Estimating space–time wave statistics using a sequential sampling method and Gaussian process regression

The traditional Monte Carlo sampling of waves requires generating tens thousands random to achieve stable statistics in the tail distribution, which is computationally costly for numerical simulations and time-consuming often impractical experiments. To improve efficiency, we present a sequential method, predicts wave based on nonlinear response deterministic groups. This data-driven method starts with parameterising linear field series Gaussian system from water then approximated by observations through evolution groups carefully designed initial conditions. A introduced during this procedure, determines next best point previous distance metric. We examine performance proposed simulation fields as well grid search strategy. results show can computational cost savings over several orders magnitude simulations. also suggest such be used determine test matrix experiments better coverage parameter space.