Bias correction of operational storm surge forecasts using Neural Networks
Tedesco, Paulina Souza; Rabault, Jean; Sætra, Martin Lilleeng; Kristensen, Nils Melsom; Aarnes, Ole Johan; Breivik, Øyvind; Mauritzen, Cecilie; Sætra, Øyvind
Peer reviewed, Journal article
Published version
Date
2024Metadata
Show full item recordCollections
Abstract
Storm surges can give rise to extreme floods in coastal areas. The Norwegian Meteorological Institute (MET Norway) produces 120 h regional operational storm surge forecasts along the coast of Norway based on the Regional Ocean Modeling System (ROMS), using a model setup called Nordic4-SS. Despite advances in the development of models and computational capabilities, forecast errors remain large enough to impact response measures and issued alerts, in particular, during the strongest storm events. Reducing these errors will positively impact the efficiency of the warning systems while minimizing efforts and resources. Here, we investigate how forecasts can be improved with residual learning, i.e., training data-driven models to predict the residuals in forecasts from Nordic4-SS. A simple error mapping technique and a more sophisticated Neural Network (NN) method are tested. The simple error mapping technique provides a reduction in the Root Mean Square Error (RMSE) of less than 4%. Using the NN residual correction method, the RMSE in the Oslo Fjord is reduced by 36% for lead times of one hour, 9% for 24 h, and 5% for 60 h. Therefore, the residual NN method is a promising direction for correcting storm surge forecasts, especially on short timescales. Moreover, it is well adapted to being deployed operationally, as (i) the correction is applied on top of the existing model and requires no changes to it, (ii) all predictors used for NN inference are already available operationally, (iii) prediction by the NNs is very fast, typically a few seconds per station, and (iv) the NN correction can be provided to a human expert who may inspect it, compare it with the model output, and see how much correction is brought by the NN, allowing to capitalize on human expertise as a quality validation of the NN output. While no changes to the hydrodynamic model are necessary to calibrate the neural networks, they are specific to a given model and must be recalibrated when the numerical models are updated.