Assessment of the discrimination ability of MERIS spectral data for burned area mapping using ROC curves
Keywords:separability, non-parametric analysis, forest fires, satellite images
AbstractTraditionally, the selection of the most appropriate bands to classify the target cover was supported by statistical indices that measured the discrimination ability of the spectral bands based on the Gaussian distribution assumption. However, that assumption might not be fulfilled in every instance. In this study we applied a non-parametric test (receiver operating characteristic, ROC) to measure the discrimination ability of MERIS sensor spectral bands and derived spectral indices to classify burned areas. The discrimination potential of each band was computed from the post-fire image, and from the temporal difference of the images. In both cases, the sources of confusion between burned areas and other covers were identified. The bands with higher discrimination ability were the NIR bands and the best indices were η, GEMI, BAI, α B8, α B10, DGEMI and DBAI.
How to Cite
©The authors of the articles and other contributions published in GeoFocus keep intact the intellectual property rights over them. The authors and the publisher authorize the total or partial reproduction of the contents of the journal in the following terms:
1) Express mention of the author and the reference of the original publication.
2) Do not perform a commercial or lucrative use of them. Otherwise, you should contact the authors to make the appropriate arrangements.
3) Authors preserve their property rights and give to the journal the rights of the first publication of the work, registered with the Licencia Creative Commons Atribución-NoComercial-SinDerivar 4.0 Internacional, which allows third parties to use the published data whenever the authorship of the work and first publication in this journal is mentioned.
4) It is allowed that authors disseminate electronically (e.g., in institutional repositories or on their own website) the published version of their work, as it encourages the earliest circulation and dissemination, and thus a possible increase in the citation and scope in the academic community.