A Prediction Model for Local Scour Depth around Piers Based on CNN

A prediction model for the local scouring depth at bridge piers is built using convolutional neural network (CNN). Measured data which is collected from laboratory tests and field observation is used to train the predicting model which is verified by the measured data of Hangzhou Bay Bridge. The result shows that the predicted value of the local scouring depth at piers obtained by the machine learning model is in good agreement with the measured ones, which is more suitable than existing general formula. The machine learning method is effective in predicting the local scour depth at bridge piers.