Alexander von Humboldt Foundation (AvH)

Forschungsprojekt: Prediction of OpenStreetMap Data

How Good Can Agent-Based Modeling Predict OpenStreetMap Data?

The main objective of this research project is to monitor the spatio-temporal pattern of OpenStreetMap (OSM) dataset so far and also develop a new method for predicting its future states through Agent-Based Modeling (ABM). The project is intended to measure and monitor several data quality aspects over the OSM lifetime. Since OSM is growing fast and being employed in a broad range of applications, modeling the past, current, and future states of OSM contributions and contributors is a demanding research agenda. As individuals are the main actors in OSM project, ABM seems to be the most appropriate modeling technique to project the behaviors of actors (contributors) together with the contributions. Contributors are considered as agents and their contributions as their behaviors within the OSM environment.

The OSM contributions labeled by their contributors are examined and compared against the proprietary data in order to identify the data quality aspects and possibly indicate new quality indicators suitable for OSM datasets. Subsequently, the contributors’ mapping behaviors are recognized and possible correlations between the contributors mapping behaviors and socio-demographic data and land features are ascertained. Therefore, a simulation environment has to be designed in order to study the progress of OSM across time and space and also consequently to develop a novel technique based on ABM to figure out how the future status of OSM could be drawn.

The project helps to get to know the contributors in a better and computational way and accordingly predict their contributions automatically. The expected developed method can be applied for other VGI-based projects in order to obtain a better understanding of interactions between humans and collaborative mapping projects. The project is intended to address the following research questions:

  • What are the characteristics and behaviors of OSM contributors that can be extracted from the OSM history file?
  • Is it possible to model the characteristics and behaviors of contributors? If so, is agent-based modeling capable of simulation of forthcoming contributions based on users’ specifications?
  • How reliable can we model the future states of OSM dataset using ABM?
  • What factors associated to the volunteers influence the quality of OSM data? Which recommendations could be given to improve the quality of OSM contributions?
Further reading

Book Chapters

  • Jokar Arsanjani, J., Mooney, P., Zipf, A., Schauss, A., (2015): Quality assessment of the contributed land use information from OpenStreetMap versus authoritative datasets. In: Jokar Arsanjani, J., Zipf, A., Mooney, P., Helbich, M., OpenStreetMap in GIScience: experiences, research, applications. ISBN:978-3-319-14279-1, PP. 37-58, Springer Press.
  • Jokar Arsanjani, J., Zipf, A., Mooney, P., Helbich, M., (2015): An introduction to OpenStreetMap in GIScience: Experiences, Research, Applications. In: Jokar Arsanjani, J., Zipf, A., Mooney, P., Helbich, M., OpenStreetMap in GIScience: experiences, research, applications. ISBN:978-3-319-14279-1, PP. 1-15, Springer Press.
  • Helbich, M., Jokar Arsanjani, J., & Leitner, M. (2015). Computational Approaches for Urban Environments: An Editorial. In M. Helbich, J. Jokar Arsanjani, & M. Leitner (Eds.), Computational Approaches for Urban Environments SE – 1 (Vol. 13, pp. 1–9). Springer International Publishing. doi:10.1007/978-3-319-11469-9_1.
  • Bakillah, M., Lauer, J., Liang, S., Zipf, A., Jokar Arsanjani, J., Loos, L., Mobasheri, A., (2014): Exploiting Big VGI to Improve Routing and Navigation Services, a book chapter in Karimi H, Big Data Techniques and Technologies in Geoinformatics.
  • Sester, M., Jokar Arsanjani, J., Klammer, R., Burghardt, D., & Haunert, J.-H. (2014). Integrating and Generalising Volunteered Geographic Information. In D. Burghardt, C. Duchêne, & W. Mackaness (Eds.), Abstracting Geographic Information in a Data Rich World SE – 5 (pp. 119–155). Springer International Publishing. doi:10.1007/978-3-319-00203-3_5.

Journal Papers

Conference Papers

Seitenbearbeiter: Webmaster-Team
Latest Revision: 12.04.2015
zum Seitenanfang/up