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.
Spatial Reflectance at Sub-Leaf Scale Discriminating NPK Stress Characteristics in Barley Using Multiway Partial Least Squares Regression
Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.orgCitation: Paper number 031138, 2003 ASAE Annual Meeting . (doi: 10.13031/2013.13744) @2003
Authors: L.K. Christensen, R.N. Jørgensen
Keywords: NPK discrimination, hyper spectral reflectance, barley, sub-leaf scale, N-PLS
Non-destructive stress diagnostics is essential to optimise variable nutrient application with a minimal environmental load. The identifying characteristics when spectrally determining nitrogen, phosphorous and potassium stress in a canopy are dominantly nonspecific symptoms expressed as varying levels of chlorophyll in the leaves. The challenge is spectrally based discrimination between N, P and K stress. This paper introduces a methodology able to discriminate between N, P and K stress symptoms utilising both the spectral and spatial dimension simultaneously. The methodology was tested on spring barley grown under controlled conditions. The spectral range used was 450-1000 nm. Nine spectral measurement were carried out on each plant. The measuring points were spatially located at the tip, middle and base of the three last fully developed leaves. This design generated a fourdimensional data set consisting of the specific plant, the spectral dimension, the plant leaf position, and position on the leaf. Sequential mutiway Partial Least Squares Regression model (N-PLS) analysis with dummy variables was able to correctly classify the four nutrient conditions with 92% accuracy regardless of the respective growth stages within a time window of two weeks. Thus inclusion of the spatial dimension to the spectral dimension was shown to be a promissing nutrient diagnostic tool.(Download PDF) (Export to EndNotes)