Leveraging data science and machine learning for urban climate adaptation in two major African cities: a HE²AT Center...

Area of Science:

• Environmental Health
• Urban Planning
• Climate Science

Background:

• African cities like Abidjan and Johannesburg experience rapid urbanization, informality, and strained health systems.
• Climate change exacerbates urban heat island effects, posing significant health risks.
• Vulnerable populations in these cities are disproportionately affected by heat hazards.

Purpose of the Study:

• To map intraurban heat risk and exposure using diverse datasets.
• To develop a stratified heat-health forecast model for predicting adverse health outcomes.
• To establish an early warning system for timely heatwave alerts and promote climate-resilient African cities.

Main Methods:

• Utilizing health, socioeconomic, climate, and satellite imagery data from Johannesburg and Abidjan (2000-2022).
• Employing statistical evaluation, machine learning, and deep learning for data analysis.
• Quantifying heat-health exposure, risk extent, and morbidity.

Main Results:

• Detailed intraurban heat risk and exposure maps will be generated.
• A predictive model for heat-related adverse health outcomes will be created.
• An operational early warning system for heatwaves will be established.

Conclusions:

• The study aims to enhance climate resilience in African cities.
• Findings will support targeted interventions to protect vulnerable populations from heat stress.
• Dissemination through workshops, forums, conferences, and publications will ensure knowledge transfer.