Evaluation of Wave-induced Liquefaction in a Porous Seabed: Using an Artificial Neural Network and aGenetic Algorithm -based model

摘要

The evaluation of wave-induced liquefaction is one of the key factorsrnfor analysing seabed characteristics and the design of marine structures.rnNumerous investigations of wave-induced liquefaction have beenrnproposed. However, most previous research has focused onrncomplicated mathematical theories and laboratory work. In this study,rnwe contribute an alternative approach for the prediction of the waveinducedrnliquefaction using an Artificial Neural Network (ANN) and arnGenetic Algorithm (GA)-based model. Combined ANN and GA-basedrnmodels are still a newly developed area in coastal engineering. In thisrnstudy, a Genetic Algorithm-based approach is proposed to find optimalrnweights for the ANN model. It reduces the training time, and improvesrnthe forecasting accuracy for wave-induced maximum liquefactionrndepth, compared to using the normal ANN training procedure.rnSimulation results demonstrate the capacity of the proposed ANNrnmodel for the prediction of wave induced maximum liquefaction depthrnin addition to the proposal of GAs for training the ANN model.