This paper proposes a method to estimate leaf water content from reflectance in four commercial vineyard varieties by estimating the local maxima of a distance correlation function. First, it applies four different functional regression models to the data and compares the models to test the viability of estimating water content from reflectance. It then applies our methodology to select a small number of wavelengths (optimum wavelengths) from the continuous spectrum, which simplifies the regression problem. Finally, it compares the results to those obtained by means of two different methods: a nonparametric kernel smoothing for variable selection in functional data and a wavelet-based weighted LASSO functional linear regression. Our approach proved to have some advantages over these two testing approaches, mainly in terms of the computing time and the lack of assumption of an underlying model. Finally, the paper concludes that estimating water content from a few wavelengths is almost equivalent to doing so using larger wavelength intervals.
Type of Publication:
Chemometrics and Intelligent Laboratory Systems
Q1 7/123 h-index 2.701 (JCR2017)
This study was made possible with financial funding from: a) FC-15-GRUPIN14-033 of the Fundación para el Fomento en Asturias de la Investigación Científica Aplicada y la Tecnología (FICYT) (Spain), with FEDER support included, b) Ministry of Economy and Competitiveness (MTM2016-76969P) and European Regional Development Fund, b) Spanish Ministry of Economy and Competitiveness (Grant numbers MTM2013-41383-P and MTM2016-76969-P) and European Regional Development Fund (ERDF). c)Grupo de Referencia Competitiva, 2016–2019 (ED431C 2016/040), financiado pola Consellería de Cultura, Educación e Ordenación Universitaria, Xunta de Galicia.