High-resolution land cover classification for Stordalen, Abisko region, northern Sweden
An object-based approach was used to generate a detailed land cover classification covering the Stordalen area near Abisko, northern Sweden. First, an orthophoto was combined with the DEM resampled to 1 m spatial resolution. A segmentation layer was generated by grouping pixels into homogeneous area...
Main Author: | |
---|---|
Format: | Dataset |
Language: | English |
Published: |
PANGAEA
2018
|
Subjects: | |
Online Access: | https://doi.pangaea.de/10.1594/PANGAEA.886298 https://doi.org/10.1594/PANGAEA.886298 |
id |
ftpangaea:oai:pangaea.de:doi:10.1594/PANGAEA.886298 |
---|---|
record_format |
openpolar |
spelling |
ftpangaea:oai:pangaea.de:doi:10.1594/PANGAEA.886298 2023-05-15T12:59:17+02:00 High-resolution land cover classification for Stordalen, Abisko region, northern Sweden Siewert, Matthias Benjamin LATITUDE: 68.333000 * LONGITUDE: 18.833000 * MINIMUM ELEVATION: 1206.0 m * MAXIMUM ELEVATION: 1206.0 m 2018-02-16 application/zip, 17.7 MBytes https://doi.pangaea.de/10.1594/PANGAEA.886298 https://doi.org/10.1594/PANGAEA.886298 en eng PANGAEA Siewert, Matthias Benjamin (2018): High-resolution digital mapping of soil organic carbon in permafrost terrain using machine learning: a case study in a sub-Arctic peatland environment. Biogeosciences, 15(6), 1663-1682, https://doi.org/10.5194/bg-15-1663-2018 https://doi.pangaea.de/10.1594/PANGAEA.886298 https://doi.org/10.1594/PANGAEA.886298 CC-BY-3.0: Creative Commons Attribution 3.0 Unported Access constraints: unrestricted info:eu-repo/semantics/openAccess CC-BY ABI Abisko Lappland northern Sweden Changing Permafrost in the Arctic and its Global Effects in the 21st Century MULT Multiple investigations PAGE21 Dataset 2018 ftpangaea https://doi.org/10.1594/PANGAEA.886298 https://doi.org/10.5194/bg-15-1663-2018 2023-01-20T09:10:26Z An object-based approach was used to generate a detailed land cover classification covering the Stordalen area near Abisko, northern Sweden. First, an orthophoto was combined with the DEM resampled to 1 m spatial resolution. A segmentation layer was generated by grouping pixels into homogeneous areas with a minimum region size of 130 m². From this a water mask was classified using the red band of the orthophoto and a slope layer. A land cover training set was created by combining field survey information with visual interpretation of the orthophoto and topography. The following layers were used as input for the classification algorithm: an orthophoto, elevation and slope; a SPOT5 4-band satellite image, and NDVI, SAVI and NIR/SWIR as SPOT5 derivatives. The segments were then classified using a support vector machine algorithm. Artificial surfaces were hand digitized and masked out. The individual thematic classes are described in TableA1. The quality of the classification was assessed using a set of 108 ground control points. The accuracy assessment results in a Kappa value of 0.71 and an overall accuracy of 74% for all land covers excluding water and artificial areas see TableA2. Dataset Abisko Arctic Arctic Lappland Northern Sweden permafrost PANGAEA - Data Publisher for Earth & Environmental Science Arctic Lappland ENVELOPE(18.067,18.067,65.900,65.900) Abisko ENVELOPE(18.829,18.829,68.349,68.349) Stordalen ENVELOPE(7.337,7.337,62.510,62.510) ENVELOPE(18.833000,18.833000,68.333000,68.333000) |
institution |
Open Polar |
collection |
PANGAEA - Data Publisher for Earth & Environmental Science |
op_collection_id |
ftpangaea |
language |
English |
topic |
ABI Abisko Lappland northern Sweden Changing Permafrost in the Arctic and its Global Effects in the 21st Century MULT Multiple investigations PAGE21 |
spellingShingle |
ABI Abisko Lappland northern Sweden Changing Permafrost in the Arctic and its Global Effects in the 21st Century MULT Multiple investigations PAGE21 Siewert, Matthias Benjamin High-resolution land cover classification for Stordalen, Abisko region, northern Sweden |
topic_facet |
ABI Abisko Lappland northern Sweden Changing Permafrost in the Arctic and its Global Effects in the 21st Century MULT Multiple investigations PAGE21 |
description |
An object-based approach was used to generate a detailed land cover classification covering the Stordalen area near Abisko, northern Sweden. First, an orthophoto was combined with the DEM resampled to 1 m spatial resolution. A segmentation layer was generated by grouping pixels into homogeneous areas with a minimum region size of 130 m². From this a water mask was classified using the red band of the orthophoto and a slope layer. A land cover training set was created by combining field survey information with visual interpretation of the orthophoto and topography. The following layers were used as input for the classification algorithm: an orthophoto, elevation and slope; a SPOT5 4-band satellite image, and NDVI, SAVI and NIR/SWIR as SPOT5 derivatives. The segments were then classified using a support vector machine algorithm. Artificial surfaces were hand digitized and masked out. The individual thematic classes are described in TableA1. The quality of the classification was assessed using a set of 108 ground control points. The accuracy assessment results in a Kappa value of 0.71 and an overall accuracy of 74% for all land covers excluding water and artificial areas see TableA2. |
format |
Dataset |
author |
Siewert, Matthias Benjamin |
author_facet |
Siewert, Matthias Benjamin |
author_sort |
Siewert, Matthias Benjamin |
title |
High-resolution land cover classification for Stordalen, Abisko region, northern Sweden |
title_short |
High-resolution land cover classification for Stordalen, Abisko region, northern Sweden |
title_full |
High-resolution land cover classification for Stordalen, Abisko region, northern Sweden |
title_fullStr |
High-resolution land cover classification for Stordalen, Abisko region, northern Sweden |
title_full_unstemmed |
High-resolution land cover classification for Stordalen, Abisko region, northern Sweden |
title_sort |
high-resolution land cover classification for stordalen, abisko region, northern sweden |
publisher |
PANGAEA |
publishDate |
2018 |
url |
https://doi.pangaea.de/10.1594/PANGAEA.886298 https://doi.org/10.1594/PANGAEA.886298 |
op_coverage |
LATITUDE: 68.333000 * LONGITUDE: 18.833000 * MINIMUM ELEVATION: 1206.0 m * MAXIMUM ELEVATION: 1206.0 m |
long_lat |
ENVELOPE(18.067,18.067,65.900,65.900) ENVELOPE(18.829,18.829,68.349,68.349) ENVELOPE(7.337,7.337,62.510,62.510) ENVELOPE(18.833000,18.833000,68.333000,68.333000) |
geographic |
Arctic Lappland Abisko Stordalen |
geographic_facet |
Arctic Lappland Abisko Stordalen |
genre |
Abisko Arctic Arctic Lappland Northern Sweden permafrost |
genre_facet |
Abisko Arctic Arctic Lappland Northern Sweden permafrost |
op_relation |
Siewert, Matthias Benjamin (2018): High-resolution digital mapping of soil organic carbon in permafrost terrain using machine learning: a case study in a sub-Arctic peatland environment. Biogeosciences, 15(6), 1663-1682, https://doi.org/10.5194/bg-15-1663-2018 https://doi.pangaea.de/10.1594/PANGAEA.886298 https://doi.org/10.1594/PANGAEA.886298 |
op_rights |
CC-BY-3.0: Creative Commons Attribution 3.0 Unported Access constraints: unrestricted info:eu-repo/semantics/openAccess |
op_rightsnorm |
CC-BY |
op_doi |
https://doi.org/10.1594/PANGAEA.886298 https://doi.org/10.5194/bg-15-1663-2018 |
_version_ |
1766380521505423360 |