From 1-3 September 2026, MAP Dar, in partnership with the Manhiça Health Research Center (CISM) and the Clinton Health Access Initiative (CHAI), hosted a three-day intensive training on “Geospatial Modelling for Public Health Applications.” The program concluded with the graduation of 29 participants from government and non-governmental institutions, including the Mozambican and Angolan National Malaria Control Programmes, CISM and Malaria Consortium. This is part of the workshop series from the MaMOD Africa consortium led by African Institute for Mathematical Science (AIMS) funded by the Gates Foundation Grand Challenges.

The training tackled a crucial question in malaria research: why can neighbouring areas show drastically different malaria risks? Participants built up an intuition for geospatial modelling including advanced techniques like INLA models, learned to fill gaps in surveillance data, visualize patterns accurately, and generate actionable insights to guide malaria control efforts in underreported and hard-to-reach areas.

The workshop was lead by Dr Punam Amratia, and facilitated by Herieth Mboya (MAP Dar) and Ernest Moyo (MAP Dar/Vector Atlas) and Yuval Berman (MAP Perth), enriched by insights from James Colborn and Josh Fortmann (CHAI epidemiologists), as well as Alfredo Muxlhanga (lecturer at Universidade Eduardo Mondlane). The course combined world-class expertise with practical, hands-on learning.

Feedback from the workshop was hugely positive, given an overall rating of 4.6/5, and a rating of 4.9/5 for the question “would you recommend this workshop to a colleague”.

As the second workshop in the Geospatial modelling series by MaMOD Africa, participants return to their institutions ready to apply their skills, strengthening research, policy, and practice to drive real-world public health impact across Mozambique. Our next workshop is currently in planning for the Benin malaria program and partners in the west Africa region as part of MaMOD Africa’s consortium’s effort to improve policy makers understanding of modelling to support decision making.