Abstract
This study presents gene-expression programming (GEP) as an alternative tool for the prediction of scour depth around a circular pile due to waves in a medium dense silt and sand bed. The proposed models are developed in terms of dimensional and non-dimensional parameters affecting scour process the most. The training and testing data sets of the proposed GEP and other models are experimental results sourced from the literature. The performance of GEP is then compared with the performance of neural networks technique, and also regression-based equations developed by the authors and others. The training and testing results are given in terms of the most widely used statistical measures and also scatter plots. The predictive performance of GEP models was found to be superior to the neural networks technique and regression-based equations.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have