Quantitative Analysis of Total Nitrogen Content in Monoammonium Phosphate Fertilizer Using Visible-Near Infrared Spectroscopy and Least Squares Support Vector Machine

А quantitative analysis method to determine the total nitrogen content in monoammonium phosphate (MAP) fertilizer using visible-near infrared (Vis-NIR) spectroscopy and least squares support vector machine (LS-SVM) is proposed. Sample set partitioning based on the joint x–y distance (SPXY) was used...

Full description

Saved in:
Bibliographic Details
Published in:Journal of applied spectroscopy 2019-07, Vol.86 (3), p.465-469
Main Authors: Wang, L. S., Wang, R. J., Lu, C. P., Wang, J., Huang, W., Jian, Q., Wang, Y. B., Lin, L. Z., Song, L. T.
Format: Article
Language:English
Subjects:
Ammonium dihydrogen phosphate
Analysis
Analytical Chemistry
Atomic/Molecular Structure and Spectra
Calibration
Discrete Wavelet Transform
Fertilizers
Infrared analysis
Infrared spectroscopy
Least squares
Near infrared radiation
Nitrogen
Physics
Physics and Astronomy
Quantitative analysis
Radial basis function
Smoothing
Spectrum analysis
Support vector machines
Wavelet transforms
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:А quantitative analysis method to determine the total nitrogen content in monoammonium phosphate (MAP) fertilizer using visible-near infrared (Vis-NIR) spectroscopy and least squares support vector machine (LS-SVM) is proposed. Sample set partitioning based on the joint x–y distance (SPXY) was used to select the calibration set. Fourteen spectral pre-processing methods were then employed to deal with the spectral data including Savitzky–Golay (SG) smoothing, fi rst derivative (D 1 ) and second derivative (D 2 ) with SG smoothing, multiplicative scatter correction (MSC), standard normal variate (SNV), wavelet, and combination thereof. Next, the LS-SVM model with radial basis function kernel was established with the best pre-processing method, and its performance was compared with that of partial least squares (PLS) model. The results revealed LS-SVM calibration with the discrete wavelet transform provided the best prediction for total nitrogen content in MAP fertilizer, yielding R 2 , root mean square error of prediction (RMSEP), and ratio of performance to deviation (RPD) values of 0.91, 0.101, and 3.34, respectively.
ISSN:0021-9037
1573-8647
DOI:10.1007/s10812-019-00842-0