Bias Correction of Operational Storm Surge Forecasts Using Neural Networks

Abstract

Storm surges can give rise to extreme floods in coastal areas. The Norwegian Meteorological Institute (MET Norway) produces 120-hour 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 spent on mitigation. 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. Using the NN residual correction method, the Root Mean Square Error (RMSE) in the Oslo Fjord is reduced by 36% for lead times of one hour and 9% for 24 hours. 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.

A Review of Application of Machine Learning in Storm Surge Problems

“…A summary of the studies using ANN before 2020 can be found in Al Kajbaf and Bensi [19]. In recent years, ANNs have continued to be applied in storm surge problems [10,19,44,57,90,91,[120][121][122][123] and are also used in combination with CNN to extract feature representation from spatial data [78,124]. However, ANNs also have some limitations, especially in time series prediction.…”

“…Tayel and Oumeraci [137] developed a NARX neural network for nonlinearly correcting the numerical forecast results of storm tides. Tedesco et al [121] demonstrated that the forecasts of the Regional Ocean Modeling System (ROMS) can be improved with residual learning by testing a simple error mapping technique and a more sophisticated neural network. These studies show that ML-aided post-processing is a promising direction that can not only enhance the efficiency and accuracy of numerical models but also reduce computational demands.…”