Quantitatively estimating main soil water-soluble salt ions content based on Visible-near infrared wavelength selected using GC, SR and VIP

Abstract

Soil salinization is the primary obstacle to the sustainable development of agriculture and eco-environment in arid regions. The accurate inversion of the major water-soluble salt ions in the soil using visible-near infrared (VIS-NIR) spectroscopy technique can enhance the effectiveness of saline soil management. However, the accuracy of spectral models of soil salt ions turns out to be affected by high dimensionality and noise information of spectral data. This study aims to improve the model accuracy by optimizing the spectral models based on the exploration of the sensitive spectral intervals of different salt ions. To this end, 120 soil samples were collected from Shahaoqu Irrigation Area in Inner Mongolia, China. After determining the raw reflectance spectrum and content of salt ions in the lab, the spectral data were pre-treated by standard normal variable (SNV). Subsequently the sensitive spectral intervals of each ion were selected using methods of gray correlation (GC), stepwise regression (SR) and variable importance in projection (VIP). Finally, the performance of both models of partial least squares regression (PLSR) and support vector regression (SVR) was investigated on the basis of the sensitive spectral intervals. The results indicated that the model accuracy based on the sensitive spectral intervals selected using different analytical methods turned out to be different: VIP was the highest, SR came next and GC was the lowest. The optimal inversion models of different ions were different. In general, both PLSR and SVR had achieved satisfactory model accuracy, but PLSR outperformed SVR in the forecasting effects. Great difference existed among the optimal inversion accuracy of different ions: the predicative accuracy of Ca2+, Na+, Cl−, Mg2+ and SO42− was very high, that of CO32− was high and K+ was relatively lower, but HCO3− failed to have any predicative power. These findings provide a new approach for the optimization of the spectral model of water-soluble salt ions and improvement of its predicative precision.

Quantitative estimation of wastewater quality parameters by hyperspectral band screening using GC, VIP and SPA

“…In general, the PLSR model had a good spectral prediction of water quality parameters (Wang et al, 2019). The GC-PLSR model was proved to be optimal for COD, BOD, NH3-N and TH with the best prediction.…”

“…These two methods had their fixed preferences in terms of information preservation and redundancy elimination. Therefore, the two methods had quite different performance in the band selection for the parameters and modeling methods, and their performance was very unstable (Wang et al, 2019). Of the two methods, the GC method had better performance in redundancy elimination.…”

“…Therefore, in current researches, scholars are trying to adopt some methods to screen the characteristic spectrum, to remove redundant information, and to improve the stability and predictability of the model (Feng et al, 2018). The variable importance in projection (VIP) algorithm has successfully distinguished the hyperspectral band subsets of forest species by identifying the importance of the independent variables (Peerbhay, Mutanga & Ismail, 2013); the gray correlation (GC) method, using the gray values of the independent variables, has achieved the screening of spectral intervals of soil ion characteristics (Wang et al, 2019). So far these two methods have rarely been applied in the screening of the characteristic spectrum of water pollution parameters.…”

“…Iterative progressive elimination combined with PLSR has a good performance in the inversion of chlorophyll A and total suspended solids (Wang et al, 2018a). VIP combined with PLSR and SVR has significantly improved the inversion effect of characteristic spectra of water-soluble ions in soil, while GC combined with PLSR and SVR showed relatively poor inversion effect (Wang et al, 2019). However, GC combined with ELM has a good effect on the prediction and inversion of total nitrogen content in soil (Zhou et al, 2017).…”

Estimation of soil salt content by combining UAV-borne multispectral sensor and machine learning algorithms

“…So far there are many researches on hyperspectral data mining (Wang et al, 2019a), but very few reports on deep mining of UAV-borne multispectral data. We try to answer the following questions: The correlation between spectral indexes and SSC tends to vary, so which spectral indexes are suitable for this study and which variable selection method is the most effective?…”