Improving Classification of Airborne Laser Scanning Echoes in the Forest-Tundra Ecotone Using Geostatistical and Statistical Measures
The vegetation in the forest-tundra ecotone zone is expected to be highly affected by climate change and requires effective monitoring techniques. Airborne laser scanning (ALS) has been proposed as a tool for the detection of small pioneer trees for such vast areas using laser height and intensity d...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2014
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs6054582 https://doaj.org/article/14f99f9560de4b8998273a789f3e83c7 |
id |
ftdoajarticles:oai:doaj.org/article:14f99f9560de4b8998273a789f3e83c7 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:14f99f9560de4b8998273a789f3e83c7 2023-05-15T17:43:30+02:00 Improving Classification of Airborne Laser Scanning Echoes in the Forest-Tundra Ecotone Using Geostatistical and Statistical Measures Nadja Stumberg Marius Hauglin Ole Martin Bollandsås Terje Gobakken Erik Næsset 2014-05-01T00:00:00Z https://doi.org/10.3390/rs6054582 https://doaj.org/article/14f99f9560de4b8998273a789f3e83c7 EN eng MDPI AG http://www.mdpi.com/2072-4292/6/5/4582 https://doaj.org/toc/2072-4292 2072-4292 doi:10.3390/rs6054582 https://doaj.org/article/14f99f9560de4b8998273a789f3e83c7 Remote Sensing, Vol 6, Iss 5, Pp 4582-4599 (2014) airborne laser scanning classification forest-tundra ecotone Science Q article 2014 ftdoajarticles https://doi.org/10.3390/rs6054582 2022-12-30T20:33:57Z The vegetation in the forest-tundra ecotone zone is expected to be highly affected by climate change and requires effective monitoring techniques. Airborne laser scanning (ALS) has been proposed as a tool for the detection of small pioneer trees for such vast areas using laser height and intensity data. The main objective of the present study was to assess a possible improvement in the performance of classifying tree and nontree laser echoes from high-density ALS data. The data were collected along a 1000 km long transect stretching from southern to northern Norway. Different geostatistical and statistical measures derived from laser height and intensity values were used to extent and potentially improve more simple models ignoring the spatial context. Generalised linear models (GLM) and support vector machines (SVM) were employed as classification methods. Total accuracies and Cohen’s kappa coefficients were calculated and compared to those of simpler models from a previous study. For both classification methods, all models revealed total accuracies similar to the results of the simpler models. Concerning classification performance, however, the comparison of the kappa coefficients indicated a significant improvement for some models both using GLM and SVM, with classification accuracies >94%. Article in Journal/Newspaper Northern Norway Tundra Directory of Open Access Journals: DOAJ Articles Norway Remote Sensing 6 5 4582 4599 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
airborne laser scanning classification forest-tundra ecotone Science Q |
spellingShingle |
airborne laser scanning classification forest-tundra ecotone Science Q Nadja Stumberg Marius Hauglin Ole Martin Bollandsås Terje Gobakken Erik Næsset Improving Classification of Airborne Laser Scanning Echoes in the Forest-Tundra Ecotone Using Geostatistical and Statistical Measures |
topic_facet |
airborne laser scanning classification forest-tundra ecotone Science Q |
description |
The vegetation in the forest-tundra ecotone zone is expected to be highly affected by climate change and requires effective monitoring techniques. Airborne laser scanning (ALS) has been proposed as a tool for the detection of small pioneer trees for such vast areas using laser height and intensity data. The main objective of the present study was to assess a possible improvement in the performance of classifying tree and nontree laser echoes from high-density ALS data. The data were collected along a 1000 km long transect stretching from southern to northern Norway. Different geostatistical and statistical measures derived from laser height and intensity values were used to extent and potentially improve more simple models ignoring the spatial context. Generalised linear models (GLM) and support vector machines (SVM) were employed as classification methods. Total accuracies and Cohen’s kappa coefficients were calculated and compared to those of simpler models from a previous study. For both classification methods, all models revealed total accuracies similar to the results of the simpler models. Concerning classification performance, however, the comparison of the kappa coefficients indicated a significant improvement for some models both using GLM and SVM, with classification accuracies >94%. |
format |
Article in Journal/Newspaper |
author |
Nadja Stumberg Marius Hauglin Ole Martin Bollandsås Terje Gobakken Erik Næsset |
author_facet |
Nadja Stumberg Marius Hauglin Ole Martin Bollandsås Terje Gobakken Erik Næsset |
author_sort |
Nadja Stumberg |
title |
Improving Classification of Airborne Laser Scanning Echoes in the Forest-Tundra Ecotone Using Geostatistical and Statistical Measures |
title_short |
Improving Classification of Airborne Laser Scanning Echoes in the Forest-Tundra Ecotone Using Geostatistical and Statistical Measures |
title_full |
Improving Classification of Airborne Laser Scanning Echoes in the Forest-Tundra Ecotone Using Geostatistical and Statistical Measures |
title_fullStr |
Improving Classification of Airborne Laser Scanning Echoes in the Forest-Tundra Ecotone Using Geostatistical and Statistical Measures |
title_full_unstemmed |
Improving Classification of Airborne Laser Scanning Echoes in the Forest-Tundra Ecotone Using Geostatistical and Statistical Measures |
title_sort |
improving classification of airborne laser scanning echoes in the forest-tundra ecotone using geostatistical and statistical measures |
publisher |
MDPI AG |
publishDate |
2014 |
url |
https://doi.org/10.3390/rs6054582 https://doaj.org/article/14f99f9560de4b8998273a789f3e83c7 |
geographic |
Norway |
geographic_facet |
Norway |
genre |
Northern Norway Tundra |
genre_facet |
Northern Norway Tundra |
op_source |
Remote Sensing, Vol 6, Iss 5, Pp 4582-4599 (2014) |
op_relation |
http://www.mdpi.com/2072-4292/6/5/4582 https://doaj.org/toc/2072-4292 2072-4292 doi:10.3390/rs6054582 https://doaj.org/article/14f99f9560de4b8998273a789f3e83c7 |
op_doi |
https://doi.org/10.3390/rs6054582 |
container_title |
Remote Sensing |
container_volume |
6 |
container_issue |
5 |
container_start_page |
4582 |
op_container_end_page |
4599 |
_version_ |
1766145591710056448 |