Estimating tropical pasture quality at canopy level using band depth analysis with continuum removal in the visible domain

Pasture quality, expressed as a percentage of total digestible nutrients (nitrogen, potassium, phosphorous, calcium and magnesium), is a major factor determining the grazing patterns of wildlife and livestock. Existing rangeland monitoring techniques seldom reflect the nutritive quality of the pastures and are consequently of limited value in explaining animal distribution. Techniques that can estimate pasture quality on a large scale are therefore critical in understanding and explaining wildlife and livestock distribution. We present the results of a greenhouse experiment designed to estimate the concentrations of nitrogen, potassium, phosphorous, calcium, magnesium and non-detergent fibre (NDF), using the reflectance of a tropical grass (Cenchrus ciliaris) canopy. Canopy spectral measurements were taken under controlled laboratory conditions using a GER 3700 spectroradiometer. We tested the utility of using the band depth analysis methodology in the visible region (where water absorption is less effective) to estimate foliar chemistry in fresh canopies. Continuum removal was applied to the visible absorption feature centred at 670 nm, and band depth ratios (BDRs) were calculated. Stepwise linear regression was used to select wavelengths from calculated BDRs that were highly correlated with foliar chemistry in a randomly selected training dataset. The resulting regression models were used to predict foliar chemistry in a test dataset. Results indicate that stepwise regression on bands calculated from continuum-removed reflectance spectra could predict foliar nutrient concentration with high accuracy. The correlations were highest for magnesium and nitrogen (R(2)=0.77 and 0.73 respectively, using the normalized band depth index (NBDI)) between the measured and estimated biochemicals-a satisfactory result in estimating foliar chemistry in fresh standing pastures. With the advent of new sensors such as Hymap and MERIS, these results lay the basis for developing algorithms to rapidly estimate and ultimately map pasture quality in tropical rangelands.