Selection of Spectral Preprocessing Methods for Soil Texture Classification

Hai Qing Yang; Bo Yan Kuang; Abdul M. Mouazen

doi:10.4028/www.scientific.net/AMR.181-182.416

Paper Titles

Design on a Small Sprinkler Irrigation System for Saving Water Effectively
p.395

Study on Influencing Factors on Removal of Diesel Oil from Unsaturated Zone by Soil Vapor Extraction
p.401

Preparation of Particleboard Made from Wheat Straw with Low-Formaldehyde-Emission Composite Adhesive
p.406

A Novel Method for Representation of Spectral Images Based on Color Matching Functions
p.410

Selection of Spectral Preprocessing Methods for Soil Texture Classification
p.416

On Orthogonal Waveform Design for MIMO Radar
p.422

Preparation of β-Cyclodextrin Modified Poly(d,l-Lactic Acid) and its Blood Compatibility
p.429

Application of Fuzzy Neural Network in Relay Protection
p.434

Application of Wavelet Neural Network in Power Load Forecasting
p.439

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 181-182Selection of Spectral Preprocessing Methods for...

Selection of Spectral Preprocessing Methods for Soil Texture Classification

Abstract:

Fast classification of soil with different texture is essential for site-specific application of different inputs into farmland. Total 178 soil samples with five textures were collected from Silsoe Farm, Cranfield University, England. Using a Vis/NIR spectrophotometer (LabSpec2500, ASD), spectra of soil samples were scanned for the study. Amongst various pre-processing methods, smoothing with moving average(MA), standard normal variation(SNV) and 1st derivatives were mainly investigated. PCA was applied to evaluate the discriminative capacity of the pre-processing methods on soil spectra. The score plot of PCs shows that 1st derivative with variable smoothing points can help classify soil samples much more effectively than others. With the increase of smoothing points, the cumulative variance of first few PCs in PCA tends to increase while the discriminative capability based on these PCs becomes worse. A trade-off between cumulative variance and discriminative capability should be concerned. In the study, an appropriate range of smoothing points in the 1st derivative is 7-21.

You might also be interested in these eBooks

Advanced Materials Science and Technology, ICMST 2010

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 181-182)

Pages:

416-421

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.181-182.416

Citation:

Cite this paper

Online since:

January 2011

Authors:

Hai Qing Yang, Bo Yan Kuang, Abdul M. Mouazen

Keywords:

Derivative, Pre-Processing, Principal Component Analysis (PCA), Soil Classification

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] A.M. Mouazen, K. Dumont, K. Maertens and H. Ramon: Soil Till. R., 2003, 74(1): 91-102.

Google Scholar

[2] H. Yang, J. Yao and Y. He: Spec. Sp. A., 2009, 29(6): 1607-1610.

Google Scholar

[3] H. Yang, Y. He, Y. Chen, P. Lin and D. Wu: Spec. Sp. A., 2008, 28(6): 1232-1236.

Google Scholar

[4] H. Yang, D. Wu and Y. He, in: MIPPR2007: Pattern Recognition and Computer Vision, edited by S.J. Maybank, volume 6788 of Proceedings of the Society of Photo-optical Instrumentation Engineering (SPIE), SPIE International Society of Optical Engineering Publishers, (2007).

Google Scholar

[5] H. Yang and Y. He, in: Computer and Computing Technologies in Agriculture II, edited by D. Li, Volume 293 of International Federation for Information Processing, Springer, (2009).

Google Scholar

[6] A.M. Mouazen, J. De Baerdemacker and H. Ramon: Soil Till. R., 2005, 80(1-2): 171-183.

Google Scholar

[7] A.M. Mouazen, B. Kuang, J. De Baerdemaeker and H. Ramon: Geoderma, 2010, 158: 23-31.

Google Scholar