Cities are contradictory human constructions: while they offer opportunity, they also harbor deep misery. These inequalities are found in specific physical areas commonly known as slums (informal human settlements). With almost a quarter of the world’s urban population living in them, preventing millions of people from living in extremely vulnerable conditions is a matter of global social justice. Therefore, in order to anticipate crises and develop citizen-centric responses, it is essential to generate reliable data with global coverage.
When identifying urban poverty, socio-economic indicators such as income, literacy or housing conditions are often used, but the physical characteristics of the place are overlooked. The differences within the city must be taken into account as they lead to greater vulnerability and risk of exclusion and expose residents to other facets of poverty that do not only include the monetary dimension. For example, an area prone to flooding or fires exposes its residents to greater health risks and this also leads to greater economic fragility.
Currently more than sixty percent of Africa’s population lives in slums and it is estimated that this number will triple in less than thirty years
Identifying the spatial patterns that characterize urban poverty is crucial to guide the development of strategies aimed at fighting for more inclusive cities. First, it can help local politicians identify the most critical areas and guide urban regeneration programs. And second to the global, to generate high-quality and up-to-date open data that uses indicators to measure the United Nations Sustainable Development Goals (SDGs). The data would help launch integrated action plans for just global progress and the end of poverty (SDG 1 and SDG 11).
However, detailed and disaggregated data at inner-city level is still lacking. This prevents the measurement and characterization of the physical differences that help to understand the spatial and temporal differences in living conditions in cities. Censuses and surveys often provide urban data about households, such as B. Residential characteristics and socioeconomic status of residents, but their low periodicity and gaps in coverage remain patchy with respect to slums. This makes them ineffective tools for tackling poverty at its roots.
Earth Observation Science provides geolocated data resources, also called spatial data, such as remote sensing (e.g. satellite imagery) with full coverage to characterize poverty and fill data gaps both locally and across borders. Artificial intelligence, through machine learning techniques, enables the systematic analysis of satellite imagery and the creation of efficient and transferrable processes to capture the features of the physical environment.
The number of remote sensing-based poverty studies has increased over the past decade, highlighting the ability to locate poor neighborhoods with greater profitability, coverage, detail, and frequency than traditional methods such as censuses or surveys. Most studies focus on mapping the extension and its location, drawing its boundaries and contrasting it with the rest of the city. However, urban poverty is not a mere binary phenomenon, ie slum versus non-slum; Poverty levels exist between slums and other planned areas of the city, and within each of these areas. There are differences, for example, in the type of construction, in the proximity to risk areas such as landfills or floodable rivers, in the accessibility of municipal services such as schools or hospitals.
Urban poverty is not just a binary phenomenon; Poverty levels exist between slums and other planned areas of the city, and within each of these areas
High-resolution satellite imagery and machine learning techniques have revealed that there are large intraphysical disparities in neighborhoods with higher poverty rates. For example, an artificial intelligence model has managed to extract the outlines of various urban elements such as buildings, trees, ground surface, rivers, garbage cans and cars from satellite images of various slums in African cities. Morphological metrics were also applied and a great variety in its physical constitution was noted, characterized by the size of the buildings, the nature of the width of the streets, the characteristic internal irregularity of each structure, and the patterns of orientation that make up the whole. . . If this work was done by different people, it would take hundreds of hours and cause a lot of errors, while the algorithm does it very precisely in a matter of seconds.
In sub-Saharan Africa, this line of research, combining artificial intelligence and satellite imagery, will show great promise as the populations and levels of urbanization in these areas are increasing – and are expected to continue to do so at uncontrollable levels. Currently, more than 70% of Africa’s population lives in slums and it is estimated that this figure will triple in less than 30 years, reaching the continent to host more than two billion people in conditions of vulnerability. It’s time to look for creative and effective ways to turn the situation around.
You can follow PLANETA FUTURO at TwitterFacebook and Instagram and subscribe to our “Newsletter” here.