Comparative analysis of three regression methods for the winter wheat biomass estimation using hyperspectral measurements
- 10.2991/iccsee.2013.434How to use a DOI?
- winter wheat biomass,hyperspectral,partial least squares regression,principal component regression, stepwise multiple linear regression,spectral transformation
Hyperspectal data contain more useful information for characterizing vegetation biomass, compared with multi-spectral data. However, 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 (PCR), partial least square regression (PLSR) and stepwise multiple linear regression (SMLR). They are specifically designed to deal with multi-collinearity problem. Furthermore, to identify reliable winter wheat biomass predictive models different types of spectral transformations (continuum removal, first derivative) were combined with the three regression methods, respectively. The comparative analysis was conducted on the data sets collected in 2008 and 2009 field campaigns in Tongzhou and Shunyi district, Beijing, China. Compared with the other combination, 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 the use of 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.
- © 2013, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Yuanyuan Fu AU - Guijun Yang AU - Haikuan Feng AU - Xiaoyu Song AU - Xingang Xu AU - Jihua Wang PY - 2013/03 DA - 2013/03 TI - Comparative analysis of three regression methods for the winter wheat biomass estimation using hyperspectral measurements BT - Proceedings of the 2nd International Conference on Computer Science and Electronics Engineering (ICCSEE 2013) PB - Atlantis Press SP - 1733 EP - 1736 SN - 1951-6851 UR - https://doi.org/10.2991/iccsee.2013.434 DO - 10.2991/iccsee.2013.434 ID - Fu2013/03 ER -