Monitoring properties of the salt-affected soils by multivariate analysis of the visible and near-infrared hyperspectral data

Abstract

The study aimed to estimate the properties of the salt-affected soils (SAS) using hyperspectral remote sensing. The study was carried out on typical SAS from 372 locations covering 17 coastal districts from the west coast region of India. The spectral reflectance of processed soil samples was recorded in the wavelength range of 350–2500 nm. The full dataset (n = 372) was split into two as a calibration dataset (n = 260, 70% of full dataset) to develop the model and validation dataset (n = 112, 30% of full dataset) to evaluate the performance of the model independently. The spectral data were calibrated using the laboratory estimated soil properties with five different multivariate techniques (a) Linear – partial component regression (PCR) and partial least square regression (PLSR) and (b) Non-linear– multivariate adaptive regression spline (MARS), random forest (RF) and support vector regression (SVR). In general, the spectral reflectance from the soils decreased with increasing levels of salinity (electrical conductivity, EC). The wavelengths 427, 487, 950, 1414, 1917, 2206, 2380 and 2460 nm showed peculiar absorption characteristics. The study showed significant achievement in predicting soil pH, salinity (EC), bulk density, soil available nitrogen, exchangeable magnesium, soil available zinc, and boron with acceptable to excellent predictions (ratio of performance to deviation ranged 1.48–2.06). Amongst predicted models, SVR, PLSR, and PCR were found to be more robust than MARS and RF. The results of the study indicated that the visible near-infrared spectroscopy has the potential to predict properties of the SAS.