Comparative analysis of three chemometric techniques for the spectroradiometric assessment of canopy chlorophyll content in winter wheat

By Clement Atzberger, M. Guérif, Frédéric Baret, Willy Werner. 2010

240 citations recorded by the source corpus.

Subfields: Analytical Chemistry, Ecology, Plant Science

View Paper: https://www.semanticscholar.org/paper/48b3102425b0ab23ef82b4a5ac7547e069df60d8

How researchers see this paper

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

In Analytical Chemistry

In Ecology

In Plant Science

Citations in the corpus

Evaluation of Sentinel-2 Red-Edge Bands for Empirical Estimation of Green LAI and Chlorophyll Content (2011, methodology): “include: stepwise multiple linear regression, principal component regression, partial least square regression [41,64,70].”
Hyperspectral analysis of mangrove foliar chemistry using PLSR and support vector regression (2013, methodology): “PLSR has been used extensively in biochemical modelling (Asner 2008; Darvishzadeh et al. 2008; Atzberger et al. 2010), and it is particularly suited to handle a full reflectance spectrum with many collinear variables (Wold, Sjöström, and Eriksson 2001).”
Comparison of various modelling approaches for water deficit stress monitoring in rice crop through hyperspectral remote sensing (2019, methodology): “The random forest regression technique is an addition to the bagging (Breiman, 1994) of classification trees.”
Machine learning regression algorithms for biophysical parameter retrieval: Opportunities for Sentinel-2 and -3 (2012, methodology): “Lately linear multivariate feature extraction methods have been successfully introduced for biophysical parameter retrieval (Atzberger et al., 2010; Hansen & Schjoerring, 2003).”
LAI assessment of wheat and potato crops by VENμS and Sentinel-2 bands (2011, methodology): “Since PLS prediction models can deal efficiently with the multi-collinearity present among the predictors (in this case wavelengths of spectral data), and analyze spectra when the number of wavelengths is either larger or smaller than the number of observations as well as deal with noisy spectra (At”
Hyperspectral remote sensing of plant biochemistry using Bayesian model averaging with variable and band selection (2013, methodology): “Along with many recent studies, our findings accumulate further empirical evidence suggesting that it is difficult, if not impossible, to establish a generic statistical framework in hyperspectral remote sensing of plant biochemistry for diverse vegetation communities across the globe (Atzberger et ”
Estimation of Leaf Water Content in Winter Wheat Using Grey Relational Analysis-Partial Least Squares Modeling with Hyperspectral Data (2013, unknown): “Several researchers have used PLS to estimate chlorophyll content, N content (Atzberger et al., 2010), and leaf EWT (Colombo et al.”
Spectroscopic determination of ecologically relevant plant secondary metabolites (2016, methodology): “…regression techniques, PLSR reduces a large number of collinear predictor variables into relatively few, uncorrelated latent variables, and has become the preferred method for chemometric analyses (Bolster, Martin & Aber 1996; Asner & Martin 2008, 2011; Atzberger et al. 2010; Serbin et al. 2014).”
Quantifying Vegetation Biophysical Variables from Imaging Spectroscopy Data: A Review on Retrieval Methods (2018, result): “(2012) demonstrated that the model developed by SMLR led to a higher correlation coefficient and lower errors than model applications based on narrowband VIs.”
Estimating winter wheat (Triticum aestivum) LAI and leaf chlorophyll content from canopy reflectance data by integrating agronomic prior knowledge with the PROSAIL model (2015, methodology): “Atzberger et al. (2010) compared three chemometric techniques (PLSR, PCA, and step-wise multiple linear regression (SMLR)) for the spectroradiometry of canopy chlorophyll content in winter wheat and found that PLSR was better than PCA or SMLR for estimating the chlorophyll content in winter wheat.”
Comparison of different regression models and validation techniques for the assessment of wheat leaf area index from hyperspectral data (2015, background): “…however, were achieved for PLSR, which is less influenced by this problem because the high number of spectral bands is reduced to a distinctly lower number of uncorrelated LV representing an orthogonal linear combination of the original spectral bands (Atzberger et al. 2010; Yu et al. 2015).”