Non-linear partial least square regression increases the estimation accuracy of grass nitrogen and phosphorus using in situ hyperspectral and environmental data

A. Ramoelo, A. Ramoelo, A.K. Skidmore, M.A. Cho, R. Mathieu, I.M.A. Heitkonig, M. Dudendi-Tlhone, M. Schlerf, H.H.T. Prins

Research output: Contribution to journalArticleAcademicpeer-review

49 Citations (Scopus)

Abstract

Grass nitrogen (N) and phosphorus (P) concentrations are direct indicators of rangeland quality and provide imperative information for sound management of wildlife and livestock. It is challenging to estimate grass N and P concentrations using remote sensing in the savanna ecosystems. These areas are diverse and heterogeneous in soil and plant moisture, soil nutrients, grazing pressures, and human activities. The objective of the study is to test the performance of non-linear partial least squares regression (PLSR) for predicting grass N and P concentrations through integrating in situ hyperspectral remote sensing and environmental variables (climatic, edaphic and topographic). Data were collected along a land use gradient in the greater Kruger National Park region. The data consisted of: (i) in situ-measured hyperspectral spectra, (ii) environmental variables and measured grass N and P concentrations. The hyperspectral variables included published starch, N and protein spectral absorption features, red edge position, narrow-band indices such as simple ratio (SR) and normalized difference vegetation index (NDVI). The results of the non-linear PLSR were compared to those of conventional linear PLSR. Using non-linear PLSR, integrating in situ hyperspectral and environmental variables yielded the highest grass N and P estimation accuracy (R2 = 0.81, root mean square error (RMSE) = 0.08, and R2 = 0.80, RMSE = 0.03, respectively) as compared to using remote sensing variables only, and conventional PLSR. The study demonstrates the importance of an integrated modeling approach for estimating grass quality which is a crucial effort towards effective management and planning of protected and communal savanna ecosystems.
Original languageEnglish
Pages (from-to)27-40
JournalISPRS journal of photogrammetry and remote sensing
Volume82
DOIs
Publication statusPublished - 2013

Fingerprint

grasses
phosphorus
Phosphorus
regression analysis
Remote sensing
grass
Nitrogen
nitrogen
Mean square error
Ecosystems
remote sensing
soil moisture
root-mean-square errors
Soil moisture
ecosystems
Starch
Land use
savanna
Agriculture
Nutrients

Keywords

  • METIS-302230
  • IR-90378
  • ITC-ISI-JOURNAL-ARTICLE

Cite this

Ramoelo, A. ; Ramoelo, A. ; Skidmore, A.K. ; Cho, M.A. ; Mathieu, R. ; Heitkonig, I.M.A. ; Dudendi-Tlhone, M. ; Schlerf, M. ; Prins, H.H.T. / Non-linear partial least square regression increases the estimation accuracy of grass nitrogen and phosphorus using in situ hyperspectral and environmental data. In: ISPRS journal of photogrammetry and remote sensing. 2013 ; Vol. 82. pp. 27-40.
@article{f72a51bedb754ed187d32b3277b09afa,
title = "Non-linear partial least square regression increases the estimation accuracy of grass nitrogen and phosphorus using in situ hyperspectral and environmental data",
abstract = "Grass nitrogen (N) and phosphorus (P) concentrations are direct indicators of rangeland quality and provide imperative information for sound management of wildlife and livestock. It is challenging to estimate grass N and P concentrations using remote sensing in the savanna ecosystems. These areas are diverse and heterogeneous in soil and plant moisture, soil nutrients, grazing pressures, and human activities. The objective of the study is to test the performance of non-linear partial least squares regression (PLSR) for predicting grass N and P concentrations through integrating in situ hyperspectral remote sensing and environmental variables (climatic, edaphic and topographic). Data were collected along a land use gradient in the greater Kruger National Park region. The data consisted of: (i) in situ-measured hyperspectral spectra, (ii) environmental variables and measured grass N and P concentrations. The hyperspectral variables included published starch, N and protein spectral absorption features, red edge position, narrow-band indices such as simple ratio (SR) and normalized difference vegetation index (NDVI). The results of the non-linear PLSR were compared to those of conventional linear PLSR. Using non-linear PLSR, integrating in situ hyperspectral and environmental variables yielded the highest grass N and P estimation accuracy (R2 = 0.81, root mean square error (RMSE) = 0.08, and R2 = 0.80, RMSE = 0.03, respectively) as compared to using remote sensing variables only, and conventional PLSR. The study demonstrates the importance of an integrated modeling approach for estimating grass quality which is a crucial effort towards effective management and planning of protected and communal savanna ecosystems.",
keywords = "METIS-302230, IR-90378, ITC-ISI-JOURNAL-ARTICLE",
author = "A. Ramoelo and A. Ramoelo and A.K. Skidmore and M.A. Cho and R. Mathieu and I.M.A. Heitkonig and M. Dudendi-Tlhone and M. Schlerf and H.H.T. Prins",
year = "2013",
doi = "10.1016/j.isprsjprs.2013.04.012",
language = "English",
volume = "82",
pages = "27--40",
journal = "ISPRS journal of photogrammetry and remote sensing",
issn = "0924-2716",
publisher = "Elsevier",

}

Non-linear partial least square regression increases the estimation accuracy of grass nitrogen and phosphorus using in situ hyperspectral and environmental data. / Ramoelo, A.; Ramoelo, A.; Skidmore, A.K.; Cho, M.A.; Mathieu, R.; Heitkonig, I.M.A.; Dudendi-Tlhone, M.; Schlerf, M.; Prins, H.H.T.

In: ISPRS journal of photogrammetry and remote sensing, Vol. 82, 2013, p. 27-40.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Non-linear partial least square regression increases the estimation accuracy of grass nitrogen and phosphorus using in situ hyperspectral and environmental data

AU - Ramoelo, A.

AU - Ramoelo, A.

AU - Skidmore, A.K.

AU - Cho, M.A.

AU - Mathieu, R.

AU - Heitkonig, I.M.A.

AU - Dudendi-Tlhone, M.

AU - Schlerf, M.

AU - Prins, H.H.T.

PY - 2013

Y1 - 2013

N2 - Grass nitrogen (N) and phosphorus (P) concentrations are direct indicators of rangeland quality and provide imperative information for sound management of wildlife and livestock. It is challenging to estimate grass N and P concentrations using remote sensing in the savanna ecosystems. These areas are diverse and heterogeneous in soil and plant moisture, soil nutrients, grazing pressures, and human activities. The objective of the study is to test the performance of non-linear partial least squares regression (PLSR) for predicting grass N and P concentrations through integrating in situ hyperspectral remote sensing and environmental variables (climatic, edaphic and topographic). Data were collected along a land use gradient in the greater Kruger National Park region. The data consisted of: (i) in situ-measured hyperspectral spectra, (ii) environmental variables and measured grass N and P concentrations. The hyperspectral variables included published starch, N and protein spectral absorption features, red edge position, narrow-band indices such as simple ratio (SR) and normalized difference vegetation index (NDVI). The results of the non-linear PLSR were compared to those of conventional linear PLSR. Using non-linear PLSR, integrating in situ hyperspectral and environmental variables yielded the highest grass N and P estimation accuracy (R2 = 0.81, root mean square error (RMSE) = 0.08, and R2 = 0.80, RMSE = 0.03, respectively) as compared to using remote sensing variables only, and conventional PLSR. The study demonstrates the importance of an integrated modeling approach for estimating grass quality which is a crucial effort towards effective management and planning of protected and communal savanna ecosystems.

AB - Grass nitrogen (N) and phosphorus (P) concentrations are direct indicators of rangeland quality and provide imperative information for sound management of wildlife and livestock. It is challenging to estimate grass N and P concentrations using remote sensing in the savanna ecosystems. These areas are diverse and heterogeneous in soil and plant moisture, soil nutrients, grazing pressures, and human activities. The objective of the study is to test the performance of non-linear partial least squares regression (PLSR) for predicting grass N and P concentrations through integrating in situ hyperspectral remote sensing and environmental variables (climatic, edaphic and topographic). Data were collected along a land use gradient in the greater Kruger National Park region. The data consisted of: (i) in situ-measured hyperspectral spectra, (ii) environmental variables and measured grass N and P concentrations. The hyperspectral variables included published starch, N and protein spectral absorption features, red edge position, narrow-band indices such as simple ratio (SR) and normalized difference vegetation index (NDVI). The results of the non-linear PLSR were compared to those of conventional linear PLSR. Using non-linear PLSR, integrating in situ hyperspectral and environmental variables yielded the highest grass N and P estimation accuracy (R2 = 0.81, root mean square error (RMSE) = 0.08, and R2 = 0.80, RMSE = 0.03, respectively) as compared to using remote sensing variables only, and conventional PLSR. The study demonstrates the importance of an integrated modeling approach for estimating grass quality which is a crucial effort towards effective management and planning of protected and communal savanna ecosystems.

KW - METIS-302230

KW - IR-90378

KW - ITC-ISI-JOURNAL-ARTICLE

UR - https://ezproxy2.utwente.nl/login?url=https://webapps.itc.utwente.nl/library/2013/isi/skidmore_non.pdf

U2 - 10.1016/j.isprsjprs.2013.04.012

DO - 10.1016/j.isprsjprs.2013.04.012

M3 - Article

VL - 82

SP - 27

EP - 40

JO - ISPRS journal of photogrammetry and remote sensing

JF - ISPRS journal of photogrammetry and remote sensing

SN - 0924-2716

ER -