Evaluation of the Landsat-Based Canadian Wetland Inventory Map Using Multiple Sources: Challenges of Large-Scale Wetland Classification Using Remote Sensing
The first Canadian wetland inventory (CWI) map, which was based on Landsat data, was produced in 2019 using the Google Earth Engine (GEE) big data processing platform. The proposed GEE-based method to create the preliminary CWI map proved to be a cost, time, and computationally efficient approach. A...
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9254004/ |
| _version_ | 1818438264431837184 |
|---|---|
| author | Meisam Amani Brian Brisco Sahel Mahdavi Arsalan Ghorbanian Armin Moghimi Evan R. DeLancey Michael Merchant Raymond Jahncke Lee Fedorchuk Amy Mui Thierry Fisette Mohammad Kakooei Seyed Ali Ahmadi Brigitte Leblon Armand LaRocque |
| author_facet | Meisam Amani Brian Brisco Sahel Mahdavi Arsalan Ghorbanian Armin Moghimi Evan R. DeLancey Michael Merchant Raymond Jahncke Lee Fedorchuk Amy Mui Thierry Fisette Mohammad Kakooei Seyed Ali Ahmadi Brigitte Leblon Armand LaRocque |
| author_sort | Meisam Amani |
| collection | DOAJ |
| description | The first Canadian wetland inventory (CWI) map, which was based on Landsat data, was produced in 2019 using the Google Earth Engine (GEE) big data processing platform. The proposed GEE-based method to create the preliminary CWI map proved to be a cost, time, and computationally efficient approach. Although the initial effort to produce the CWI map was valuable with a 71% overall accuracy (OA), there were several inevitable limitations (e.g., low-quality samples for the training and validation of the map). Therefore, it was important to comprehensively investigate those limitations and develop effective solutions to improve the accuracy of the Landsat-based CWI (L-CWI) map. Over the past year, the L-CWI map was shared with several governmental, academic, environmental nonprofit, and industrial organizations. Subsequently, valuable feedback was received on the accuracy of this product by comparing it with various in situ data, photo-interpreted reference samples, land cover/land use maps, and high-resolution aerial images. It was generally observed that the accuracy of the L-CWI map was lower relative to the other available products. For example, the average OA in four Canadian provinces using in situ data was 60%. Moreover, including reliable in situ data, using an object-based classification method, and adding more optical and synthetic aperture radar datasets were identified as the main practical solutions to improve the CWI map in the future. Finally, limitations and solutions discussed in this study are applicable to any large-scale wetland mapping using remote sensing methods, especially to CWI generation using optical satellite data in GEE. |
| first_indexed | 2024-12-14T17:37:48Z |
| format | Article |
| id | doaj.art-42c8fff3e3e4427b9e06b26ff12dbf76 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-14T17:37:48Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-42c8fff3e3e4427b9e06b26ff12dbf762022-12-21T22:52:56ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352021-01-0114325210.1109/JSTARS.2020.30368029254004Evaluation of the Landsat-Based Canadian Wetland Inventory Map Using Multiple Sources: Challenges of Large-Scale Wetland Classification Using Remote SensingMeisam Amani0https://orcid.org/0000-0002-9495-4010Brian Brisco1https://orcid.org/0000-0001-8439-362XSahel Mahdavi2https://orcid.org/0000-0002-1670-151XArsalan Ghorbanian3https://orcid.org/0000-0001-8406-683XArmin Moghimi4https://orcid.org/0000-0002-0455-4882Evan R. DeLancey5Michael Merchant6Raymond Jahncke7Lee Fedorchuk8https://orcid.org/0000-0002-1686-049XAmy Mui9Thierry Fisette10Mohammad Kakooei11https://orcid.org/0000-0002-2318-8216Seyed Ali Ahmadi12https://orcid.org/0000-0003-3920-2390Brigitte Leblon13Armand LaRocque14Wood Environment and Infrastructure Solutions, Ottawa, ON, CanadaCanada Center for Mapping and Earth Observation, Ottawa, ON, CanadaWood Environment and Infrastructure Solutions, Ottawa, ON, CanadaDepartment of Remote Sensing and Photogrammetry, Faculty of Geodesy and Geomatics Engineering, K. N. Toosi University of Technology, Tehran, IranDepartment of Remote Sensing and Photogrammetry, Faculty of Geodesy and Geomatics Engineering, K. N. Toosi University of Technology, Tehran, IranAlberta Biodiversity Monitoring Institute, University of Alberta, Edmonton, AB, CanadaNational Boreal Program, Ducks Unlimited Canada, Surrey, BC, CanadaNova Scotia Department of Lands and Forestry, Truro, NS, CanadaManitoba Agriculture and Resource Development, Manitoba Forestry Branch, Winnipeg, MB, CanadaDepartment of Earth and Environmental Sciences, Dalhousie University, Halifax, NS, CanadaAgriculture and Agri-Food Canada, Ottawa, ON, CanadaDepartment of Electronic Engineering, Babol Noshirvani University of Technology, Babol, IranDepartment of Remote Sensing and Photogrammetry, Faculty of Geodesy and Geomatics Engineering, K. N. Toosi University of Technology, Tehran, IranFaculty of Forestry and Environmental Management, University of New Brunswick, Fredericton, NB, CanadaFaculty of Forestry and Environmental Management, University of New Brunswick, Fredericton, NB, CanadaThe first Canadian wetland inventory (CWI) map, which was based on Landsat data, was produced in 2019 using the Google Earth Engine (GEE) big data processing platform. The proposed GEE-based method to create the preliminary CWI map proved to be a cost, time, and computationally efficient approach. Although the initial effort to produce the CWI map was valuable with a 71% overall accuracy (OA), there were several inevitable limitations (e.g., low-quality samples for the training and validation of the map). Therefore, it was important to comprehensively investigate those limitations and develop effective solutions to improve the accuracy of the Landsat-based CWI (L-CWI) map. Over the past year, the L-CWI map was shared with several governmental, academic, environmental nonprofit, and industrial organizations. Subsequently, valuable feedback was received on the accuracy of this product by comparing it with various in situ data, photo-interpreted reference samples, land cover/land use maps, and high-resolution aerial images. It was generally observed that the accuracy of the L-CWI map was lower relative to the other available products. For example, the average OA in four Canadian provinces using in situ data was 60%. Moreover, including reliable in situ data, using an object-based classification method, and adding more optical and synthetic aperture radar datasets were identified as the main practical solutions to improve the CWI map in the future. Finally, limitations and solutions discussed in this study are applicable to any large-scale wetland mapping using remote sensing methods, especially to CWI generation using optical satellite data in GEE.https://ieeexplore.ieee.org/document/9254004/Big dataCanadaGoogle Earth EngineLandsatremote sensing (RS)wetlands |
| spellingShingle | Meisam Amani Brian Brisco Sahel Mahdavi Arsalan Ghorbanian Armin Moghimi Evan R. DeLancey Michael Merchant Raymond Jahncke Lee Fedorchuk Amy Mui Thierry Fisette Mohammad Kakooei Seyed Ali Ahmadi Brigitte Leblon Armand LaRocque Evaluation of the Landsat-Based Canadian Wetland Inventory Map Using Multiple Sources: Challenges of Large-Scale Wetland Classification Using Remote Sensing IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Big data Canada Google Earth Engine Landsat remote sensing (RS) wetlands |
| title | Evaluation of the Landsat-Based Canadian Wetland Inventory Map Using Multiple Sources: Challenges of Large-Scale Wetland Classification Using Remote Sensing |
| title_full | Evaluation of the Landsat-Based Canadian Wetland Inventory Map Using Multiple Sources: Challenges of Large-Scale Wetland Classification Using Remote Sensing |
| title_fullStr | Evaluation of the Landsat-Based Canadian Wetland Inventory Map Using Multiple Sources: Challenges of Large-Scale Wetland Classification Using Remote Sensing |
| title_full_unstemmed | Evaluation of the Landsat-Based Canadian Wetland Inventory Map Using Multiple Sources: Challenges of Large-Scale Wetland Classification Using Remote Sensing |
| title_short | Evaluation of the Landsat-Based Canadian Wetland Inventory Map Using Multiple Sources: Challenges of Large-Scale Wetland Classification Using Remote Sensing |
| title_sort | evaluation of the landsat based canadian wetland inventory map using multiple sources challenges of large scale wetland classification using remote sensing |
| topic | Big data Canada Google Earth Engine Landsat remote sensing (RS) wetlands |
| url | https://ieeexplore.ieee.org/document/9254004/ |
| work_keys_str_mv | AT meisamamani evaluationofthelandsatbasedcanadianwetlandinventorymapusingmultiplesourceschallengesoflargescalewetlandclassificationusingremotesensing AT brianbrisco evaluationofthelandsatbasedcanadianwetlandinventorymapusingmultiplesourceschallengesoflargescalewetlandclassificationusingremotesensing AT sahelmahdavi evaluationofthelandsatbasedcanadianwetlandinventorymapusingmultiplesourceschallengesoflargescalewetlandclassificationusingremotesensing AT arsalanghorbanian evaluationofthelandsatbasedcanadianwetlandinventorymapusingmultiplesourceschallengesoflargescalewetlandclassificationusingremotesensing AT arminmoghimi evaluationofthelandsatbasedcanadianwetlandinventorymapusingmultiplesourceschallengesoflargescalewetlandclassificationusingremotesensing AT evanrdelancey evaluationofthelandsatbasedcanadianwetlandinventorymapusingmultiplesourceschallengesoflargescalewetlandclassificationusingremotesensing AT michaelmerchant evaluationofthelandsatbasedcanadianwetlandinventorymapusingmultiplesourceschallengesoflargescalewetlandclassificationusingremotesensing AT raymondjahncke evaluationofthelandsatbasedcanadianwetlandinventorymapusingmultiplesourceschallengesoflargescalewetlandclassificationusingremotesensing AT leefedorchuk evaluationofthelandsatbasedcanadianwetlandinventorymapusingmultiplesourceschallengesoflargescalewetlandclassificationusingremotesensing AT amymui evaluationofthelandsatbasedcanadianwetlandinventorymapusingmultiplesourceschallengesoflargescalewetlandclassificationusingremotesensing AT thierryfisette evaluationofthelandsatbasedcanadianwetlandinventorymapusingmultiplesourceschallengesoflargescalewetlandclassificationusingremotesensing AT mohammadkakooei evaluationofthelandsatbasedcanadianwetlandinventorymapusingmultiplesourceschallengesoflargescalewetlandclassificationusingremotesensing AT seyedaliahmadi evaluationofthelandsatbasedcanadianwetlandinventorymapusingmultiplesourceschallengesoflargescalewetlandclassificationusingremotesensing AT brigitteleblon evaluationofthelandsatbasedcanadianwetlandinventorymapusingmultiplesourceschallengesoflargescalewetlandclassificationusingremotesensing AT armandlarocque evaluationofthelandsatbasedcanadianwetlandinventorymapusingmultiplesourceschallengesoflargescalewetlandclassificationusingremotesensing |