In the last decade, flood events have cost more than US$100 billion, with more than 100,000 people being killed, and 1 billion left without a home worldwide. A quick response can substantially reduce the damage caused by floods. However, the rapid provision of damage information for floods is challenging and remains barely explored. In this project, we aim to develop an approach to rapidly assess building damage after flood events. Particularly, we propose to explore three machine learning-based approaches: (i) a multi-sensor change detection method to provide near real-time damage assessment, (ii) a large-scale building footprint damage assessment technique, benefiting from existing global urban mapping data, and (iii) a semi-supervised and few-shot learning approach, to include the few labelled data collected in the early stage of the flood. We will study the uncertainty and evaluate the quality of the rapid flood-damage assessment models using empirical data. The expected results of this project, i.e., the methods for rapid flood-damage assessment, will be of high relevance for the (re)insurance industry as well as for regional and national governments to support decisions about flood compensation programmes and reconstruction activities.

The SURF project is being carried out in cooperation between the German Aerospace Agency (DLR) as coordinator and the GFZ Helmholtz Centre for Geosciences.