Unravelling the dynamics of deprived urban areas in the Majority World using AI and Earth Observation to foster evidence-based sustainable planning (DEPRIMAP)

Rapid urbanization in the Majority World (MW) is leading to the proliferation of deprived urban areas (DUAs). By 2030, the number of people living in DUAs will reach 2 billion.

These communities are at a higher risk of exposure to infectious diseases, environmentally related health issues, and to the effects of climate change when compared to the planned, more affluent neighbourhoods of a city.

Unfortunately, monitoring data for DUAs in many MW countries are incomplete or inconsistent, while there exists a clear knowledge gap with respect to their characteristics and risk variations.

To address this data gap, DEPRIMAP proposes a geospatial framework that incorporates Copernicus satellite data and publicly available datasets such as building footprints, coupled with machine learning and deep learning state-of-the-art techniques to map, model and characterize DUAs in a geographically diverse selection of case studies across the world (Buenos Aires, Khartoum, Lagos, Nairobi, Dhaka).

The project development is melded though tailored stakeholder and community engagement.

The overarching objective of the project is to improve knowledge of the physical, demographic, and socio-economic characteristics of DUAs in the MW and quantify the differences between DUAs and non-DUAs concerning relevant natural hazards such as flooding, drought and heatwaves in order to contribute to a more sustainable future in accordance with SDGs for the most vulnerable urban citizens.