• DocumentCode
    2611949
  • Title

    Research on spectral characteristics model of lettuce canopy nitrogen content

  • Author

    Hongyan, Gao ; Hanping, Mao ; Xiaodong, Zhang ; Jun, Sun

  • Author_Institution
    Key Lab. of Modern Agric. Equip. & Technol., Jiangsu Univ., Zhenjiang, China
  • Volume
    5
  • fYear
    2011
  • fDate
    15-17 Oct. 2011
  • Firstpage
    2335
  • Lastpage
    2338
  • Abstract
    Lettuce canopy spectral reflectance was measured by hand-held portable spectrum analyzer, the reflectance characteristics was analyzed in the different nitrogen levels and different growth. After the first derivative treatment, then correlation analysis, lettuce canopy nitrogen associated with the four-sensitive band, which were 400 ~ 470nm, 510 ~ 590nm, 600 ~ 670nm, 680 ~ 750nm. Further used stepwise regression analysis, selected the sensitive wavelengths in different growth stages. Partial least squares regression was used for setting up prediction models in different growth. 24 samples were verified models in the same period, the measured and predicted of the correlation coefficient were 0.8570, 0.8853 and 0.8591, and RMSE were 0.6355, 0.6122 and 0.5472.
  • Keywords
    geochemistry; regression analysis; spectral analysers; vegetation; correlation analysis; correlation coefficient; four-sensitive band; hand-held portable spectrum analyzer; lettuce canopy nitrogen content; lettuce canopy spectral reflectance; nitrogen levels; partial least squares regression; prediction models; reflectance characteristics; spectral characteristics model; stepwise regression analysis; Correlation; Educational institutions; Laboratories; Mathematical model; Nitrogen; Predictive models; Reflectivity; Lettuce; Nitrogen; Partial Least Squares Regression Analysis; Reflectance Spectra;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Image and Signal Processing (CISP), 2011 4th International Congress on
  • Conference_Location
    Shanghai
  • Print_ISBN
    978-1-4244-9304-3
  • Type

    conf

  • DOI
    10.1109/CISP.2011.6100675
  • Filename
    6100675