Wave-by-wave prediction for spread seas using a machine learning model with physical understanding

• DOI: 10.1016/j.oceaneng.2023.115450
• Publication Date: 2023-07-31T17:10:48Z
• Authors: Jialun Chen; Paul H. Taylor; Ian A. Milne; David Gunawan; Wenhua Zhao
• Keywords: Model Predictive Control; Wave model; Quantile; Time horizon

Accurate surface wave predictions have the potential to greatly enhance safety and efficiency of many offshore applications, such as active control energy converters floating wind turbines. However, real-time prediction becomes increasingly challenging when large directional spreading is considered. To address this challenge, present study introduces a machine learning model that utilizes an Artificial Neural Network (ANN) for predicting moderate waves. Linear, short-crested time histories are synthesized numerically assess capability our model. The ANN demonstrates better than recently developed theoretical scheme (Hlophe et al., 2022), extending horizon by approximately one peak period into future. Further, quantile loss function introduced quantify uncertainty, enhancing practical value in decision-making processes engineering renewable systems.