Energy dispersive X-ray fluorescence and scattering assessment of soil quality via partial least squares and artificial neural networks analytical modeling approaches

Kaniu, M.I.; Angeyo, K.H.; Mwala, A.K.; Mwangi, F.K.

doi:10.1016/j.talanta.2012.06.081

Cited by 40 publications

(9 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In the present study, the prediction accuracy achieved by PLSR was higher than those reported by Weber et al () and Nocita et al (). However, the R 2 and RMSE values were lower than previous investigations (Kaniu et al, ; Zhang & Harrington, ), which may be a function of the small sample size. While a larger sample size would be ideal, small sample sizes are a reality in many regions of the world, and although additional field work to fill in gaps is the most desirable solution (Sanchez et al, ; Brevik et al, ), finding better ways to extract needed information from these small sample sizes is also important (Brevik et al, ).…”

Section: Discussionmentioning

confidence: 99%

Assessment and Monitoring of Soil Degradation during Land Use Change Using Multivariate Analysis

et al. 2016

View full text Add to dashboard Cite

Not only are soil erosion and overall loss of soil fertility serious issues for loess‐derived soils of developing nations, such as Iran, but they are also global problems. This research investigated the role of land use change and its effect on soil degradation in cultivated, pasture, and urban lands, when compared with native forest in terms of declining of soil quality and fertility. Multivariate statistical methods including principal component analysis and cluster analysis were employed to determine the relative magnitude of anthropogenic and natural influences on soil quality. Partial least squares (PLS), principal component regression, and ordinary least squares regression were used to predict soil cation exchange capacity using soil characteristics. Principal component analysis identified five primary components of soil quality. PC1 explained 41·01% of the total variance, PC2 accounted for 15·29%, and PC3 accounted for 11·3%. PC4 and PC5 accounted for 7·37% and 4·19% of the total variance, respectively. Cluster analysis revealed that the lowest soil quality occurred in urban soils. An exponential semivariogram using PLS predictions revealed stronger spatial dependence among cation exchange capacity [r2 = 0·80, root mean square error (RMSE) = 1·99] than the other methods, principal component regression [r2 = 0·84, RMSE = 2·45] and ordinary least squares [r2 = 0·84, RMSE = 2·45]. Therefore, the PLS method provided the best model for the data. In stepwise regression analysis, mean weight diameter and labile carbon were selected as influential variables in all soils. This study quantified reductions in numerous soil quality parameters resulting from extensive land‐use changes and urbanization in the Ziarat watershed in northern Iran. Copyright © 2016 John Wiley & Sons, Ltd.

show abstract

Section: Discussionmentioning

confidence: 99%

Assessment and Monitoring of Soil Degradation during Land Use Change Using Multivariate Analysis

et al. 2016

View full text Add to dashboard Cite

show abstract

“…M. I. Kaniu used the method proposed by H. Demuth in the application of energy‐dispersive X‐ray fluorescence (EDXRF) and scattering assessment for soil quality in 2012; when the neural network test error increases, the training process is automatically stopped to minimize overfitting . The experimental results show that the method can better overcome the degree of overfitting and give accurate results.…”

Section: Overfittingmentioning

confidence: 99%

Application of artificial neural networks to X‐ray fluorescence spectrum analysis

et al. 2018

X-Ray Spectrometry

View full text Add to dashboard Cite

X‐ray fluorescence (XRF) is widely applied as a mature nondestructive testing method, and appropriate improvement of quantitative analysis methods can improve the accuracy of XRF. Artificial neural network is an intelligent information processing system, its developments and application in XRF are reviewed, and representative models (back propagation, radial basis function, genetic algorithm artificial neural network, and others) are discussed in more details in overfitting, generalization, and algorithm efficiency. Potential directions of developing artificial neural network applied in XRF are proposed in this review as a further study.

show abstract

“…Another powerful method of PSS is XRF spectrometry, which is extensively used in elemental analysis [9]. Nevertheless, its performance in analyzing low-Z elements-i.e., K, P, calcium (Ca), and magnesium (Mg)-is less promising [10,11]. Since neither vis-NIR nor XRF can measure all required soil properties satisfactorily, the hypothesis of the study was that the fusion of the data of the two sensors can improve the prediction accuracy of selected soil (NIR active and non-active) fertility attributes.…”

Section: Introductionmentioning

confidence: 99%

Data Fusion of XRF and Vis-NIR Using Outer Product Analysis, Granger–Ramanathan, and Least Squares for Prediction of Key Soil Attributes

Javadi

Mouazen

2021

Remote Sensing

View full text Add to dashboard Cite

Visible-near-infrared (vis-NIR) and X-ray fluorescence (XRF) are key technologies becoming pervasive in proximal soil sensing (PSS), whose fusion holds promising potential to improve the estimation accuracy of soil attributes. In this paper, we examine different data fusion methods for the prediction of key soil fertility attributes including pH, organic carbon (OC), magnesium (Mg), and calcium (Ca). To this end, the vis-NIR and XRF spectra of 267 soil samples were collected from nine fields in Belgium, from which the soil samples of six fields were used for calibration of the single-sensor and data fusion models while the validation was performed on the remaining three fields. The first fusion method was the outer product analysis (OPA), for which the outer product (OP) of the two spectra is computed, flattened, and then subjected to partial least squares (PLS) regression model. Two versions of OPA were evaluated: (i) OPA-FS in which the full spectra were used as input; and (ii) OPA-SS in which selected spectral ranges were used as input. In addition, we examined the potential of least squares (LS) and Granger–Ramanathan (GR) analyses for the fusion of the predictions provided by the single-sensor PLS models. Results demonstrate that the prediction performance of the single-sensor PLS models is improved by GR in addition to the LS fusion method for all soil attributes since it accounts for residuals. Resorting to LS, the largest improvements compared to the single-sensor models were obtained, respectively, for Mg (residual prediction deviation (RPD) = 4.08, coefficient of determination (R2) = 0.94, ratio of performance of inter-quantile (RPIQ) = 1.64, root mean square error (RMSE) = 4.57 mg/100 g), OC (RPD = 1.79, R2 = 0.69, RPIQ = 2.82, RMSE = 0.16%), pH (RPD = 1.61, R2 = 0.61, RPIQ = 3.06, RMSE = 0.29), and Ca (RPD = 3.33, R2 = 0.91, RPIQ = 1, RMSE = 207.48 mg/100 g). OPA-FS and OPA-SS outperformed the individual, GR, and LS models for pH only, while OPA-FS was effective in improving the individual sensor models for Mg as well. The results of this study suggest LS as a robust fusion method in improving the prediction accuracy for all the studied soil attributes.

show abstract

Energy dispersive X-ray fluorescence and scattering assessment of soil quality via partial least squares and artificial neural networks analytical modeling approaches

Cited by 40 publications

References 20 publications

Assessment and Monitoring of Soil Degradation during Land Use Change Using Multivariate Analysis

Assessment and Monitoring of Soil Degradation during Land Use Change Using Multivariate Analysis

Application of artificial neural networks to X‐ray fluorescence spectrum analysis

Data Fusion of XRF and Vis-NIR Using Outer Product Analysis, Granger–Ramanathan, and Least Squares for Prediction of Key Soil Attributes

Contact Info

Product

Resources

About