Identifying deprived “slum” neighbourhoods in the Greater Accra Metropolitan Area of Ghana using census and remote sensing data
Bibliographic record
Abstract
Background: Identifying urban deprived areas, including slums, can facilitate more targeted planning and development policies in cities to reduce socio-economic and health inequities, but methods to identify them are often ad-hoc, resource intensive, and cannot keep pace with rapidly urbanizing communities. Objectives: We apply a spatial modelling approach to identify census enumeration areas (EAs) in the Greater Accra Metropolitan Area (GAMA) of Ghana with a high probability of being a deprived area using publicly available census and remote sensing data. Methods: We obtained United Nations (UN) supported field mapping data that identified deprived "slum" areas in Accra's urban core, data on housing and population conditions from the most recent census, and remotely sensed data on environmental conditions in the GAMA. We first fitted a Bayesian logistic regression model on the data in Accra's urban core (n=2,414 EAs) that estimated the relationship between housing, population, and environmental predictors and being a deprived area according to the UN's deprived area assessment. Using these relationships, we predicted the probability of being a deprived area for each of the 4,615 urban EAs in GAMA. Results: 899 (19%) of the 4,615 urban EAs in GAMA, with an estimated 745,714 residents (22% of its urban population), had a high predicted probability (≥80%) of being a deprived area. These deprived EAs were dispersed across GAMA and relatively heterogeneous in their housing and environmental conditions, but shared some common features including a higher population density, lower elevation and vegetation abundance, and less access to indoor piped water and sanitation. Conclusion: Our approach using ubiquitously available administrative and satellite data can be used to identify deprived neighbourhoods where interventions are warranted to improve living conditions, and track progress in achieving the Sustainable Development Goals aiming to reduce the population living in unsafe or vulnerable human settlements.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".