A Data Fusion Framework for Exploring Mobility Around Disruptive Events (Short Paper)

Authors Evgeny Noi , Somayeh Dodge

Thumbnail PDF


  • Filesize: 1.59 MB
  • 6 pages

Document Identifiers

Author Details

Evgeny Noi
  • Department of Geography, University of California Santa Barbara, CA, USA
Somayeh Dodge
  • Department of Geography, University of California Santa Barbara, CA, USA


The authors gratefully acknowledge the support from the National Science Foundation through award BCS #2043202. Mobility data provided by ©MapBox and ©SafeGraph.

Cite AsGet BibTex

Evgeny Noi and Somayeh Dodge. A Data Fusion Framework for Exploring Mobility Around Disruptive Events (Short Paper). In 12th International Conference on Geographic Information Science (GIScience 2023). Leibniz International Proceedings in Informatics (LIPIcs), Volume 277, pp. 57:1-57:6, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2023)


This paper proposes a data fusion framework that seeks to investigate joint mobility signals around wildfires in relation to geographic scale of analysis (level of spatial aggregation), as well as spatial and temporal extents (i.e. distance to the event and duration of the observation period). We highlight the usefulness of our framework using intra-urban mobility data from Mapbox and SafeGraph for two wildfires in California: Lake Fire (August-September 2020, Los Angeles County) and Silverado Fire (October-November 2020, Orange County). We identify two distinct patterns of mobility behavior: one associated with the wildfire event and another one - with the routine daily mobility of the nearby urban core. Using the combination of data fusion and tensor decomposition, the framework allows us to capture additional insights from the data, that were otherwise unavailable in raw mobility data.

Subject Classification

ACM Subject Classification
  • Information systems → Geographic information systems
  • geographic extent
  • geographic scale
  • tensor decomposition
  • spatio-temporal analysis


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


  1. Somayeh Dodge. A data science framework for movement. Geographical Analysis, 53(1):92-112, 2021. URL: https://doi.org/10.1111/gean.12212.
  2. A Stewart Fotheringham and David WS Wong. The modifiable areal unit problem in multivariate statistical analysis. Environment and planning A, 23(7):1025-1044, 1991. URL: https://doi.org/10.1068/a231025.
  3. Michael F Goodchild. A GIScience perspective on the uncertainty of context. Annals of the American Association of Geographers, 108(6):1476-1481, 2018. URL: https://doi.org/10.1080/24694452.2017.1416281.
  4. Henk AL Kiers, Jos MF Ten Berge, and Rasmus Bro. PARAFAC2—Part I. A direct fitting algorithm for the PARAFAC2 model. Journal of Chemometrics: A Journal of the Chemometrics Society, 13(3-4):275-294, 1999. URL: https://doi.org/10.1002/(SICI)1099-128X(199905/08)13:3/4%3C275::AID-CEM543%3E3.0.CO;2-B.
  5. Mei-Po Kwan and Tijs Neutens. Space-time research in GIScience. International Journal of Geographical Information Science, 28(5):851-854, 2014. URL: https://doi.org/10.1080/13658816.2014.889300.
  6. Evgeny Noi, Alexander Rudolph, and Somayeh Dodge. Assessing COVID-induced changes in spatiotemporal structure of mobility in the United States in 2020: a multi-source analytical framework. International Journal of Geographical Information Science, 36(3):585-616, 2022. URL: https://doi.org/10.1080/13658816.2021.2005796.
  7. Evangelos E Papalexakis, Christos Faloutsos, and Nicholas D Sidiropoulos. Tensors for data mining and data fusion: Models, applications, and scalable algorithms. ACM Transactions on Intelligent Systems and Technology (TIST), 8(2):1-44, 2016. URL: https://doi.org/10.1145/2915921.
  8. Marie Roald. MatCoupLy: Learning coupled matrix factorizations with Python. SoftwareX, 21:101292, 2023. URL: https://doi.org/10.1016/j.softx.2022.101292.
  9. Marie Roald, Carla Schenker, Vince D Calhoun, Tulay Adali, Rasmus Bro, Jeremy E Cohen, and Evrim Acar. An AO-ADMM approach to constraining PARAFAC2 on all modes. SIAM Journal on Mathematics of Data Science, 4(3):1191-1222, 2022. URL: https://doi.org/10.1137/21M1450033.
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