Part B: Innovative Data Augmentation Approach to Boost Machine Learning for Hydrodynamic Purposes—Computational Efficiency

The increasing influence of AI across various scientific domains has prompted engineering to embark on new explorations. However, studies often overlook the foundational aspects of the maritime field, leading to over-optimistic or oversimplified outputs for real-world applications. We previously highlighted the sensitivity of trained models to noise, the importance of computational efficiency, and the need for feature engineering/compactness in hydrodynamic models due to the stochastic nature of waves. A novel data analysis framework was introduced with two purposes to augment data for machine learning (ML) models: transferring features from high-fidelity to low-fidelity surrogates and enhancing simulation data and increasing computational efficiency. The current issue addresses the second objectives. Wave-induced response time series data from experiments on a spherical model under various wave conditions were analyzed using continuous wavelet transform to extract spectral-temporal features. These features were then reorganized into a new feature map and augmented with additional endogenous features to enhance their uniqueness. Different ML models were trained; the new framework substantially reduced training costs while maintaining fair accuracy, with training times slashed from hours to seconds. The significance of the current study extends beyond the maritime context and can be utilized for ML applications in intrinsically stochastic data.