Artificial Intelligence for Predicting Local Scour Depth around Piers Based on Dimensional Analysis

Dong, H.; Sun, Z.; Li, Z.; Chong, L., and Zhou, H., 2020. Artificial intelligence for predicting local scour depth around piers based on dimensional analysis. In: Liu, X. and Zhao, L. (eds.), Today's Modern Coastal Society: Technical and Sociological Aspects of Coastal Research. Journal of Coastal Research, Special Issue No. 111, pp. 21–25. Coconut Creek (Florida), ISSN 0749-0208.Accurate and reliable prediction of scour depth around bridge piers is essential for bridge engineering. The nondimensional parameters and artificial intelligence algorithms are combined to predict local scour depth. Based on the results of field observation and laboratory tests, five machine-learning models are applied and compared with the Hydraulic Engineering Circular No. 18 (HEC-18) formula, which is widely used in the United States. The results show that the machine-learning models are more accurate than the traditional HEC-18 formula and that the neural network models are more suitable for the prediction of bridge pier erosion than the linear regression model.