A Comparison of Spectral Angle Mapper and Artificial Neural Network Classifiers Combined with Landsat TM Imagery Analysis for Obtaining Burnt Area Mapping
Satellite remote sensing, with its unique synoptic coverage capabilities, can provide accurate and immediately valuable information on fire analysis and post-fire assessment, including estimation of burnt areas. In this study the potential for burnt area mapping of the combined use of Artificial Neu...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2010-03-01
|
Series: | Sensors |
Subjects: | |
Online Access: | http://www.mdpi.com/1424-8220/10/3/1967/ |
_version_ | 1798002821432344576 |
---|---|
author | Marko Scholze George Karantounias Gavriil Xanthopoulos Krishna Prasad Vadrevu George P. Petropoulos |
author_facet | Marko Scholze George Karantounias Gavriil Xanthopoulos Krishna Prasad Vadrevu George P. Petropoulos |
author_sort | Marko Scholze |
collection | DOAJ |
description | Satellite remote sensing, with its unique synoptic coverage capabilities, can provide accurate and immediately valuable information on fire analysis and post-fire assessment, including estimation of burnt areas. In this study the potential for burnt area mapping of the combined use of Artificial Neural Network (ANN) and Spectral Angle Mapper (SAM) classifiers with Landsat TM satellite imagery was evaluated in a Mediterranean setting. As a case study one of the most catastrophic forest fires, which occurred near the capital of Greece during the summer of 2007, was used. The accuracy of the two algorithms in delineating the burnt area from the Landsat TM imagery, acquired shortly after the fire suppression, was determined by the classification accuracy results of the produced thematic maps. In addition, the derived burnt area estimates from the two classifiers were compared with independent estimates available for the study region, obtained from the analysis of higher spatial resolution satellite data. In terms of the overall classification accuracy, ANN outperformed (overall accuracy 90.29%, Kappa coefficient 0.878) the SAM classifier (overall accuracy 83.82%, Kappa coefficient 0.795). Total burnt area estimates from the two classifiers were found also to be in close agreement with the other available estimates for the study region, with a mean absolute percentage difference of ~1% for ANN and ~6.5% for SAM. The study demonstrates the potential of the examined here algorithms in detecting burnt areas in a typical Mediterranean setting. |
first_indexed | 2024-04-11T11:58:21Z |
format | Article |
id | doaj.art-424d7fcd6057464c91b4611d943649b7 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-04-11T11:58:21Z |
publishDate | 2010-03-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-424d7fcd6057464c91b4611d943649b72022-12-22T04:24:58ZengMDPI AGSensors1424-82202010-03-011031967198510.3390/s100301967A Comparison of Spectral Angle Mapper and Artificial Neural Network Classifiers Combined with Landsat TM Imagery Analysis for Obtaining Burnt Area MappingMarko ScholzeGeorge KarantouniasGavriil XanthopoulosKrishna Prasad VadrevuGeorge P. PetropoulosSatellite remote sensing, with its unique synoptic coverage capabilities, can provide accurate and immediately valuable information on fire analysis and post-fire assessment, including estimation of burnt areas. In this study the potential for burnt area mapping of the combined use of Artificial Neural Network (ANN) and Spectral Angle Mapper (SAM) classifiers with Landsat TM satellite imagery was evaluated in a Mediterranean setting. As a case study one of the most catastrophic forest fires, which occurred near the capital of Greece during the summer of 2007, was used. The accuracy of the two algorithms in delineating the burnt area from the Landsat TM imagery, acquired shortly after the fire suppression, was determined by the classification accuracy results of the produced thematic maps. In addition, the derived burnt area estimates from the two classifiers were compared with independent estimates available for the study region, obtained from the analysis of higher spatial resolution satellite data. In terms of the overall classification accuracy, ANN outperformed (overall accuracy 90.29%, Kappa coefficient 0.878) the SAM classifier (overall accuracy 83.82%, Kappa coefficient 0.795). Total burnt area estimates from the two classifiers were found also to be in close agreement with the other available estimates for the study region, with a mean absolute percentage difference of ~1% for ANN and ~6.5% for SAM. The study demonstrates the potential of the examined here algorithms in detecting burnt areas in a typical Mediterranean setting.http://www.mdpi.com/1424-8220/10/3/1967/Landsat TMburnt area mappingArtificial Neural NetworksSpectral Angle MapperGreek forest fires 2007 |
spellingShingle | Marko Scholze George Karantounias Gavriil Xanthopoulos Krishna Prasad Vadrevu George P. Petropoulos A Comparison of Spectral Angle Mapper and Artificial Neural Network Classifiers Combined with Landsat TM Imagery Analysis for Obtaining Burnt Area Mapping Sensors Landsat TM burnt area mapping Artificial Neural Networks Spectral Angle Mapper Greek forest fires 2007 |
title | A Comparison of Spectral Angle Mapper and Artificial Neural Network Classifiers Combined with Landsat TM Imagery Analysis for Obtaining Burnt Area Mapping |
title_full | A Comparison of Spectral Angle Mapper and Artificial Neural Network Classifiers Combined with Landsat TM Imagery Analysis for Obtaining Burnt Area Mapping |
title_fullStr | A Comparison of Spectral Angle Mapper and Artificial Neural Network Classifiers Combined with Landsat TM Imagery Analysis for Obtaining Burnt Area Mapping |
title_full_unstemmed | A Comparison of Spectral Angle Mapper and Artificial Neural Network Classifiers Combined with Landsat TM Imagery Analysis for Obtaining Burnt Area Mapping |
title_short | A Comparison of Spectral Angle Mapper and Artificial Neural Network Classifiers Combined with Landsat TM Imagery Analysis for Obtaining Burnt Area Mapping |
title_sort | comparison of spectral angle mapper and artificial neural network classifiers combined with landsat tm imagery analysis for obtaining burnt area mapping |
topic | Landsat TM burnt area mapping Artificial Neural Networks Spectral Angle Mapper Greek forest fires 2007 |
url | http://www.mdpi.com/1424-8220/10/3/1967/ |
work_keys_str_mv | AT markoscholze acomparisonofspectralanglemapperandartificialneuralnetworkclassifierscombinedwithlandsattmimageryanalysisforobtainingburntareamapping AT georgekarantounias acomparisonofspectralanglemapperandartificialneuralnetworkclassifierscombinedwithlandsattmimageryanalysisforobtainingburntareamapping AT gavriilxanthopoulos acomparisonofspectralanglemapperandartificialneuralnetworkclassifierscombinedwithlandsattmimageryanalysisforobtainingburntareamapping AT krishnaprasadvadrevu acomparisonofspectralanglemapperandartificialneuralnetworkclassifierscombinedwithlandsattmimageryanalysisforobtainingburntareamapping AT georgeppetropoulos acomparisonofspectralanglemapperandartificialneuralnetworkclassifierscombinedwithlandsattmimageryanalysisforobtainingburntareamapping AT markoscholze comparisonofspectralanglemapperandartificialneuralnetworkclassifierscombinedwithlandsattmimageryanalysisforobtainingburntareamapping AT georgekarantounias comparisonofspectralanglemapperandartificialneuralnetworkclassifierscombinedwithlandsattmimageryanalysisforobtainingburntareamapping AT gavriilxanthopoulos comparisonofspectralanglemapperandartificialneuralnetworkclassifierscombinedwithlandsattmimageryanalysisforobtainingburntareamapping AT krishnaprasadvadrevu comparisonofspectralanglemapperandartificialneuralnetworkclassifierscombinedwithlandsattmimageryanalysisforobtainingburntareamapping AT georgeppetropoulos comparisonofspectralanglemapperandartificialneuralnetworkclassifierscombinedwithlandsattmimageryanalysisforobtainingburntareamapping |