Identifying Disaster Impacted Areas with Machine Learning and Geospatial Analysis Using Twitter Data

Date: 

Thursday, March 7, 2019, 12:00pm

Location: 

CGIS South, Room S050

By Clemens Havas, University of Salzburg

Abstract: Emergency management relies on up-to-date information about the impact of a disaster in an area. However, current emergency systems rely on data sources that do not provide a complete geospatial and temporal view of the disaster or have a temporal lag due to activation or orbital constraints. To fill these important information gaps, georeferenced social media posts are analysed in near-real time. The Evolution of Copernicus Services (E2mC) - project aims at demonstrating the technical and operational feasibility of the integration of social media analysis and crowdsourcing by developing a prototype of the innovative Copernicus Witness, a new Copernicus Emergency Management Service component. In this talk one particular module of this new component is presented that analyses Twitter data and provides a “big picture” of the area of interest. Semi-supervised topic models enable the automatic interpretation of topics to identify disaster-relevant information as the social media corpus includes a high degree of noise. A hot spot analysis is applied on the extracted posts that creates hot and cold spots in the area of interest. In this talk multiple use cases of hurricanes and other disasters in the last years are presented that demonstrate the provided information of this methodology in real use cases. The trajectory of the hurricanes as well as the impacted areas could be visualised on maps by distinctly highlighting the impacted areas.

Speaker Bio: Clemens Havas is a PhD candidate at University of Salzburg’s Department of Geoinformatics – Z_GIS with a background in computer science. He specializes in combining state-of-the-art machine learning algorithms with geospatial analysis to extract information about large-scale events like natural disasters. The information is provided in near real-time after the outbreak of an event by utilizing new data sources like social media networks.

Lunch will be served.