A deep learning method for the prediction of focused waves in a wave flume

Abstract

Rogue waves pose a significant risk to marine safety, emphasizing the need to accurately predict their occurrence in the open ocean. However, the complexity of their evolution, which may involve nonlinear physical phenomena such as wave-wave interaction and modulation instability, makes this task challenging. Currently the reconstruction of rogue waves involves generating focused waves through the superposition of different spectral components of irregular waves that are in phase at the focusing point. Despite its effectiveness, this approach is limited. The paper introduces a deep learning method based on Long short-term memory (LSTM) to predict focused waves generated in a Computational Fluid Dynamics (CFD) flume in the time domain. The model is trained on 60% of the generated wave time series, with the remaining 40% used for both validation and testing. The results demonstrate that the proposed method can assist with the prediction of focused waves at various observation points, indicating its potential as a promising approach for predicting rogue wave behaviour in the ocean.