Regional storm surge hazard quantification using Gaussian process metamodeling techniques

The recent, very active hurricane seasons, as well as emerging concerns related to the future effects of sea-level rise, hurricane intensification, and increased storm recurrence rates on coastal areas, make the prediction of storm-induced flood hazard a key priority when discussing coastal community resilience. To address this priority, researchers have placed substantial efforts in developing improved high-fidelity, numerical models to predict the storm surge for a given storm event. For promoting computational efficiency when utilizing these models within hazard estimation applications, metamodeling (also referred to as surrogate modeling) techniques have emerged as a popular strategy. The accuracy of such techniques in this context has been examined so far using cross-validation (CV) techniques or by testing their performance for a (very) small number of historical storms. This paper investigates this topic within a different setting, examining the resultant regional storm surge hazard maps, specifically using Gaussian process (GP) as the metamodel of choice. This is accomplished by examining the hazard products (hazard maps or curves) obtained by GP implementations, as well as the hazard products established through alternative, simplified Monte Carlo approaches. Examining this accuracy fills in an important knowledge gap and provides an answer to the question “what are the benefits in coastal hazard estimation by using metamodels?”, while simultaneously improving the trustworthiness of the associated results within the context of coastal risk quantification. The selection of the storm ensemble supporting the GP development is also examined, and it is shown that an adaptive implementation provides distinct advantages. This implementation selects batches of storms in stages, leveraging the GP developed using the storms identified up to the current stage, to choose the next batch. Finally, a computationally efficient framework is presented to explicitly consider the uncertainty associated with the GP predictions to provide confidence bounds for the hazard products.