Quantitative estimation of soil salinity by means of different modeling methods and visible-near infrared (VIS-NIR) spectroscopy, Ebinur Lake Wetland, Northwest China - PubMed Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2018 May 3:6:e4703.
doi: 10.7717/peerj.4703. eCollection 2018.

Quantitative estimation of soil salinity by means of different modeling methods and visible-near infrared (VIS-NIR) spectroscopy, Ebinur Lake Wetland, Northwest China

Jingzhe Wang  1   2   3 , Jianli Ding  1   2   3 , Aerzuna Abulimiti  1   2   3 , Lianghong Cai  1   2   3
Affiliations

Quantitative estimation of soil salinity by means of different modeling methods and visible-near infrared (VIS-NIR) spectroscopy, Ebinur Lake Wetland, Northwest China

Jingzhe Wang et al. PeerJ. .

Abstract

Soil salinization is one of the most common forms of land degradation. The detection and assessment of soil salinity is critical for the prevention of environmental deterioration especially in arid and semi-arid areas. This study introduced the fractional derivative in the pretreatment of visible and near infrared (VIS-NIR) spectroscopy. The soil samples (n = 400) collected from the Ebinur Lake Wetland, Xinjiang Uyghur Autonomous Region (XUAR), China, were used as the dataset. After measuring the spectral reflectance and salinity in the laboratory, the raw spectral reflectance was preprocessed by means of the absorbance and the fractional derivative order in the range of 0.0-2.0 order with an interval of 0.1. Two different modeling methods, namely, partial least squares regression (PLSR) and random forest (RF) with preprocessed reflectance were used for quantifying soil salinity. The results showed that more spectral characteristics were refined for the spectrum reflectance treated via fractional derivative. The validation accuracies showed that RF models performed better than those of PLSR. The most effective model was established based on RF with the 1.5 order derivative of absorbance with the optimal values of R2 (0.93), RMSE (4.57 dS m-1), and RPD (2.78 ≥ 2.50). The developed RF model was stable and accurate in the application of spectral reflectance for determining the soil salinity of the Ebinur Lake wetland. The pretreatment of fractional derivative could be useful for monitoring multiple soil parameters with higher accuracy, which could effectively help to analyze the soil salinity.

Keywords: Ebinur Lake; Machine learning; PLSR; RF; Soil salinity; VIS–NIR; Wetland.

PubMed Disclaimer

Conflict of interest statement

The authors declare there are no competing interests.

Figures

Figure 1
Figure 1. Distribution of sampling sites in the study area.
(A) Location map of XUAR. (B) Ebinur Lake wetland region. (C and D) Typical landscape photograph (Photograph credit: Jingzhe Wang). (E) The schema of sampling method (4 points) within the 30 m × 30 m cell grid.
Figure 2
Figure 2. Flow chart of the study.
Figure 3
Figure 3. Box plot and distribution of soil salinity for the whole, calibration, and validation dataset (dS m −1).
S.D. indicates standard deviation.
Figure 4
Figure 4. Reflectance spectra curves of soils with different salinity degrees.
(A) Spectral curves. (B) Continuum removal curves. (C) Absorbance curves.
Figure 5
Figure 5. The soil salinity quantitative models using calibration dataset.
(A) PLSR model based on 1.6 order of reflectance. (B) PLSR model based on 1.5 order of absorbance. (C) RF model based on 1.6 order of reflectance. (D) RF model based on 1.5 order of absorbance. The black line represents the fitted line, the red line represents the 1:1 line, and the gray regions represent the confidence intervals with 95% probability.
Figure 6
Figure 6. The soil salinity quantitative models using validation dataset.
(A) PLSR model based on 1.6 order of reflectance. (B) PLSR model based on 1.5 order of absorbance. (C) RF model based on 1.6 order of reflectance. (D) RF model based on 1.5 order of absorbance. The black line represents the fitted line, the red line represents the 1:1 line, and the gray regions represent the confidence intervals with 95% probability.
Figure 7
Figure 7. Fractional derivative results of the reflectance in the range of LW–NIR (1,100–2,400 nm).
(A) 0–0.5 order. (B) 0.5–1.0 order. (C) 1.0–1.5 order. (D) 1.5–2.0 order.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Abliz A, Tiyip T, Ghulam A, Halik Ü, Ding J-L, Sawut M, Zhang F, Nurmemet I, Abliz A. Effects of shallow groundwater table and salinity on soil salt dynamics in the Keriya Oasis, Northwestern China. Environmental Earth Sciences. 2016;75:260. doi: 10.1007/s12665-015-4794-8. - DOI
    1. Akramkhanov A, Martius C, Park SJ, Hendrickx JMH. Environmental factors of spatial distribution of soil salinity on flat irrigated terrain. Geoderma. 2011;163:55–62. doi: 10.1016/j.geoderma.2011.04.001. - DOI
    1. Allbed A, Kumar L, Aldakheel YY. Assessing soil salinity using soil salinity and vegetation indices derived from IKONOS high-spatial resolution imageries: applications in a date palm dominated region. Geoderma. 2014;230–231:1–8. doi: 10.1016/j.geoderma.2014.03.025. - DOI
    1. Bao S. Soil and agricultural chemistry analysis. Beijing: China Agricultural Science and Technology; 2000. (in Chinese)
    1. Ben-Dor E, Banin A. Near-infrared analysis as a aapid method to simultaneously evaluate several soil properties. Soil Science Society of America Journal. 1995;59:364–372. doi: 10.2136/sssaj1995.03615995005900020014x. - DOI

Grants and funding

This study was supported by the National Natural Science Foundation of China (41771470, U1603241, 31700386 and 41661046). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.

LinkOut - more resources