Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Combining Sentinel-2 Data and Risk Maps to Detect Trees Predisposed to and Attacked by European Spruce Bark Beetle : Remote Sensing

Olsson, Per-Ola LU ; Zhao, Pengxiang LU ; Müller, Mitro LU orcid ; Mansourian, Ali LU orcid and Ardö, Jonas LU orcid (2024) In Remote Sensing 16(22).
Abstract
The European spruce bark beetle is a major disturbance agent in Norway spruce forests in Europe, and with a changing climate it is predicted that damage will increase. To prevent the bark beetle population buildup, and to limit further spread during outbreaks, it is crucial to detect attacked trees early. In this study, we utilize Sentinel-2 data in combination with a risk map, created from geodata and forestry data, to detect trees predisposed to and attacked by the European spruce bark beetle. Random forest models were trained over two tiles (90 × 90 km) in southern Sweden for all dates with a sufficient number of cloud-free Sentinel-2 pixels during the period May–September in 2017 and 2018. The pixels were classified into attacked and... (More)
The European spruce bark beetle is a major disturbance agent in Norway spruce forests in Europe, and with a changing climate it is predicted that damage will increase. To prevent the bark beetle population buildup, and to limit further spread during outbreaks, it is crucial to detect attacked trees early. In this study, we utilize Sentinel-2 data in combination with a risk map, created from geodata and forestry data, to detect trees predisposed to and attacked by the European spruce bark beetle. Random forest models were trained over two tiles (90 × 90 km) in southern Sweden for all dates with a sufficient number of cloud-free Sentinel-2 pixels during the period May–September in 2017 and 2018. The pixels were classified into attacked and healthy to study how detection accuracy changed with time after bark beetle swarming and to find which Sentinel-2 bands are more important for detecting bark beetle attacked trees. Random forest models were trained with (1) single-date data, (2) temporal features (1-year difference), (3) single-date and temporal features combined, and (4) Sentinel-2 data and a risk map combined. We also included a spatial variability metric. The results show that detection accuracy was high already before the trees were attacked in May 2018, indicating that the Sentinel-2 data detect predisposed trees and that the early signs of attack are low for trees at high risk of being attacked. For single-date models, the accuracy ranged from 63 to 79% and 84 to 94% for the two tiles. For temporal features, accuracy ranged from 65 to 81% and 81 to 92%. When the single-date and temporal features were combined, the accuracy ranged from 70 to 84% and 90 to 96% for the two tiles, and with the risk map included, the accuracy ranged from 83 to 91% and 92 to 97%, showing that remote sensing data and geodata can be combined to increase detection accuracy. The differences in accuracy between the two tiles indicate that local differences can influence accuracy, suggesting that geographically weighted methods should be applied. For the single-date models, the SWIR, red-edge, and blue bands were generally more important, and the SWIR bands were more important after the attack, suggesting that they are most suitable for detecting the early signs of a bark beetle attack. For the temporal features, the SWIR and blue bands were more important, and for the variability metric, the green band was generally more important. (Less)
Please use this url to cite or link to this publication:
author
; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
European spruce bark beetle, Sentinel-2, predisposed tree detection
in
Remote Sensing
volume
16
issue
22
article number
4166
publisher
MDPI AG
external identifiers
  • scopus:85210258677
ISSN
2072-4292
DOI
10.3390/rs16224166
language
English
LU publication?
yes
id
da7812bd-54e6-48ad-8877-3bd51ac3bcea
date added to LUP
2024-11-23 16:28:45
date last changed
2025-04-04 14:37:18
@article{da7812bd-54e6-48ad-8877-3bd51ac3bcea,
  abstract     = {{The European spruce bark beetle is a major disturbance agent in Norway spruce forests in Europe, and with a changing climate it is predicted that damage will increase. To prevent the bark beetle population buildup, and to limit further spread during outbreaks, it is crucial to detect attacked trees early. In this study, we utilize Sentinel-2 data in combination with a risk map, created from geodata and forestry data, to detect trees predisposed to and attacked by the European spruce bark beetle. Random forest models were trained over two tiles (90 × 90 km) in southern Sweden for all dates with a sufficient number of cloud-free Sentinel-2 pixels during the period May–September in 2017 and 2018. The pixels were classified into attacked and healthy to study how detection accuracy changed with time after bark beetle swarming and to find which Sentinel-2 bands are more important for detecting bark beetle attacked trees. Random forest models were trained with (1) single-date data, (2) temporal features (1-year difference), (3) single-date and temporal features combined, and (4) Sentinel-2 data and a risk map combined. We also included a spatial variability metric. The results show that detection accuracy was high already before the trees were attacked in May 2018, indicating that the Sentinel-2 data detect predisposed trees and that the early signs of attack are low for trees at high risk of being attacked. For single-date models, the accuracy ranged from 63 to 79% and 84 to 94% for the two tiles. For temporal features, accuracy ranged from 65 to 81% and 81 to 92%. When the single-date and temporal features were combined, the accuracy ranged from 70 to 84% and 90 to 96% for the two tiles, and with the risk map included, the accuracy ranged from 83 to 91% and 92 to 97%, showing that remote sensing data and geodata can be combined to increase detection accuracy. The differences in accuracy between the two tiles indicate that local differences can influence accuracy, suggesting that geographically weighted methods should be applied. For the single-date models, the SWIR, red-edge, and blue bands were generally more important, and the SWIR bands were more important after the attack, suggesting that they are most suitable for detecting the early signs of a bark beetle attack. For the temporal features, the SWIR and blue bands were more important, and for the variability metric, the green band was generally more important.}},
  author       = {{Olsson, Per-Ola and Zhao, Pengxiang and Müller, Mitro and Mansourian, Ali and Ardö, Jonas}},
  issn         = {{2072-4292}},
  keywords     = {{European spruce bark beetle; Sentinel-2; predisposed tree detection}},
  language     = {{eng}},
  month        = {{11}},
  number       = {{22}},
  publisher    = {{MDPI AG}},
  series       = {{Remote Sensing}},
  title        = {{Combining Sentinel-2 Data and Risk Maps to Detect Trees Predisposed to and Attacked by European Spruce Bark Beetle : Remote Sensing}},
  url          = {{http://dx.doi.org/10.3390/rs16224166}},
  doi          = {{10.3390/rs16224166}},
  volume       = {{16}},
  year         = {{2024}},
}