Geospatial modelling of road-traffic noise levels and frequency and the attributable burden of annoyance and sleep disturbance in Accra, Ghana
Bibliographic record
Abstract
Background and aim: Limited city-wide data on environmental noise and sources in rapidly growing sub-Saharan African (SSA) cities constitutes a major barrier for investigating health impacts as well as environmental policy making. In a first of its kind study in SSA, we modelled and predicted noise levels and road-traffic-specific sounds in Accra, Ghana, and estimated the attributable burden of being highly annoyed and sleep disturbed in high-spatial resolution. Methods: From 2019-2020, we collected measurements of sound levels and audio recordings along the roadside in a large-scale campaign. The audio was processed with a deep learning acoustic classifier to identify the frequency of road-traffic sounds. We combined the acoustic data with geospatial predictors in land use regression models (mixed models/random forest) to predict noise levels (Lden, Lnight) and the frequency of road-traffic-specific sounds across the city. Finally, by combining population exposures to predicted Lden and Lnight with literature informed exposure-response relationships and disability weights, we estimated the attributable burden of being highly annoyed and sleep disturbed in aggregate and by census enumeration area (median size: 0.03km2). Results: Predicted road-traffic sounds were prevalent throughout the day (median: 81% of the time present) and nighttime (median: 62%) in Accra. Furthermore, 99% of the population in lived in census enumeration areas where average Lden and Lnight surpassed WHO guidelines for road-traffic noise (Lden <53; Lnight <45). Noise exposures in Accra translated into 21% and 7% of the population highly annoyed and sleep disturbed, with significant variation across areas, and a combined 10,761 Disability Adjusted Life Years lost. Conclusions: In an area of the world where noise research is severely lacking, this work can support epidemiological studies, burden of disease assessments, and the development of policies and interventions that address noise exposure within Accra. Keywords: Noise, Africa, health burden, land-use-regression, audio processing, road-traffic noise
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 | 0.000 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 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".