DEVELOPMENT OF A MODEL FOR EVALUATING RISK OF DISASTER DUE TO SCOURING AROUND THE PIER BASED ON MACHINE LEARNING

Abstract

 In recent years, heavy rainfall disasters have caused frequent damage to bridge piers due to scouring and the resulting fall of bridges in many areas. The purpose of this study is to develop a model for evaluating risk of disaster due to scouring based on machine learning. We developed models by four different machine learning algorithm based on the data of disasters in the past, and compared the performance of the models. As a result, we selected the neural networks(NN) algorithm as its the most performance. In addition, we developed the model to apply NN based on importive explanatory variables selected by the feature selection, the model can make possible to evaluate the risk for initiation of disaster due to the scouring.