versão On-line ISSN 1678-992X

Resumo

OLIVEIRA, Luiz Felipe Ramalho de  e  SANTANA, Reynaldo Campos. Estimation of leaf nutrient concentration from hyperspectral reflectance in Eucalyptus using partial least squares regression. Sci. agric. (Piracicaba, Braz.) [online]. 2020, vol.77, n.6, e20180409.  Epub 24-Jan-2020. ISSN 1678-992X.  http://dx.doi.org/10.1590/1678-992x-2018-0409.

Leaf hyperspectral reflectance has been used to estimate nutrient concentrations in plants in narrow bands of the electromagnetic spectrum. The aim of this study was to estimate leaf nutrient concentrations using leaf hyperspectral reflectance and verify the variable selection methods using the partial least squares regression (PLSR). Two studies were carried out using stands with Eucalyptus clones. Study I was established in Eucalyptus stands with three clones, classifying leaves into five colour patterns using the Munsell chart for plant tissues. Immediately after leaf collection, leaf reflectance was read and the chemical analysis was performed. Study II was carried out in commercial clonal stands of Eucalyptus performing the same leaf sampling and chemical analysis as used in Study I. All leaf reflectance spectra were smoothed and three more pre-processing procedures were applied. In addition, three methods of PLSR were tested. The first derivative was more accurate for predicting nitrogen ( $R c v 2 = 0.95$), phosphorous ( $R c v 2 = 0.93$), and sulphur concentration ( $R c v 2 = 0.85$). The estimates for concentrations of calcium ( $R c v 2 = 0.81$), magnesium ( $R c v 2 = 0.22$), and potassium ( $R c v 2 = 0.76$) were more accurate using the logarithm transformation. Only the estimates for iron concentrations were performed with higher accuracy ( $R c v 2 = 0.35$) using the smoothed reflectance. The copper concentrations were more accurate ( $R c v 2 = 0.78$) using the logarithm transformation. Concentrations of boron ( $R c v 2 = 0.68$) and manganese ( $R c v 2 = 0.79$) were more accurate using the first derivative, while zinc ( $R c v 2 = 0.31$) concentration was most accurate using the second derivative.

Palavras-chave : remote sensing; tree monitoring; modelling; variable selection.

· texto em Inglês     · Inglês ( pdf )