Interpreting sensor measurements in dikes - experiences from UrbanFlood pilot sites

The UrbanFlood project is creating an Early Warning System framework that can be used to link sensors via the Internet to predictive models and emergency warning systems. The project includes
four pilot sites to apply and validate at full scale the technology being developed in the project: Amsterdam (Netherlands), Boston (UK) and Rhine River (Germany). This paper focuses on a description of the sensor instrumentation installed at the pilot sites and the emerging conclusions from the analysis of the results obtained to date. The sensors installed at the various sites include various MEMS modules to measure displacement and pore pressure and fibre optic cables able to detect strains. The gathered data are used for dike stability evaluation with different models and also, combined with an Artificial Intelligence (AI) component, for detection of anomalies in dike behaviour. Detected anomalies trigger assessment of the likelihood of levee breach and the consequences in terms of flood propagation and damage in the defended urban area.