Statistical Prediction of Extreme Storm Surges Based on a Fully Supervised Weather-Type Downscaling Model

Increasing our capacity to predict extreme storm surges is one of the key issues in terms of coastal flood risk prevention and adaptation. Dynamically forecasting storm surges is computationally expensive. Here, we focus on an alternative data-driven approach and set up a weather-type statistical downscaling for daily maximum storm surge (SS) prediction, using atmospheric hindcasts (CFSR and CFSv2) and 15 years of tidal gauge station measurements. We focus on predicting the storm surge at La Rochelle-La Pallice tidal gauge station. First, based on a sensitivity analysis to the various parameters of the weather-type approach, we find that the model configuration providing the best performance in SS prediction relies on a fully supervised classification using minimum daily sea level pressure (SLP) and maximum SLP gradient, with 1 degrees resolution in the northeast Atlantic domain as the predictor. Second, we compare the resulting optimal model with the inverse barometer approach and other statistical models (multi-linear regression; semi-supervised and unsupervised weather-types based approaches). The optimal configuration provides more accurate predictions for extreme storm surges, but also the capacity to identify unusual atmospheric storm patterns that can lead to extreme storm surges, as the Xynthia storm for instance (a decrease in the maximum absolute error of 50%).