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

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 Neu...

Full description

Bibliographic Details
Main Authors: Premysl Stych, Barbora Jerabkova, Josef Lastovicka, Martin Riedl, Daniel Paluba
Format: Article
Language:English
Published: MDPI AG 2019-09-01
Series:Geosciences
Subjects:
neural network
support vector machine
Landsat 8
WorldView-2
Czechia
forest disturbances
Online Access:https://www.mdpi.com/2076-3263/9/9/396
id doaj-0ccfe269df084a229c20a2c44364a0d6
record_format Article
spelling doaj-0ccfe269df084a229c20a2c44364a0d62020-11-25T02:13:36ZengMDPI AGGeosciences2076-32632019-09-019939610.3390/geosciences9090396geosciences9090396A 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 MountainsPremysl Stych0Barbora Jerabkova1Josef Lastovicka2Martin Riedl3Daniel Paluba4Department of Applied Geoinformatics and Cartography, Faculty of Science, Charles University, Albertov 6, 128 43 Prague 2, Czech RepublicDepartment of Applied Geoinformatics and Cartography, Faculty of Science, Charles University, Albertov 6, 128 43 Prague 2, Czech RepublicDepartment of Applied Geoinformatics and Cartography, Faculty of Science, Charles University, Albertov 6, 128 43 Prague 2, Czech RepublicDepartment of Applied Geoinformatics and Cartography, Faculty of Science, Charles University, Albertov 6, 128 43 Prague 2, Czech RepublicDepartment of Applied Geoinformatics and Cartography, Faculty of Science, Charles University, Albertov 6, 128 43 Prague 2, Czech RepublicThe 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.https://www.mdpi.com/2076-3263/9/9/396neural networksupport vector machineLandsat 8WorldView-2Czechiaforest disturbances
collection DOAJ
language English
format Article
sources DOAJ
author Premysl Stych
Barbora Jerabkova
Josef Lastovicka
Martin Riedl
Daniel Paluba
spellingShingle Premysl Stych
Barbora Jerabkova
Josef Lastovicka
Martin Riedl
Daniel Paluba
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
Geosciences
neural network
support vector machine
Landsat 8
WorldView-2
Czechia
forest disturbances
author_facet Premysl Stych
Barbora Jerabkova
Josef Lastovicka
Martin Riedl
Daniel Paluba
author_sort Premysl Stych
title 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
title_short 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
title_full 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
title_fullStr 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
title_full_unstemmed 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
title_sort 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
publisher MDPI AG
series Geosciences
issn 2076-3263
publishDate 2019-09-01
description 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.
topic neural network
support vector machine
Landsat 8
WorldView-2
Czechia
forest disturbances
url https://www.mdpi.com/2076-3263/9/9/396
work_keys_str_mv AT premyslstych acomparisonofworldview2andlandsat8imagesfortheclassificationofforestsaffectedbybarkbeetleoutbreaksusingasupportvectormachineandaneuralnetworkacasestudyinthesumavamountains
AT barborajerabkova acomparisonofworldview2andlandsat8imagesfortheclassificationofforestsaffectedbybarkbeetleoutbreaksusingasupportvectormachineandaneuralnetworkacasestudyinthesumavamountains
AT joseflastovicka acomparisonofworldview2andlandsat8imagesfortheclassificationofforestsaffectedbybarkbeetleoutbreaksusingasupportvectormachineandaneuralnetworkacasestudyinthesumavamountains
AT martinriedl acomparisonofworldview2andlandsat8imagesfortheclassificationofforestsaffectedbybarkbeetleoutbreaksusingasupportvectormachineandaneuralnetworkacasestudyinthesumavamountains
AT danielpaluba acomparisonofworldview2andlandsat8imagesfortheclassificationofforestsaffectedbybarkbeetleoutbreaksusingasupportvectormachineandaneuralnetworkacasestudyinthesumavamountains
AT premyslstych comparisonofworldview2andlandsat8imagesfortheclassificationofforestsaffectedbybarkbeetleoutbreaksusingasupportvectormachineandaneuralnetworkacasestudyinthesumavamountains
AT barborajerabkova comparisonofworldview2andlandsat8imagesfortheclassificationofforestsaffectedbybarkbeetleoutbreaksusingasupportvectormachineandaneuralnetworkacasestudyinthesumavamountains
AT joseflastovicka comparisonofworldview2andlandsat8imagesfortheclassificationofforestsaffectedbybarkbeetleoutbreaksusingasupportvectormachineandaneuralnetworkacasestudyinthesumavamountains
AT martinriedl comparisonofworldview2andlandsat8imagesfortheclassificationofforestsaffectedbybarkbeetleoutbreaksusingasupportvectormachineandaneuralnetworkacasestudyinthesumavamountains
AT danielpaluba comparisonofworldview2andlandsat8imagesfortheclassificationofforestsaffectedbybarkbeetleoutbreaksusingasupportvectormachineandaneuralnetworkacasestudyinthesumavamountains
_version_ 1724904165038096384

Similar Items