Local scour is a primary reason for bridge collapse, presenting a complex challenge due to the numerous factors influencing its occurrence. The complexity of local scour increases with clay-sand beds, particularly in predicting scour depth, as empirical equations are inadequate for such calculations. This study aims to predict local scour around cylindrical bridge piers in clay-sand beds using an artificial neural network (ANN) model. The ANN model was developed using 264 observations from various laboratory experiments. Eight variables were included in the ANN model: clay fraction, pier diameter, flow depth, flow velocity, critical sediment velocity, sediment particle size, bed shear strength, and pier Reynolds number. Sensitivity and statistical analyses were conducted to evaluate the impact of each variable and the accuracy of the ANN model in predicting local scour depth in clay-sand beds. The findings indicate that the ANN model predicted local scour with high accuracy, achieving a mean absolute percentage error (MAPE) of 14.6%. All dimensional variables significantly influenced the prediction of local scour depth, particularly clay fraction and bed shear strength, which were identified as the most crucial parameters. Finally, the MAPE values for local scour depth calculated using empirical equations were significantly higher than those for the ANN model, leading to an overestimation of local scour depth by the empirical equations.
Scour around bridge piers is a well-known threat to bridge stability worldwide. It can cause losses in lives and the economy, especially during floods. Therefore, an artificial intelligence approach called artificial neural network (ANN) was used to predict the scour depth around bridge piers. The ANN model was trained with laboratory data, including pier width, flow velocity, particle diameter, sediment critical velocity, flow depth, and scour depth. The data was divided into 70% for training, 15 for validation, and 15% for testing. Besides, the ANN model was trained using various training algrthins and a single hidden layer with 20 neurons in the hidden layer. The results showed that the ANN model with Bayesian regularization backpropagation training algorithm provides a better predicted scour depth with a correlation coefficient (R) equal to 0. 9692 and 0.926 for training and test stages, respectively. Besides, it showed a low mean squared error (MSE), which was 0.0034 for training and 0.0066 for the test. These results were slightly better than the ANN with Levenberg-Marquardt backpropagation with R training equals 0.9552 (MSE training = 0.0047), and R test equals 0.838 (MSE test = 0.007).On the other hand, the ANN model with a scaled conjugate gradient backpropagation training algorithm showed worse predictions (R training = 0.7407 and R test = 0.6409). Besides, the ANN model shows better outcomes than the linear regression model. Finally, the sensitivity analysis has shown that the pier width is the most crucial parameter for estimating scour depth using the ANN model.