Algorithms and Predictors for Land Cover Classification of Polar Deserts: A Case Study Highlighting Challenges and Recommendations for Future Applications
The use of remote sensing for developing land cover maps in the Arctic has grown considerably in the last two decades, especially for monitoring the effects of climate change. The main challenge is to link information extracted from satellite imagery to ground covers due to the fine-scale spatial he...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , , , , , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2023
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs15123090 |
id |
ftmdpi:oai:mdpi.com:/2072-4292/15/12/3090/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2072-4292/15/12/3090/ 2023-08-20T04:03:46+02:00 Algorithms and Predictors for Land Cover Classification of Polar Deserts: A Case Study Highlighting Challenges and Recommendations for Future Applications Émilie Desjardins Sandra Lai Laurent Houle Alain Caron Véronique Thériault Andrew Tam François Vézina Dominique Berteaux agris 2023-06-13 application/pdf https://doi.org/10.3390/rs15123090 EN eng Multidisciplinary Digital Publishing Institute Environmental Remote Sensing https://dx.doi.org/10.3390/rs15123090 https://creativecommons.org/licenses/by/4.0/ Remote Sensing; Volume 15; Issue 12; Pages: 3090 High Arctic remote sensing multispectral imagery WorldView-2/3 ensemble classifier majority voting snow vegetation water shadow human infrastructure Text 2023 ftmdpi https://doi.org/10.3390/rs15123090 2023-08-01T10:27:49Z The use of remote sensing for developing land cover maps in the Arctic has grown considerably in the last two decades, especially for monitoring the effects of climate change. The main challenge is to link information extracted from satellite imagery to ground covers due to the fine-scale spatial heterogeneity of Arctic ecosystems. There is currently no commonly accepted methodological scheme for high-latitude land cover mapping, but the use of remote sensing in Arctic ecosystem mapping would benefit from a coordinated sharing of lessons learned and best practices. Here, we aimed to produce a highly accurate land cover map of the surroundings of the Canadian Forces Station Alert, a polar desert on the northeastern tip of Ellesmere Island (Nunavut, Canada) by testing different predictors and classifiers. To account for the effect of the bare soil background and water limitations that are omnipresent at these latitudes, we included as predictors soil-adjusted vegetation indices and several hydrological predictors related to waterbodies and snowbanks. We compared the results obtained from an ensemble classifier based on a majority voting algorithm to eight commonly used classifiers. The distance to the nearest snowbank and soil-adjusted indices were the top predictors allowing the discrimination of land cover classes in our study area. The overall accuracy of the classifiers ranged between 75 and 88%, with the ensemble classifier also yielding a high accuracy (85%) and producing less bias than the individual classifiers. Some challenges remained, such as shadows created by boulders and snow covered by soil material. We provide recommendations for further improving classification methodology in the High Arctic, which is important for the monitoring of Arctic ecosystems exposed to ongoing polar amplification. Text Arctic Climate change Ellesmere Island Nunavut polar desert MDPI Open Access Publishing Arctic Nunavut Ellesmere Island Canada Canadian Forces Station Alert ENVELOPE(-62.350,-62.350,82.499,82.499) Remote Sensing 15 12 3090 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
High Arctic remote sensing multispectral imagery WorldView-2/3 ensemble classifier majority voting snow vegetation water shadow human infrastructure |
spellingShingle |
High Arctic remote sensing multispectral imagery WorldView-2/3 ensemble classifier majority voting snow vegetation water shadow human infrastructure Émilie Desjardins Sandra Lai Laurent Houle Alain Caron Véronique Thériault Andrew Tam François Vézina Dominique Berteaux Algorithms and Predictors for Land Cover Classification of Polar Deserts: A Case Study Highlighting Challenges and Recommendations for Future Applications |
topic_facet |
High Arctic remote sensing multispectral imagery WorldView-2/3 ensemble classifier majority voting snow vegetation water shadow human infrastructure |
description |
The use of remote sensing for developing land cover maps in the Arctic has grown considerably in the last two decades, especially for monitoring the effects of climate change. The main challenge is to link information extracted from satellite imagery to ground covers due to the fine-scale spatial heterogeneity of Arctic ecosystems. There is currently no commonly accepted methodological scheme for high-latitude land cover mapping, but the use of remote sensing in Arctic ecosystem mapping would benefit from a coordinated sharing of lessons learned and best practices. Here, we aimed to produce a highly accurate land cover map of the surroundings of the Canadian Forces Station Alert, a polar desert on the northeastern tip of Ellesmere Island (Nunavut, Canada) by testing different predictors and classifiers. To account for the effect of the bare soil background and water limitations that are omnipresent at these latitudes, we included as predictors soil-adjusted vegetation indices and several hydrological predictors related to waterbodies and snowbanks. We compared the results obtained from an ensemble classifier based on a majority voting algorithm to eight commonly used classifiers. The distance to the nearest snowbank and soil-adjusted indices were the top predictors allowing the discrimination of land cover classes in our study area. The overall accuracy of the classifiers ranged between 75 and 88%, with the ensemble classifier also yielding a high accuracy (85%) and producing less bias than the individual classifiers. Some challenges remained, such as shadows created by boulders and snow covered by soil material. We provide recommendations for further improving classification methodology in the High Arctic, which is important for the monitoring of Arctic ecosystems exposed to ongoing polar amplification. |
format |
Text |
author |
Émilie Desjardins Sandra Lai Laurent Houle Alain Caron Véronique Thériault Andrew Tam François Vézina Dominique Berteaux |
author_facet |
Émilie Desjardins Sandra Lai Laurent Houle Alain Caron Véronique Thériault Andrew Tam François Vézina Dominique Berteaux |
author_sort |
Émilie Desjardins |
title |
Algorithms and Predictors for Land Cover Classification of Polar Deserts: A Case Study Highlighting Challenges and Recommendations for Future Applications |
title_short |
Algorithms and Predictors for Land Cover Classification of Polar Deserts: A Case Study Highlighting Challenges and Recommendations for Future Applications |
title_full |
Algorithms and Predictors for Land Cover Classification of Polar Deserts: A Case Study Highlighting Challenges and Recommendations for Future Applications |
title_fullStr |
Algorithms and Predictors for Land Cover Classification of Polar Deserts: A Case Study Highlighting Challenges and Recommendations for Future Applications |
title_full_unstemmed |
Algorithms and Predictors for Land Cover Classification of Polar Deserts: A Case Study Highlighting Challenges and Recommendations for Future Applications |
title_sort |
algorithms and predictors for land cover classification of polar deserts: a case study highlighting challenges and recommendations for future applications |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2023 |
url |
https://doi.org/10.3390/rs15123090 |
op_coverage |
agris |
long_lat |
ENVELOPE(-62.350,-62.350,82.499,82.499) |
geographic |
Arctic Nunavut Ellesmere Island Canada Canadian Forces Station Alert |
geographic_facet |
Arctic Nunavut Ellesmere Island Canada Canadian Forces Station Alert |
genre |
Arctic Climate change Ellesmere Island Nunavut polar desert |
genre_facet |
Arctic Climate change Ellesmere Island Nunavut polar desert |
op_source |
Remote Sensing; Volume 15; Issue 12; Pages: 3090 |
op_relation |
Environmental Remote Sensing https://dx.doi.org/10.3390/rs15123090 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/rs15123090 |
container_title |
Remote Sensing |
container_volume |
15 |
container_issue |
12 |
container_start_page |
3090 |
_version_ |
1774714208879902720 |