5. Multi-source data fusion for rapid flood mapping

 

Kai Schröter

We work on the development of methods to quantify flood risk and to assess strategies for climate adaptation. We investigate the whole chain of flood risk processes, covering causative meteorological processes, hydrological and hydraulic processes in catchments and rivers, as well as implications of protection measures and adverse consequences of flooding. We develop and couple simulation models for these processes, using new data sources and new methods.

What is the data science project’s research question? How can we combine and update data from heterogeneous data sources for rapid flood inundation mapping? 

What data will be worked on? Remote sensing based flood masks, water level observations, geo-located photos of flooded areas, web cam live streams

What tasks will this project involve? The project will include the concept development for combining information from different data sources, the selection and data-science methods, implementation and testing of algorithms and prototype implementation.

What makes this project interesting to work on? Globally increasing flood losses underline the need for effective emergency response and recovery. Knowing the inundation situation and resulting losses during or shortly after a flood is crucial for decision making in emergency response and recovery. With increasing amounts of data available from a growing number and diversity of sensors and data sources, data science methods offer great opportunities for combining data and extracting knowledge about flood processes in near real-time. 

What is the expected outcome? Contribution to research paper

What infrastructure, programs and tools will be used? Can they be used remotely?  Algorithms will be implemented in Python3.9 (using e.g. xarray, rioxarray, geopanda packages) within the GitLab software development platform for working collaboratively and remotely.

What skills are necessary for this project? Data analytics / statistics, Data mining / Machine learning, Geographic Information Systems

Is the data open source? partly open source 

Interested candidates should be at Master level.  Kai Schröter is looking for 1 visiting scientist, working on the project together with the team.