Exploring the Potential of Machine and Deep Learning Models for OpenStreetMap Data Quality Assessment and Improvement (Short Paper)

Authors Salim Miloudi , Bouhadjar Meguenni

Thumbnail PDF


  • Filesize: 0.5 MB
  • 6 pages

Document Identifiers

Author Details

Salim Miloudi
  • Spatial Reference Information Systems Department, Space Techniques Center, Oran, Algeria
Bouhadjar Meguenni
  • Spatial Reference Information Systems Department, Space Techniques Center, Oran, Algeria


We would like to thank the anonymous reviewers for their valuable comments.

Cite AsGet BibTex

Salim Miloudi and Bouhadjar Meguenni. Exploring the Potential of Machine and Deep Learning Models for OpenStreetMap Data Quality Assessment and Improvement (Short Paper). In 12th International Conference on Geographic Information Science (GIScience 2023). Leibniz International Proceedings in Informatics (LIPIcs), Volume 277, pp. 53:1-53:6, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2023)


The OpenStreetMap (OSM) project is a widely-used crowdsourced geographic data platform that allows users to contribute, edit, and access geographic information. However, the quality of the data in OSM is often uncertain, and assessing the quality of OSM data is crucial for ensuring its reliability and usability. Recently, the use of machine and deep learning models has shown to be promising in assessing and improving the quality of OSM data. In this paper, we explore the current state-of-the-art machine learning models for OSM data quality assessment and improvement as an attempt to discuss and classify the underlying methods into different categories depending on (1) the associated learning paradigm (supervised or unsupervised learning-based methods), (2) the usage of extrinsic or intrinsic-based metrics (i.e., assessing OSM data by comparing it against authoritative external datasets or via computing some internal quality indicators), and (3) the use of traditional or deep learning-based models for predicting and evaluating OSM features. We then identify the main trends and challenges in this field and provide recommendations for future research aiming at improving the quality of OSM data in terms of completeness, accuracy, and consistency.

Subject Classification

ACM Subject Classification
  • Information systems → Geographic information systems
  • OpenStreetMap (OSM)
  • Volunteered Geographic Information (VGI)
  • Machine Learning (ML)
  • Deep Learning (DL)
  • Quality Assessment (QA)
  • Building Footprint Detection
  • Semantic Segmentation


  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    PDF Downloads


  1. Ahmed Loai Ali, Falko Schmid, Rami Al-Salman, and Tomi Kauppinen. Ambiguity and plausibility: Managing classification quality in volunteered geographic information. In Proceedings of the 22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, SIGSPATIAL '14, pages 143-152, New York, NY, USA, 2014. Association for Computing Machinery. URL: https://doi.org/10.1145/2666310.2666392.
  2. Jamal Jokar Arsanjani and Eric Vaz. An assessment of a collaborative mapping approach for exploring land use patterns for several european metropolises. International Journal of Applied Earth Observation and Geoinformation, 2015. URL: https://doi.org/10.1016/j.jag.2014.09.009.
  3. Nicolas Audebert, Bertrand Le Saux, and Sébastien Lefèvre. Joint learning from earth observation and openstreetmap data to get faster better semantic maps. CoRR, abs/1705.06057, 2017. URL: https://arxiv.org/abs/1705.06057.
  4. Hongchao Fan, Alexander Zipf, Qing Fu, and Pascal Neis. Quality assessment for building footprints data on openstreetmap. International Journal of Geographical Information Science, 2014. URL: https://doi.org/10.1080/13658816.2013.867495.
  5. Cidália Costa Fonte, Lucy Bastin, Linda See, Giles M. Foody, and Flavio Lupia. Usability of vgi for validation of land cover maps. International Journal of Geographical Information Science, 2015. URL: https://doi.org/10.1080/13658816.2015.1018266.
  6. Stefan Funke, Robin Schirrmeister, and Sabine Storandt. Automatic extrapolation of missing road network data in openstreetmap. In Proceedings of the 2nd International Conference on Mining Urban Data - Volume 1392, MUD'15, pages 27-35, Aachen, DEU, 2015. CEUR-WS.org. Google Scholar
  7. Jean-François Girres and Guillaume Touya. Quality assessment of the french openstreetmap dataset. Transactions in Gis, 2010. URL: https://doi.org/10.1111/j.1467-9671.2010.01203.x.
  8. Marcus Goetz and Alexander Zipf. Using crowdsourced geodata for agent-based indoor evacuation simulations. ISPRS international journal of geo-information, 2012. URL: https://doi.org/10.3390/ijgi1020186.
  9. Michael F. Goodchild. Citizens as sensors: the world of volunteered geography. GeoJournal, 2007. URL: https://doi.org/10.1007/s10708-007-9111-y.
  10. Mordechai Haklay. How good is volunteered geographical information? a comparative study of openstreetmap and ordnance survey datasets:. Environment and Planning B-planning & Design, 2010. URL: https://doi.org/10.1068/b35097.
  11. Benjamin Herfort, Hao Li, Sascha Fendrich, Sven Lautenbach, and Alexander Zipf. Mapping human settlements with higher accuracy and less volunteer efforts by combining crowdsourcing and deep learning. Remote Sensing, 11(15), 2019. URL: https://doi.org/10.3390/rs11151799.
  12. Kent T. Jacobs and Scott W. Mitchell. Openstreetmap quality assessment using unsupervised machine learning methods. Transactions in GIS, 24(5):1280-1298, 2020. URL: https://doi.org/10.1111/tgis.12680.
  13. Musfira Jilani, Michela Bertolotto, Padraig Corcoran, and Amerah Alghanim. Traditional vs. machine-learning techniques for OSM quality assessment. In Cláudio Elízio Calazans Campelo, Michela Bertolotto, and Padraig Corcoran, editors, Volunteered Geographic Information and the Future of Geospatial Data, pages 47-64. IGI Global, 2017. URL: https://doi.org/10.4018/978-1-5225-2446-5.ch003.
  14. Musfira Jilani, Padraig Corcoran, and Michela Bertolotto. Automated highway tag assessment of openstreetmap road networks. In Proceedings of the 22nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, SIGSPATIAL '14, pages 449-452, New York, NY, USA, 2014. Association for Computing Machinery. URL: https://doi.org/10.1145/2666310.2666476.
  15. Thomas Koukoletsos, Mordechai Haklay, and Claire Ellul. Assessing data completeness of vgi through an automated matching procedure for linear data. Transactions in Gis, 2012. URL: https://doi.org/10.1111/j.1467-9671.2012.01304.x.
  16. Bill Y Lin, Frank F Xu, Eve Q Liao, and Kenny Q Zhu. Transfer learning for traffic speed prediction: A preliminary study. In Workshops at the Thirty-Second AAAI Conference on Artificial Intelligence, 2018. Google Scholar
  17. Aphiwe Madubedube, Serena Coetzee, and Victoria Rautenbach. A contributor-focused intrinsic quality assessment of openstreetmap in mozambique using unsupervised machine learning. ISPRS International Journal of Geo-Information, 10(3), 2021. URL: https://doi.org/10.3390/ijgi10030156.
  18. Volodymyr Mnih and Geoffrey Hinton. Learning to label aerial images from noisy data. In Proceedings of the 29th International Coference on International Conference on Machine Learning, ICML'12, pages 203-210, Madison, WI, USA, 2012. Omnipress. Google Scholar
  19. Peter Mooney and Padraig Corcoran. The annotation process in openstreetmap. Transactions in Gis, 2012. URL: https://doi.org/10.1111/j.1467-9671.2012.01306.x.
  20. Pascal Neis and Dennis Zielstra. Recent developments and future trends in volunteered geographic information research: The case of openstreetmap. Future Internet, 2014. URL: https://doi.org/10.3390/fi6010076.
  21. Pascal Neis, Dennis Zielstra, and Alexander Zipf. The street network evolution of crowdsourced maps: Openstreetmap in germany 2007-2011. Future Internet, 2011. URL: https://doi.org/10.3390/fi4010001.
  22. Martin Over, Arne Schilling, S. Neubauer, and Alexander Zipf. Generating web-based 3d city models from openstreetmap: The current situation in germany. Computers, Environment and Urban Systems, 2010. URL: https://doi.org/10.1016/j.compenvurbsys.2010.05.001.
  23. J. Pisl, H. Li, S. Lautenbach, B. Herfort, and A. Zipf. Detecting openstreetmap missing buildings by transferring pre-trained deep neural networks. AGILE: GIScience Series, 2:39, 2021. URL: https://doi.org/10.5194/agile-giss-2-39-2021.
  24. Hansi Senaratne, Amin Mobasheri, Ahmed Loai Ali, Cristina Capineri, and Mordechai Haklay. A review of volunteered geographic information quality assessment methods. International Journal of Geographical Information Science, 2017. URL: https://doi.org/10.1080/13658816.2016.1189556.
  25. Shivangi Srivastava, John E. Vargas Muñoz, Sylvain Lobry, and Devis Tuia. Fine-grained landuse characterization using ground-based pictures: a deep learning solution based on globally available data. International Journal of Geographical Information Science, 2018. URL: https://doi.org/10.1080/13658816.2018.1542698.
  26. Shivangi Srivastava, John E. Vargas-Munoz, and Devis Tuia. Understanding urban landuse from the above and ground perspectives: A deep learning, multimodal solution. Remote Sensing of Environment, 2019. URL: https://doi.org/10.1016/j.rse.2019.04.014.
  27. John E. Vargas-Munoz, Sylvain Lobry, Alexandre X. Falcão, and Devis Tuia. Correcting rural building annotations in openstreetmap using convolutional neural networks. Isprs Journal of Photogrammetry and Remote Sensing, 2019. URL: https://doi.org/10.1016/j.isprsjprs.2018.11.010.
  28. Yongyang Xu, Zhanlong Chen, Zhong Xie, and Liang Wu. Quality assessment of building footprint data using a deep autoencoder network. International Journal of Geographical Information Science, 2017. URL: https://doi.org/10.1080/13658816.2017.1341632.
  29. Xiao Xiang Zhu, Devis Tuia, Lichao Mou, Gui-Song Xia, Liangpei Zhang, Feng Xu, and Friedrich Fraundorfer. Deep learning in remote sensing: A comprehensive review and list of resources. IEEE Geoscience and Remote Sensing Magazine, 2017. URL: https://doi.org/10.1109/mgrs.2017.2762307.
  30. Alexander Zipf, Steffen Neubauer, G Walenciak, Martin Over, Pascal Neis, and Arne Schilling. Interoperable location based services for 3d cities on the web using user generated content from openstreetmap. Urban and Regional Data Management, 2009. URL: https://doi.org/10.1201/9780203869352.ch7.
Questions / Remarks / Feedback

Feedback for Dagstuhl Publishing

Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail