Habitat mapping and quality assessment of NATURA 2000 heathland using airborne imaging spectroscopy

Birgen Haest*, Jeroen Vanden Borre, Toon Spanhove, Guy Thoonen, Stephanie Delalieux, Lammert Kooistra, Sander Mücher, Desiré Paelinckx, Paul Scheunders, Pieter Kempeneers

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

10 Citations (Scopus)

Abstract

Appropriate management of (semi-)natural areas requires detailed knowledge of the ecosystems present and their status. Remote sensing can provide a systematic, synoptic view at regular time intervals, and is therefore often suggested as a powerful tool to assist with the mapping and monitoring of protected habitats and vegetation. In this study, we present a multi-step mapping framework that enables detailed NATURA 2000 (N2000) heathland habitat patch mapping and the assessment of their conservation status at patch level. The method comprises three consecutive steps: (1) a hierarchical land/vegetation type (LVT) classification using airborne AHS imaging spectroscopy and field reference data; (2) a spatial re-classification to convert the LVT map to a patch map based on life forms; and (3) identification of the N2000 habitat type and conservation status parameters for each of the patches. Based on a multivariate analysis of 1325 vegetation reference plots acquired in 2006-2007, 24 LVT classes were identified that were considered relevant for the assessment of heathland conservation status. These labelled data were then used as ground reference for the supervised classification of the AHS image data to an LVT classification map, using Linear Discriminant Analysis in combination with Sequential-Floating-Forward-Search feature selection. Overall classification accuracies for the LVT mapping varied from 83% to 92% (Kappa ≈ 0.82-0.91), depending on the level of detail in the hierarchical classification. After converting the LVT map to a N2000 habitat type patch map, an overall accuracy of 89% was obtained. By combining the N2000 habitat type patch map with the LVT map, two important conservation status parameters were directly deduced per patch: tree and shrub cover, and grass cover, showing a strong similarity to an independent dataset with estimates made in the field in 2009. The results of this study indicate the potential of imaging spectroscopy for detailed heathland habitat characterization of N2000 sites in a way that matches the current field-based workflows of the user.

Original languageEnglish
Article number266
Number of pages25
JournalRemote Sensing
Volume9
Issue number3
DOIs
Publication statusPublished - 2017

Fingerprint

heathland
vegetation type
spectroscopy
conservation status
habitat
habitat type
habitat conservation
vegetation
image classification
land
discriminant analysis
multivariate analysis
shrub
grass
remote sensing
ecosystem
monitoring

Keywords

  • Calluna vulgaris
  • Classification
  • Conservation status
  • Grass encroachment
  • Habitat mapping
  • Heathland
  • Hyperspectral
  • NATURA 2000
  • Species mapping
  • Tree encroachment

Cite this

Haest, B., Borre, J. V., Spanhove, T., Thoonen, G., Delalieux, S., Kooistra, L., ... Kempeneers, P. (2017). Habitat mapping and quality assessment of NATURA 2000 heathland using airborne imaging spectroscopy. Remote Sensing, 9(3), [266]. https://doi.org/10.3390/rs9030266
Haest, Birgen ; Borre, Jeroen Vanden ; Spanhove, Toon ; Thoonen, Guy ; Delalieux, Stephanie ; Kooistra, Lammert ; Mücher, Sander ; Paelinckx, Desiré ; Scheunders, Paul ; Kempeneers, Pieter. / Habitat mapping and quality assessment of NATURA 2000 heathland using airborne imaging spectroscopy. In: Remote Sensing. 2017 ; Vol. 9, No. 3.
@article{7ef37c1b41dd4ec0a977675f7d22650e,
title = "Habitat mapping and quality assessment of NATURA 2000 heathland using airborne imaging spectroscopy",
abstract = "Appropriate management of (semi-)natural areas requires detailed knowledge of the ecosystems present and their status. Remote sensing can provide a systematic, synoptic view at regular time intervals, and is therefore often suggested as a powerful tool to assist with the mapping and monitoring of protected habitats and vegetation. In this study, we present a multi-step mapping framework that enables detailed NATURA 2000 (N2000) heathland habitat patch mapping and the assessment of their conservation status at patch level. The method comprises three consecutive steps: (1) a hierarchical land/vegetation type (LVT) classification using airborne AHS imaging spectroscopy and field reference data; (2) a spatial re-classification to convert the LVT map to a patch map based on life forms; and (3) identification of the N2000 habitat type and conservation status parameters for each of the patches. Based on a multivariate analysis of 1325 vegetation reference plots acquired in 2006-2007, 24 LVT classes were identified that were considered relevant for the assessment of heathland conservation status. These labelled data were then used as ground reference for the supervised classification of the AHS image data to an LVT classification map, using Linear Discriminant Analysis in combination with Sequential-Floating-Forward-Search feature selection. Overall classification accuracies for the LVT mapping varied from 83{\%} to 92{\%} (Kappa ≈ 0.82-0.91), depending on the level of detail in the hierarchical classification. After converting the LVT map to a N2000 habitat type patch map, an overall accuracy of 89{\%} was obtained. By combining the N2000 habitat type patch map with the LVT map, two important conservation status parameters were directly deduced per patch: tree and shrub cover, and grass cover, showing a strong similarity to an independent dataset with estimates made in the field in 2009. The results of this study indicate the potential of imaging spectroscopy for detailed heathland habitat characterization of N2000 sites in a way that matches the current field-based workflows of the user.",
keywords = "Calluna vulgaris, Classification, Conservation status, Grass encroachment, Habitat mapping, Heathland, Hyperspectral, NATURA 2000, Species mapping, Tree encroachment",
author = "Birgen Haest and Borre, {Jeroen Vanden} and Toon Spanhove and Guy Thoonen and Stephanie Delalieux and Lammert Kooistra and Sander M{\"u}cher and Desir{\'e} Paelinckx and Paul Scheunders and Pieter Kempeneers",
year = "2017",
doi = "10.3390/rs9030266",
language = "English",
volume = "9",
journal = "Remote Sensing",
issn = "2072-4292",
publisher = "MDPI",
number = "3",

}

Haest, B, Borre, JV, Spanhove, T, Thoonen, G, Delalieux, S, Kooistra, L, Mücher, S, Paelinckx, D, Scheunders, P & Kempeneers, P 2017, 'Habitat mapping and quality assessment of NATURA 2000 heathland using airborne imaging spectroscopy', Remote Sensing, vol. 9, no. 3, 266. https://doi.org/10.3390/rs9030266

Habitat mapping and quality assessment of NATURA 2000 heathland using airborne imaging spectroscopy. / Haest, Birgen; Borre, Jeroen Vanden; Spanhove, Toon; Thoonen, Guy; Delalieux, Stephanie; Kooistra, Lammert; Mücher, Sander; Paelinckx, Desiré; Scheunders, Paul; Kempeneers, Pieter.

In: Remote Sensing, Vol. 9, No. 3, 266, 2017.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Habitat mapping and quality assessment of NATURA 2000 heathland using airborne imaging spectroscopy

AU - Haest, Birgen

AU - Borre, Jeroen Vanden

AU - Spanhove, Toon

AU - Thoonen, Guy

AU - Delalieux, Stephanie

AU - Kooistra, Lammert

AU - Mücher, Sander

AU - Paelinckx, Desiré

AU - Scheunders, Paul

AU - Kempeneers, Pieter

PY - 2017

Y1 - 2017

N2 - Appropriate management of (semi-)natural areas requires detailed knowledge of the ecosystems present and their status. Remote sensing can provide a systematic, synoptic view at regular time intervals, and is therefore often suggested as a powerful tool to assist with the mapping and monitoring of protected habitats and vegetation. In this study, we present a multi-step mapping framework that enables detailed NATURA 2000 (N2000) heathland habitat patch mapping and the assessment of their conservation status at patch level. The method comprises three consecutive steps: (1) a hierarchical land/vegetation type (LVT) classification using airborne AHS imaging spectroscopy and field reference data; (2) a spatial re-classification to convert the LVT map to a patch map based on life forms; and (3) identification of the N2000 habitat type and conservation status parameters for each of the patches. Based on a multivariate analysis of 1325 vegetation reference plots acquired in 2006-2007, 24 LVT classes were identified that were considered relevant for the assessment of heathland conservation status. These labelled data were then used as ground reference for the supervised classification of the AHS image data to an LVT classification map, using Linear Discriminant Analysis in combination with Sequential-Floating-Forward-Search feature selection. Overall classification accuracies for the LVT mapping varied from 83% to 92% (Kappa ≈ 0.82-0.91), depending on the level of detail in the hierarchical classification. After converting the LVT map to a N2000 habitat type patch map, an overall accuracy of 89% was obtained. By combining the N2000 habitat type patch map with the LVT map, two important conservation status parameters were directly deduced per patch: tree and shrub cover, and grass cover, showing a strong similarity to an independent dataset with estimates made in the field in 2009. The results of this study indicate the potential of imaging spectroscopy for detailed heathland habitat characterization of N2000 sites in a way that matches the current field-based workflows of the user.

AB - Appropriate management of (semi-)natural areas requires detailed knowledge of the ecosystems present and their status. Remote sensing can provide a systematic, synoptic view at regular time intervals, and is therefore often suggested as a powerful tool to assist with the mapping and monitoring of protected habitats and vegetation. In this study, we present a multi-step mapping framework that enables detailed NATURA 2000 (N2000) heathland habitat patch mapping and the assessment of their conservation status at patch level. The method comprises three consecutive steps: (1) a hierarchical land/vegetation type (LVT) classification using airborne AHS imaging spectroscopy and field reference data; (2) a spatial re-classification to convert the LVT map to a patch map based on life forms; and (3) identification of the N2000 habitat type and conservation status parameters for each of the patches. Based on a multivariate analysis of 1325 vegetation reference plots acquired in 2006-2007, 24 LVT classes were identified that were considered relevant for the assessment of heathland conservation status. These labelled data were then used as ground reference for the supervised classification of the AHS image data to an LVT classification map, using Linear Discriminant Analysis in combination with Sequential-Floating-Forward-Search feature selection. Overall classification accuracies for the LVT mapping varied from 83% to 92% (Kappa ≈ 0.82-0.91), depending on the level of detail in the hierarchical classification. After converting the LVT map to a N2000 habitat type patch map, an overall accuracy of 89% was obtained. By combining the N2000 habitat type patch map with the LVT map, two important conservation status parameters were directly deduced per patch: tree and shrub cover, and grass cover, showing a strong similarity to an independent dataset with estimates made in the field in 2009. The results of this study indicate the potential of imaging spectroscopy for detailed heathland habitat characterization of N2000 sites in a way that matches the current field-based workflows of the user.

KW - Calluna vulgaris

KW - Classification

KW - Conservation status

KW - Grass encroachment

KW - Habitat mapping

KW - Heathland

KW - Hyperspectral

KW - NATURA 2000

KW - Species mapping

KW - Tree encroachment

U2 - 10.3390/rs9030266

DO - 10.3390/rs9030266

M3 - Article

VL - 9

JO - Remote Sensing

JF - Remote Sensing

SN - 2072-4292

IS - 3

M1 - 266

ER -