Using Artificial Neural Networks to Assess Earthquake Vulnerability in Urban Blocks of Tehran

The purpose of this study is to assess the vulnerability urban blocks earthquakes for Tehran as a city built on geological faults using an artificial neural network—multi-layer perceptron (ANN-MLP). Therefore, we first classified earthquake evaluation criteria into three categories: exposure, sensitivity, and adaptability capacity attributed total 16 spatial criteria, which were inputted network. To train network compute map, used combined Multi-Criteria Decision Analysis (MCDA) process with 167 vulnerable locations training data, 70% (117 points) training, 30% (50 testing validation. Mean Average Error (MAE) implemented was 0.085, proves efficacy designed model. results showed that 29% Tehran’s area extremely earthquakes. Our factor importance analysis factors such proximity fault lines, high population density, environmental gained higher scores assessment given case study. This methodical approach choice data methods can provide insight scaling up other regions. In addition, resultant outcomes help decision makers relevant stakeholders mitigate risks through resilience building.