New Approach of Sample Generation and Classification for Wildfire Fuel Mapping on Hyperspectral (Prisma) Image

Abstract

Hyperspectral images have its applications in various fields. Here, hyperspectral image from PRISMA which is a fundamental satellite of Italian Space Agency is being used for discriminating the wildfire fuel types on Sardinian Island of Italy. PRISMA is an on-demand mission and the available data in the archive are limited. There is no literature available on land use/vegetation classification using PRISMA data. In this paper, a new approach for generating samples to form a dataset for classifying the wildfire fuels and for classifying mixed pixels using iso-bioclimatic conditions are proposed. The classified map created using the dataset and using the iso-bioclimatic conditions is been validated. From the accuracy assessment, SVM classifier showed an overall accuracy of 86% and kappa coefficient of 0.79. Then, the classified map is converted into fuel map. This study suggests that the proposed approach can be used to generate samples for land use/vegetation classification and to assign vegetation types to mixed pixels depending upon the iso-bioclimatic conditions.