Effect of data normalisation in estimating wave overtopping discharge parameter of semicircular breakwater using ANN and Random Forest.

Abstract

Abstract Breakwaters are the structures constructed in the coastal areas to maintain calm inside the port or prevent beach erosion. Semi-circular Breakwater (SCB) is an innovative type of Breakwater made of hollow caisson on a base slab with or without perforations. In this study, the wave overtopping discharge parameter of an SCB is estimated using Artificial Neural Network and Random Forest. The data is collected and used in the current research from an experimental investigation conducted in the Wave Mechanics Laboratory of the Department of Water Resources and Ocean Engineering (WROE), NITK Surathkal. Using this experimental data, the ANN and Random Forest models are developed for the prediction of the wave overtopping discharge parameter of an SCB. The performance of the models is evaluated using different statistical parameters. Data with and without normalisation are used separately to check the effect of normalisation in the prediction of wave overtopping discharge parameter using ANN and Random Forest. From the results, it is found that ANN gives better results when the data is normalised. The performance of Random Forest is independent of the data normalisation.