Advancing Data for Street-level Flood Vulnerability: Extraction of Variables from Google Street View in Quito, Ecuador
This addresses the problem of limited flood vulnerability data for humanitarian aid and community support in urban areas, though it is incremental as it focuses on data collection rather than automation.
The paper tackled the lack of flood vulnerability data in many regions by developing a mixed-methods approach using crowdsourcing with satellite images and Google Street View to extract variables in Quito, Ecuador, aiming to build training datasets for future automated mapping.
Data relevant to flood vulnerability is minimal and infrequently collected, if at all, for much of the world. This makes it difficult to highlight areas for humanitarian aid, monitor changes, and support communities in need. It would be time consuming and resource intensive to do an exhaustive study for multiple flood relevant vulnerability variables using a field survey. We use a mixed methods approach to develop a survey on variables of interest and utilize an open-source crowdsourcing technique to remotely collect data with a human-machine interface using high-resolution satellite images and Google Street View. This paper focuses on Quito, Ecuador as a case study, but the methodology can be quickly replicated to produce labelled training data in other areas. The overall project goal is to build training datasets that in the future will allow us to automate the mapping of flood vulnerability for urban areas in geographic regions.