IMPROVEMENTS OF THE VIS-NIRS MODEL IN THE PREDICTION OF SOIL ORGANIC MATTER CONTENT USING SPECTRAL PRETREATMENTS, SAMPLE SELECTION, AND WAVELENGTH OPTIMIZATION
Abstract
A total of 130 topsoil samples collected from Guoyang County, Anhui Province, China, were used to establish a Vis-NIR model for the prediction of organic matter content (OMC) in lime concretion black soils. Different spectral pretreatments were applied for minimizing the irrelevant and useless information of the spectra and increasing the spectra correlation with the measured values. Subsequently, the Kennard-Stone (KS) method and sample set partitioning based on joint x-y distances (SPXY) were used to select the training set. Successive projection algorithm (SPA) and genetic algorithm (GA) were then applied for wavelength optimization. Finally, the principal component regression (PCR) model was constructed, in which the optimal number of principal components was determined using the leave-one-out cross validation technique. The results show that the combination of the Savitzky-Golay (SG) filter for smoothing and multiplicative scatter correction (MSC) can eliminate the effect of noise and baseline drift; the SPXY method is preferable to KS in the sample selection; both the SPA and the GA can significantly reduce the number of wavelength variables and favorably increase the accuracy, especially GA, which greatly improved the prediction accuracy of soil OMC with Rcc, RMSEP, and RPD up to 0.9316, 0.2142, and 2.3195, respectively.
About the Authors
Z. D. Lin
Institute of Intelligent Machines, Chinese Academy of Sciences; University of Science and Technology of China; Electronic Engineering Institute
Russian Federation
Russian Federation
Y. B. Wang
Institute of Intelligent Machines, Chinese Academy of Sciences
Russian Federation
Russian Federation
R. J. Wang
Institute of Intelligent Machines, Chinese Academy of Sciences
Russian Federation
Russian Federation
L. S. Wang
Institute of Intelligent Machines, Chinese Academy of Sciences
Russian Federation
Russian Federation
C. P. Lu
Institute of Intelligent Machines, Chinese Academy of Sciences
Russian Federation
Russian Federation
Z. Y. Zhang
Institute of Intelligent Machines, Chinese Academy of Sciences
Russian Federation
Russian Federation
L. T. Song
Institute of Intelligent Machines, Chinese Academy of Sciences
Russian Federation
Russian Federation
Y. . Liu
Institute of Intelligent Machines, Chinese Academy of Sciences
Russian Federation
Russian Federation
References
1. E. Ben-Dor, A. Banin, Soil Sci. Soc. Am. J., 59, 364-372 (1995).
2. J. B. Reeves, G. W. McCarty, J. J. Meisinger, JNIRS, 8, 161-170 (2000).
3. J. B. Reeves, G. W. McCarty, V. B. Reeves, R. F. Follet, J. M. Kimble, Abstr. Am. Chem. Soc., 223, U141-U142 (2002).
4. B. W. Dunn, H. G. Beecher, G. D. Batten, S. Ciavarella, Aust. J. Exp. Agric., 42, 607-614 (2002).
5. K. D. Shepherd, M. G. Walsh, SSSA, 66, 988-998 (2002).
6. K. Islam, B. Singh, A. B. McBratney, Aust. J. Soil Res., 41, 1101-1114 (2003).
7. E. Ben-Dor, J. Irons, G. F. Epema, In: Soil Reflectance: Remote Sensing for the Earth Science, Ed. N. Andrew Rencz, 3rd edn., Manual of Remote Sensing, 3 (1999).
8. G. M. Vasques, S. Grunwald, J. O. Sickman, Geoderma, 146, 14-25 (2008).
9. G. M. Vasques, S. Grunwald, J. O. Sickman, Soil Sci. Soc. Am. J., 73, 176-184 (2009).
10. A. M. Mouazen, B. Kuang, J. De Baerdemaeker, H. Ramon, Geoderma, 158, 23-31 (2010).
11. A. Stevens, T. Udelhoven, A. Denis, B. Tychon, R. Lioy, L. Hoffmann, B. Van Wesemael, Geoderma, 158, 32-45 (2010).
12. R. A. Viscarra Rossel, T. Behrens, Geoderma, 158, 46-54 (2010).
13. C. W. Chang, A. L. David, J. M. Maurice, R. H. Charles, Soil Sci. Soc. Am. J., 65, 480-490 (2001).
14. Y. B. Wang, T. Y. Huang, J. Liu, Z. D. Lin, S. H. Li, R. J. Wang, Y. J. Ge, Comput. Electron. Agric., 111, 69-77 (2015).
15. L. W. Liu, Pedosphere, 1, 3-15 (1991).
16. L. J. Li, X. S. Guo, D. Z. Wang, Y. X. Sun, C. L. He, P. P. Wu, J. Anhui Agric. Sci., 34, 722-723 (2006).
17. M. Nathan, Ron. Gelderman, Recommended Chemical Soil Test Procedures for the North Central Region, North Central Regional Research Publication No. 221 (Revised, 2012). 509-7
18. R. Lu, Chemical Analysis Method of Agricultural Soil, China Agricultural Science Press, Beijing, 106-107 (in Chinese) (2000).
19. A. Rinan, F. Vanden Berg, S. B. Engelsen, Trends Anal. Chem., 28, 1201-1222 (2009).
20. A. Savitzky, M. J. E. Golay, Anal. Chem., 36, 1627-1639 (1964).
21. W. Wu, B. Walczak, D.L. Massart, S. Heuerding, F. Erni, I. R. Last, K. A. Prebble, Chemometr. Intell. Lab. Syst., 33, 35-46 (1996).
22. R. Kawakami Harrop Galvão, M. César Ugulino Araujo, G. Emıdio Jose, M. Jose Coelho Pontes, E. Cirino Silva, T. Cristina Bezerra Saldanha, Talanta, 67, 736-740 (2005).
23. M. C. U. Argújo, T. C. B. Saldanha, R. K. H. Galväo, T. Yoneyama. H. C. Chame, V. Visani, Chemometr. Intell. Lab. Syst., 57 (2), 65-73 (2001).
24. W. Z. Lu, H. F. Yuan, G. T. Xu, Model NIR Spectroscopy, Beijing, China Petro-chemical Press, 56-67 (2001).
25. H. Abdi, L. J. Williams, Wiley Interdiscipl. Rev.:Comput. Stat., 2, 433-459 (2010).
26. A. M. Mouazen, J. D. Baerdemaeker, H. Ramon, JNIRS, 14, 189-199 (2006).
Review
For citations:
Lin Z.D., Wang Y.B., Wang R.J., Wang L.S., Lu C.P., Zhang Z.Y., Song L.T., Liu Y. IMPROVEMENTS OF THE VIS-NIRS MODEL IN THE PREDICTION OF SOIL ORGANIC MATTER CONTENT USING SPECTRAL PRETREATMENTS, SAMPLE SELECTION, AND WAVELENGTH OPTIMIZATION. Zhurnal Prikladnoii Spektroskopii. 2017;84(3):509(1)-509(7). (In Russ.)
Views: 274
Email this article 