Click on “Download PDF” for the PDF version or on the title for the HTML version.


If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Prediction of Chlorophyll Content in Wheat Leaves Using Hyperspectral Images

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.org

Citation:  2010 Pittsburgh, Pennsylvania, June 20 - June 23, 2010  1009492.(doi:10.13031/2013.29919)
Authors:   Yankun Peng, Hui Huang, Wei Wang, Xiu Wang, Jianhu Wu, Leilei Zhang
Keywords:   Wheat leaves; Chlorophyll content; Hyperspectral imaging; Least squares support vector machine.

Chlorophyll content in wheat leaves can indicate the plant health status. The objective of this study was to explore a way for nondestructive measurement of chlorophyll content in wheat leaves and establish quantitative models for real-time monitoring of chlorophyll content status in wheat plant with VIS/NIR hyperspectral images. Five ?eld experiments were conducted with different nitrogen (N) application rates. Hyperspectral images of wheat plants were collected in the region of 400-1100 nm, then the cube image data was constructed and the region of interest (ROI) was selected. Multiplicative scatter correction (MSC) and Savitsky-Golay smoothing as preprocessing method were used to eliminate noise and smooth spectral curve. Stepwise multivariate linear regression (SMLR) was used to select optimal wavelength combination. Chlorophyll content prediction models were developed using least squares support vector machine (LSSVM) based on wave band and wavelength combination separately. The best predictions were obtained with Rv2= 0.88 and RMSECV= 0.06. The research demonstrated that it is feasible to predict the chlorophyll content in wheat leaves using hyperspectral images.

(Download PDF)    (Export to EndNotes)