Prediction of Soil Salinity Using Near-Infrared Reflectance Spectroscopy with Nonnegative Matrix Factorization

Chen, Hongyan; Zhao, Gengxing; Sun, Li; Wang, Ruiyan; Liu, Yaqiu

doi:10.1177/0003702816662605

Cited by 11 publications

(4 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, Nawar et al [8] collected the soil of the EI-Tina plain in Egypt, and used partial least squares regression (PLSR) and multivariate adaptive regression splines (MARS) to predict soil salt, and it was found that the MARS model was superior to the PLSR model in salt prediction and mapping performance. Chen et al [9] collected saline soil samples from the Yellow River Delta in China, and studied them using near infrared reflectance spectroscopy based on non-negative matrix factorization (NMF) to predict soil salt content. The simulation results showed that the method of NMF combining indoor and outdoor spectra can improve the correlation between salt content and spectra as well as improve the accuracy of prediction models.…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral Prediction of Soil Total Salt Content by Different Disturbance Degree under a Fractional-Order Differential Model with Differing Spectral Transformations

et al. 2021

View full text Add to dashboard Cite

Soil salinization is an ecological challenge across the world. Particularly in arid and semi-arid regions where evaporation is rapid and rainfall is scarce, both primary soil salinization and secondary salinization due to human activity pose serious concerns. Soil is subject to various human disturbances in Xinjiang in this area. Samples with a depth of 0–10 cm from 90 soils were taken from three areas: a slightly disturbed area (Area A), a moderately disturbed area (Area B), and a severely disturbed area (Area C). In this study, we first calculated the hyperspectral reflectance of five spectra (R, R, 1/R, lgR, 1/lgR, or original, root mean square, reciprocal, logarithm, and reciprocal logarithm, respectively) using different fractional-order differential (FOD) models, then extracted the bands that passed the 0.01 significance level between spectra and total salt content, and finally proposed a partial least squares regression (PLSR) model based on the FOD of the significance level band (SLB). This proposed model (FOD-SLB-PLSR) is compared with the other three PLSR models to predict with precision the total salt content. The other three models are All-PLSR, FOD-All-PLSR, and IOD-SLB-PLSR, which respectively represent PLSR models based on all bands, all fractional-order differential bands, and significance level bands of the integral differential. The simulations show that: (1) The optimal model for predicting total salt content in Area A was the FOD-SLB-PLSR based on a 1.6 order 1/lgR, which provided good predictability of total salt content with a RPD (ratio of the performance to deviation) between 1.8 and 2.0. The optimal model for predicting total salt content in Area B was a FOD-SLB-PLSR based on a 1.7 order 1/R, which showed good predictability for total salt content with RPDs between 2.0 and 2.5. The optimal model for predicting total salt content in Area C was a FOD-SLB-PLSR based on a 1.8 order lgR, which also showed good predictability for total salt content with RPDs between 2.0 and 2.5. (2) Soils subject to various disturbance levels had optimal FOD-SLB-PLSR models located in the higher fractional order between 1.6 and 1.8. This indicates that higher-order FODs have a stronger ability to extract feature data from complex information. (3) The optimal FOD-SLB-PLSR model for each area was superior to the corresponding All-PSLR, FOD-All-PLSR, and IOD-SLB-PLSR models in predicting total salt content. The RPD value for the optimal FOD-SLB-PLSR model in each area compared to the best integral differential model showed an improvement of 9%, 45%, and 22% for Areas A, B, and C, respectively. It further showed that the fractional-order differential model provides superior prediction over the integral differential. (4) The RPD values that provided an optimal FOD-SLB-PLSR model for each area were: Area A (1.9061) < Area B (2.0761) < Area C (2.2892). This indicates that the prediction effect of data processed by fractional-order differential increases with human disturbance increases and results in a higher-precision model.

show abstract

Section: Introductionmentioning

confidence: 99%

Hyperspectral Prediction of Soil Total Salt Content by Different Disturbance Degree under a Fractional-Order Differential Model with Differing Spectral Transformations

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In addition, the differential transformation (Xia et al, 2017) and fractional derivative (Wang et al, 2017; Wang et al, 2018c) can fully utilize the potential spectral information and enhance model accuracy. The methods of spectral classification (Jin et al, 2015) and water influence elimination (Chen et al, 2016; Peng et al, 2016b; Yang & Yu, 2017) work well in improving the quantitative inversion accuracy of soil salinity. Therefore, the remote sensing technique is reliable to inverse the soil salinity quantitatively on different scales.…”

Section: Introductionmentioning

confidence: 99%

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

Wang

Chen

Zhang

et al. 2019

PeerJ

View full text Add to dashboard Cite

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.

show abstract

“…Most of the studies of hyper-spectral soil degradation in the Yellow River Deltafocus on soil salinization, and which are partial to the study method of information extraction. Moreover, there is little research on soil nutrient impoverishment, and study of the hyper-spectral response of soil degradation remains insufficient [26][27][28][29]. On one hand, the research methods are immature, and the results are still objectionable.…”

Section: Introductionmentioning

confidence: 99%

Hyper-spectral response and estimation model of soil degradation in Kenli County, the Yellow River Delta

et al. 2020

Self Cite

View full text Add to dashboard Cite

The ecological environment of the Yellow River Delta is fragile, and the soil degradation in the region is serious. Therefore it is important to discern the status of the soil degradation in a timely manner for soil conservation and utilization. The study area of this study was Kenli County in the Yellow River Delta of China. First, physical and chemical data of the soil were obtained by field investigations and soil sample analyses, and the hyper-spectra of air-dried soil samples were obtained via spectrometer. Then, the soil degradation index (SDI) was constructed by the key indicators of soil degradation, including pH, SSC, OM, AN, AP, AK, and soil texture. Next, according to a cluster analysis, soil degradation was divided into the following three grades: light degradation, moderate degradation, and heavy degradation. Moreover, the spectral characteristics of soil degradation were analyzed, and an estimation model of SDI was established by multiple stepwise regression. The results showed that the overall level of reflectance spectra increased with increased degree of soil degradation, that both derivative transformation and waveband reorganization could enhance the spectral information of soil degradation, and that the correlation between SDI and the spectral parameter of (R λ2 +R λ1)/(R λ2-R λ1) was the highest among all the spectral parameters studied. On this basis, the optimum estimation model of SDI was established with the correlation coefficient of 0.811. This study fully embodies the potential of hyper-spectral technology in the study of soil degradation and provides a technical reference for the rapid extraction of information from soil degradation. Additionally, the study area is typical and representative, and thus can indirectly reflect the soil degradation situation of the whole Yellow River Delta.

show abstract

Prediction of Soil Salinity Using Near-Infrared Reflectance Spectroscopy with Nonnegative Matrix Factorization

Cited by 11 publications

References 33 publications

Hyperspectral Prediction of Soil Total Salt Content by Different Disturbance Degree under a Fractional-Order Differential Model with Differing Spectral Transformations

Hyperspectral Prediction of Soil Total Salt Content by Different Disturbance Degree under a Fractional-Order Differential Model with Differing Spectral Transformations

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

Hyper-spectral response and estimation model of soil degradation in Kenli County, the Yellow River Delta

Contact Info

Product

Resources

About