Remote sensing-based neural network mapping of tsunami damage in Aceh, Indonesia

Abstract

In addition to the loss of human life, the tsunami event of 26 December 2004 caused extensive damage to coastal areas. The scale of the disaster was such that remote sensing may be the only way to determine its effects on the landscape. This paper presents the results of a neural network-based mapping of part of the region of Aceh, Sumatra. Before-and-after satellite imagery, combined with a novel neural network methodology, enabled a characterisation of landscape change. The neural network technique used a threshold of acceptance for identification, in combination with a bootstrapped identification method for identifying problem pixels. Map analysis allowed identification of urban areas that were inaccessible by road, and which aid agencies could therefore only reach by air or sea. The methods used provide a rapid and effective mapping ability and would be a useful tool for aid agencies, insurance underwriters and environmental monitoring. © 2007 Overseas Development Institute.