Predictive Analysis of the Building Damage From the 2011 Great East Japan Tsunami Using Decision Tree Classification Related Algorithms

Abstract

When considering a tsunami disaster, many researchers have considered the tsunami's flow depth and velocity as the primary contributors to the building damage. Additionally, the majority of these studies have used the maximum value as the measure of each of these two factors. However, building damage may not occur when the maximum flow depth and the maximum flow velocity of the tsunami are reached. This study addressed two objectives based on the 2011 Great East Japan Earthquake and Tsunami. Firstly, to find out whether the maximum values of the flow depth and flow velocity are the same as their critical values and, secondly, to verify which combination of the parameters is the best predictor of the building damage level. The data from 18,000 buildings in Ishinomaki City, Japan, with the cooperation of the Japanese joint survey team, were analyzed using the decision tree related algorithms. The critical variables were the simulated data at the time when the buildings collapsed. The analysis showed the accuracy of the prediction based on the group of variables. Finally, the findings showed that the combination of the critical flow depth and maximum flow velocity provided the highest accuracy for classifying the level of building damage.

Keywords

• Building damages
• data mining
• decision tree algorithm
• 2011 Great East Japan earthquake and tsunami