ASSESSMENT OF URBAN VULNERABILITY TO EARTHQUAKE HAZARD FOR TABRIZ CITY, NW IRAN USING ANP-ANN MODEL

摘要

Tabriz city is a seismic-prone province in the northwestern part of Iran with recurring devastating earthquakes which have resulted in heavy casualties and damages. This research developed a new computational framework to investigate four main dimensions of vulnerability such as environmental, social, economic and physical in Tabriz City. The Analytic Network Process (ANP) and Artificial Neural Network (ANN) Model were applied to achieve the objectives of this investigation. Firstly, a literature survey was performed to explore indicators with significant impact on the dimensions of vulnerability to the earthquake in the study area. In the next stage, twenty indicators were identified and analyzed using geographic information system (GIS) software package (ARC GIS 10.3) to generate earthquake vulnerability maps. The classified and standardized indicators were subsequently weighed and ranked using ANP model to construct the training database. Then, standardized maps along with the training site maps were presented as input to a Multilayer Perceptron (MLP) and Self-Organizing Map (SOM) neural network. The resulting Earthquake Vulnerability Maps (EVMs) were categorized into five classes, namely very high, high, moderate, low and very low. Additionally, the impact of the vulnerability of Tabriz city on population during an earthquake was included in this analysis for accurate risk forecasting. The comparison of data provided by Earthquake Vulnerability Map (EVM) with the Population Vulnerability (PV) of Tabriz city approved the validity of the results. The findings of this research are useful for decision-makers and government authorities to obtain a better knowledge of a city's vulnerability dimensions and to adopt better preparedness strategies in the future.