A new app to identify mosquito breeding habitats in East Africa

By PAULINE KAIRU

East Africa is testing a new technology that identifies the locations of previously unknown mosquito breeding habitats and treats them in the same day.

The technology involves a smartphone app that combines an algorithm with a drone and satellite data using geospatial artificial intelligence to identify locations of previously unknown mosquito breeding habitats, for treatment.

Called “Seek and Destroy”, the program has been piloted in Uganda and will be extended to infectious areas of Kenya and Rwanda in East Africa and Cambodia, enabling governments to quickly and effectively direct resources to vulnerable areas before outbreaks occur. .

Developed by public health researcher and University of South Florida associate professor Benjamin Jacob, it is hoped the technology will be used by insect control agencies to real-time monitor, map and eradicate vectors and pests. malaria larvae.

So far, most research has focused on Uganda, where malaria is the leading cause of death, especially among children under five.

A low-cost (

Advertisement

The system works by identifying specific environments and organisms by their unique “fingerprint”, mapping and assigning a red-green-blue value associated exclusively with a species or habitat.

‘Seek and Destroy’

For “Seek and Destroy” to succeed, Jacob trained the drone to detect and capture image datasets through his algorithms that allow the system to understand key features, like mud or vegetation, based on their “fingerprints”.

Each image is then processed and gridded with identified water sources on these surfaces.

The data is then classified into different categories based on the presence or absence of mosquito larvae and whether the water is positive for mosquitoes.

Combined with Jacob’s algorithms, the drone was 100% accurate in locating bodies of water where mosquitoes are most likely to breed.

“We retrieved each geo-referenced sentinel site signature in real-time which was then archived in the drone’s dashboard spectral library using the smartphone app. Each geo-referenced capture point, detected by UAV, was inspected using a mobile field team comprising local villagers trained and led by a vector control officer on the same day the habitats were mapped, spatially predicted and processed with the geo-AI signature,” he explained.

the American Journal of Entomology says Jacob found that each of the 120 homes he studied was infested with at least 200 mosquitoes. With the help of the local insect control officers he trained, Jacob destroyed 100% of the identified habitats in 31 days.