A method for delineating riparian forests using region-based image classification and depth-to-water analysis

Abstract

Riparian formations are often narrow strips of vegetation near the banks of streams governed by good water availability. With the advent of high-resolution satellite imagery, the study of riparian forests using space-borne remote sensing has gained more attention. However, the sole use of remotely sensed data is seldom sufficient to delineate riparian forests and their special hydrological and geomorphological context should also be considered. In this study, we propose a twofold method to delineate riparian forests in a Brazilian savannah context. Four sites on the banks of the Pandeiros River were used to test our approach, each in a different hydrological context. In our approach, the hydrographic network and a digital surface model are processed using the depth-to-water analysis to create a mask of the riparian zone, then the riparian forests are extracted using region-based image classification. Both steps are fully explained. Three region-based image classification programs (e-Cognition, Sistema de Processamento de Informações Georeferenciadas (SPRING), and MAGIC (map-guided ice classification)) are briefly described and tested. A special validation scheme was created using the independent interpretation of five photo-interpreters to test the accuracy of the results. All three programs achieved a success rate of over 90%. The approach is also tested on a much larger area of the Pandeiros River to assess its applicability in a more operational context. The discussion focuses on methodological issues and the advantages and drawbacks of the approach.

Acknowledgements

This work is part of the doctoral thesis of Thiago Alencar-Silva under the supervision of Philippe Maillard at the Universidade Federal de Minas Gerais and was made possible through the financial support of the Brazilian Federal Government (CAPES). The authors wish to acknowledge the work of Dr Yule Roberta Ferreira Nunes and her team at the Department of Ecology of the Unimonte University for providing field data used in this work. We would also like to thank the Instituto Estadual de Florestas of Minas Gerais for their logistic support. We are also grateful to Dr David Clausi of the University of Waterloo for providing MAGIC and to Dr Benoit St-Onge of the Université du Québec à Montréal for providing e-Cognition and for their contribution to this work. ASTER GDEM is produced and provided free of charge by METI and NASA.