IDENTIFICATION OF FLOODED AREAS DUE TO SEVERE STORM USING ENVISAT ASAR DATA AND NEURAL NETWORKS

Abstract

The specific objective of the present study is to identify flooded areas due to cyclonic storm using Envisat ASAR VV polarized data and Artificial Neural Network (ANN). On October 30, 2006, the Ogni storm crossed the Indian coast. It impacted three coastal districts in Andhra Pradesh, including Guntur, Prakasam, and Krishna. The present study considers only nine mandals of Guntur district of Andhra Pradesh for identification of flooded areas. For this purpose, pre and post event images of study area were procured of Envisat satellite (April 23, 2006 and November 4, 2006). Field visit to the affected district after the disaster was carried out to gather landcover information. In all, 564 pixels landcover information was collected during the visit (These were corresponding to pre event Envisat image of April 23, 2006). Out of the 564 pixels, randomly 406 pixels (91 were water and the remaining 315 were non-water pixels) were used for training the Neural Network and the remaining for testing. Using the trained ANN model, the total water area in the nine mandals of Guntur using Envisat ASAR satellite imagery of April 23, 2006 was found to be 2.344 thousand hectares. The trained model was applied to the post event Envisat ASAR image of November 4, 2006 to obtain completely submerged and partial/non submerged areas under water. The completely submerged landcover under water in nine mandals of Guntur district on November 4, 2006 was found to be 13.2705 thousand hectares. Results suggest a high accuracy of classification and indicate that this may be a rapid tool for damage estimation and post disaster relief and recovery efforts.