Prediction of local scour around bridge piers using the ANFIS method

Local scour around bridge piers is a complicated physical process and involves highly three-dimensional flows. Thus, the scour depth, which is directly related to the safety of a bridge, cannot be given in the form of the exact relationship of dependent variables via an analytical method. This paper proposes the use of the adaptive neuro-fuzzy inference system (ANFIS) method for predicting the scour depth around a bridge pier. Five variables including mean velocity, flow depth, size of sediment particles, critical velocity for particles’ initiation of motion, and pier width were used for the scour depth. For comparison, predictions by the artificial neural network (ANN) model were also provided. Both the ANN model and ANFIS method were trained and validated. The findings indicate that the modeling with dimensional variables yields better predictions than when normalized variables are used. The ANN model was applied to a field-scale dataset. Prediction results indicated that the errors are much larger compared to the case of a laboratory-scale dataset. The MAPE by the ANN model trained with part of the field data was not seriously different from that by the model trained with the laboratory data. However, the application of the ANFIS method improved the predictions significantly, reducing the MAPE to the half of that by the ANN model. Five selected empirical formulas were also applied to the same dataset, and Sheppard and Melville’s formula was found to provide the best prediction. However, the MAPEs for the scour depths predicted by empirical formulas are much larger than MAPEs by either the ANN or the ANFIS method. The ANFIS method predicts much better if the range of the training dataset is sufficiently wide to cover the range of the application dataset.

     

Change in fish community composition following weir removal,field observations,and physical habitat simulations

The number of untended weirs has increased in Korea in recent years due to land use changes. The removal of abandoned weirs in streams has been attempted following an agreement between local government and residents. The Gongneung Weir‐2 was built for irrigation in the 1970s and was removed in 2006. The objective of this study was to investigate the impact of the removal of Gongneung Weir‐2 on the composition of the fish community. The study area was a 900‐m‐long reach in the Gongneung‐cheon River in Korea, and Gongneung Weir‐2 was located in the middle of the reach. Before weir removal, field monitoring revealed that five fish species were dominant and accounted for more than 80% of the entire fish community. The composition of the fish community changed significantly after weir removal. Lotic fish became dominant after weir removal, whereas lentic fish were dominant prior to weir removal. Physical habitat simulations (PHSs) for individual dominant fish species were carried out. For the PHS, the River2D model and the adaptive neuro‐fuzzy inference system method were used for hydraulic and habitat simulations, respectively. The distributions of the highly suitable portion for each fish species were identified before and after weir removal. The PHS successfully predicted changes in the composition of the fish community after weir removal. The PHSs for the entire fish community and for the lotic and lentic guilds were undertaken and the simulated results were compared with each other. The PHSs for the entire fish community could not account for the less dominant fish species in the fish community.     

Prediction of time‐dependent local scour around bridge piers

Most formulas for predicting the scour depth around bridge piers result in over‐predictions. This is partly due to ignoring the fact that the local scour is a time‐dependent process. Formulas that take into account time‐dependent local scour around bridge piers have been developed in the past. However, these formulas predict the scour process well, but only when applied to datasets from which they were constructed. Motivated by this, the present study proposes a relationship for time‐dependent local scour using dimensional analysis and nonlinear regression. Similarly, another relationship for the time to equilibrium is also developed. The findings indicate that the proposed relationship predicts time‐dependent local scour better than existing formulas. The proposed relationships are applicable to local scour around cylindrical bridge piers. It is assumed that the bed sediment is uniform and the bedform effect is minor and can be ignored.