Fresh biomass estimation in heterogeneous grassland using hyperspectral measurements and multivariate statistical analysis

R. Darvishzadeh, A.K. Skidmore, M. Mirzaie, C. Atzberger, M. Schlerf

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

Accurate estimation of grassland biomass at their peak productivity can provide crucial information regarding the functioning and productivity of the rangelands. Hyperspectral remote sensing has proved to be valuable for estimation of vegetation biophysical parameters such as biomass using different statistical techniques. However, in statistical analysis of hyperspectral data, multicollinearity is a common problem due to large amount of correlated hyper-spectral reflectance measurements. The aim of this study was to examine the prospect of above ground biomass estimation in a heterogeneous Mediterranean rangeland employing multivariate calibration methods. Canopy spectral measurements were made in the field using a GER 3700 spectroradiometer, along with concomitant in situ measurements of above ground biomass for 170 sample plots. Multivariate calibrations including partial least squares regression (PLSR), principal component regression (PCR), and Least-Squared Support Vector Machine (LS-SVM) were used to estimate the above ground biomass. The prediction accuracy of the multivariate calibration methods were assessed using cross validated R2 and RMSE. The best model performance was obtained using LS_SVM and then PLSR both calibrated with first derivative reflectance dataset with R2CV=0.88 & 0.86 and RMSECV=1.15 & 1.07 respectively. The weakest prediction accuracy was appeared when PCR were used (R2CV = 0.31 and RMSECV= 2.48). The obtained results highlight the importance of multivariate calibration methods for biomass estimation when hyperspectral data are used.
Original languageEnglish
Title of host publicationProceedings of the 2015 annual ASPRS conference, IGTF, 4-8 may, 2015, Tampa, Florida
Place of PublicationTampa, Florida
PublisherASPRS
Pages171-177
Number of pages7
Publication statusPublished - 2015

Fingerprint

statistical analysis
aboveground biomass
grassland
calibration
biomass
rangeland
productivity
spectral reflectance
prediction
in situ measurement
reflectance
canopy
remote sensing
vegetation
method

Keywords

  • METIS-311385

Cite this

Darvishzadeh, R., Skidmore, A. K., Mirzaie, M., Atzberger, C., & Schlerf, M. (2015). Fresh biomass estimation in heterogeneous grassland using hyperspectral measurements and multivariate statistical analysis. In Proceedings of the 2015 annual ASPRS conference, IGTF, 4-8 may, 2015, Tampa, Florida (pp. 171-177). Tampa, Florida: ASPRS.
Darvishzadeh, R. ; Skidmore, A.K. ; Mirzaie, M. ; Atzberger, C. ; Schlerf, M. / Fresh biomass estimation in heterogeneous grassland using hyperspectral measurements and multivariate statistical analysis. Proceedings of the 2015 annual ASPRS conference, IGTF, 4-8 may, 2015, Tampa, Florida. Tampa, Florida : ASPRS, 2015. pp. 171-177
@inproceedings{00186eaa60d3405386692ff6220720c0,
title = "Fresh biomass estimation in heterogeneous grassland using hyperspectral measurements and multivariate statistical analysis",
abstract = "Accurate estimation of grassland biomass at their peak productivity can provide crucial information regarding the functioning and productivity of the rangelands. Hyperspectral remote sensing has proved to be valuable for estimation of vegetation biophysical parameters such as biomass using different statistical techniques. However, in statistical analysis of hyperspectral data, multicollinearity is a common problem due to large amount of correlated hyper-spectral reflectance measurements. The aim of this study was to examine the prospect of above ground biomass estimation in a heterogeneous Mediterranean rangeland employing multivariate calibration methods. Canopy spectral measurements were made in the field using a GER 3700 spectroradiometer, along with concomitant in situ measurements of above ground biomass for 170 sample plots. Multivariate calibrations including partial least squares regression (PLSR), principal component regression (PCR), and Least-Squared Support Vector Machine (LS-SVM) were used to estimate the above ground biomass. The prediction accuracy of the multivariate calibration methods were assessed using cross validated R2 and RMSE. The best model performance was obtained using LS_SVM and then PLSR both calibrated with first derivative reflectance dataset with R2CV=0.88 & 0.86 and RMSECV=1.15 & 1.07 respectively. The weakest prediction accuracy was appeared when PCR were used (R2CV = 0.31 and RMSECV= 2.48). The obtained results highlight the importance of multivariate calibration methods for biomass estimation when hyperspectral data are used.",
keywords = "METIS-311385",
author = "R. Darvishzadeh and A.K. Skidmore and M. Mirzaie and C. Atzberger and M. Schlerf",
year = "2015",
language = "English",
pages = "171--177",
booktitle = "Proceedings of the 2015 annual ASPRS conference, IGTF, 4-8 may, 2015, Tampa, Florida",
publisher = "ASPRS",

}

Darvishzadeh, R, Skidmore, AK, Mirzaie, M, Atzberger, C & Schlerf, M 2015, Fresh biomass estimation in heterogeneous grassland using hyperspectral measurements and multivariate statistical analysis. in Proceedings of the 2015 annual ASPRS conference, IGTF, 4-8 may, 2015, Tampa, Florida. ASPRS, Tampa, Florida, pp. 171-177.

Fresh biomass estimation in heterogeneous grassland using hyperspectral measurements and multivariate statistical analysis. / Darvishzadeh, R.; Skidmore, A.K.; Mirzaie, M.; Atzberger, C.; Schlerf, M.

Proceedings of the 2015 annual ASPRS conference, IGTF, 4-8 may, 2015, Tampa, Florida. Tampa, Florida : ASPRS, 2015. p. 171-177.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Fresh biomass estimation in heterogeneous grassland using hyperspectral measurements and multivariate statistical analysis

AU - Darvishzadeh, R.

AU - Skidmore, A.K.

AU - Mirzaie, M.

AU - Atzberger, C.

AU - Schlerf, M.

PY - 2015

Y1 - 2015

N2 - Accurate estimation of grassland biomass at their peak productivity can provide crucial information regarding the functioning and productivity of the rangelands. Hyperspectral remote sensing has proved to be valuable for estimation of vegetation biophysical parameters such as biomass using different statistical techniques. However, in statistical analysis of hyperspectral data, multicollinearity is a common problem due to large amount of correlated hyper-spectral reflectance measurements. The aim of this study was to examine the prospect of above ground biomass estimation in a heterogeneous Mediterranean rangeland employing multivariate calibration methods. Canopy spectral measurements were made in the field using a GER 3700 spectroradiometer, along with concomitant in situ measurements of above ground biomass for 170 sample plots. Multivariate calibrations including partial least squares regression (PLSR), principal component regression (PCR), and Least-Squared Support Vector Machine (LS-SVM) were used to estimate the above ground biomass. The prediction accuracy of the multivariate calibration methods were assessed using cross validated R2 and RMSE. The best model performance was obtained using LS_SVM and then PLSR both calibrated with first derivative reflectance dataset with R2CV=0.88 & 0.86 and RMSECV=1.15 & 1.07 respectively. The weakest prediction accuracy was appeared when PCR were used (R2CV = 0.31 and RMSECV= 2.48). The obtained results highlight the importance of multivariate calibration methods for biomass estimation when hyperspectral data are used.

AB - Accurate estimation of grassland biomass at their peak productivity can provide crucial information regarding the functioning and productivity of the rangelands. Hyperspectral remote sensing has proved to be valuable for estimation of vegetation biophysical parameters such as biomass using different statistical techniques. However, in statistical analysis of hyperspectral data, multicollinearity is a common problem due to large amount of correlated hyper-spectral reflectance measurements. The aim of this study was to examine the prospect of above ground biomass estimation in a heterogeneous Mediterranean rangeland employing multivariate calibration methods. Canopy spectral measurements were made in the field using a GER 3700 spectroradiometer, along with concomitant in situ measurements of above ground biomass for 170 sample plots. Multivariate calibrations including partial least squares regression (PLSR), principal component regression (PCR), and Least-Squared Support Vector Machine (LS-SVM) were used to estimate the above ground biomass. The prediction accuracy of the multivariate calibration methods were assessed using cross validated R2 and RMSE. The best model performance was obtained using LS_SVM and then PLSR both calibrated with first derivative reflectance dataset with R2CV=0.88 & 0.86 and RMSECV=1.15 & 1.07 respectively. The weakest prediction accuracy was appeared when PCR were used (R2CV = 0.31 and RMSECV= 2.48). The obtained results highlight the importance of multivariate calibration methods for biomass estimation when hyperspectral data are used.

KW - METIS-311385

UR - https://ezproxy2.utwente.nl/login?url=https://webapps.itc.utwente.nl/library/2015/conf/darvishzadeh_fre.pdf

M3 - Conference contribution

SP - 171

EP - 177

BT - Proceedings of the 2015 annual ASPRS conference, IGTF, 4-8 may, 2015, Tampa, Florida

PB - ASPRS

CY - Tampa, Florida

ER -

Darvishzadeh R, Skidmore AK, Mirzaie M, Atzberger C, Schlerf M. Fresh biomass estimation in heterogeneous grassland using hyperspectral measurements and multivariate statistical analysis. In Proceedings of the 2015 annual ASPRS conference, IGTF, 4-8 may, 2015, Tampa, Florida. Tampa, Florida: ASPRS. 2015. p. 171-177