Projects / AI Innovation Challenge

Preventing Malaria Infections Through AI Driven Satellite Image Analysis

Project Completed!


Preventing Malaria Infections Through AI-Driven Satellite Image Analysis

Background

Malaria, a mosquito-borne disease, claims over 400,000 lives annually, primarily affecting children under five. Controlling or eliminating the disease involves targeting water bodies where mosquitoes lay eggs. Governments and organizations face challenges in identifying these breeding grounds quickly and cost-effectively, especially in large regions like Ghana or Kenya, before the wet season accelerates mosquito proliferation.

Objective

To develop an AI-powered solution that identifies stagnant water bodies, enabling governments and organizations to efficiently allocate resources to high-risk areas for malaria prevention.

Approach

The team of 40 AI changemakers collaborated to build a model leveraging multiple data sources, including:

  • Satellite images for geographic insights.
  • Topography data to determine water flow and accumulation areas.
  • Population density data for risk prioritization.
  • The algorithm analyzed regions in Ghana and Amhara, producing grids with risk scores for stagnant water bodies.
AI Malaria

Highlighted Grids have a higher risk of containing water bodies

Advanced machine learning techniques and periodic data batches from project partner Zzapp Malaria guided the iterative development process.

Results and Impact

The project successfully created an algorithm capable of identifying mosquito breeding sites with enhanced speed and precision. Highlights include:

  • Faster identification of high-risk water bodies.
  • Improved resource allocation, allowing governments to focus on susceptible areas.
  • Alignment with UN Sustainable Development Goal 3 to end malaria epidemics by 2030.

This innovation could significantly reduce malaria cases in regions like Ghana and Kenya, supporting global malaria prevention efforts.

Below you can watch how the app of Zzapp Malaria works. For more details on the challenge read this case study.

Future Implications

The findings can guide future AI-driven strategies for mosquito-borne disease prevention. By integrating real-time data, such models could enhance global health policies and contribute to eliminating malaria, potentially benefiting millions worldwide. Further research could expand this approach to other regions and refine its effectiveness against emerging climate challenges.

This project has been hosted with our friends at
Zzapp Malaria
Logo


Thumbnail Image
Accurately Identifying Crop Types Using Remote Sensing and Machine Learning
Thumbnail Image
AI-Driven Indoor Temperature Prediction for Tanzanian Classrooms
Thumbnail Image
CanopyWatch - Enhancing Deforestation Monitoring and Conservation in the Congo Basin using Machine Learning

Become an Omdena Collaborator

media card
Visit the Omdena Collaborator Dashboard Learn More