REBEC: Robust Evolutionary-based Calibration Approach for the Numerical Wind Wave Model
This work addresses the calibration of wind wave models for oceanography, offering a robust method to prevent over-tuning, but it appears incremental as it builds on evolutionary algorithms like SPEA2.
The paper tackled the problem of calibrating numerical wind wave models to local conditions without over-tuning to specific events, proposing the REBEC approach which builds a stochastic ensemble for a trade-off between quality and robustness, and it outperformed the baseline SPEA2 algorithm in experiments with the SWAN model for the Kara Sea domain.
The adaptation of numerical wind wave models to the local time-spatial conditions is a problem that can be solved by using various calibration techniques. However, the obtained sets of physical parameters become over-tuned to specific events if there is a lack of observations. In this paper, we propose a robust evolutionary calibration approach that allows to build the stochastic ensemble of perturbed models and use it to achieve the trade-off between quality and robustness of the target model. The implemented robust ensemble-based evolutionary calibration (REBEC) approach was compared to the baseline SPEA2 algorithm in a set of experiments with the SWAN wind wave model configuration for the Kara Sea domain. Provided metrics for the set of scenarios confirm the effectiveness of the REBEC approach for the majority of calibration scenarios.