Multivariate regression methods for estimating basic density in Eucalyptus wood from near infrared spectroscopic data
Near infrared (NIR) spectroscopy is a fast and efficient technique to predict a range of wood traits; however, methods for extracting useful information from the NIR spectra could be improved. Thus, the aim of this study was to evaluate the statistic performance of two regression methods for estimating the basic density in Eucalyptus urophylla x grandis wood from near infrared spectroscopic data. The predictive models calibrated by principal component regression (PCR) or partial least square regression (PLSR) method provided fine correlations. The coefficients of determination (R2cv) of the PCR models ranged from 0.78 to 0.85 with standard error of cross-validation (SECV) and the ratio of performance to deviation (RPD) varying from 32.8 to 41.2 kg/m3 and from 1.6 to 1.9, respectively. The PLSR models presented R2cv with relatively lower magnitude (from 0.65 to 0.78); but also lower SECV (from 29.8 to 38.9 kg/m3) and higher RPD values (from 1.6 to 2.1). In short, PCR method provides higher R2 between Lab-measured and NIR-predicted values while PLSR produces lower standard errors of cross-validations. For both regression methods, the pre-treatments on NIR spectra, and the wavelength selection improved the calibration statistics, reducing the SECV and increasing the R2cv and the RPD values. Thus, PCR and PLS regression can be applied successfully for predicting basic density in Eucalyptus urophylla x grandis wood from the near infrared spectroscopic data.
Main Author: | |
---|---|
Format: | article biblioteca |
Language: | eng |
Subjects: | K50 - Technologie des produits forestiers, U30 - Méthodes de recherche, Eucalyptus, bois, densité, méthode statistique, normalisation, spectroscopie infrarouge, mesure (activité), calibrage, http://aims.fao.org/aos/agrovoc/c_2683, http://aims.fao.org/aos/agrovoc/c_8421, http://aims.fao.org/aos/agrovoc/c_2186, http://aims.fao.org/aos/agrovoc/c_7377, http://aims.fao.org/aos/agrovoc/c_7366, http://aims.fao.org/aos/agrovoc/c_28568, http://aims.fao.org/aos/agrovoc/c_4668, http://aims.fao.org/aos/agrovoc/c_36549, http://aims.fao.org/aos/agrovoc/c_4847, |
Online Access: | http://agritrop.cirad.fr/556351/ |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
dig-cirad-fr-556351 |
---|---|
record_format |
koha |
spelling |
dig-cirad-fr-5563512024-01-28T18:33:34Z http://agritrop.cirad.fr/556351/ http://agritrop.cirad.fr/556351/ Multivariate regression methods for estimating basic density in Eucalyptus wood from near infrared spectroscopic data. Gherardi Hein Paulo Ricardo. 2010. Revista Cerne, 16 : 90-96. Multivariate regression methods for estimating basic density in Eucalyptus wood from near infrared spectroscopic data Gherardi Hein, Paulo Ricardo eng 2010 Revista Cerne K50 - Technologie des produits forestiers U30 - Méthodes de recherche Eucalyptus bois densité méthode statistique normalisation spectroscopie infrarouge mesure (activité) calibrage http://aims.fao.org/aos/agrovoc/c_2683 http://aims.fao.org/aos/agrovoc/c_8421 http://aims.fao.org/aos/agrovoc/c_2186 http://aims.fao.org/aos/agrovoc/c_7377 http://aims.fao.org/aos/agrovoc/c_7366 http://aims.fao.org/aos/agrovoc/c_28568 http://aims.fao.org/aos/agrovoc/c_4668 http://aims.fao.org/aos/agrovoc/c_36549 Minas Gerais http://aims.fao.org/aos/agrovoc/c_4847 Near infrared (NIR) spectroscopy is a fast and efficient technique to predict a range of wood traits; however, methods for extracting useful information from the NIR spectra could be improved. Thus, the aim of this study was to evaluate the statistic performance of two regression methods for estimating the basic density in Eucalyptus urophylla x grandis wood from near infrared spectroscopic data. The predictive models calibrated by principal component regression (PCR) or partial least square regression (PLSR) method provided fine correlations. The coefficients of determination (R2cv) of the PCR models ranged from 0.78 to 0.85 with standard error of cross-validation (SECV) and the ratio of performance to deviation (RPD) varying from 32.8 to 41.2 kg/m3 and from 1.6 to 1.9, respectively. The PLSR models presented R2cv with relatively lower magnitude (from 0.65 to 0.78); but also lower SECV (from 29.8 to 38.9 kg/m3) and higher RPD values (from 1.6 to 2.1). In short, PCR method provides higher R2 between Lab-measured and NIR-predicted values while PLSR produces lower standard errors of cross-validations. For both regression methods, the pre-treatments on NIR spectra, and the wavelength selection improved the calibration statistics, reducing the SECV and increasing the R2cv and the RPD values. Thus, PCR and PLS regression can be applied successfully for predicting basic density in Eucalyptus urophylla x grandis wood from the near infrared spectroscopic data. article info:eu-repo/semantics/article Journal Article info:eu-repo/semantics/closedAccess http://catalogue-bibliotheques.cirad.fr/cgi-bin/koha/opac-detail.pl?biblionumber=209266 |
institution |
CIRAD FR |
collection |
DSpace |
country |
Francia |
countrycode |
FR |
component |
Bibliográfico |
access |
En linea |
databasecode |
dig-cirad-fr |
tag |
biblioteca |
region |
Europa del Oeste |
libraryname |
Biblioteca del CIRAD Francia |
language |
eng |
topic |
K50 - Technologie des produits forestiers U30 - Méthodes de recherche Eucalyptus bois densité méthode statistique normalisation spectroscopie infrarouge mesure (activité) calibrage http://aims.fao.org/aos/agrovoc/c_2683 http://aims.fao.org/aos/agrovoc/c_8421 http://aims.fao.org/aos/agrovoc/c_2186 http://aims.fao.org/aos/agrovoc/c_7377 http://aims.fao.org/aos/agrovoc/c_7366 http://aims.fao.org/aos/agrovoc/c_28568 http://aims.fao.org/aos/agrovoc/c_4668 http://aims.fao.org/aos/agrovoc/c_36549 http://aims.fao.org/aos/agrovoc/c_4847 K50 - Technologie des produits forestiers U30 - Méthodes de recherche Eucalyptus bois densité méthode statistique normalisation spectroscopie infrarouge mesure (activité) calibrage http://aims.fao.org/aos/agrovoc/c_2683 http://aims.fao.org/aos/agrovoc/c_8421 http://aims.fao.org/aos/agrovoc/c_2186 http://aims.fao.org/aos/agrovoc/c_7377 http://aims.fao.org/aos/agrovoc/c_7366 http://aims.fao.org/aos/agrovoc/c_28568 http://aims.fao.org/aos/agrovoc/c_4668 http://aims.fao.org/aos/agrovoc/c_36549 http://aims.fao.org/aos/agrovoc/c_4847 |
spellingShingle |
K50 - Technologie des produits forestiers U30 - Méthodes de recherche Eucalyptus bois densité méthode statistique normalisation spectroscopie infrarouge mesure (activité) calibrage http://aims.fao.org/aos/agrovoc/c_2683 http://aims.fao.org/aos/agrovoc/c_8421 http://aims.fao.org/aos/agrovoc/c_2186 http://aims.fao.org/aos/agrovoc/c_7377 http://aims.fao.org/aos/agrovoc/c_7366 http://aims.fao.org/aos/agrovoc/c_28568 http://aims.fao.org/aos/agrovoc/c_4668 http://aims.fao.org/aos/agrovoc/c_36549 http://aims.fao.org/aos/agrovoc/c_4847 K50 - Technologie des produits forestiers U30 - Méthodes de recherche Eucalyptus bois densité méthode statistique normalisation spectroscopie infrarouge mesure (activité) calibrage http://aims.fao.org/aos/agrovoc/c_2683 http://aims.fao.org/aos/agrovoc/c_8421 http://aims.fao.org/aos/agrovoc/c_2186 http://aims.fao.org/aos/agrovoc/c_7377 http://aims.fao.org/aos/agrovoc/c_7366 http://aims.fao.org/aos/agrovoc/c_28568 http://aims.fao.org/aos/agrovoc/c_4668 http://aims.fao.org/aos/agrovoc/c_36549 http://aims.fao.org/aos/agrovoc/c_4847 Gherardi Hein, Paulo Ricardo Multivariate regression methods for estimating basic density in Eucalyptus wood from near infrared spectroscopic data |
description |
Near infrared (NIR) spectroscopy is a fast and efficient technique to predict a range of wood traits; however, methods for extracting useful information from the NIR spectra could be improved. Thus, the aim of this study was to evaluate the statistic performance of two regression methods for estimating the basic density in Eucalyptus urophylla x grandis wood from near infrared spectroscopic data. The predictive models calibrated by principal component regression (PCR) or partial least square regression (PLSR) method provided fine correlations. The coefficients of determination (R2cv) of the PCR models ranged from 0.78 to 0.85 with standard error of cross-validation (SECV) and the ratio of performance to deviation (RPD) varying from 32.8 to 41.2 kg/m3 and from 1.6 to 1.9, respectively. The PLSR models presented R2cv with relatively lower magnitude (from 0.65 to 0.78); but also lower SECV (from 29.8 to 38.9 kg/m3) and higher RPD values (from 1.6 to 2.1). In short, PCR method provides higher R2 between Lab-measured and NIR-predicted values while PLSR produces lower standard errors of cross-validations. For both regression methods, the pre-treatments on NIR spectra, and the wavelength selection improved the calibration statistics, reducing the SECV and increasing the R2cv and the RPD values. Thus, PCR and PLS regression can be applied successfully for predicting basic density in Eucalyptus urophylla x grandis wood from the near infrared spectroscopic data. |
format |
article |
topic_facet |
K50 - Technologie des produits forestiers U30 - Méthodes de recherche Eucalyptus bois densité méthode statistique normalisation spectroscopie infrarouge mesure (activité) calibrage http://aims.fao.org/aos/agrovoc/c_2683 http://aims.fao.org/aos/agrovoc/c_8421 http://aims.fao.org/aos/agrovoc/c_2186 http://aims.fao.org/aos/agrovoc/c_7377 http://aims.fao.org/aos/agrovoc/c_7366 http://aims.fao.org/aos/agrovoc/c_28568 http://aims.fao.org/aos/agrovoc/c_4668 http://aims.fao.org/aos/agrovoc/c_36549 http://aims.fao.org/aos/agrovoc/c_4847 |
author |
Gherardi Hein, Paulo Ricardo |
author_facet |
Gherardi Hein, Paulo Ricardo |
author_sort |
Gherardi Hein, Paulo Ricardo |
title |
Multivariate regression methods for estimating basic density in Eucalyptus wood from near infrared spectroscopic data |
title_short |
Multivariate regression methods for estimating basic density in Eucalyptus wood from near infrared spectroscopic data |
title_full |
Multivariate regression methods for estimating basic density in Eucalyptus wood from near infrared spectroscopic data |
title_fullStr |
Multivariate regression methods for estimating basic density in Eucalyptus wood from near infrared spectroscopic data |
title_full_unstemmed |
Multivariate regression methods for estimating basic density in Eucalyptus wood from near infrared spectroscopic data |
title_sort |
multivariate regression methods for estimating basic density in eucalyptus wood from near infrared spectroscopic data |
url |
http://agritrop.cirad.fr/556351/ |
work_keys_str_mv |
AT gherardiheinpauloricardo multivariateregressionmethodsforestimatingbasicdensityineucalyptuswoodfromnearinfraredspectroscopicdata |
_version_ |
1792497630871289856 |