Scour around bridge piers is one of the main causes of bridge failures and is of great importance for hydraulic engineers and scientists. Prediction of the scour depth around piers is complicated, and accurate results are rarely achieved by the existing models. Recently, data mining approaches such as artificial neural networks and fuzzy inference systems have been applied successfully to predict scour depth around hydraulic structures. In this study, an alternative robust data mining approach was used for the predictions of the scour depth around piers, and the results were compared with those of three empirical approaches. Performances of developed models were tested by experimental data sets collected in laboratory experiments and field measurements, together with existing empirical approaches. Statistical measures indicate that the proposed M5′ model provides a better prediction of scour depth than the empirical approaches.
- bridge pier
- data mining approaches
- M5′ model tree
- soft computing
- unidirectional flow
- First received 30 March 2014.
- Accepted in revised form 5 October 2014.
- © IWA Publishing 2015