Object-based extraction of bark beetle (<i>Ips typographus</i> L.) infestations using multi-date LANDSAT and SPOT satellite imagery

Latifi, Hooman; Fassnacht, Fabian Ewald; Schumann, Bastian; Dech, Stefan

doi:10.1177/0309133314550670

Cited by 31 publications

(18 citation statements)

References 53 publications

(76 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As prevention is the most effective defence against bark beetle, it is necessary to focus on the deceleration of its spread; however, the spatial and temporal dynamics of the pest's disturbances are not fully understood yet [11,12]. For the measures to be successful, the earliest possible detection of infested trees is needed [13]. An infested tree starts to evince visual changes as well as changes in spectral characteristics as soon as a few weeks after infestation [14].…”

Section: Introductionmentioning

confidence: 99%

“…The satellite-borne multispectral imagery [11][12][13], hyperspectral imagery [4,5,18,19], airborne LiDAR [7,20], or a combination of those have been applied to study bark beetle across large extents. On the other hand, the close-range RS techniques (e.g., drones) may be used for precise detection of infested trees at a very detailed scale [4,[21][22][23][24].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The Use of UAV Mounted Sensors for Precise Detection of Bark Beetle Infestation

et al. 2019

View full text Add to dashboard Cite

The bark beetle (Ips typographus) disturbance represents serious environmental and economic issue and presents a major challenge for forest management. A timely detection of bark beetle infestation is therefore necessary to reduce losses. Besides wood production, a bark beetle outbreak affects the forest ecosystem in many other ways including the water cycle, nutrient cycle, or carbon fixation. On that account, (not just) European temperate coniferous forests may become endangered ecosystems. Our study was performed in the unmanaged zone of the Krkonoše Mountains National Park in the northern part of the Czech Republic where the natural spreading of bark beetle is slow and, therefore, allow us to continuously monitor the infested trees that are, in contrast to managed forests, not being removed. The aim of this work is to evaluate possibilities of unmanned aerial vehicle (UAV)-mounted low-cost RGB and modified near-infrared sensors for detection of different stages of infested trees at the individual level, using a retrospective time series for recognition of still green but already infested trees (so-called green attack). A mosaic was created from the UAV imagery, radiometrically calibrated for surface reflectance, and five vegetation indices were calculated; the reference data about the stage of bark beetle infestation was obtained through a combination of field survey and visual interpretation of an orthomosaic. The differences of vegetation indices between infested and healthy trees over four time points were statistically evaluated and classified using the Maximum Likelihood classifier. Achieved results confirm our assumptions that it is possible to use a low-cost UAV-based sensor for detection of various stages of bark beetle infestation across seasons; with increasing time after infection, distinguishing infested trees from healthy ones grows easier. The best performance was achieved by the Greenness Index with overall accuracy of 78%–96% across the time periods. The performance of the indices based on near-infrared band was lower.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

The Use of UAV Mounted Sensors for Precise Detection of Bark Beetle Infestation

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Six types of textural information were obtained from the gray level co-occurrence matrix (GLCM) [36]. We did not use geometry information in the object-based method because Hooman Latifi et al [37] revealed that spatial metrics did not play a major role in characterizing the infested stands. CART could be used to filter features according to the importance ranking in regression [38,39].…”

Section: Extraction Of Tree Mortality At a Single-tree Scalementioning

confidence: 99%

Combining GF-2 and Sentinel-2 Images to Detect Tree Mortality Caused by Red Turpentine Beetle during the Early Outbreak Stage in North China

Zhan

et al. 2020

Forests

View full text Add to dashboard Cite

In recent years, the red turpentine beetle (RTB) (Dendroctonus valens LeConte) has invaded the northern regions of China. Due to the short invasion time, the outbreak of tree mortality corresponded to a low level of damage. Important information about tree mortality, provided by remote sensing at both single-tree and forest stand scale, is needed in forest management at the early stages of outbreak. In order to detect RTB-induced tree mortality at a single-tree scale, we evaluated the classification accuracies of Gaofen-2 (GF2) imagery at different spatial resolutions (1 and 4 m) using a pixel-based method. We also simultaneously applied an object-based method to 1 m pan-sharpened images. We used Sentinel-2 (S2) imagery with different resolutions (10 and 20 m) to detect RTB-induced tree mortality and compared their classification accuracies at a larger scale—the stand scale. Three kinds of machine learning algorithms—the classification and regression tree (CART), the random forest (RF), and the support vector machine (SVM)—were applied and compared in this study. The results showed that 1 m resolution GF2 images had the highest classification accuracy using the pixel-based method and SVM algorithm (overall accuracy = 77.7%). We found that the classification of three degrees of damage percentage within the S2 pixel (0%, <15%, and 15% < x < 50%) was not successful at a forest stand scale. However, 10 m resolution S2 images could acquire effective binary classification (<15%: overall accuracy = 74.9%; 15% < x < 50%: overall accuracy = 81.0%). Our results indicated that identifying tree mortality caused by RTB at a single-tree and forest stand scale was accomplished with the combination of GF2 and S2 images. Our results are very useful for the future exploration of the patterns of spatial and temporal changes in insect pest transmission at different spatial scales.

show abstract

“…In recent years, the area of state-of-the-art classifiers, such as Support Vector Machines (SVMs), Neural Networks (NNs) or Object-Based Classification (OBIA), has been intensively developed in connection with the development and availability of data with better spatial and spectral resolutions. Latifi et al [25] used OBIA to classify Landsat images for an 11-year period in the Bavarian National Park to map the related forest mortality classes. The SVM method was successfully used by Hart and Veblen [26], who classified a bark beetle forest from satellite and aerial photographs.…”

Section: Introductionmentioning

confidence: 99%

A Comparison of WorldView-2 and Landsat 8 Images for the Classification of Forests Affected by Bark Beetle Outbreaks Using a Support Vector Machine and a Neural Network: A Case Study in the Sumava Mountains

et al. 2019

View full text Add to dashboard Cite

The objective of this paper is to assess WorldView-2 (WV2) and Landsat OLI (L8) images in the detection of bark beetle outbreaks in the Sumava National Park. WV2 and L8 images were used for the classification of forests infected by bark beetle outbreaks using a Support Vector Machine (SVM) and a Neural Network (NN). After evaluating all the available results, the SVM can be considered the best method used in this study. This classifier achieved the highest overall accuracy and Kappa index for both classified images. In the cases of WV2 and L8, total overall accuracies of 86% and 71% and Kappa indices of 0.84 and 0.66 were achieved with SVM, respectively. The NN algorithm using WV2 also produced very promising results, with over 80% overall accuracy and a Kappa index of 0.79. The methods used in this study may be inspirational for testing other types of satellite data (e.g., Sentinel-2) or other classification algorithms such as the Random Forest Classifier.

show abstract

Object-based extraction of bark beetle (Ips typographus L.) infestations using multi-date LANDSAT and SPOT satellite imagery

Cited by 31 publications

References 53 publications

The Use of UAV Mounted Sensors for Precise Detection of Bark Beetle Infestation

The Use of UAV Mounted Sensors for Precise Detection of Bark Beetle Infestation

Combining GF-2 and Sentinel-2 Images to Detect Tree Mortality Caused by Red Turpentine Beetle during the Early Outbreak Stage in North China

A Comparison of WorldView-2 and Landsat 8 Images for the Classification of Forests Affected by Bark Beetle Outbreaks Using a Support Vector Machine and a Neural Network: A Case Study in the Sumava Mountains

Contact Info

Product

Resources

About