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

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.

[1]  Yuzhong Shen,et al.  Fusion of landsat and worldview images , 2019, Defense + Commercial Sensing.

[2]  Thomas T. Veblen,et al.  Detection of spruce beetle-induced tree mortality using high- and medium-resolution remotely sensed imagery , 2015 .

[3]  Shogoro Fujiki,et al.  Estimation of the stand ages of tropical secondary forests after shifting cultivation based on the combination of WorldView-2 and time-series Landsat images , 2016 .

[4]  M. Nilsson,et al.  Combining national forest inventory field plots and remote sensing data for forest databases , 2008 .

[5]  Joanna Adamczyk,et al.  Red-edge vegetation indices for detecting and assessing disturbances in Norway spruce dominated mountain forests , 2015, Int. J. Appl. Earth Obs. Geoinformation.

[6]  Roger Wheate,et al.  Detection of red attack stage mountain pine beetle infestation with high spatial resolution satellite imagery , 2005 .

[7]  Lucie Hromádková.  Classification of meadow vegetation in the Krkonoše Mts. using aerial hyperspectral data and support vector machines classifier , 2015 .

[8]  Martin Hais,et al.  Landsat Imagery Spectral Trajectories - Important Variables for Spatially Predicting the Risks of Bark Beetle Disturbance , 2016, Remote. Sens..

[9]  P. Hostert,et al.  Post-socialist forest disturbance in the Carpathian border region of Poland, Slovakia, and Ukraine. , 2007, Ecological applications : a publication of the Ecological Society of America.

[10]  Beat Wermelinger,et al.  Ecology and management of the spruce bark beetle Ips typographus—a review of recent research , 2004 .

[11]  J. Hicke,et al.  Evaluating the potential of multispectral imagery to map multiple stages of tree mortality , 2011 .

[12]  Jakub Langhammer,et al.  Comparison of two types of forest disturbance using multitemporal Landsat TM/ETM+ imagery and field vegetation data. , 2009 .

[13]  Kenneth Grogan,et al.  Mapping Clearances in Tropical Dry Forests Using Breakpoints, Trend, and Seasonal Components from MODIS Time Series: Does Forest Type Matter? , 2016, Remote. Sens..

[14]  Guobin Zhu,et al.  Classification using ASTER data and SVM algorithms;: The case study of Beer Sheva, Israel , 2002 .

[15]  Christine Estreguil,et al.  Forest cover changes in the northern Carpathians in the 20th century: a slow transition , 2007 .

[16]  Veronika Oubrechtová.  Využití umělých neuronových sítí v klasifikaci land cover , 2012 .

[17]  C. Woodcock,et al.  Continuous change detection and classification of land cover using all available Landsat data , 2014 .

[18]  Vladimir Vapnik,et al.  The Nature of Statistical Learning , 1995 .

[19]  Jesse A. Logan,et al.  Mapping whitebark pine mortality caused by a mountain pine beetle outbreak with high spatial resolution satellite imagery , 2009 .

[20]  P. Dennison,et al.  Assessing canopy mortality during a mountain pine beetle outbreak using GeoEye-1 high spatial resolution satellite data. , 2010 .

[21]  H. Jones,et al.  Remote Sensing of Vegetation: Principles, Techniques, and Applications , 2010 .

[22]  M. Canty.  Image Analysis, Classification, and Change Detection in Remote Sensing , 2006 .

[23]  P. Hostert,et al.  Forest disturbances, forest recovery, and changes in forest types across the Carpathian ecoregion from 1985 to 2010 based on Landsat image composites , 2014 .

[24]  Gidudu Anthony,et al.  Classification of Images Using Support Vector Machines , 2007, 0709.3967.

[25]  J. R. Jensen.  Remote Sensing of the Environment: An Earth Resource Perspective , 2000 .

[26]  Clement Atzberger,et al.  Early Detection of Bark Beetle Infestation in Norway Spruce ( Picea abies , L.) using WorldView-2 Data Frühzeitige Erkennung von Borkenkä ferbefall an Fichten mittels WorldView-2 Satellitendaten , 2014 .

[27]  R. Justin DeRose,et al.  Combining dendrochronological data and the disturbance index to assess Engelmann spruce mortality caused by a spruce beetle outbreak in southern Utah, USA , 2011 .

[28]  Z. Lhotáková,et al.  Forest cover and disturbance changes, and their driving forces: A case study in the Ore Mountains, Czechia, heavily affected by anthropogenic acidic pollution in the second half of the 20th century , 2018, Environmental Research Letters.

[29]  V. Radeloff,et al.  The effect of protected areas on forest disturbance in the Carpathian Mountains 1985–2010 , 2017, Conservation biology : the journal of the Society for Conservation Biology.

[30]  Stefan Dech,et al.  Object-based extraction of bark beetle (Ips typographus L.) infestations using multi-date LANDSAT and SPOT satellite imagery , 2014 .

[31]  F. Zemek,et al.  Semi-natural Forested Landscape under a Bark Beetle Outbreak: A case study of the Bohemian Forest (Czech Republic) , 2003 .

[32]  R. Lucas,et al.  Detection of changes in semi-natural grasslands by cross correlation analysis with WorldView-2 images and new Landsat 8 data , 2016, Remote sensing of environment.