A COMPARISON OF TREE-BASED ALGORITHMS FOR COMPLEX WETLAND CLASSIFICATION USING THE GOOGLE EARTH ENGINE
Wetlands are endangered ecosystems that are required to be systematically monitored. Wetlands have significant contributions to the well-being of human-being, fauna, and fungi. They provide vital services, including water storage, carbon sequestration, food security, and protecting the shorelines fr...
Published in: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
---|---|
Main Authors: | , , |
Format: | Text |
Language: | English |
Published: |
2021
|
Subjects: | |
Online Access: | https://doi.org/10.5194/isprs-archives-XLVI-4-W5-2021-313-2021 https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLVI-4-W5-2021/313/2021/ |
id |
ftcopernicus:oai:publications.copernicus.org:isprs-archives100435 |
---|---|
record_format |
openpolar |
spelling |
ftcopernicus:oai:publications.copernicus.org:isprs-archives100435 2023-05-15T17:22:21+02:00 A COMPARISON OF TREE-BASED ALGORITHMS FOR COMPLEX WETLAND CLASSIFICATION USING THE GOOGLE EARTH ENGINE Jamali, A. Mahdianpari, M. Karaş, İ. R. 2021-12-23 application/pdf https://doi.org/10.5194/isprs-archives-XLVI-4-W5-2021-313-2021 https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLVI-4-W5-2021/313/2021/ eng eng doi:10.5194/isprs-archives-XLVI-4-W5-2021-313-2021 https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLVI-4-W5-2021/313/2021/ eISSN: 2194-9034 Text 2021 ftcopernicus https://doi.org/10.5194/isprs-archives-XLVI-4-W5-2021-313-2021 2021-12-27T17:22:18Z Wetlands are endangered ecosystems that are required to be systematically monitored. Wetlands have significant contributions to the well-being of human-being, fauna, and fungi. They provide vital services, including water storage, carbon sequestration, food security, and protecting the shorelines from floods. Remote sensing is preferred over the other conventional earth observation methods such as field surveying. It provides the necessary tools for the systematic and standardized method of large-scale wetland mapping. On the other hand, new cloud computing technologies for the storage and processing of large-scale remote sensing big data such as the Google Earth Engine (GEE) have emerged. As such, for the complex wetland classification in the pilot site of the Avalon, Newfoundland, Canada, we compare the results of three tree-based classifiers of the Decision Tree (DT), Random Forest (RF), and Extreme Gradient Boosting (XGB) available in the GEE code editor using Sentinel-2 images. Based on the results, the XGB classifier with an overall accuracy of 82.58% outperformed the RF (82.52%) and DT (77.62%) classifiers. Text Newfoundland Copernicus Publications: E-Journals Canada The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLVI-4/W5-2021 313 319 |
institution |
Open Polar |
collection |
Copernicus Publications: E-Journals |
op_collection_id |
ftcopernicus |
language |
English |
description |
Wetlands are endangered ecosystems that are required to be systematically monitored. Wetlands have significant contributions to the well-being of human-being, fauna, and fungi. They provide vital services, including water storage, carbon sequestration, food security, and protecting the shorelines from floods. Remote sensing is preferred over the other conventional earth observation methods such as field surveying. It provides the necessary tools for the systematic and standardized method of large-scale wetland mapping. On the other hand, new cloud computing technologies for the storage and processing of large-scale remote sensing big data such as the Google Earth Engine (GEE) have emerged. As such, for the complex wetland classification in the pilot site of the Avalon, Newfoundland, Canada, we compare the results of three tree-based classifiers of the Decision Tree (DT), Random Forest (RF), and Extreme Gradient Boosting (XGB) available in the GEE code editor using Sentinel-2 images. Based on the results, the XGB classifier with an overall accuracy of 82.58% outperformed the RF (82.52%) and DT (77.62%) classifiers. |
format |
Text |
author |
Jamali, A. Mahdianpari, M. Karaş, İ. R. |
spellingShingle |
Jamali, A. Mahdianpari, M. Karaş, İ. R. A COMPARISON OF TREE-BASED ALGORITHMS FOR COMPLEX WETLAND CLASSIFICATION USING THE GOOGLE EARTH ENGINE |
author_facet |
Jamali, A. Mahdianpari, M. Karaş, İ. R. |
author_sort |
Jamali, A. |
title |
A COMPARISON OF TREE-BASED ALGORITHMS FOR COMPLEX WETLAND CLASSIFICATION USING THE GOOGLE EARTH ENGINE |
title_short |
A COMPARISON OF TREE-BASED ALGORITHMS FOR COMPLEX WETLAND CLASSIFICATION USING THE GOOGLE EARTH ENGINE |
title_full |
A COMPARISON OF TREE-BASED ALGORITHMS FOR COMPLEX WETLAND CLASSIFICATION USING THE GOOGLE EARTH ENGINE |
title_fullStr |
A COMPARISON OF TREE-BASED ALGORITHMS FOR COMPLEX WETLAND CLASSIFICATION USING THE GOOGLE EARTH ENGINE |
title_full_unstemmed |
A COMPARISON OF TREE-BASED ALGORITHMS FOR COMPLEX WETLAND CLASSIFICATION USING THE GOOGLE EARTH ENGINE |
title_sort |
comparison of tree-based algorithms for complex wetland classification using the google earth engine |
publishDate |
2021 |
url |
https://doi.org/10.5194/isprs-archives-XLVI-4-W5-2021-313-2021 https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLVI-4-W5-2021/313/2021/ |
geographic |
Canada |
geographic_facet |
Canada |
genre |
Newfoundland |
genre_facet |
Newfoundland |
op_source |
eISSN: 2194-9034 |
op_relation |
doi:10.5194/isprs-archives-XLVI-4-W5-2021-313-2021 https://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLVI-4-W5-2021/313/2021/ |
op_doi |
https://doi.org/10.5194/isprs-archives-XLVI-4-W5-2021-313-2021 |
container_title |
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
container_volume |
XLVI-4/W5-2021 |
container_start_page |
313 |
op_container_end_page |
319 |
_version_ |
1766108938979246080 |