Mozambique tested drone-and-AI malaria control across six areas—but results are not yet reported
The three-month Matola pilot compared technology-guided larval control with conventional control and no intervention. WHO disclosed the design and baseline, not comparative effects.
The short version
- What happened
- WHO ran a three-month pilot in six areas of Matola, comparing drone-and-AI-guided larval control with conventional control and areas receiving no larval-control intervention.
- Who it affects
- Residents may benefit if field teams find urban breeding sites faster, but the public report does not show fewer mosquitoes or malaria cases. Entomologists and community workers remained essential to verification, treatment and trust.
- What remains unproven
- Three-month pilot
Keep in mind
Three-month pilot
Six areas of Matola
176 baseline water bodies
Comparator design described
AI accuracy absent
Group denominators absent
No malaria outcome results
Source analysis · 1 linked source. Primary analysed source date: 29 October 2026.
Read the full report · 4 min The evidence, methods, implications and limitations
AI helped decide where field teams should look
A three-month public-health pilot in Matola, Mozambique used drones and artificial intelligence to flag possible mosquito breeding sites before entomologists checked them on the ground, WHO reported on 29 October. Confirmed sites were added to digital maps that guided targeted application of a WHO-prequalified larvicide. The aim was to make urban larval surveillance faster in residential and hard-to-reach areas, not to replace field expertise.
The project compared technology-assisted larval control in six areas with conventional larval control and with places where no larval-control intervention occurred. That comparator structure is more informative than a simple demonstration. At the end of May, teams assessed 176 water bodies for baseline data and detected Anopheles larvae at all six study sites. Later work included habitat checks, adult-mosquito trapping, field visits and laboratory analysis.[1]
The intervention mixed technology with people and training
The AI component was only one link in the chain. Drones supplied high-resolution images; software identified candidate locations; entomologists verified them; a digital platform organised the field record; and trained teams carried out treatment and surveillance. WHO says 19 entomology assistants and surveillance staff received basic entomology training, 14 technicians learned the digital platform and 13 community mobilisers supported neighbourhood work.
That human workflow matters because a map error can send scarce teams to the wrong place, while a technically correct location may still be inaccessible or unacceptable to residents. Community meetings and local mobilisation were part of the pilot. The report says the programme gained a new way to scan large areas, but it does not separate the contribution of AI from drones, extra surveillance, training, mapping, community engagement or the larvicide itself.[1]
The distinction that matters
How a candidate site became a treatment target
The intervention kept people at the verification and delivery stages.
Survey
Drone captures high-resolution images
AI flags possible breeding sites
Verify
Entomologists inspect candidates
Confirmed sites enter digital maps
Act
Field teams target larvicide and monitor
Comparative health effect not yet published
A real-world pilot without an effectiveness result
WHO describes the work as generating operational evidence, yet the published page does not report how the six areas were allocated, their population or area, how many sites AI flagged, how many were confirmed, or the system's sensitivity and false-positive rate. It also gives no comparative change in larval density, adult mosquitoes, malaria infections, staff time, cost or unintended environmental effects. Baseline presence is not an outcome.
Unitaid funded the project, which WHO implemented with Mozambique's Ministry of Health and technical partners. A stronger assessment would publish the protocol and full denominator, pre-specified outcomes, group-by-group results, uncertainty and costs, then test whether effects persist across seasons and other cities. Until those data appear, the pilot demonstrates an operational pathway and local capacity building—not that AI-guided control reduced malaria transmission.[1]