UNU-INWEH is developing a flood mapping and future flood risk prediction tool. This tool consists of two modules; a flood mapping module that addresses the data gap of historical flood maps and a flood risk predicting module, which addresses the issue of possible risk in the future. The historical flood mapping module uses a water classification algorithm (Modified Normalized Difference Water Index) applied to ‘stacks’ of historical Landsat and Sentinel 2 satellite imagery to reveal patterns of inundationover space and time across the landscapes. The prototype of the tool is ready, which uses Landsat data to identify water patterns.The second module will use AI models to predict the future flood risk for a given area. The AI models will be trained usingthe historical flood maps from the first module, and open temporal datasets including land use land cover, population, infrastructure, precipitation, temperature, and sex and age disaggregated socio-economic data. This module will help identify the most flood-risk areas for the future. We are looking for an intern who can work remotely to assist in the development of the first module of the tool by integrating the Harmonized Landsat Sentinel-2 data.
Description of Responsibilities
- Integrate the Harmonized Landsat Sentinel–2 data.
- Test the integration against recent flood events (validation data is available).
- Optimize the HFMT system flow where possible.
- Undertake additional tasks as assigned by the supervisor