Prediction of Earthquake Damage Degree Using a Neuro-Fuzzy Systems

Earthquakes have been a recurring phenomenon throughout history and will likely continue to occur in the future. The occurrence of such an event has, in most cases, left devastating effects on human settlements and has imposed heavy casualties on their inhabitants. Identifying damage caused by severe earthquakes to structures is crucial for several reasons, including public safety, effective resource management, infrastructure maintenance, and informed urban planning. After the earthquake, engineers must assess the safety of existing structures and decide on the actions that should be taken. Therefore, this paper presents a form of earthquake damage prediction using a neuro-fuzzy system to predict the resistance of buildings. The advantages of this method are the absence of complex formulation, high speed, and easy procedure. In this research, the 2017 Sarpol-e-Zahab earthquake in Iran is also used as a case study. The accuracy of the proposed model is evaluated using a 10-fold validation method and is equal to (94.5 ± 3.2)%.