper-spectral reflectance data

摘要

Hetao Irrigation District located in Inner Mongolia, is one of the three largest irrigated area in China. In the irrigationalagriculture region, for the reasons that many efforts have been put on irrigation rather than on drainage, as a result muchsedimentary salt that usually is solved in water has been deposited in surface soil. So there has arisen a problem in suchirrigation district that soil salinity has become a chief fact which causes land degrading. Remote sensing technology is anefficiency way to map the salinity in regional scale. In the principle of remote sensing, soil spectrum is one of the mostimportant indications which can be used to reflect the status of soil salinity. In the past decades, many efforts have beenmade to reveal the spectrum characteristics of the salinized soil, such as the traditional statistic regression method. But italso has been found that when the hyper-spectral reflectance data are considered, the traditional regression method can'tbe treat the large dimension data, because the hyper-spectral data usually have too higher spectral band number. In thispaper, a partial least squares regression (PLSR) model was established based on the statistical analysis on the soil salinityand the reflectance of hyper-spectral. Dataset were collect through the field soil samples were collected in the region ofHetao irrigation from the end of July to the beginning of August. The independent validation using data which are notincluded in the calibration model reveals that the proposed model can predicate the main soil components such as thecontent of total ions(S%), PH with higher determination coefficients(R2) of 0.728 and 0.715 respectively. And the rate ofprediction to deviation(RPD) of the above predicted value are larger than 1.6, which indicates that the calibrated PLSRmodel can be used as a tool to retrieve soil salinity with accurate results. When the PLSR model's regression coefficientswere aggregated according to the wavelength of visual (blue, green, red) and near infrared bands of LandSat ThematicMapper(TM) sensor, some significant response values were observed, which indicates that the proposed method in thispaper can be used to analysis the remotely sensed data from the space-boarded platform.