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

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