Estimating soil salinity with different fractional vegetation cover
using remote sensing
Abstract
Soil salinization is a serious restrictive factor of sustainable
agricultural development, and its monitoring accuracy is mainly
influenced by such factors as mineral composition, organic matter, and
Fractional Vegetation Cover (FVC). Previous research mostly focused on
the first two factors and the study of FVC is scarce and unsystematic.
In order to systematically explore the effect of FVC, we monitored the
soil salinization with different vegetation coverage in Jiefangzha
Irrigation District in Inner Mongolia using satellite remote sensing.
From May to August 2018, we carried out field sampling at different
depths (0-20cm, 0-40cm, 0-60cm) in each month, and calculated FVC and
spectral covariates using GF-1 satellite images in the corresponding
sampling period. Based on the FVC division criteria of Inner Mongolia,
we took the following steps: (1) setting up control treatment A (the
full data with undivided FVC,TA) and experimental treatment B (bare
land, TB), C (mid-low FVC, TC), D (mid FVC, TD) and E (high FVC, TE);
(2) conducting the Best Subset Selection (BSS) for all spectral
covariates at different depths of each treatment; and (3) constructing
the Soil Salt Content (SSC) inversion models by Partial Least Square
Regression (PLSR), Cubist, and Extreme Learning Machine (ELM). The
results indicated that classifying FVC could improve the stability and
predictive ability of the models. The results can provide references for
soil salinization prevention and agricultural production in Jiefangzha
Irrigation District and other areas with the same vegetation cover.