Multi‐Source Mapping of Peatland Types Using Sentinel‐1, Sentinel‐2, and Terrain Derivatives—A Comparison Between Five High‐Latitude Landscapes
Mapping wetland types in northern-latitude regions with Earth Observation (EO) data is important for several practical and scientific applications, but at the same time challenging due to the variability and dynamic nature in wetland features introduced by differences in geophysical conditions. The...
Published in: | Journal of Geophysical Research: Biogeosciences |
---|---|
Main Authors: | , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Linköpings universitet, Tema Miljöförändring
2023
|
Subjects: | |
Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-193214 https://doi.org/10.1029/2022jg007195 |
id |
ftlinkoepinguniv:oai:DiVA.org:liu-193214 |
---|---|
record_format |
openpolar |
spelling |
ftlinkoepinguniv:oai:DiVA.org:liu-193214 2023-10-09T21:49:28+02:00 Multi‐Source Mapping of Peatland Types Using Sentinel‐1, Sentinel‐2, and Terrain Derivatives—A Comparison Between Five High‐Latitude Landscapes Karlson, Martin Bastviken, David 2023 application/pdf http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-193214 https://doi.org/10.1029/2022jg007195 eng eng Linköpings universitet, Tema Miljöförändring Linköpings universitet, Filosofiska fakulteten Journal of Geophysical Research - Biogeosciences, 2169-8953, 2023, 128:4, orcid:0000-0002-3926-3671 orcid:0000-0003-0038-2152 http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-193214 doi:10.1029/2022jg007195 ISI:000972246100001 info:eu-repo/semantics/openAccess peatland types land cover classification data fusion arctic northern latitude regions terrain derivatives Geosciences Multidisciplinary Multidisciplinär geovetenskap Remote Sensing Fjärranalysteknik Physical Geography Naturgeografi Article in journal info:eu-repo/semantics/article text 2023 ftlinkoepinguniv https://doi.org/10.1029/2022jg007195 2023-09-20T22:32:18Z Mapping wetland types in northern-latitude regions with Earth Observation (EO) data is important for several practical and scientific applications, but at the same time challenging due to the variability and dynamic nature in wetland features introduced by differences in geophysical conditions. The objective of this study was to better understand the ability of Sentinel-1 radar data, Sentinel-2 optical data and terrain derivatives derived from Copernicus digital elevation model to distinguish three main peatland types, two upland classes, and surface water, in five contrasting landscapes located in the northern parts of Alaska, Canada and Scandinavia. The study also investigated the potential benefits for classification accuracy of using regional classification models constructed from region-specific training data compared to a global classification model based on pooled reference data from all five sites. Overall, the results show high promise for classifying peatland types and the three other land cover classes using the fusion approach that combined all three EO data sources (Sentinel-1, Sentinel-2 and terrain derivatives). Overall accuracy for the individual sites ranged between 79.7% and 90.3%. Class specific accuracies for the peatland types were also high overall but differed between the five sites as well as between the three classes bog, fen and swamp. A key finding is that regional classification models consistently outperformed the global classification model by producing significantly higher classification accuracies for all five sites. This suggests for progress in identifying effective approaches for continental scale peatland mapping to improve scaling of for example, hydrological- and greenhouse gas-related processes in Earth system models. Funding: Swedish Research Council Formas [2017-01944, 2018-01794, 2018-00570]; European Space Agency Article in Journal/Newspaper Arctic Alaska LIU - Linköping University: Publications (DiVA) Arctic Canada Journal of Geophysical Research: Biogeosciences 128 4 |
institution |
Open Polar |
collection |
LIU - Linköping University: Publications (DiVA) |
op_collection_id |
ftlinkoepinguniv |
language |
English |
topic |
peatland types land cover classification data fusion arctic northern latitude regions terrain derivatives Geosciences Multidisciplinary Multidisciplinär geovetenskap Remote Sensing Fjärranalysteknik Physical Geography Naturgeografi |
spellingShingle |
peatland types land cover classification data fusion arctic northern latitude regions terrain derivatives Geosciences Multidisciplinary Multidisciplinär geovetenskap Remote Sensing Fjärranalysteknik Physical Geography Naturgeografi Karlson, Martin Bastviken, David Multi‐Source Mapping of Peatland Types Using Sentinel‐1, Sentinel‐2, and Terrain Derivatives—A Comparison Between Five High‐Latitude Landscapes |
topic_facet |
peatland types land cover classification data fusion arctic northern latitude regions terrain derivatives Geosciences Multidisciplinary Multidisciplinär geovetenskap Remote Sensing Fjärranalysteknik Physical Geography Naturgeografi |
description |
Mapping wetland types in northern-latitude regions with Earth Observation (EO) data is important for several practical and scientific applications, but at the same time challenging due to the variability and dynamic nature in wetland features introduced by differences in geophysical conditions. The objective of this study was to better understand the ability of Sentinel-1 radar data, Sentinel-2 optical data and terrain derivatives derived from Copernicus digital elevation model to distinguish three main peatland types, two upland classes, and surface water, in five contrasting landscapes located in the northern parts of Alaska, Canada and Scandinavia. The study also investigated the potential benefits for classification accuracy of using regional classification models constructed from region-specific training data compared to a global classification model based on pooled reference data from all five sites. Overall, the results show high promise for classifying peatland types and the three other land cover classes using the fusion approach that combined all three EO data sources (Sentinel-1, Sentinel-2 and terrain derivatives). Overall accuracy for the individual sites ranged between 79.7% and 90.3%. Class specific accuracies for the peatland types were also high overall but differed between the five sites as well as between the three classes bog, fen and swamp. A key finding is that regional classification models consistently outperformed the global classification model by producing significantly higher classification accuracies for all five sites. This suggests for progress in identifying effective approaches for continental scale peatland mapping to improve scaling of for example, hydrological- and greenhouse gas-related processes in Earth system models. Funding: Swedish Research Council Formas [2017-01944, 2018-01794, 2018-00570]; European Space Agency |
format |
Article in Journal/Newspaper |
author |
Karlson, Martin Bastviken, David |
author_facet |
Karlson, Martin Bastviken, David |
author_sort |
Karlson, Martin |
title |
Multi‐Source Mapping of Peatland Types Using Sentinel‐1, Sentinel‐2, and Terrain Derivatives—A Comparison Between Five High‐Latitude Landscapes |
title_short |
Multi‐Source Mapping of Peatland Types Using Sentinel‐1, Sentinel‐2, and Terrain Derivatives—A Comparison Between Five High‐Latitude Landscapes |
title_full |
Multi‐Source Mapping of Peatland Types Using Sentinel‐1, Sentinel‐2, and Terrain Derivatives—A Comparison Between Five High‐Latitude Landscapes |
title_fullStr |
Multi‐Source Mapping of Peatland Types Using Sentinel‐1, Sentinel‐2, and Terrain Derivatives—A Comparison Between Five High‐Latitude Landscapes |
title_full_unstemmed |
Multi‐Source Mapping of Peatland Types Using Sentinel‐1, Sentinel‐2, and Terrain Derivatives—A Comparison Between Five High‐Latitude Landscapes |
title_sort |
multi‐source mapping of peatland types using sentinel‐1, sentinel‐2, and terrain derivatives—a comparison between five high‐latitude landscapes |
publisher |
Linköpings universitet, Tema Miljöförändring |
publishDate |
2023 |
url |
http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-193214 https://doi.org/10.1029/2022jg007195 |
geographic |
Arctic Canada |
geographic_facet |
Arctic Canada |
genre |
Arctic Alaska |
genre_facet |
Arctic Alaska |
op_relation |
Journal of Geophysical Research - Biogeosciences, 2169-8953, 2023, 128:4, orcid:0000-0002-3926-3671 orcid:0000-0003-0038-2152 http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-193214 doi:10.1029/2022jg007195 ISI:000972246100001 |
op_rights |
info:eu-repo/semantics/openAccess |
op_doi |
https://doi.org/10.1029/2022jg007195 |
container_title |
Journal of Geophysical Research: Biogeosciences |
container_volume |
128 |
container_issue |
4 |
_version_ |
1779312485584601088 |