Measurement of Soil Total Nitrogen Using Near Infrared Spectroscopy Combined with RCA and SPA
FANG Xiao-rong1, ZHANG Hai-liang2, 3, HUANG Ling-xia4, HE Yong2*
1. Jinhua Polytechnic, Jinhua 321017, China 2. College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, China 3. School of Railway Tracks and Transportation, East China Jiaotong University, Nanchang 330013, China 4. College of Animal Sciences, Zhejiang University, Hangzhou 310058, China
Abstract：Visible near infrared spectra technology was adopted to detect soil total nitrogen content. 394 soil samples were collected from Wencheng, Zhejiang province to be used for calibration model (n=263) and independent prediction set (n=131). Raw spectra and wavelength-reduced spectra with five different pretreatment methods (SG smoothing, SNV, MSC, 1st-D and 2nd-D) were compared to determine the optimal wavelength range and pretreatment method for analysis. The results with 5 different pretreatment methods were not improved compared to that both of full spectra PLS model and wavelength reduction spectra model. Spectral variable selection is an important strategy in spectrum modeling analysis, because it tends to parsimonious data representation and can lead to multivariate models with better performance. In order to simply calibration models, the wavelength variables selected by two different variable selection methods (i.e. regression coefficient analysis (RCA) and successive projections algorithm (SPA) were proposed to be the inputs of calibration methods of PLS, MLR and LS-SVM models separately. These calibration models were also compared to select the best model to predict soil TN. In total, 9 different models were built and the best results indicated that PLS, MLR and LS-SVM obtained the highest precision with determination coefficient of prediction R2pre=0.81, RMSEP=0.0031 and RPD=2.26 based on wavelength variables selected by RCA (0.0002) and SPA as inputs of models. SPA-MLR model and other three models based on 7 sensitive variables selected by RC using 0.0002 regression coefficient threshold value obtained the best result with R2pre, RMSEP and RPD as 0.81, 0.0031 and 2.26. This prediction accuracy is classied to be very good. For all the models, it could be concluded that RCA and SPA could be very useful ways to selected sensitive wavelengths, and the selected wavelengths were effective to estimate soil TN. It is recommended to adopt SPA variable selection or RCA variable selection method with both linear and nonlinear calibration models for measurement of the soil TN using Vis-NIR spectroscopy technology, and wavelengths selection could be very useful to reduce collinearity and redundancies of spectra.
Key words：Visible near infrared spectroscopy;Soil total N;Regression coefficient analysis (RCA);Successive projections algorithm (SPA)
[1] Vohland M, Ludwig M, Thiele-Bruhn S, et al. Geoderma, 2014, 223-225: 88. [2] Debaene G, Niedzwiecki J, Pecio A, et al. Geoderma, 2014, 214-215: 114. [3] Nocita M, Stevens A, Toth G, et al. Soil Biology and Biochemistry, 2014, 68: 337. [4] Kuang B Y, Mouazen A M. Biosystems Engineering, 2013, 114(3): 249. [5] SHEN Zhang-quan, LU Bi-hui, SHAN Ying-jie, et al(沈掌泉，卢必慧，单英杰，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2013, 33(07): 1775. [6] Shi T Z, Cui L J, Wang J J, et al. Plant and Soil, 2013, 366(1-2): 363. [7] Marques J, Siqueira D S, Camargo L A, et al. Geoderma, 2014, 219-220: 63. [8] YANG Mei-hua, ZHAO Xiao-min, FANG Qian, et al(杨梅花，赵小敏，方 倩, 等). Scientia Agricutcura Sinica(中国农业科学), 2014, 47(12): 2374. [9] BAO Shi-dan(鲍士旦). Soil Agrichemical Analysis(土壤农化分析). Beijing: China Agriculture Press(北京: 中国农业出版社), 1999. 30. [10] Liu F, He Y, Wang L, et al. Food and Bioprocess Technology, 2011, 4(8): 1331. [11] Wu D, Shi H, Wang S, et al. Analytica Chimica Acta, 2012, 726: 57. [12] Shao Y N, Zhao C J, Bao Y D, et al. Food and Bioprocess Technology, 2012, 5(1): 100.
