The value of hyperspectral UAV imagery in characterizing tundra vegetation
The fine-scale spatial heterogeneity of low-growth Arctic tundra landscapes necessitates the use of high-spatial-resolution remote sensing data for accurate detection of vegetation patterns. While multispectral satellite and aerial imaging, including the use of uncrewed aerial vehicles (UAVs), are c...
Published in: | Remote Sensing of Environment |
---|---|
Main Authors: | , , , , , , , , , |
Other Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Elsevier
|
Subjects: | |
Online Access: | https://jukuri.luke.fi/handle/10024/554950 https://doi.org/10.1016/j.rse.2024.114175 |
id |
ftluke:oai:jukuri.luke.fi:10024/554950 |
---|---|
record_format |
openpolar |
spelling |
ftluke:oai:jukuri.luke.fi:10024/554950 2024-06-09T07:44:25+00:00 The value of hyperspectral UAV imagery in characterizing tundra vegetation Putkiranta, Pauli Räsänen, Aleksi Korpelainen, Pasi Erlandsson, Rasmus Kolari, Tiina M. H. Pang, Yuwen Villoslada, Miguel Wolff, Franziska Kumpula, Timo Virtanen, Tarmo orcid:0000-0002-3629-1837 4100311110 Luonnonvarakeskus true https://jukuri.luke.fi/handle/10024/554950 https://doi.org/10.1016/j.rse.2024.114175 en eng Elsevier Remote sensing of environment 10.1016/j.rse.2024.114175 0034-4257 1879-0704 308 114175 https://jukuri.luke.fi/handle/10024/554950 URN:NBN:fi-fe2024051530827 https://doi.org/10.1016/j.rse.2024.114175 CC BY 4.0 tundra plant communities multispectral imaging hyperspectral imaging drone biodiversity publication fi=A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä|sv=A1 Originalartikel i en vetenskaplig tidskrift|en=A1 Journal article (refereed), original research| fi=Publisher's version|sv=Publisher's version|en=Publisher's version| ftluke https://doi.org/10.1016/j.rse.2024.114175 2024-05-15T23:38:57Z The fine-scale spatial heterogeneity of low-growth Arctic tundra landscapes necessitates the use of high-spatial-resolution remote sensing data for accurate detection of vegetation patterns. While multispectral satellite and aerial imaging, including the use of uncrewed aerial vehicles (UAVs), are common approaches, hyperspectral UAV imaging has not been thoroughly explored in these ecosystems. Here, we assess the added value of hyperspectral UAV imaging relative to multispectral UAV imaging in modelling plant communities in low-growth oroarctic tundra heaths in Saariselkä, northern Finland. We compare three different spectral compositions: 4-channel broadband aerial images, 5-channel broadband UAV images and 112-channel narrowband UAV images. Based on field vegetation plot data, we estimate vascular plant aboveground biomass, leaf area index, species richness, Shannon's diversity index, and community composition. We use spectral and topographic information to compile 12 explanatory datasets for random forest regression and classification. For aboveground biomass and leaf area index, the highest R2 values were 0.60 and 0.65, respectively, and broadband variables were most important. In the best models for biodiversity metrics species richness and Shannon's index R2 values were 0.53 and 0.46, respectively, with hyperspectral, topographic, and multispectral variables having high importance. For 4 floristically determined community clusters, both random forest classifications and fuzzy cluster membership regressions were conducted. Overall accuracy (OA) for classification was 0.67 at best, while cluster membership was estimated with an R2 of 0.29–0.53. Variable importance was heavily dependent on community composition, but topographic, multispectral, and hyperspectral data were all selected for these community composition models. Hyperspectral models generally outperformed multispectral ones when topographic data were excluded. With topographic data, this difference was diminished, and performance improvements from ... Article in Journal/Newspaper Arctic Northern Finland Tundra Natural Resources Institute Finland: Jukuri Arctic Remote Sensing of Environment 308 114175 |
institution |
Open Polar |
collection |
Natural Resources Institute Finland: Jukuri |
op_collection_id |
ftluke |
language |
English |
topic |
tundra plant communities multispectral imaging hyperspectral imaging drone biodiversity |
spellingShingle |
tundra plant communities multispectral imaging hyperspectral imaging drone biodiversity Putkiranta, Pauli Räsänen, Aleksi Korpelainen, Pasi Erlandsson, Rasmus Kolari, Tiina M. H. Pang, Yuwen Villoslada, Miguel Wolff, Franziska Kumpula, Timo Virtanen, Tarmo The value of hyperspectral UAV imagery in characterizing tundra vegetation |
topic_facet |
tundra plant communities multispectral imaging hyperspectral imaging drone biodiversity |
description |
The fine-scale spatial heterogeneity of low-growth Arctic tundra landscapes necessitates the use of high-spatial-resolution remote sensing data for accurate detection of vegetation patterns. While multispectral satellite and aerial imaging, including the use of uncrewed aerial vehicles (UAVs), are common approaches, hyperspectral UAV imaging has not been thoroughly explored in these ecosystems. Here, we assess the added value of hyperspectral UAV imaging relative to multispectral UAV imaging in modelling plant communities in low-growth oroarctic tundra heaths in Saariselkä, northern Finland. We compare three different spectral compositions: 4-channel broadband aerial images, 5-channel broadband UAV images and 112-channel narrowband UAV images. Based on field vegetation plot data, we estimate vascular plant aboveground biomass, leaf area index, species richness, Shannon's diversity index, and community composition. We use spectral and topographic information to compile 12 explanatory datasets for random forest regression and classification. For aboveground biomass and leaf area index, the highest R2 values were 0.60 and 0.65, respectively, and broadband variables were most important. In the best models for biodiversity metrics species richness and Shannon's index R2 values were 0.53 and 0.46, respectively, with hyperspectral, topographic, and multispectral variables having high importance. For 4 floristically determined community clusters, both random forest classifications and fuzzy cluster membership regressions were conducted. Overall accuracy (OA) for classification was 0.67 at best, while cluster membership was estimated with an R2 of 0.29–0.53. Variable importance was heavily dependent on community composition, but topographic, multispectral, and hyperspectral data were all selected for these community composition models. Hyperspectral models generally outperformed multispectral ones when topographic data were excluded. With topographic data, this difference was diminished, and performance improvements from ... |
author2 |
orcid:0000-0002-3629-1837 4100311110 Luonnonvarakeskus |
format |
Article in Journal/Newspaper |
author |
Putkiranta, Pauli Räsänen, Aleksi Korpelainen, Pasi Erlandsson, Rasmus Kolari, Tiina M. H. Pang, Yuwen Villoslada, Miguel Wolff, Franziska Kumpula, Timo Virtanen, Tarmo |
author_facet |
Putkiranta, Pauli Räsänen, Aleksi Korpelainen, Pasi Erlandsson, Rasmus Kolari, Tiina M. H. Pang, Yuwen Villoslada, Miguel Wolff, Franziska Kumpula, Timo Virtanen, Tarmo |
author_sort |
Putkiranta, Pauli |
title |
The value of hyperspectral UAV imagery in characterizing tundra vegetation |
title_short |
The value of hyperspectral UAV imagery in characterizing tundra vegetation |
title_full |
The value of hyperspectral UAV imagery in characterizing tundra vegetation |
title_fullStr |
The value of hyperspectral UAV imagery in characterizing tundra vegetation |
title_full_unstemmed |
The value of hyperspectral UAV imagery in characterizing tundra vegetation |
title_sort |
value of hyperspectral uav imagery in characterizing tundra vegetation |
publisher |
Elsevier |
url |
https://jukuri.luke.fi/handle/10024/554950 https://doi.org/10.1016/j.rse.2024.114175 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic Northern Finland Tundra |
genre_facet |
Arctic Northern Finland Tundra |
op_relation |
Remote sensing of environment 10.1016/j.rse.2024.114175 0034-4257 1879-0704 308 114175 https://jukuri.luke.fi/handle/10024/554950 URN:NBN:fi-fe2024051530827 https://doi.org/10.1016/j.rse.2024.114175 |
op_rights |
CC BY 4.0 |
op_doi |
https://doi.org/10.1016/j.rse.2024.114175 |
container_title |
Remote Sensing of Environment |
container_volume |
308 |
container_start_page |
114175 |
_version_ |
1801373152333266944 |