A generalized supervised classification scheme to produce provincial wetland inventory maps: an application of Google Earth Engine for big geo data processing
Wetlands are important natural resources due to their numerous ecological services. Consequently, identifying their locations and extents is imperative. The stability, repeatability, cost-effectiveness, multi-scale coverage, and proper spatial resolution imagery of satellites provide a valuable oppo...
Published in: | Big Earth Data |
---|---|
Main Authors: | , , , , , , , |
Other Authors: | |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2019
|
Subjects: | |
Online Access: | http://hdl.handle.net/2117/344952 https://doi.org/10.1080/20964471.2019.1690404 |
id |
ftupcatalunyair:oai:upcommons.upc.edu:2117/344952 |
---|---|
record_format |
openpolar |
spelling |
ftupcatalunyair:oai:upcommons.upc.edu:2117/344952 2024-09-15T18:20:14+00:00 A generalized supervised classification scheme to produce provincial wetland inventory maps: an application of Google Earth Engine for big geo data processing Amani, Meisam Brisco, Brian Afshar, Majid Mirmazloumi, Seyed Mohammad Mahdavi, Sahel Mirzadeh, Sayyed Mohammad Javad Huang, Weimin Granger, Jean Universitat Politècnica de Catalunya. Doctorat en Ciència i Tecnologia Aeroespacials 2019-10-02 17 p. application/pdf http://hdl.handle.net/2117/344952 https://doi.org/10.1080/20964471.2019.1690404 eng eng https://www.tandfonline.com/doi/full/10.1080/20964471.2019.1690404 Amani, M. [et al.]. A generalized supervised classification scheme to produce provincial wetland inventory maps: an application of Google Earth Engine for big geo data processing. "Big Earth Data", 2 Octubre 2019, vol. 3, núm. 4, p. 378-394. 2096-4471 http://hdl.handle.net/2117/344952 doi:10.1080/20964471.2019.1690404 Attribution-NonCommercial-NoDerivs 3.0 Spain http://creativecommons.org/licenses/by-nc-nd/3.0/es/ Open Access Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Telemàtica i xarxes d'ordinadors::Trànsit de dades Google Earth Wetlands Remote sensing Google Earth Engine Big geo data Image classification Zones humides Article 2019 ftupcatalunyair https://doi.org/10.1080/20964471.2019.1690404 2024-07-25T11:00:39Z Wetlands are important natural resources due to their numerous ecological services. Consequently, identifying their locations and extents is imperative. The stability, repeatability, cost-effectiveness, multi-scale coverage, and proper spatial resolution imagery of satellites provide a valuable opportunity for their use in various large-scale applications, such as provincial wetland mapping. To do so, it is required to (1) process and classify big geo data (i.e. a large amount of satellite datasets) in a time- and computationally-efficient approach and (2) collect a large amount of field samples. In this study, Google Earth Engine (GEE) and machine learning algorithms were utilized to process thousands of remote sensing images and produce provincial wetland inventory maps of the three Canadian provinces of Manitoba, Quebec, and Newfoundland and Labrador (NL). Additionally, using GEE, a generalized supervised classification method is proposed to produce a regional wetland map from a large area (e.g., a province) when lacking field samples. In fact, using the field data from only Manitoba and assuming that all wetlands in Canada have similar characteristics, the wetland maps were generated for the other two provinces. The overall classification accuracies for Manitoba, Quebec, and NL were 84%, 78%, and 82%, respectively, indicating the high potential of the proposed method for aiding provincial wetland inventory systems. Postprint (published version) Article in Journal/Newspaper Newfoundland Universitat Politècnica de Catalunya, BarcelonaTech: UPCommons - Global access to UPC knowledge Big Earth Data 3 4 378 394 |
institution |
Open Polar |
collection |
Universitat Politècnica de Catalunya, BarcelonaTech: UPCommons - Global access to UPC knowledge |
op_collection_id |
ftupcatalunyair |
language |
English |
topic |
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Telemàtica i xarxes d'ordinadors::Trànsit de dades Google Earth Wetlands Remote sensing Google Earth Engine Big geo data Image classification Zones humides |
spellingShingle |
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Telemàtica i xarxes d'ordinadors::Trànsit de dades Google Earth Wetlands Remote sensing Google Earth Engine Big geo data Image classification Zones humides Amani, Meisam Brisco, Brian Afshar, Majid Mirmazloumi, Seyed Mohammad Mahdavi, Sahel Mirzadeh, Sayyed Mohammad Javad Huang, Weimin Granger, Jean A generalized supervised classification scheme to produce provincial wetland inventory maps: an application of Google Earth Engine for big geo data processing |
topic_facet |
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Telemàtica i xarxes d'ordinadors::Trànsit de dades Google Earth Wetlands Remote sensing Google Earth Engine Big geo data Image classification Zones humides |
description |
Wetlands are important natural resources due to their numerous ecological services. Consequently, identifying their locations and extents is imperative. The stability, repeatability, cost-effectiveness, multi-scale coverage, and proper spatial resolution imagery of satellites provide a valuable opportunity for their use in various large-scale applications, such as provincial wetland mapping. To do so, it is required to (1) process and classify big geo data (i.e. a large amount of satellite datasets) in a time- and computationally-efficient approach and (2) collect a large amount of field samples. In this study, Google Earth Engine (GEE) and machine learning algorithms were utilized to process thousands of remote sensing images and produce provincial wetland inventory maps of the three Canadian provinces of Manitoba, Quebec, and Newfoundland and Labrador (NL). Additionally, using GEE, a generalized supervised classification method is proposed to produce a regional wetland map from a large area (e.g., a province) when lacking field samples. In fact, using the field data from only Manitoba and assuming that all wetlands in Canada have similar characteristics, the wetland maps were generated for the other two provinces. The overall classification accuracies for Manitoba, Quebec, and NL were 84%, 78%, and 82%, respectively, indicating the high potential of the proposed method for aiding provincial wetland inventory systems. Postprint (published version) |
author2 |
Universitat Politècnica de Catalunya. Doctorat en Ciència i Tecnologia Aeroespacials |
format |
Article in Journal/Newspaper |
author |
Amani, Meisam Brisco, Brian Afshar, Majid Mirmazloumi, Seyed Mohammad Mahdavi, Sahel Mirzadeh, Sayyed Mohammad Javad Huang, Weimin Granger, Jean |
author_facet |
Amani, Meisam Brisco, Brian Afshar, Majid Mirmazloumi, Seyed Mohammad Mahdavi, Sahel Mirzadeh, Sayyed Mohammad Javad Huang, Weimin Granger, Jean |
author_sort |
Amani, Meisam |
title |
A generalized supervised classification scheme to produce provincial wetland inventory maps: an application of Google Earth Engine for big geo data processing |
title_short |
A generalized supervised classification scheme to produce provincial wetland inventory maps: an application of Google Earth Engine for big geo data processing |
title_full |
A generalized supervised classification scheme to produce provincial wetland inventory maps: an application of Google Earth Engine for big geo data processing |
title_fullStr |
A generalized supervised classification scheme to produce provincial wetland inventory maps: an application of Google Earth Engine for big geo data processing |
title_full_unstemmed |
A generalized supervised classification scheme to produce provincial wetland inventory maps: an application of Google Earth Engine for big geo data processing |
title_sort |
generalized supervised classification scheme to produce provincial wetland inventory maps: an application of google earth engine for big geo data processing |
publishDate |
2019 |
url |
http://hdl.handle.net/2117/344952 https://doi.org/10.1080/20964471.2019.1690404 |
genre |
Newfoundland |
genre_facet |
Newfoundland |
op_relation |
https://www.tandfonline.com/doi/full/10.1080/20964471.2019.1690404 Amani, M. [et al.]. A generalized supervised classification scheme to produce provincial wetland inventory maps: an application of Google Earth Engine for big geo data processing. "Big Earth Data", 2 Octubre 2019, vol. 3, núm. 4, p. 378-394. 2096-4471 http://hdl.handle.net/2117/344952 doi:10.1080/20964471.2019.1690404 |
op_rights |
Attribution-NonCommercial-NoDerivs 3.0 Spain http://creativecommons.org/licenses/by-nc-nd/3.0/es/ Open Access |
op_doi |
https://doi.org/10.1080/20964471.2019.1690404 |
container_title |
Big Earth Data |
container_volume |
3 |
container_issue |
4 |
container_start_page |
378 |
op_container_end_page |
394 |
_version_ |
1810458599540916224 |