Skip to main content

LUP Student Papers

LUND UNIVERSITY LIBRARIES

Detecting bark beetle damage with Sentinel-2 multi-temporal data in Sweden

Yang, Shuo LU (2019) In Student thesis series INES NGEM01 20191
Dept of Physical Geography and Ecosystem Science
Abstract
The European spruce bark beetle is considered as one of the most destructive forest insects to Norway spruce trees in Europe. Climate change may increase the frequency and intensity of bark beetle outbreaks. It is therefore of vital importance to detect the bark beetle outbreaks and take it under control to prevent further damages. Remote sensing techniques may provide a cost-efficient solution to the detection of bark beetle outbreaks. In the past years, the detection of bark beetle outbreaks in Northern America has achieved success with the aid of the long time series of LANDSAT satellite images. Sentinel-2 provides satellite images of high spatial and temporal resolution which may be suitable for bark beetle detection in Europe.
The... (More)
The European spruce bark beetle is considered as one of the most destructive forest insects to Norway spruce trees in Europe. Climate change may increase the frequency and intensity of bark beetle outbreaks. It is therefore of vital importance to detect the bark beetle outbreaks and take it under control to prevent further damages. Remote sensing techniques may provide a cost-efficient solution to the detection of bark beetle outbreaks. In the past years, the detection of bark beetle outbreaks in Northern America has achieved success with the aid of the long time series of LANDSAT satellite images. Sentinel-2 provides satellite images of high spatial and temporal resolution which may be suitable for bark beetle detection in Europe.
The extreme drought and heat in the summer in 2018 favored the outbreaks of bark beetles in central and southern Sweden. In this project, detection of two stages (gray-attack and green-attack stage) of bark beetle outbreaks in southern and central Sweden was carried out separately with Sentinel-2 level 2A satellite multi-temporal images. In bark beetle gray-attack stage detection, the two most commonly used methods: maximum likelihood and random forest classification, were performed and compared on different combinations of Sentinel-2 10m resolution raw bands sensed in March-April and VIs derived from them. Maximum likelihood classification method with EVI and GNDVI gave the highest accuracy: total accuracy of 89% and Kappa of 0.74 (substantial agreement). Random forest classification method with all variables achieved the second best result: total accuracy of 85% and Kappa of 0.62 (substantial agreement). The two best methods were thereafter applied to two test areas in southern (test area 1) and central Sweden (test area 2). Random forest classification method with all variables obtained higher accuracy: total accuracy of 76% and Kappa of 0.53 (moderate agreement) in test area 1 and total accuracy of 71% and Kappa of 0.39 (fair agreement) in test area 2.
Based on detection result from the first part, random forest classification method was employed for bark beetle green-attack stage detection. A series of VIs derived from Sentinel-2 20m resolution bands sensed in the summer in 2018 were calculated and the importance of the VIs and raw bands were ranked with random forest algorithm. The first 13 or 14 most important variables were used for classification. Results show that water content related raw bands and VIs, red-edge VIs and the NIR band are the most sensitive variables to bark beetle green-attack. Bark beetle green-attack stage detection obtained high accuracy in study area 1: total accuracy of 88% and Kappa of 0.67 (substantial agreement) on July 26th and total accuracy of 84% and Kappa of 0.58 (moderate agreement) on October 12th. Relatively low accuracy were achieved in test area 1: total accuracy of 53% and Kappa of 0.03 (no or rarely any agreement). Moderate accuracy were achieved in test area 2: total accuracy of 64% and Kappa of 0.27 (fair agreement) on July 8th, and total accuracy of 71% and Kappa of 0.42 (moderate agreement) on July 31st. (Less)
Popular Abstract
The European spruce bark beetle is a huge disaster to the Norway spruce trees in Europe, affecting the ecosystem and social economy. Climate changes is bringing warmer temperatures and more frequent storms, which will possibly lead to more bark beetle outbreaks in the future. Traditional detection methods requires a lot of man power, money and time. Remote sensing techniques use images taken from far away, like satellites and drones. These images are cheap or even free to download and cover large areas. They have previously been used a lot in pest detection, and have been proven useful for bark beetle detection. Sentinel-2 provide free satellite data with high resolution and short revisiting time. The aim of this project is to test the... (More)
The European spruce bark beetle is a huge disaster to the Norway spruce trees in Europe, affecting the ecosystem and social economy. Climate changes is bringing warmer temperatures and more frequent storms, which will possibly lead to more bark beetle outbreaks in the future. Traditional detection methods requires a lot of man power, money and time. Remote sensing techniques use images taken from far away, like satellites and drones. These images are cheap or even free to download and cover large areas. They have previously been used a lot in pest detection, and have been proven useful for bark beetle detection. Sentinel-2 provide free satellite data with high resolution and short revisiting time. The aim of this project is to test the potential of using Sentinel-2 data to detect bark beetle outbreaks in Sweden.
There are three stages of the outbreak: green, red and gray-attack stage, which are related to the changes in the needles of the attacked tree. The green-attack stage is the most important stage, because the bark beetles are still inside the attacked tree. If we cut down the tree at this stage, we can stop bark beetles from damaging other trees. It is however the most difficult stage to detect with satellite images. Satellite remote sensing use the differences in the reflectance of the items on earth in different wavelengths (such as blue, green, red, NIR).
For gray-attack stage, we used the images with highest spatial resolution in March and April 2019, and achieved good results. Spatial resolution means the smallest item that can be recognized from the images. We compared the two most commonly used methods: maximum likelihood and random forest classification method based on different combinations of raw bands (blue, green, red and NIR) and VIs (Indices calculated from more than one band). Maximum likelihood method achieved better accuracy and agreement than random forest in the main study area, but random forest achieved better accuracy when applied to the test study areas. Using combinations of bands and VIs we got better results.
20m resolution bands were used in green-attack stage detection because they include bands (red-edge and SWIR) that are sensitive to water and pigments in the needles. The green-attack stage detection is more complex and the achieved results were not as good, but still reasonable. The importance of variables (all bands and VIs) were ranked using random forest method and the first 13-14 most important variables were considered. Result shows that the water content related and red-edge VIs and bands are the most important variables, with NIR band also being an important variable. The methods developed in green-attack stage is not accurate enough to use in forest management but results are in consistency with previous studies. The potential of Sentinel-2 to detect bark beetle green-attack stage outbreaks is confirmed. However further researches is required to develop a practical method to use. (Less)
Please use this url to cite or link to this publication:
author
Yang, Shuo LU
supervisor
organization
alternative title
Using Sentinel-2 satellite images to detect bark beetle outbreaks
course
NGEM01 20191
year
type
H2 - Master's Degree (Two Years)
subject
keywords
Physical Geography and Ecosystem Analysis, Remote Sensing, Bark Beetle, Insect Detection, Sentinel-2, Forest Health, Maximum Likelihood, Random Forest, Spectral Signature, Vegetation Indices
publication/series
Student thesis series INES
report number
490
language
English
id
8989179
date added to LUP
2019-07-03 11:36:28
date last changed
2019-07-03 11:36:28
@misc{8989179,
  abstract     = {{The European spruce bark beetle is considered as one of the most destructive forest insects to Norway spruce trees in Europe. Climate change may increase the frequency and intensity of bark beetle outbreaks. It is therefore of vital importance to detect the bark beetle outbreaks and take it under control to prevent further damages. Remote sensing techniques may provide a cost-efficient solution to the detection of bark beetle outbreaks. In the past years, the detection of bark beetle outbreaks in Northern America has achieved success with the aid of the long time series of LANDSAT satellite images. Sentinel-2 provides satellite images of high spatial and temporal resolution which may be suitable for bark beetle detection in Europe. 
The extreme drought and heat in the summer in 2018 favored the outbreaks of bark beetles in central and southern Sweden. In this project, detection of two stages (gray-attack and green-attack stage) of bark beetle outbreaks in southern and central Sweden was carried out separately with Sentinel-2 level 2A satellite multi-temporal images. In bark beetle gray-attack stage detection, the two most commonly used methods: maximum likelihood and random forest classification, were performed and compared on different combinations of Sentinel-2 10m resolution raw bands sensed in March-April and VIs derived from them. Maximum likelihood classification method with EVI and GNDVI gave the highest accuracy: total accuracy of 89% and Kappa of 0.74 (substantial agreement). Random forest classification method with all variables achieved the second best result: total accuracy of 85% and Kappa of 0.62 (substantial agreement). The two best methods were thereafter applied to two test areas in southern (test area 1) and central Sweden (test area 2). Random forest classification method with all variables obtained higher accuracy: total accuracy of 76% and Kappa of 0.53 (moderate agreement) in test area 1 and total accuracy of 71% and Kappa of 0.39 (fair agreement) in test area 2. 
Based on detection result from the first part, random forest classification method was employed for bark beetle green-attack stage detection. A series of VIs derived from Sentinel-2 20m resolution bands sensed in the summer in 2018 were calculated and the importance of the VIs and raw bands were ranked with random forest algorithm. The first 13 or 14 most important variables were used for classification. Results show that water content related raw bands and VIs, red-edge VIs and the NIR band are the most sensitive variables to bark beetle green-attack. Bark beetle green-attack stage detection obtained high accuracy in study area 1: total accuracy of 88% and Kappa of 0.67 (substantial agreement) on July 26th and total accuracy of 84% and Kappa of 0.58 (moderate agreement) on October 12th. Relatively low accuracy were achieved in test area 1: total accuracy of 53% and Kappa of 0.03 (no or rarely any agreement). Moderate accuracy were achieved in test area 2: total accuracy of 64% and Kappa of 0.27 (fair agreement) on July 8th, and total accuracy of 71% and Kappa of 0.42 (moderate agreement) on July 31st.}},
  author       = {{Yang, Shuo}},
  language     = {{eng}},
  note         = {{Student Paper}},
  series       = {{Student thesis series INES}},
  title        = {{Detecting bark beetle damage with Sentinel-2 multi-temporal data in Sweden}},
  year         = {{2019}},
}