Operator Learning for Surrogate Modeling of Wave-Induced Forces from Sea Surface Waves

2026-04-07

AI Summary

This study addresses the high computational cost of traditional numerical wave models, which hinders their efficient coupling with circulation models for accurate storm surge prediction. For the first time, Deep Operator Networks (DeepONets) are employed to develop a surrogate model for nearshore wave forcing, effectively emulating the SWAN model to predict wave radiation stress gradients and significant wave heights. The proposed framework is validated through one- and two-dimensional steady-state numerical experiments, demonstrating its capability to handle variable offshore wave conditions and wind field inputs. Applied to the Duck site in North Carolina, the surrogate model achieves high predictive accuracy for key wave parameters while substantially reducing computational expense compared to conventional approaches.

Abstract

Wave setup plays a significant role in transferring wave-induced energy to currents and causing an increase in water elevation. This excess momentum flux, known as radiation stress, motivates the coupling of circulation models with wave models to improve the accuracy of storm surge prediction, however, traditional numerical wave models are complex and computationally expensive. As a result, in practical coupled simulations, wave models are often executed at much coarser temporal resolution than circulation models. In this work, we explore the use of Deep Operator Networks (DeepONets) as a surrogate for the Simulating WAves Nearshore (SWAN) numerical wave model. The proposed surrogate model was tested on three distinct 1-D and 2-D steady-state numerical examples with variable boundary wave conditions and wind fields. When applied to a realistic numerical example of steady state wave simulation in Duck, NC, the model achieved consistently high accuracy in predicting the components of the radiation stress gradient and the significant wave height across representative scenarios.

Problem

• surrogate modeling
• wave-induced forces
• radiation stress
• storm surge prediction
• numerical wave models

Innovation

• Deep Operator Networks
• surrogate modeling
• radiation stress
• SWAN model
• wave-induced forces