Comparison of Three Regression Methods for the Winter Wheat Biomass Estimation Using Hyperspectral Data

Abstract:

To make full use of the hyperspectral data, the strong multi-collinearity in the data is supposed to be taken into account. With this study we evaluated three multivariate regression methods which are principal component regression, partial least square regression (PLSR) and stepwise multiple linear regression. Furthermore, to identify reliable winter wheat biomass predictive models, two different types of spectral transformations (continuum removal, first derivative) were combined with the three regression methods, respectively. Amongst these combinations, the respective combination of three regression methods and continuum removal got the highest estimation accuracy, especially, the combination of PLSR and continuum removal (R²=0.715, RMSE=0.218kg/m²). The experimental results demonstrated that PLSR is recommended for highly multi-collinear data sets. The combination of continuum removal and PLSR could improve the estimation accuracy of winter wheat biomass.

• Periodical: Applied Mechanics and Materials (Volumes 380-384)
• Pages: 1843-1846
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.380-384.1843
• Online since: August 2013
• Authors: Yuan Yuan Fu, Ji Hua Wang, Gui Jun Yang, Hai Kuan Feng
• Keywords: Partial Least Squares Regression, Principal Component Regression, Spectral Transformation, Stepwise Multiple Linear Regression, Winter Wheat Biomass

References

[1] J. G. P. W. Clevers, G. W. A. M. Van der Heijden, S. Verzakov, et al. Estimating grassland biomass using SVM band shaving of hyperspectral data [J]. Photogrammetric Engineering & Remote Sensing , 2007, 73(10): 1141-1148.

DOI: 10.14358/pers.73.10.1141

[2] H. T. Nguyen, B. W. Lee. Assessment of rice leaf growth and nitrogen status by hyperspectal canopy reflectance and partial least square regression . European Journal of Agronomy, 2006, 24(4): 349-356.

DOI: 10.1016/j.eja.2006.01.001

[3] G. El-Masry, N. Wang, A. El-Sayed, et al. Hyperspectral imaging for nondestructive determination of some quality attributes for strawberry [J]. Journal of Food Engineering, 2007, 81(1): 98-107.

DOI: 10.1016/j.jfoodeng.2006.10.016

[4] C. Atzberger, M. Guerif, B. Frederic, et al. Comparative analysis of three chemometric techniques for the specroradiometric assessment of canopy chlorophyll content in winter wheat [J]. Computers and Electronics in Agriculture, 2010, 73: 165-173.

DOI: 10.1016/j.compag.2010.05.006

[5] R.F. Kokaly, C.A. Hlavka, D.L. Peterson. Spectroscopic determination of leaf biochemistry using band-depth analysis of absorption features and stepwise multiple linear regression [J]. Remote Sensing of Environment, 1994, 67: 267-287.

DOI: 10.1016/s0034-4257(98)00084-4

[6] C. Atzberger, T. Jarmer, M. Schlerf, et al. Spectroradiometric determination of wheat bio-physical variables: comparison of different empirical-statistical approaches [C]. Remote Sensing in Transitions, Proc. 23rd EARSeL symposium, Belgium, 2003, 463-470.

[7] P. Geladi, B. R. Kowalski. Partial least-squares regression: a tutorial. Anal. Chim. Acta, 1986, 185: 1-17.

DOI: 10.1016/0003-2670(86)80028-9

[8] R. Darvishzadeh, A. Skidmore, M. Schlerf, et al. LAI and chlorophyll estimation for a heterogeneous grassland using hyperspectral measurements [J]. Journal of Photogrammetric & Remote Sensing, 2008, 63: 409-426.

DOI: 10.1016/j.isprsjprs.2008.01.001