Wetland Classification Using Multi-Source and Multi-Temporal Optical Remote Sensing Data in Newfoundland and Labrador, Canada
Newfoundland and Labrador (NL) is the only province in Atlantic Canada that does not have a wetland inventory system. As a consequence, both classifying and monitoring wetland areas are necessary for wetland conservation and human services in the province. In this study, wetlands in 5 pilot sites, d...
Published in: | Canadian Journal of Remote Sensing |
---|---|
Main Authors: | , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English French |
Published: |
Taylor & Francis Group
2017
|
Subjects: | |
Online Access: | https://doi.org/10.1080/07038992.2017.1346468 https://doaj.org/article/14f0eed13af7490f8fad9984420dd01c |
id |
ftdoajarticles:oai:doaj.org/article:14f0eed13af7490f8fad9984420dd01c |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:14f0eed13af7490f8fad9984420dd01c 2023-11-12T04:21:18+01:00 Wetland Classification Using Multi-Source and Multi-Temporal Optical Remote Sensing Data in Newfoundland and Labrador, Canada Meisam Amani Bahram Salehi Sahel Mahdavi Jean Elizabeth Granger Brian Brisco Alan Hanson 2017-07-01T00:00:00Z https://doi.org/10.1080/07038992.2017.1346468 https://doaj.org/article/14f0eed13af7490f8fad9984420dd01c EN FR eng fre Taylor & Francis Group http://dx.doi.org/10.1080/07038992.2017.1346468 https://doaj.org/toc/1712-7971 1712-7971 doi:10.1080/07038992.2017.1346468 https://doaj.org/article/14f0eed13af7490f8fad9984420dd01c Canadian Journal of Remote Sensing, Vol 43, Iss 4, Pp 360-373 (2017) Environmental sciences GE1-350 Technology T article 2017 ftdoajarticles https://doi.org/10.1080/07038992.2017.1346468 2023-10-15T00:36:32Z Newfoundland and Labrador (NL) is the only province in Atlantic Canada that does not have a wetland inventory system. As a consequence, both classifying and monitoring wetland areas are necessary for wetland conservation and human services in the province. In this study, wetlands in 5 pilot sites, distributed across NL, were classified using multi-source and multi-temporal optical remote sensing images. The procedures involved the application of an object-based method to segment and classify the images. To classify the areas, 5 different machine learning algorithms were examined. The results showed that the Random Forest (RF) algorithm in combination with an object-based approach was the most accurate method to classify wetlands. The average producer and user accuracies of wetland classes considering all pilot sites were 68% and 73%, respectively. The overall classification accuracies, which considered the accuracy of all wetland and non-wetland classes varied from 86% to 96% across all pilot sites confirming the robustness of the methodology despite the biological, ecological, and geographical differences among the study areas. Additionally, we assessed the effects of the tuning parameters on the accuracy of results, as well as the difference between pixel-based and object-based methods for wetland classification in this study. Article in Journal/Newspaper Newfoundland Directory of Open Access Journals: DOAJ Articles Canada Newfoundland Canadian Journal of Remote Sensing 43 4 360 373 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English French |
topic |
Environmental sciences GE1-350 Technology T |
spellingShingle |
Environmental sciences GE1-350 Technology T Meisam Amani Bahram Salehi Sahel Mahdavi Jean Elizabeth Granger Brian Brisco Alan Hanson Wetland Classification Using Multi-Source and Multi-Temporal Optical Remote Sensing Data in Newfoundland and Labrador, Canada |
topic_facet |
Environmental sciences GE1-350 Technology T |
description |
Newfoundland and Labrador (NL) is the only province in Atlantic Canada that does not have a wetland inventory system. As a consequence, both classifying and monitoring wetland areas are necessary for wetland conservation and human services in the province. In this study, wetlands in 5 pilot sites, distributed across NL, were classified using multi-source and multi-temporal optical remote sensing images. The procedures involved the application of an object-based method to segment and classify the images. To classify the areas, 5 different machine learning algorithms were examined. The results showed that the Random Forest (RF) algorithm in combination with an object-based approach was the most accurate method to classify wetlands. The average producer and user accuracies of wetland classes considering all pilot sites were 68% and 73%, respectively. The overall classification accuracies, which considered the accuracy of all wetland and non-wetland classes varied from 86% to 96% across all pilot sites confirming the robustness of the methodology despite the biological, ecological, and geographical differences among the study areas. Additionally, we assessed the effects of the tuning parameters on the accuracy of results, as well as the difference between pixel-based and object-based methods for wetland classification in this study. |
format |
Article in Journal/Newspaper |
author |
Meisam Amani Bahram Salehi Sahel Mahdavi Jean Elizabeth Granger Brian Brisco Alan Hanson |
author_facet |
Meisam Amani Bahram Salehi Sahel Mahdavi Jean Elizabeth Granger Brian Brisco Alan Hanson |
author_sort |
Meisam Amani |
title |
Wetland Classification Using Multi-Source and Multi-Temporal Optical Remote Sensing Data in Newfoundland and Labrador, Canada |
title_short |
Wetland Classification Using Multi-Source and Multi-Temporal Optical Remote Sensing Data in Newfoundland and Labrador, Canada |
title_full |
Wetland Classification Using Multi-Source and Multi-Temporal Optical Remote Sensing Data in Newfoundland and Labrador, Canada |
title_fullStr |
Wetland Classification Using Multi-Source and Multi-Temporal Optical Remote Sensing Data in Newfoundland and Labrador, Canada |
title_full_unstemmed |
Wetland Classification Using Multi-Source and Multi-Temporal Optical Remote Sensing Data in Newfoundland and Labrador, Canada |
title_sort |
wetland classification using multi-source and multi-temporal optical remote sensing data in newfoundland and labrador, canada |
publisher |
Taylor & Francis Group |
publishDate |
2017 |
url |
https://doi.org/10.1080/07038992.2017.1346468 https://doaj.org/article/14f0eed13af7490f8fad9984420dd01c |
geographic |
Canada Newfoundland |
geographic_facet |
Canada Newfoundland |
genre |
Newfoundland |
genre_facet |
Newfoundland |
op_source |
Canadian Journal of Remote Sensing, Vol 43, Iss 4, Pp 360-373 (2017) |
op_relation |
http://dx.doi.org/10.1080/07038992.2017.1346468 https://doaj.org/toc/1712-7971 1712-7971 doi:10.1080/07038992.2017.1346468 https://doaj.org/article/14f0eed13af7490f8fad9984420dd01c |
op_doi |
https://doi.org/10.1080/07038992.2017.1346468 |
container_title |
Canadian Journal of Remote Sensing |
container_volume |
43 |
container_issue |
4 |
container_start_page |
360 |
op_container_end_page |
373 |
_version_ |
1782336793230704640 |