Multi-method ensemble selection of spectral bands related to leaf biochemistry

176 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Quantifying Vegetation Biophysical Variables from Imaging Spectroscopy Data: A Review on Retrieval Methods (2018, background): “Alternatively, RF is inherently able to identify sensitive spectral bands, and selection of only those sensitive bands can subsequently improve the regression model (Balzarolo et al. 2015; Feilhauer et al. 2015).”
Optical remote sensing and the retrieval of terrestrial vegetation bio-geophysical properties - A review (2015, methodology): “Also other non-parametric regression methods provide insight in band relevancy, such as SVR, PLSR and random forests (Feilhauer et al., 2015).”
PROSPECT-PRO for estimating content of nitrogen-containing leaf proteins and other carbon-based constituents (2020, methodology): “The most unsuitable spectral wavelengths can be identified and removed by hybrid methods featuring band selection, feature extraction or band weighting procedures (Fassnacht et al., 2014; Feilhauer et al., 2015; Verrelst et al., 2015).”
Comparison of support vector machine, random forest and neural network classifiers for tree species classification on airborne hyperspectral APEX images (2017, methodology): “…PLS or support vector machine regression were reported to provide better selection of spectral bands than that used in this research (Fassnacht et al., 2014; Feilhauer, Asner, & Martin, 2015), although this holds true to SVM and RF classification algorithms, because ANN were not investigated.”