Title: Can real-time crisis SMS messages help in diagnosing the spatial distribution of structural damage? Analysis of the relationship between the distribution of damage and the location of SMS messages sent during the Haiti crisis
Authors: CORBAN CHRISTINALEMOINE GuidoKAUFFMANN MAYEUL
Citation: Proceedings of the 2nd International workshop on Validation of geo-information products for crisis management - VALgEO 2010 - ISBN 978-92-79-15630 p. 117-125
Publisher: Publications Office of the European Union
Publication Year: 2010
JRC N°: JRC61864
URI: http://publications.jrc.ec.europa.eu/repository/handle/JRC61864
DOI: 10.2788/15759
Type: Contributions to Conferences
Abstract: Just 4 days after the earthquake, Haitians could send SMS messages on their location and urgent needs through the on-line mapping platform Ushahidi. The real-time crowd-sourcing of crisis information provided direct support to key humanitarian actors on the ground including Search and Rescue teams. In addition to its use as a knowledge base for rescue operations, the spatial distribution of geolocated SMS messages could represent an interesting early indicator on the distribution and on the intensity of building damage. This work explores the relationship between the spatial patterns of SMS messages and building damage. The latter correspond to the detailed damage assessments of individual buildings conducted on post-earthquake airborne photos. The interaction between SMS messages and building damage is studied by analyzing the spatial structure of the corresponding bivariate patterns. This is performed through the implementation of cross Ripley¿s K-function which is suitable for characterizing the spatial structure of a bivariate pattern, and more precisely the spatial relationship between two types of points located in the same study area. The results show a strong attraction between the patterns exhibited by SMS messages and building damages. They also prove that the distributions of SMS messages and building damages are not spatially independent. The interactions identified between the two patterns suggest that the geolocated SMS can be used as early indicators of the spatial distribution of building damage. Accordingly a statistical model has been developed allowing to map the distribution of building damage from the geolocated SMS. The preliminary results will be presented and discussed.
JRC Institute:Institute for the Protection and Security of the Citizen

Files in This Item:
There are no files associated with this item.


Items in repository are protected by copyright, with all rights reserved, unless otherwise indicated.