Towards High-Resolution Land-Cover Classification of Greenland: A Case Study Covering Kobbefjord, Disko and Zackenberg
Mapping of the Arctic region is increasingly important in light of global warming as land cover maps can provide the foundation for upscaling of ecosystem properties and processes. To this end, satellite images provide an invaluable source of Earth observations to monitor land cover in areas that ar...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2021
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs13183559 https://doaj.org/article/18262f6914cb46aab07ddaa59ca71c90 |
id |
ftdoajarticles:oai:doaj.org/article:18262f6914cb46aab07ddaa59ca71c90 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:18262f6914cb46aab07ddaa59ca71c90 2023-05-15T14:58:40+02:00 Towards High-Resolution Land-Cover Classification of Greenland: A Case Study Covering Kobbefjord, Disko and Zackenberg Daniel Alexander Rudd Mojtaba Karami Rasmus Fensholt 2021-09-01T00:00:00Z https://doi.org/10.3390/rs13183559 https://doaj.org/article/18262f6914cb46aab07ddaa59ca71c90 EN eng MDPI AG https://www.mdpi.com/2072-4292/13/18/3559 https://doaj.org/toc/2072-4292 doi:10.3390/rs13183559 2072-4292 https://doaj.org/article/18262f6914cb46aab07ddaa59ca71c90 Remote Sensing, Vol 13, Iss 3559, p 3559 (2021) Sentinel-2 google earth engine vegetation phenology random forest red-edge Science Q article 2021 ftdoajarticles https://doi.org/10.3390/rs13183559 2022-12-30T20:18:49Z Mapping of the Arctic region is increasingly important in light of global warming as land cover maps can provide the foundation for upscaling of ecosystem properties and processes. To this end, satellite images provide an invaluable source of Earth observations to monitor land cover in areas that are otherwise difficult to access. With the continuous development of new satellites, it is important to optimize the existing maps for further monitoring of Arctic ecosystems. This study presents a scalable classification framework, producing novel 10 m resolution land cover maps for Kobbefjord, Disko, and Zackenberg in Greenland. Based on Sentinel-2, a digital elevation model, and Google Earth Engine (GEE), this framework classifies the areas into nine classes. A vegetation land cover classification for 2019 is achieved through a multi-temporal analysis based on 41 layers comprising phenology, spectral indices, and topographical features. Reference data (1164 field observations) were used to train a random forest classifier, achieving a cross-validation accuracy of 91.8%. The red-edge bands of Sentinel-2 data proved to be particularly well suited for mapping the fen vegetation class. The study presents land cover mapping in the three study areas with an unprecedented spatial resolution and can be extended via GEE for further ecological monitoring in Greenland. Article in Journal/Newspaper Arctic Global warming Greenland Zackenberg Directory of Open Access Journals: DOAJ Articles Arctic Greenland Kobbefjord ENVELOPE(-51.527,-51.527,64.177,64.177) Remote Sensing 13 18 3559 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Sentinel-2 google earth engine vegetation phenology random forest red-edge Science Q |
spellingShingle |
Sentinel-2 google earth engine vegetation phenology random forest red-edge Science Q Daniel Alexander Rudd Mojtaba Karami Rasmus Fensholt Towards High-Resolution Land-Cover Classification of Greenland: A Case Study Covering Kobbefjord, Disko and Zackenberg |
topic_facet |
Sentinel-2 google earth engine vegetation phenology random forest red-edge Science Q |
description |
Mapping of the Arctic region is increasingly important in light of global warming as land cover maps can provide the foundation for upscaling of ecosystem properties and processes. To this end, satellite images provide an invaluable source of Earth observations to monitor land cover in areas that are otherwise difficult to access. With the continuous development of new satellites, it is important to optimize the existing maps for further monitoring of Arctic ecosystems. This study presents a scalable classification framework, producing novel 10 m resolution land cover maps for Kobbefjord, Disko, and Zackenberg in Greenland. Based on Sentinel-2, a digital elevation model, and Google Earth Engine (GEE), this framework classifies the areas into nine classes. A vegetation land cover classification for 2019 is achieved through a multi-temporal analysis based on 41 layers comprising phenology, spectral indices, and topographical features. Reference data (1164 field observations) were used to train a random forest classifier, achieving a cross-validation accuracy of 91.8%. The red-edge bands of Sentinel-2 data proved to be particularly well suited for mapping the fen vegetation class. The study presents land cover mapping in the three study areas with an unprecedented spatial resolution and can be extended via GEE for further ecological monitoring in Greenland. |
format |
Article in Journal/Newspaper |
author |
Daniel Alexander Rudd Mojtaba Karami Rasmus Fensholt |
author_facet |
Daniel Alexander Rudd Mojtaba Karami Rasmus Fensholt |
author_sort |
Daniel Alexander Rudd |
title |
Towards High-Resolution Land-Cover Classification of Greenland: A Case Study Covering Kobbefjord, Disko and Zackenberg |
title_short |
Towards High-Resolution Land-Cover Classification of Greenland: A Case Study Covering Kobbefjord, Disko and Zackenberg |
title_full |
Towards High-Resolution Land-Cover Classification of Greenland: A Case Study Covering Kobbefjord, Disko and Zackenberg |
title_fullStr |
Towards High-Resolution Land-Cover Classification of Greenland: A Case Study Covering Kobbefjord, Disko and Zackenberg |
title_full_unstemmed |
Towards High-Resolution Land-Cover Classification of Greenland: A Case Study Covering Kobbefjord, Disko and Zackenberg |
title_sort |
towards high-resolution land-cover classification of greenland: a case study covering kobbefjord, disko and zackenberg |
publisher |
MDPI AG |
publishDate |
2021 |
url |
https://doi.org/10.3390/rs13183559 https://doaj.org/article/18262f6914cb46aab07ddaa59ca71c90 |
long_lat |
ENVELOPE(-51.527,-51.527,64.177,64.177) |
geographic |
Arctic Greenland Kobbefjord |
geographic_facet |
Arctic Greenland Kobbefjord |
genre |
Arctic Global warming Greenland Zackenberg |
genre_facet |
Arctic Global warming Greenland Zackenberg |
op_source |
Remote Sensing, Vol 13, Iss 3559, p 3559 (2021) |
op_relation |
https://www.mdpi.com/2072-4292/13/18/3559 https://doaj.org/toc/2072-4292 doi:10.3390/rs13183559 2072-4292 https://doaj.org/article/18262f6914cb46aab07ddaa59ca71c90 |
op_doi |
https://doi.org/10.3390/rs13183559 |
container_title |
Remote Sensing |
container_volume |
13 |
container_issue |
18 |
container_start_page |
3559 |
_version_ |
1766330789190959104 |