Near-InfraRed and Visible (Vis-NIR)
spectroscopy is a promising tool allowing to quantify soil properties. It shows
that information encoded in hyperspectral data can be useful after signal
processing and model calibration steps, in
order to estimate various soil properties throughout appropriate statistical
models. However, one of the problems encountered in the case of hyperspectral
data is related to information redundancy between different spectral bands.
This redundancy is at the origin of multi-collinearity in the explanatory
variables leading to unstable regression coefficients (and, difficult to
interpret). Moreover, in hyperspectral spectrum, the information concerning the
chemical specificity is spread over several wavelengths. Therefore, it is not
wise to remove this redundancy because this removal affects both relevant and
irrelevant hyperspectral information. In this study, the faced challenge is to
optimize the estimation of some soil properties by exploiting all the spectral
richness of the hyperspectral data by providing complementary rather than
redundant information. To this end, a new reliable approach based on
hyperspectral data analysis and partial least squares regression is proposed.
References
[1]
Jobson, J.D. (1999) Applied Multivariate Data Analysis: Volume 1: Regression and Experimental Design. Springer Verlag, New York.
[2]
Abrams, M. and Hook, S.J. (1995) Simulated ASTER Data for Geological Studies. IEEE Transaction on Geo-science and Remote Sensing, 33, 692-699. https://doi.org/10.1109/36.387584
[3]
Ben Dor, E. and Patkin, K. (2002) Mapping of Several Soil Properties Using DAIS-7915 Hyperspectral Scanner Data. International Journal of Remote Sensing, 23, 1043-1062. https://doi.org/10.1080/01431160010006962
[4]
Weng, Y., Gong, P. and Zhu, Z. (2008) Reflectance Spectroscopy for the Assessment of Soil Salt Content in Soils of the Yellow River Delta of China. Interna-tional Journal of Remote Sensing, 29, 5511-5531. https://doi.org/10.1080/01431160801930248
[5]
Leone, A.P., Raphael, A., Rossel, V., Amenta, P. and Buondonno, A. (2012) Prediction of Soil Properties with PLSR and Vis-NIR Spectroscopy: Application to Mediterranean Soils from Southern Italy. Current Analytical Chemistry, 8, 283-299. https://doi.org/10.2174/157341112800392571
[6]
Savitzky, A. and Golay, M. (1964) Smoothing and Differen-tiation of Data by Simplified Least Squares Procedures. Analytical Chemistry, 36, 1627-1639. https://doi.org/10.1021/ac60214a047
[7]
McBratney, A., Santos, M.L.M. and Minasny, B. (2003) On Digital Soil Mapping. Geoderma, 117, 3-52. https://doi.org/10.1016/S0016-7061(03)00223-4
[8]
Scull, P., Franklin, J., Chadwick, O. and McArthur, D. (2003) Predictive Soil Mapping: A Review. Progress in Physical Geography: Earth and Environment, 27, 171-197. https://doi.org/10.1191/0309133303pp366ra
[9]
National Institude of Meteology (NIM). http://www.meteo.tn/default.html
[10]
Regional Commissariat for Agriculture Development of Zaghouan. http://cgdr.nat.tn/ar/index.php
[11]
Chong, I.-G. and Jun, C.-H. (2005) Performance of Some Variable Selection Methods When Multicollinearity Is Present. Chemometrics and Intelligent Laboratory Systems, 78, 103-112. https://doi.org/10.1016/j.chemolab.2004.12.011
[12]
Gosselin, R., Rodrigue, D. and Duchesne, C. (2010) A Bootstrap-VIP Approach for Selecting Wavelength Intervals in Spectral Imaging Application. Chemometrics and Intelligent Laboratory Systems, 100, 12-21. https://doi.org/10.1016/j.chemolab.2009.09.005
[13]
Lazraq, A., Cleroux, R. and Gauchi, J.-P. (2003) Selecting Both Latent and Explanatory Variables in the PLS1 Regression Model. Chemometrics and Intelligent Laboratory Systems, 66, 117-126. https://doi.org/10.1016/S0169-7439(03)00027-3
[14]
Rabah, Z.B., Farah, I.R., Solaiman, B. and Mercier, G. (2011) A New Method to Change Illumination Effect Reduction Based on Spectral Angle Constraint for Hyperspectral Image Unmixing. IEEE Geoscience and Remote Sensing Letters, 8, 1110-1114. https://doi.org/10.1109/LGRS.2011.2157890
