Usability of one-class classification in mapping and detecting changes in bare peat surfaces in the tundra
Arctic areas have experienced greening and changes in permafrost caused by climate change during recent decades. However, there has been a lack of automated methods in mapping changes in fine-scale patterns of permafrost landscapes. We mapped areal coverage of bare peat areas and changes in them in...
Published in: | International Journal of Remote Sensing |
---|---|
Main Authors: | , , |
Other Authors: | , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Taylor & Francis
2019
|
Subjects: | |
Online Access: | http://hdl.handle.net/10138/301621 |
id |
ftunivhelsihelda:oai:helda.helsinki.fi:10138/301621 |
---|---|
record_format |
openpolar |
spelling |
ftunivhelsihelda:oai:helda.helsinki.fi:10138/301621 2024-01-07T09:41:43+01:00 Usability of one-class classification in mapping and detecting changes in bare peat surfaces in the tundra Räsänen, Aleksi Elsakov, Vladimir Virtanen, Tarmo Helsinki Institute of Sustainability Science (HELSUS) Urban Environmental Policy Ecosystems and Environment Research Programme Tarmo Virtanen / Principal Investigator Environmental Change Research Unit (ECRU) 2019-05-09T15:38:01Z 21 application/pdf http://hdl.handle.net/10138/301621 eng eng Taylor & Francis 10.1080/01431161.2018.1558376 Räsänen , A , Elsakov , V & Virtanen , T 2019 , ' Usability of one-class classification in mapping and detecting changes in bare peat surfaces in the tundra ' , International Journal of Remote Sensing , vol. 40 , no. 11 , pp. 4083-4103 . https://doi.org/10.1080/01431161.2018.1558376 ORCID: /0000-0002-3629-1837/work/57306073 ORCID: /0000-0001-8660-2464/work/105284731 85059523021 ef4559c3-bd67-41c0-9b7c-b121d125f904 http://hdl.handle.net/10138/301621 000465245700002 openAccess info:eu-repo/semantics/openAccess 1172 Environmental sciences Article acceptedVersion 2019 ftunivhelsihelda 2023-12-14T00:04:15Z Arctic areas have experienced greening and changes in permafrost caused by climate change during recent decades. However, there has been a lack of automated methods in mapping changes in fine-scale patterns of permafrost landscapes. We mapped areal coverage of bare peat areas and changes in them in a peat plateau located in north-western Russia between 2007 and 2015. We utilized QuickBird and WorldView-3 satellite image data in an object-based setting. We compared four different one-class classifiers (one-class support vector machine, binary support vector machine, random forest, rotation forest) both in a fully supervised binary setting and with positive and unlabelled training data. There was notable variation in classification performance. The bare peat area F-score varied between 0.77 and 0.96 when evaluated by cross-validated training data and between 0.22 and 0.57 when evaluated by independent test data. Overall, random forest performed the most robustly but all classifiers performed well in some classifications. During the 8 year period, there was a 21%-26% decrease in the bare peat areal coverage. We conclude that (1) tested classifiers can be used in one-class settings and (2) there is a need to develop methods for tracking changes in single land cover types. Peer reviewed Article in Journal/Newspaper Arctic Climate change North-Western Russia Peat Peat plateau permafrost Tundra HELDA – University of Helsinki Open Repository Arctic International Journal of Remote Sensing 40 11 4083 4103 |
institution |
Open Polar |
collection |
HELDA – University of Helsinki Open Repository |
op_collection_id |
ftunivhelsihelda |
language |
English |
topic |
1172 Environmental sciences |
spellingShingle |
1172 Environmental sciences Räsänen, Aleksi Elsakov, Vladimir Virtanen, Tarmo Usability of one-class classification in mapping and detecting changes in bare peat surfaces in the tundra |
topic_facet |
1172 Environmental sciences |
description |
Arctic areas have experienced greening and changes in permafrost caused by climate change during recent decades. However, there has been a lack of automated methods in mapping changes in fine-scale patterns of permafrost landscapes. We mapped areal coverage of bare peat areas and changes in them in a peat plateau located in north-western Russia between 2007 and 2015. We utilized QuickBird and WorldView-3 satellite image data in an object-based setting. We compared four different one-class classifiers (one-class support vector machine, binary support vector machine, random forest, rotation forest) both in a fully supervised binary setting and with positive and unlabelled training data. There was notable variation in classification performance. The bare peat area F-score varied between 0.77 and 0.96 when evaluated by cross-validated training data and between 0.22 and 0.57 when evaluated by independent test data. Overall, random forest performed the most robustly but all classifiers performed well in some classifications. During the 8 year period, there was a 21%-26% decrease in the bare peat areal coverage. We conclude that (1) tested classifiers can be used in one-class settings and (2) there is a need to develop methods for tracking changes in single land cover types. Peer reviewed |
author2 |
Helsinki Institute of Sustainability Science (HELSUS) Urban Environmental Policy Ecosystems and Environment Research Programme Tarmo Virtanen / Principal Investigator Environmental Change Research Unit (ECRU) |
format |
Article in Journal/Newspaper |
author |
Räsänen, Aleksi Elsakov, Vladimir Virtanen, Tarmo |
author_facet |
Räsänen, Aleksi Elsakov, Vladimir Virtanen, Tarmo |
author_sort |
Räsänen, Aleksi |
title |
Usability of one-class classification in mapping and detecting changes in bare peat surfaces in the tundra |
title_short |
Usability of one-class classification in mapping and detecting changes in bare peat surfaces in the tundra |
title_full |
Usability of one-class classification in mapping and detecting changes in bare peat surfaces in the tundra |
title_fullStr |
Usability of one-class classification in mapping and detecting changes in bare peat surfaces in the tundra |
title_full_unstemmed |
Usability of one-class classification in mapping and detecting changes in bare peat surfaces in the tundra |
title_sort |
usability of one-class classification in mapping and detecting changes in bare peat surfaces in the tundra |
publisher |
Taylor & Francis |
publishDate |
2019 |
url |
http://hdl.handle.net/10138/301621 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic Climate change North-Western Russia Peat Peat plateau permafrost Tundra |
genre_facet |
Arctic Climate change North-Western Russia Peat Peat plateau permafrost Tundra |
op_relation |
10.1080/01431161.2018.1558376 Räsänen , A , Elsakov , V & Virtanen , T 2019 , ' Usability of one-class classification in mapping and detecting changes in bare peat surfaces in the tundra ' , International Journal of Remote Sensing , vol. 40 , no. 11 , pp. 4083-4103 . https://doi.org/10.1080/01431161.2018.1558376 ORCID: /0000-0002-3629-1837/work/57306073 ORCID: /0000-0001-8660-2464/work/105284731 85059523021 ef4559c3-bd67-41c0-9b7c-b121d125f904 http://hdl.handle.net/10138/301621 000465245700002 |
op_rights |
openAccess info:eu-repo/semantics/openAccess |
container_title |
International Journal of Remote Sensing |
container_volume |
40 |
container_issue |
11 |
container_start_page |
4083 |
op_container_end_page |
4103 |
_version_ |
1787422529795653632 |