Duration: 2005 - 2014
is an interdisciplinary research project of Karlsruhe Institute of Technology (KIT) and GFZ in the area of disaster management. Our contribution is the development of web-based information systems for risk management, like RiskExplorer, as well as innovative methods for extracting and providing up-to-date information from social media, i.e., Twitter, for rapid damage assessment.
To make use of data from social media in disaster management, methods and procedures must be developed to filter out appropriate data from the huge amount of information. A Subgoal of the project is the automated localization of information, in which the partially implicit spatial references of the information is placed in a local spatial context. Another subgoal is to provide quality assessments and evaluations of extracted observations for specific problems. These observations are classified by means of machine learning techniques in terms of their content.
Dransch, D.; Rotzoll, H.; Poser, K. (2010): The contribution of maps to the challenges of risk communication to the public. International Journal of Digital Earth, 3, 3, 292-311.
Poser, K.; Dransch, D. (2010): Volunteered geographic information for disaster management with application to rapid flood damage estimation. Geomatica, 64, 1, 89-98.
Prof. Dr. Doris Dransch