Usability of one-class classification in mapping and detecting changes in bare peat surfaces in the tundra

Aleksi Räsänen, Vladimir Elsakov, Tarmo Virtanen

Forskningsoutput: TidskriftsbidragArtikelVetenskapligPeer review

Sammanfattning

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.
Originalspråkengelska
TidskriftInternational Journal of Remote Sensing
Volym40
Utgåva11
Sidor (från-till)4083-4103
Antal sidor21
ISSN0143-1161
DOI
StatusPublicerad - jan 2019
MoE-publikationstypA1 Tidskriftsartikel-refererad

Vetenskapsgrenar

  • 1172 Miljövetenskap

Citera det här

@article{ef4559c3bd6741c09b7cb121d125f904,
title = "Usability of one-class classification in mapping and detecting changes in bare peat surfaces in the tundra",
abstract = "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.",
keywords = "1172 Environmental sciences",
author = "Aleksi R{\"a}s{\"a}nen and Vladimir Elsakov and Tarmo Virtanen",
year = "2019",
month = "1",
doi = "10.1080/01431161.2018.1558376",
language = "English",
volume = "40",
pages = "4083--4103",
journal = "International Journal of Remote Sensing",
issn = "0143-1161",
publisher = "Taylor & Francis",
number = "11",

}

Usability of one-class classification in mapping and detecting changes in bare peat surfaces in the tundra. / Räsänen, Aleksi; Elsakov, Vladimir; Virtanen, Tarmo.

I: International Journal of Remote Sensing, Vol. 40, Nr. 11, 01.2019, s. 4083-4103.

Forskningsoutput: TidskriftsbidragArtikelVetenskapligPeer review

TY - JOUR

T1 - Usability of one-class classification in mapping and detecting changes in bare peat surfaces in the tundra

AU - Räsänen, Aleksi

AU - Elsakov, Vladimir

AU - Virtanen, Tarmo

PY - 2019/1

Y1 - 2019/1

N2 - 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.

AB - 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.

KW - 1172 Environmental sciences

U2 - 10.1080/01431161.2018.1558376

DO - 10.1080/01431161.2018.1558376

M3 - Article

VL - 40

SP - 4083

EP - 4103

JO - International Journal of Remote Sensing

JF - International Journal of Remote Sensing

SN - 0143-1161

IS - 11

ER -