ABSTRACT
The buildings’ damages due to the recent worldwide earthquakes have highlighted the vulnerability of the existing constructions and the significance of seismic retrofitting. Many of the currently operational buildings need further evaluation to minimize seismic damage and improve performance. Precise and comprehensive building evaluation would not be feasible due to the great expenditure it requires, which is why Rapid Visual Screening (RVS) techniques are to be used to predict the level of seismic damage to the buildings that should have otherwise been evaluated using accurate assessments. Pre-earthquake building screening is thus carried out to identify the buildings with high seismic vulnerability and prioritize those that require more accurate analysis. The present study takes advantage of FEMA-154 and an artificial neural network model with a noticeable accuracy of 83% to predict the level of damage to reinforced concrete buildings and is the first to consider the two parameters of potential earthquake magnitude and the distance of the building from the earthquake epicenter. A web-based, responsive, and platform-independent application called EZRVS (available at http://www.seismohub.com/) has been developed that implemented the proposed methodology.
Disclosure Statement
No potential conflict of interest was reported by the author(s).
Data Availability Statement
The AI-based model that has been developed in this paper is available in SeismoHub (http://www.seismohub.com) and datasets that have been used in the current study are available from the corresponding author.