UAV-based classification of maritime Antarctic vegetation types using GEOBIA and random forest
Development of vegetation communities in areas of Antarctica without permanent ice cover emphasizes the need for effective remote sensing techniques for proper monitoring of local environmental changes. Detection and mapping of vegetation by image classification remains limited in the Antarctic envi...
Published in: | Ecological Informatics |
---|---|
Main Authors: | , , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Elsevier
2022
|
Subjects: | |
Online Access: | http://hdl.handle.net/10451/54694 https://doi.org/10.1016/j.ecoinf.2022.101768 |
id |
ftunivlisboa:oai:repositorio.ul.pt:10451/54694 |
---|---|
record_format |
openpolar |
spelling |
ftunivlisboa:oai:repositorio.ul.pt:10451/54694 2023-05-15T13:59:03+02:00 UAV-based classification of maritime Antarctic vegetation types using GEOBIA and random forest Sotille, Maria E. Bremer, Ulisses F. Vieira, Gonçalo Velho, Luiz F. Petsch, Carina Auger, Jeffrey D. Simões, Jefferson C. 2022-10-04T11:41:32Z http://hdl.handle.net/10451/54694 https://doi.org/10.1016/j.ecoinf.2022.101768 eng eng Elsevier e Brazilian National Council for Scientific and Technological Development - CNPq [Grant 421743/2017-4] Process 465680/2014-3 – INCT Criosfera https://www.sciencedirect.com/science/article/pii/S1574954122002187?pes=vor Sotille, M. E., Bremer, U. F., Vieira, G., Velho, Luiz F., Petsch, C., Auger, J. D. Simões, J. C. (2022). UAV-based classification of maritime Antarctic vegetation types using GEOBIA and random forest. Ecological Informatics, 71, 101768, https://doi.org/10.1016/j.ecoinf.2022.101768 1574-9541 http://hdl.handle.net/10451/54694 doi:10.1016/j.ecoinf.2022.101768 closedAccess Vegetation mapping Antarctica UAV GEOBIA Image classification Remote sensing article 2022 ftunivlisboa https://doi.org/10.1016/j.ecoinf.2022.101768 2023-03-01T01:08:29Z Development of vegetation communities in areas of Antarctica without permanent ice cover emphasizes the need for effective remote sensing techniques for proper monitoring of local environmental changes. Detection and mapping of vegetation by image classification remains limited in the Antarctic environment due to the complexity of its surface cover, and the spatial heterogeneity and spectral homogeneity of cryptogamic vegetation. As ultra-high resolution aerial images allow a comprehensive analysis of vegetation, this study aims to identify different types of vegetation cover (i.e., algae, mosses, and lichens) in an ice-free area of Hope Bay, on the northern tip of the Antarctic Peninsula. Using the geographic object-based image analysis (GEOBIA) approach, remote sensing data sets are tested in the random forest classifier in order to distinguish vegetation classes within vegetated areas. Because species of algae, mosses, and lichens may have similar spectral characteristics, subclasses are established. The results show that when only the mean values of green, red, and NIR bands are considered, the subclasses have low separability. Variations in accuracy and visual changes are identified according to the set of features used in the classification. Accuracy improves when multilayer information is used. A combination of spectral and morphometric products and by-products provides the best result for the detection and delineation of different types of vegetation, with an overall accuracy of 0.966 and a Kappa coefficient of 0.946. The method allowed for the identification of units primarily composed of algae, mosses, and lichens as well as differences in communities. This study demonstrates that ultra-high spatial resolution data can provide the necessary properties for the classification of vegetation in Maritime Antarctica, even in images obtained by sensors with low spectral resolution info:eu-repo/semantics/publishedVersion Article in Journal/Newspaper Antarc* Antarctic Antarctic Peninsula Antarctica Universidade de Lisboa: repositório.UL Antarctic The Antarctic Antarctic Peninsula Hope Bay ENVELOPE(-57.038,-57.038,-63.403,-63.403) Ecological Informatics 71 101768 |
institution |
Open Polar |
collection |
Universidade de Lisboa: repositório.UL |
op_collection_id |
ftunivlisboa |
language |
English |
topic |
Vegetation mapping Antarctica UAV GEOBIA Image classification Remote sensing |
spellingShingle |
Vegetation mapping Antarctica UAV GEOBIA Image classification Remote sensing Sotille, Maria E. Bremer, Ulisses F. Vieira, Gonçalo Velho, Luiz F. Petsch, Carina Auger, Jeffrey D. Simões, Jefferson C. UAV-based classification of maritime Antarctic vegetation types using GEOBIA and random forest |
topic_facet |
Vegetation mapping Antarctica UAV GEOBIA Image classification Remote sensing |
description |
Development of vegetation communities in areas of Antarctica without permanent ice cover emphasizes the need for effective remote sensing techniques for proper monitoring of local environmental changes. Detection and mapping of vegetation by image classification remains limited in the Antarctic environment due to the complexity of its surface cover, and the spatial heterogeneity and spectral homogeneity of cryptogamic vegetation. As ultra-high resolution aerial images allow a comprehensive analysis of vegetation, this study aims to identify different types of vegetation cover (i.e., algae, mosses, and lichens) in an ice-free area of Hope Bay, on the northern tip of the Antarctic Peninsula. Using the geographic object-based image analysis (GEOBIA) approach, remote sensing data sets are tested in the random forest classifier in order to distinguish vegetation classes within vegetated areas. Because species of algae, mosses, and lichens may have similar spectral characteristics, subclasses are established. The results show that when only the mean values of green, red, and NIR bands are considered, the subclasses have low separability. Variations in accuracy and visual changes are identified according to the set of features used in the classification. Accuracy improves when multilayer information is used. A combination of spectral and morphometric products and by-products provides the best result for the detection and delineation of different types of vegetation, with an overall accuracy of 0.966 and a Kappa coefficient of 0.946. The method allowed for the identification of units primarily composed of algae, mosses, and lichens as well as differences in communities. This study demonstrates that ultra-high spatial resolution data can provide the necessary properties for the classification of vegetation in Maritime Antarctica, even in images obtained by sensors with low spectral resolution info:eu-repo/semantics/publishedVersion |
format |
Article in Journal/Newspaper |
author |
Sotille, Maria E. Bremer, Ulisses F. Vieira, Gonçalo Velho, Luiz F. Petsch, Carina Auger, Jeffrey D. Simões, Jefferson C. |
author_facet |
Sotille, Maria E. Bremer, Ulisses F. Vieira, Gonçalo Velho, Luiz F. Petsch, Carina Auger, Jeffrey D. Simões, Jefferson C. |
author_sort |
Sotille, Maria E. |
title |
UAV-based classification of maritime Antarctic vegetation types using GEOBIA and random forest |
title_short |
UAV-based classification of maritime Antarctic vegetation types using GEOBIA and random forest |
title_full |
UAV-based classification of maritime Antarctic vegetation types using GEOBIA and random forest |
title_fullStr |
UAV-based classification of maritime Antarctic vegetation types using GEOBIA and random forest |
title_full_unstemmed |
UAV-based classification of maritime Antarctic vegetation types using GEOBIA and random forest |
title_sort |
uav-based classification of maritime antarctic vegetation types using geobia and random forest |
publisher |
Elsevier |
publishDate |
2022 |
url |
http://hdl.handle.net/10451/54694 https://doi.org/10.1016/j.ecoinf.2022.101768 |
long_lat |
ENVELOPE(-57.038,-57.038,-63.403,-63.403) |
geographic |
Antarctic The Antarctic Antarctic Peninsula Hope Bay |
geographic_facet |
Antarctic The Antarctic Antarctic Peninsula Hope Bay |
genre |
Antarc* Antarctic Antarctic Peninsula Antarctica |
genre_facet |
Antarc* Antarctic Antarctic Peninsula Antarctica |
op_relation |
e Brazilian National Council for Scientific and Technological Development - CNPq [Grant 421743/2017-4] Process 465680/2014-3 – INCT Criosfera https://www.sciencedirect.com/science/article/pii/S1574954122002187?pes=vor Sotille, M. E., Bremer, U. F., Vieira, G., Velho, Luiz F., Petsch, C., Auger, J. D. Simões, J. C. (2022). UAV-based classification of maritime Antarctic vegetation types using GEOBIA and random forest. Ecological Informatics, 71, 101768, https://doi.org/10.1016/j.ecoinf.2022.101768 1574-9541 http://hdl.handle.net/10451/54694 doi:10.1016/j.ecoinf.2022.101768 |
op_rights |
closedAccess |
op_doi |
https://doi.org/10.1016/j.ecoinf.2022.101768 |
container_title |
Ecological Informatics |
container_volume |
71 |
container_start_page |
101768 |
_version_ |
1766267421647175680 |