Estimating Malaria Mobility in Mozambique

An infected traveler can carry malaria parasites from one region to another. In Mozambique, we used aggregated mobile-network data to estimate how often those movements occurred and where they might take the parasite.

The dataset contained four months of anonymized, aggregated records from more than 8.5 million mobile subscribers; we combined the observed mobility patterns with estimates of malaria prevalence to identify areas more likely to receive or export infections.

The two maps were not the same. Estimated parasite movements sometimes followed different routes from the overall movement of people, a distinction that can affect where malaria-control resources are allocated and which routes of transmission receive priority.

Vodafone worked with Mozambique's National Malaria Control Programme, the Clinton Health Access Initiative, and WorldPop at the University of Southampton. The Bill & Melinda Gates Foundation supported the project.

Human travel formed two broad regional groups, while estimated parasite movement formed three.

Publication

@inproceedings{floyd2020malaria,
  author = {Jessica R. Floyd and Pedro Rente Lourenço and Nick W. Ruktanonchai and Andrew J. Tatem and James M. Colborn and Baltazar Candrinho and Nuria Oliver},
  title = {Malaria Parasite Mobility in Mozambique Estimated Using Mobile Phone Records},
  booktitle = {Proceedings of the European Conference on Artificial Intelligence (ECAI 2020)},
  address = {Santiago de Compostela, Spain},
  year = 2020,
  doi = {10.3233/faia200444},
  file = {/projects/malaria-mobility-mozambique/malaria-mobility-mozambique.pdf},
  cites = 0,
  citesdate = {2026-03-23}
}

More information

• Read the publication
• Read Vodafone's account of the project