Completed Plants, Animals & Ecology Infection & Immunity

Using novel technologies for real-time monitoring of the risk of mosquito- borne diseases in the context of climate and land-use changes

In plain English

AI plain-English summary

Warmer winters and heavier rains are already reshaping where mosquitoes can survive and breed, but current climate-disease models are too crude to predict local outbreaks. The problem is that most models treat entire regions as uniform, ignoring local details like whether a village’s water storage containers breed dengue mosquitoes or whether a drought has wiped out the malaria vector *Anopheles gambiae*. This project will deploy Microsoft’s Premonition platform—an automated trap that identifies captured mosquitoes in real time—across sites in Tanzania. By feeding that high-resolution entomological data into machine-learning models alongside local weather and land-use records, the team aims to predict transmission risk at a neighbourhood scale. If successful, the approach could transform how public health agencies allocate resources. Instead of blanket spraying or waiting for case reports, officials could target insecticide, bed nets, or larvicide to specific areas days or weeks before an outbreak. The same data streams could also reveal how different mosquito species adapt to shifting climates—for example, whether *Aedes aegypti* exploits new container habitats after floods—giving researchers a real-time window into how land-use change drives disease risk.

View original technical description
Transmission of mosquito-borne diseases can be affected by climate and land- use patterns in different ways. Increased temperatures can shorten the latency of malaria parasites thereby enabling transmission in previously-temperate zones. Yet extended droughts could crash populations of vectors such as Anopheles gambiae, which breed in small, open and drought-sensitive habitats. In contrast, flooding can increase populations of container-breeding dengue vectors, Aedes aegypti. Most investigations of climate and vector-borne diseases are too expansive to be computationally-practical; and often overlook local data on entomological, anthropological or land-use characteristics. Fortunately, advanced cloud-based data processing, sensor design and on-board computing now enable highly-sensitive multi-modal systems with real-time data acquisition and integration. Microsoft Premonition offers a surveillance platform that autonomously lures, identifies and selectively captures arthropods for downstream studies, including metagenomics. With Gates- Foundation support, we are deploying this system in Tanzania to enhance malaria vector surveillance. Here, we propose extending the Premonition platform to investigate local associations between climate, land-use and mosquito-borne diseases. By combining capabilities in vector-biology, spatial analytics, machine learning and mathematical modeling, we will: i) integrate environmental and entomological data-streams to predict transmission risk, ii) investigate climate-dependent survival strategies of medically-important mosquitoes and iii) evaluate entomological data for monitoring climate and land-use.

View the original record at the funder ↗

Researchers

David Smith (EPMC Awardee)Douglas Norris (EPMC Awardee)Emmanuel Kaindoa (EPMC Awardee)Ethan Jackson (EPMC Awardee)Fredros Okumu (EPMC Awardee)Isaiah Hoyer (EPMC Awardee)Michael Reddy (EPMC Awardee)Simon Frost (EPMC Awardee)

Related Research

Grants with similar aims, by meaning.

Mosquitoes populations modelling for early warning system and rapid response public by health authorities correlating climate, weather and spatial-tem
Improving malaria risk assessment in Blantyre district, Malawi by optimizing Anopheles surveillance using open-source and real-time data
Harnessing publicly available geospatial data to guide vector-borne disease interventions in sub-Saharan Africa
Development of a new tool for malaria mosquito surveillance to improve vector control
Still Waters: using hydrological models to improve malaria transmission estimates

Original classification

Discretionary Award

Plain English summaries and category classifications on this site are generated by AI and may not perfectly reflect the original research.