Mapping sub-Antarctic cushion plants using random forests to combine very high resolution satellite imagery and terrain modelling
Monitoring changes in the distribution and density of plant species often requires accurate and high-resolution baseline maps of those species. Detecting such change at the landscape scale is often problematic, particularly in remote areas. We examine a new technique to improve accuracy and objectiv...
Published in: | PLoS ONE |
---|---|
Main Authors: | , , , , |
Other Authors: | |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Public Library of Science
2013
|
Subjects: | |
Online Access: | https://espace.library.uq.edu.au/view/UQ:313028 |
id |
ftunivqespace:oai:espace.library.uq.edu.au:UQ:313028 |
---|---|
record_format |
openpolar |
spelling |
ftunivqespace:oai:espace.library.uq.edu.au:UQ:313028 2023-05-15T13:49:28+02:00 Mapping sub-Antarctic cushion plants using random forests to combine very high resolution satellite imagery and terrain modelling Bricher, Phillippa K. Lucieer, Arko Shaw, Justine Terauds, Aleks Bergstrom, Dana M. Lamb, Eric Gordon 2013-08-01 https://espace.library.uq.edu.au/view/UQ:313028 eng eng Public Library of Science doi:10.1371/journal.pone.0072093 issn:1932-6203 orcid:0000-0002-9603-2271 ASAC 3095 Not set General Biochemistry Genetics and Molecular Biology General Agricultural and Biological Sciences General Medicine 1100 Agricultural and Biological Sciences 1300 Biochemistry 2700 Medicine Journal Article 2013 ftunivqespace https://doi.org/10.1371/journal.pone.0072093 2020-12-15T00:33:21Z Monitoring changes in the distribution and density of plant species often requires accurate and high-resolution baseline maps of those species. Detecting such change at the landscape scale is often problematic, particularly in remote areas. We examine a new technique to improve accuracy and objectivity in mapping vegetation, combining species distribution modelling and satellite image classification on a remote sub-Antarctic island. In this study, we combine spectral data from very high resolution WorldView-2 satellite imagery and terrain variables from a high resolution digital elevation model to improve mapping accuracy, in both pixel- and object-based classifications. Random forest classification was used to explore the effectiveness of these approaches on mapping the distribution of the critically endangered cushion plant Azorella macquariensis Orchard (Apiaceae) on sub-Antarctic Macquarie Island. Both pixel- and object-based classifications of the distribution of Azorella achieved very high overall validation accuracies (91.6-96.3%, κ = 0.849-0.924). Both two-class and three-class classifications were able to accurately and consistently identify the areas where Azorella was absent, indicating that these maps provide a suitable baseline for monitoring expected change in the distribution of the cushion plants. Detecting such change is critical given the threats this species is currently facing under altering environmental conditions. The method presented here has applications to monitoring a range of species, particularly in remote and isolated environments. Article in Journal/Newspaper Antarc* Antarctic Macquarie Island The University of Queensland: UQ eSpace Antarctic PLoS ONE 8 8 e72093 |
institution |
Open Polar |
collection |
The University of Queensland: UQ eSpace |
op_collection_id |
ftunivqespace |
language |
English |
topic |
General Biochemistry Genetics and Molecular Biology General Agricultural and Biological Sciences General Medicine 1100 Agricultural and Biological Sciences 1300 Biochemistry 2700 Medicine |
spellingShingle |
General Biochemistry Genetics and Molecular Biology General Agricultural and Biological Sciences General Medicine 1100 Agricultural and Biological Sciences 1300 Biochemistry 2700 Medicine Bricher, Phillippa K. Lucieer, Arko Shaw, Justine Terauds, Aleks Bergstrom, Dana M. Mapping sub-Antarctic cushion plants using random forests to combine very high resolution satellite imagery and terrain modelling |
topic_facet |
General Biochemistry Genetics and Molecular Biology General Agricultural and Biological Sciences General Medicine 1100 Agricultural and Biological Sciences 1300 Biochemistry 2700 Medicine |
description |
Monitoring changes in the distribution and density of plant species often requires accurate and high-resolution baseline maps of those species. Detecting such change at the landscape scale is often problematic, particularly in remote areas. We examine a new technique to improve accuracy and objectivity in mapping vegetation, combining species distribution modelling and satellite image classification on a remote sub-Antarctic island. In this study, we combine spectral data from very high resolution WorldView-2 satellite imagery and terrain variables from a high resolution digital elevation model to improve mapping accuracy, in both pixel- and object-based classifications. Random forest classification was used to explore the effectiveness of these approaches on mapping the distribution of the critically endangered cushion plant Azorella macquariensis Orchard (Apiaceae) on sub-Antarctic Macquarie Island. Both pixel- and object-based classifications of the distribution of Azorella achieved very high overall validation accuracies (91.6-96.3%, κ = 0.849-0.924). Both two-class and three-class classifications were able to accurately and consistently identify the areas where Azorella was absent, indicating that these maps provide a suitable baseline for monitoring expected change in the distribution of the cushion plants. Detecting such change is critical given the threats this species is currently facing under altering environmental conditions. The method presented here has applications to monitoring a range of species, particularly in remote and isolated environments. |
author2 |
Lamb, Eric Gordon |
format |
Article in Journal/Newspaper |
author |
Bricher, Phillippa K. Lucieer, Arko Shaw, Justine Terauds, Aleks Bergstrom, Dana M. |
author_facet |
Bricher, Phillippa K. Lucieer, Arko Shaw, Justine Terauds, Aleks Bergstrom, Dana M. |
author_sort |
Bricher, Phillippa K. |
title |
Mapping sub-Antarctic cushion plants using random forests to combine very high resolution satellite imagery and terrain modelling |
title_short |
Mapping sub-Antarctic cushion plants using random forests to combine very high resolution satellite imagery and terrain modelling |
title_full |
Mapping sub-Antarctic cushion plants using random forests to combine very high resolution satellite imagery and terrain modelling |
title_fullStr |
Mapping sub-Antarctic cushion plants using random forests to combine very high resolution satellite imagery and terrain modelling |
title_full_unstemmed |
Mapping sub-Antarctic cushion plants using random forests to combine very high resolution satellite imagery and terrain modelling |
title_sort |
mapping sub-antarctic cushion plants using random forests to combine very high resolution satellite imagery and terrain modelling |
publisher |
Public Library of Science |
publishDate |
2013 |
url |
https://espace.library.uq.edu.au/view/UQ:313028 |
geographic |
Antarctic |
geographic_facet |
Antarctic |
genre |
Antarc* Antarctic Macquarie Island |
genre_facet |
Antarc* Antarctic Macquarie Island |
op_relation |
doi:10.1371/journal.pone.0072093 issn:1932-6203 orcid:0000-0002-9603-2271 ASAC 3095 Not set |
op_doi |
https://doi.org/10.1371/journal.pone.0072093 |
container_title |
PLoS ONE |
container_volume |
8 |
container_issue |
8 |
container_start_page |
e72093 |
_version_ |
1766251418062159872 |