Full Program »
Using Expert Crowdsourcing To Annotate Extreme Weather Events
The harsh impacts of extreme weather events like cyclones or precipitation extremes are increasingly being felt with hazardous consequences. These ex-treme events are exceptions to well-known weather patterns and therefore are not forecasted with current automatic computational methods. In this context, the use of human computation to annotate extreme atmospheric phenomena could provide novel insights for computational forecasting algo-rithms and a step forward in climate change research by enabling the early detection of abnormal weather conditions. However, existing crowd compu-ting solutions have technological limitations and show several gaps when involving expert crowds. This paper presents a research approach to fulfill some of the current technological and knowledge gaps for expert crowds’ participation. A case study on expert annotation of extreme atmospheric phenomena is used as a baseline for an innovative architecture that supports expert crowds’ participation. The full stack service-oriented architecture en-sures interoperability and provides an end-to-end approach able to fetch weather data from international databases, generating experts’ visualizations (weather maps), annotating data by expert crowds, and delivering annotated data for processing weather forecasts. An implementation of the architecture suggests that it can deliver an effective expert crowdsourcing mechanism while solving some of the identified issues with extant platforms. Therefore, we conclude that the proposed architecture has the potential to contribute as an effective annotation solution for extreme weather events using expert crowdsourcing.