The cohorts of the three-month Africa CAN training program supported participants to strengthen their data science skills and learn how to work with climate and health data. The program was designed for government officials, academics, and members of civil society, as well as data professionals who wanted to deepen their data skills and use them for social development. It focused on building literacy and analysis skills in climate and health data, then moved on to working with more advanced tools for predictive modeling and data analysis, such as Python, R, dashboards, and geospatial tools.
The curriculum was updated to incorporate lessons learned, adding more case studies, boosting peer-learning through small group activities, and sharpening focus on African contexts, while maintaining the overall structure. This was organized into six modules covering the full range of climate–health data science. It started with an overview of the intersection between climate and health data, including the African data landscape and applications of machine learning in local settings. Participants then covered data wrangling basics, such as tidy-data principles, data cleaning, and exploratory analysis. The sessions addressed the role of health data in resource allocation and system planning, with a focus on geospatial data and genetic epidemiology. Climate data training included key sources, impact assessments, adaptation strategies, and case studies on safeguarding vulnerable populations during extreme weather. Advanced sessions introduced Python programming, statistical analysis, and predictive modeling techniques. The cohorts wrapped up with data visualization and communication skills, guiding participants to craft compelling data stories, customize messages for diverse audiences, and develop interactive dashboards to translate analysis into actionable insights.