Identifying vulnerable urban neighbourhoods and their environmental, density, and housing characteristics in Accra, Ghana using census and remote sensing data
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
BACKGROUND AND AIM: Identifying vulnerable urban communities, commonly known as slums, can facilitate targeted policies to reduce urban economic and social inequities in cities, but these data are rarely available. We aimed to identify vulnerable urban neighbourhoods and their environmental and housing characteristics in Accra, Ghana using available training data on the city center (Accra Metropolitan Area - AMA) applied to the Greater Accra Metropolitan Area (GAMA). METHODS: We accessed the following enumeration area (EA)-level data for Greater Accra: slum classification available for a subset of 2,418 EAs in the AMA from the Accra Metropolitan Assembly and UN-Habitat 2011 report; housing conditions from the most recent Ghana Census (2010); and environmental quality attributes from remote sensing data provided by the United States Geological Survey and National Aeronautics and Space Administration. We fitted a Bayesian logistic regression model to evaluate associations between housing, density, and environmental attributes with vulnerable area classification of EAs in the AMA. We then applied the model to predict the probability of each urban EA in GAMA as being vulnerable. RESULTS:We estimated that approximately one-fifth of EAs in the GAMA had a vulnerable area probability greater than 80%, corresponding to a population of 752,367 likely living in suboptimal conditions. The variables associated with a higher probability of an EA being vulnerable included greater use of public toilet facilities [OR: 3.51 (95% credible interval (CI): 1.55,7.53)], higher population density [OR: 5.72 (95% CI: 3.85,8.65)], lower use of improved wall materials [OR: 0.11 (95% CI: 0.03,0.43)], lower elevation [OR: 0.45 (95% CI: 0.35, 0.58)], lower use of indoor piping as a drinking water source [OR: 0.50 (95% CI: 0.25,0.99)], and lower vegetation abundance [OR: 0.25 (95% CI: 0.16,0.39)]. CONCLUSIONS:Our approach can be used in future studies to identify geographic clusters of vulnerable areas where interventions are warranted to improve housing and environmental conditions. KEYWORDS: Built environment, Socio-economic factors, Epidemiology
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it