Burned Area Detection Using Multi-Sensor SAR, Optical, and Thermal Data in Mediterranean Pine Forest

Saygin Abdikan; Caglar Bayik; Aliihsan Sekertekin; Filiz Bektas Balcik; Sadra Karimzadeh; Masashi Matsuoka; Fusun Balik Sanli

doi:10.3390/f13020347

Burned Area Detection Using Multi-Sensor SAR, Optical, and Thermal Data in Mediterranean Pine Forest

Saygin Abdikan, Caglar Bayik, Aliihsan Sekertekin^*, Filiz Bektas Balcik, Sadra Karimzadeh, Masashi Matsuoka, Fusun Balik Sanli

^*Bu çalışma için yazışmadan sorumlu yazar

Harita Mühendisliği Bölümü

Araştırma sonucu: Dergiye katkı › Makale › bilirkişi

30 Atıf (Scopus)

Özet

Burned area (BA) mapping of a forest after a fire is required for its management and the determination of the impacts on ecosystems. Different remote sensing sensors and their combinations have been used due to their individual limitations for accurate BA mapping. This study analyzes the contribution of different features derived from optical, thermal, and Synthetic Aperture Radar (SAR) images to extract BA information from the Turkish red pine (Pinus brutia Ten.) forest in a Mediterranean ecosystem. In addition to reflectance values of the optical images, Normalized Burn Ratio (NBR) and Land Surface Temperature (LST) data are produced from both Sentinel-2 and Landsat-8 data. The backscatter of C-band Sentinel-1 and L-band ALOS-2 SAR images and the coherence feature derived from the Interferometric SAR technique were also used. The pixel-based random forest image classification method is applied to classify the BA detection in 24 scenarios created using these features. The results show that the L-band data provided a better contribution than C-band data and the combination of features created from Landsat LST, NBR, and coherence of L-band ALOS-2 achieved the highest accuracy, with an overall accuracy of 96% and a Kappa coefficient of 92.62%.

Orijinal dil	İngilizce
Makale numarası	347
Dergi	Forests
Hacim	13
Basın numarası	2
DOI'lar	https://doi.org/10.3390/f13020347
Yayın durumu	Yayınlandı - Şub 2022

Bibliyografik not

Publisher Copyright:
© 2022 by the authors. Licensee MDPI, Basel, Switzerland.

Finansman

The authors would like to thank Japan Aerospace Exploration Agency (JAXA), which provided the ALOS-2 data through the JAXA working group and ALOS World 3D data. The authors would like to thank United States Geological Survey (USGS) and the National Aeronautics and Space Administration (NASA) for providing Landsat-8 images at free of cost. Besides, the authors would like to thank European Space Agency (ESA) for providing Sentinel-1 and Sentinel-2 images freely available.

Finansörler	Finansör numarası
National Aeronautics and Space Administration
U.S. Geological Survey
European Space Agency
Japan Aerospace Exploration Agency

Belgeye Erişim

10.3390/f13020347

Diğer Dosyalar ve Linkler

Link to publication in Scopus

Alıntı Yap

@article{0bfd58645a7a44528593b6e002ee7fe8,

title = "Burned Area Detection Using Multi-Sensor SAR, Optical, and Thermal Data in Mediterranean Pine Forest",

abstract = "Burned area (BA) mapping of a forest after a fire is required for its management and the determination of the impacts on ecosystems. Different remote sensing sensors and their combinations have been used due to their individual limitations for accurate BA mapping. This study analyzes the contribution of different features derived from optical, thermal, and Synthetic Aperture Radar (SAR) images to extract BA information from the Turkish red pine (Pinus brutia Ten.) forest in a Mediterranean ecosystem. In addition to reflectance values of the optical images, Normalized Burn Ratio (NBR) and Land Surface Temperature (LST) data are produced from both Sentinel-2 and Landsat-8 data. The backscatter of C-band Sentinel-1 and L-band ALOS-2 SAR images and the coherence feature derived from the Interferometric SAR technique were also used. The pixel-based random forest image classification method is applied to classify the BA detection in 24 scenarios created using these features. The results show that the L-band data provided a better contribution than C-band data and the combination of features created from Landsat LST, NBR, and coherence of L-band ALOS-2 achieved the highest accuracy, with an overall accuracy of 96% and a Kappa coefficient of 92.62%.",

keywords = "ALOS-2, Forest fire, Landsat-8, Multi-sensor, Random forest, Sentinel-1, Sentinel-2",

author = "Saygin Abdikan and Caglar Bayik and Aliihsan Sekertekin and {Bektas Balcik}, Filiz and Sadra Karimzadeh and Masashi Matsuoka and {Balik Sanli}, Fusun",

note = "Publisher Copyright: {\textcopyright} 2022 by the authors. Licensee MDPI, Basel, Switzerland.",

year = "2022",

month = feb,

doi = "10.3390/f13020347",

language = "English",

volume = "13",

journal = "Forests",

issn = "1999-4907",

publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",

number = "2",

}

TY - JOUR

T1 - Burned Area Detection Using Multi-Sensor SAR, Optical, and Thermal Data in Mediterranean Pine Forest

AU - Abdikan, Saygin

AU - Bayik, Caglar

AU - Sekertekin, Aliihsan

AU - Bektas Balcik, Filiz

AU - Karimzadeh, Sadra

AU - Matsuoka, Masashi

AU - Balik Sanli, Fusun

PY - 2022/2

Y1 - 2022/2

N2 - Burned area (BA) mapping of a forest after a fire is required for its management and the determination of the impacts on ecosystems. Different remote sensing sensors and their combinations have been used due to their individual limitations for accurate BA mapping. This study analyzes the contribution of different features derived from optical, thermal, and Synthetic Aperture Radar (SAR) images to extract BA information from the Turkish red pine (Pinus brutia Ten.) forest in a Mediterranean ecosystem. In addition to reflectance values of the optical images, Normalized Burn Ratio (NBR) and Land Surface Temperature (LST) data are produced from both Sentinel-2 and Landsat-8 data. The backscatter of C-band Sentinel-1 and L-band ALOS-2 SAR images and the coherence feature derived from the Interferometric SAR technique were also used. The pixel-based random forest image classification method is applied to classify the BA detection in 24 scenarios created using these features. The results show that the L-band data provided a better contribution than C-band data and the combination of features created from Landsat LST, NBR, and coherence of L-band ALOS-2 achieved the highest accuracy, with an overall accuracy of 96% and a Kappa coefficient of 92.62%.

AB - Burned area (BA) mapping of a forest after a fire is required for its management and the determination of the impacts on ecosystems. Different remote sensing sensors and their combinations have been used due to their individual limitations for accurate BA mapping. This study analyzes the contribution of different features derived from optical, thermal, and Synthetic Aperture Radar (SAR) images to extract BA information from the Turkish red pine (Pinus brutia Ten.) forest in a Mediterranean ecosystem. In addition to reflectance values of the optical images, Normalized Burn Ratio (NBR) and Land Surface Temperature (LST) data are produced from both Sentinel-2 and Landsat-8 data. The backscatter of C-band Sentinel-1 and L-band ALOS-2 SAR images and the coherence feature derived from the Interferometric SAR technique were also used. The pixel-based random forest image classification method is applied to classify the BA detection in 24 scenarios created using these features. The results show that the L-band data provided a better contribution than C-band data and the combination of features created from Landsat LST, NBR, and coherence of L-band ALOS-2 achieved the highest accuracy, with an overall accuracy of 96% and a Kappa coefficient of 92.62%.

KW - ALOS-2

KW - Forest fire

KW - Landsat-8

KW - Multi-sensor

KW - Random forest

KW - Sentinel-1

KW - Sentinel-2

UR - http://www.scopus.com/inward/record.url?scp=85125301955&partnerID=8YFLogxK

U2 - 10.3390/f13020347

DO - 10.3390/f13020347

M3 - Article

AN - SCOPUS:85125301955

SN - 1999-4907

VL - 13

JO - Forests

JF - Forests

IS - 2

M1 - 347

ER -

Burned Area Detection Using Multi-Sensor SAR, Optical, and Thermal Data in Mediterranean Pine Forest

Özet

Bibliyografik not

Finansman

Belgeye Erişim

Diğer Dosyalar ve Linkler

Parmak izi

Alıntı Yap