Machine learning emulators for predicting storm surges in the North Sea

Providing accurate and timely warnings on storm surges is essential to limit the impact of flooding in coastal areas. These warnings are based on hydrodynamic models of the area which traditionally rely on numerical solvers to predict water levels.  These models are preferably run in an ensemble to also provide uncertainty information about the forecast. In addition to forecasts, these models are also used as part of climate scenarios to provide statistics on storm surges under future climate. A major bottleneck in especially the latter two applications is the computational cost of the model. 

In recent years, machine learning models have been developed that can partly or fully emulate numerical models at reduced computational cost once trained, enabling faster forecasts, larger ensembles, or longer climate runs. These emulators come in various forms, from predicting the hydrodynamics of the entire region of interest (more closely mimicking existing numerical models) to predicting water levels at selected points of interest (more closely aligning with available observational data). In this presentation we will discuss our work towards emulating the hydrodynamics of the North Sea for storm surge prediction using either type of emulator. We will demonstrate the performance of the emulators on multiple cases ranging from test problems to more realistic settings. Additionally, we will discuss how known physics of the system or observational data can be incorporated into the surrogate models, with the goal of making the model more generalizable and reducing the data requirements for training.