Abstract
Flooding is a natural hazard that takes millions of lives each year. Remote sensing and geographic information systems (GIS), two fields of surveying engineering, can play an important role in flood management by generating floodplain maps.
This paper proposes a model to generate a floodplain map for a flood event. A digital elevation model (DEM) is used to compute a flood-depth map for a given flood event. The flood-depth map is overlaid over the classified high-resolution image (IKONOS) to determine the inundated classes after flooding. This model is applied on a part of the river that is located in the northwest of Iran in Khoram-Abad city. Applying this model on this study area shows that the accuracy classification is improved by about 15% using a multi-layer perceptron neural network. This improvement could play an important role in flood risk assessment. A nonlinear regression model is also used for modelling the flood-water line.
Acknowledgements
This research was done within the project with grant no. 621/3/817 in 2006. Thanks go especially to the University of Tehran Vice Chancellor For Research for supporting the research. The author thanks National Cartographic Center for the data. The author is also very grateful to Doctors David and Pravin for editing the paper.