Le immagini satellitari ad alta risoluzione e la classificazione delle comunità vegetali per la creazione della carta della Vegetazione dell'isola di Socotra (Yemen)

Abstract

L'arcipelago di Socotra (Yemen), ospita una elevata diversità  biologica, con caratteristiche uniche tali da renderlo un territorio rilevante per la conservazione della biodiversità  a livello globale: l'alto livello di endemismo, soprattutto per le specie vegetali, lo colloca tra le isole più importanti del mondo.

Vegetation map by satellite imagery in Socotra (Yemen)

The present study has produced a high resolution vegetation map of Socotra Island (Yemen) by combining vegetation classification with remote sensing analysis. The satellite data source was  represented  by  two  multi–temporal  sets  of  RapidEyeâ„¢ satellite images with a pixel resolution of 5 m and 5 spectral bands.  More  than  370  vegetation  surveys,  carried  out  with the phytosociological method and used to identify the main vegetation types, were used to obtain the training and evaluation sets. To produce the vegetation map, spectral signatures of the vegetation classes were obtained through a Gaussian mixture distribution model. A Sequential Maximum "a Posteriori” classification method was applied to take into account the heterogeneities in the signatures of some classes and the spatial pattern of the vegetation types. Post–classification sorting was performed to adjust the classification through various rule–based operations. A total of 28 classes were mapped with an accuracy greater than 80%. The resulting map and data will represent a fundamental tool for the elaboration of conservation strategies and the sustainable use of natural resources.