Worldwide, the frequency and magnitude of extreme flooding are steadily increasing, causing considerable losses of life and property. It hampers well-being and economic growth in many countries, so that flood forecasting and flood risk assessment have become of upmost importance. New and rapidly developing techniques are becoming widespread, such as unmanned aerial vehicles (UAV), synthetic-aperture radar (SAR) or satellite-based systems. Combined with fit-for-purpose hydrodynamic models, these techniques pave the way for breakthroughs in flood assessment and flood risk management. This provides a unique platform for the scientific community to explore the driving mechanisms of flood risk and to build up efficient strategies for flood mitigation and enhancing flood resilience.
This session invites presentations on research based on high-resolution aerial and satellite techniques like UAV, SAR, Altimeter, SCATSAT-1, etc. for flood monitoring, including mapping of inundation extent, flow depths, velocity fields, flood-induced morphodynamics, debris transport. It also invites the presentation of innovative modelling techniques of flood hydrodynamics, flood hazard, damage and risk assessment, as well as flood relief prioritization, dam and dike(levees) break floods, and flood mitigation strategies. Studies dealing with the modelling uncertainties and modern techniques for model calibration and validation are particularly welcome.
Furthermore, real-time flood inundation mapping is critical aspect for the evacuation of people from low-lying areas and to reduce casualties. Acquisition of real-time data gained through UAV-based flood inundation mapping and modelling, as well as assessment of uncertainties in real-time aerial surveying are welcome in this session.

Invited speaker:
Frederik Kratzert.
Mr Kratzert holds a MSc in environmental engineering with focus on hydrology and is now doing a PhD in Machine Learning at the Johannes Kepler University, Linz, Austria under the supervision of Sepp Hochreiter. His research is focused around the use of the LSTM neural network for hydrological/environmental modeling and his PhD is funded by Google AI.