Identifying deprived “slum” neighbourhoods in the Greater Accra Metropolitan Area of Ghana using census and remote sensing data

•Using a Bayesian spatial model, we combined remote sensing and census data to predict deprived “slum” areas in Accra, Ghana.•Nearly one in five urban enumeration areas, accounting for ∼ 750,000 residents, in the Greater Accra Metropolitan Area had a high probability (≥80%) of being a deprived area.•Deprived EAs shared some common features including a higher population density, lower elevation and vegetation abundance, and less access to indoor piped water and sanitation.•Our approach provides a flexible and rigorous way to rapidly assess deprived areas in cities in low and middle-income countries.