Using spectrotemporal indices to improve the fruit-tree crop classification accuracy

This study assesses the potential of spectrotemporal indices derived from satellite image time series (SITS) to improve the classification accuracy of fruit-tree crops. Six major fruit-tree crop types in the Aconcagua Valley, Chile, were classified by applying various linear discriminant analysis (LDA) techniques on a Landsat-8 time series of nine images corresponding to the 2014–15 growing season. As features we not only used the complete spectral resolution of the SITS, but also all possible normalized difference indices (NDIs) that can be constructed from any two bands of the time series, a novel approach to derive features from SITS. Due to the high dimensionality of this ‘‘enhanced” feature set we used the lasso and ridge penalized variants of LDA (PLDA). Although classification accuracies yielded by the standard LDA applied on the full-band SITS were good (misclassification error rate, MER = 0.13), they were further improved by 23% (MER = 0.10) with ridge PLDA using the enhanced feature set. The most important bands to discriminate the crops of interest were mainly concentrated on the first two image dates of the time series, corresponding to the crops greenup stage. Despite the high predictor weights provided by the red and near infrared bands, typically used to construct greenness spectral indices, other spectral regions were also found important for the discrimination, such as the shortwave infrared band at 2.11–2.19 lm, sensitive to foliar water changes. These findings support the usefulness of spectrotemporal indices in the context of SITS-based crop type classifications, which until now have been mainly constructed by the arithmetic combination of two bands of the same image date in order to derive greenness temporal profiles like those from the normalized difference vegetation index.

Información de Publicación

Autores:

Marco Peña

Institución: Universidad Alberto Hurtado
Facultad: Ciencias Sociales
Unidad: Geografía

Liao, R

Institución: Friedrich Schiller University Jena

Brenning, A

Institución: University of Waterloo

Revista:

ISPRS Journal of Photogrammetry and Remote Sensing

Año:

2017

Mes:

Diciembre

Páginas:

158-169

Url de Publicación:

http://dx.doi.org/10.1016/j.isprsjprs.2017.03.019.