Multi-temporal land-cover classification and change analysis with conditional probability networks: the case of Lesvos Island (Greece)

Abstract

This study uses a series of Landsat images to map the main land-cover types on the Mediterranean island of Lesvos, Greece. We compare a single-year maximum likelihood classification (MLC) with a multi-temporal maximum likelihood classification (MTMLC) approach, with time-series class labels modelled using a first-order hidden Markov model comprising continuous and discrete variables. A rigorous validation scheme shows statistically significant higher accuracy figures for the multi-temporal approach. Land-cover change accuracies were also greatly improved by the proposed methodology: from 46% to 70%. The results show that when only two dates are used, the mapping of land use/cover is unreliable and a large number of the changes identified are due to the individual-year commission and omission errors.

Acknowledgements

This research was funded by an EU Marie Curie Actions Fellowship (Contract Number MOIF-CT-2005-008667) and partly supported from the GSRT 2006 matching funds. The authors are grateful to the GLCF of the University of Maryland for providing the free data. The authors also thank the Geography of Natural Disasters Laboratory of the Department of Geography, University of the Aegean, for supplying the QuickBird mosaic.