- International Journal of Environment and Geoinformatics
- Volume:8 Issue:4
- Determination of Forest Burn Scar and Burn Severity from Free Satellite Images: a Comparative Evalua...
Determination of Forest Burn Scar and Burn Severity from Free Satellite Images: a Comparative Evaluation of Spectral Indices and Machine Learning Classifiers
Authors : Nooshin MASHHADİ, Ugur ALGANCİ
Pages : 488-497
Doi:10.30897/ijegeo.879669
View : 11 | Download : 4
Publication Date : 2021-12-15
Article Type : Research Paper
Abstract :Remote sensing data indicates a considerable ability to map post-forest fire destructed areas and burned severity. In this research, the ability of spectral indices, which are difference Normalized Burned Ratio insert ignore into journalissuearticles values(dNBR);, relative differenced Normalized Burn Ratio insert ignore into journalissuearticles values(RdNBR);, Relativized Burn Ratio insert ignore into journalissuearticles values(RBR);, and difference Normalized Vegetation Index insert ignore into journalissuearticles values(dNDVI);, in mapping burn severity was investigated. The research was conducted with free access moderate to high-resolution Landsat 8 and Sentinel 2 satellite images for two forest fires cases that occurred in Izmir and Antalya provinces of Turkey. Performance of the burn severity maps from different indices were validated by use of NASA Firms active fires dataset. The results confirmed that, RdNBR showed more precise results than the other indices with an accuracy of insert ignore into journalissuearticles values(89%, 93%); and insert ignore into journalissuearticles values(84%, 79%); for Landsat 8 and Sentinel 2 satellites over Izmir and Antalya respectively. Moreover, in this research, the ability of machine learning classifiers, which are Support Vector Machine insert ignore into journalissuearticles values(SVM); and Random Forest insert ignore into journalissuearticles values(RF);, in mapping burned areas were evaluated. According to the accuracy metrics that are user’s accuracy, producer`s accuracy and Kappa coefficient, we concluded that both classifiers indicate reliable and accurate detection for both regions.Keywords : forest fire, burn scar, burn severity, landsat 8, sentinel 2