Autor: |
Arowosegbe, Oluwaseyi Olalekan1,2 (AUTHOR), Röösli, Martin1,2 (AUTHOR), Künzli, Nino1,2 (AUTHOR), Saucy, Apolline1,2 (AUTHOR), Adebayo-Ojo, Temitope C.1,2 (AUTHOR), Schwartz, Joel3 (AUTHOR), Kebalepile, Moses4 (AUTHOR), Jeebhay, Mohamed Fareed5 (AUTHOR), Dalvie, Mohamed Aqiel5 (AUTHOR), de Hoogh, Kees1,2 (AUTHOR) c.dehoogh@swisstph.ch |
Předmět: |
|
Zdroj: |
Environmental Pollution. Oct2022, Vol. 310, pN.PAG-N.PAG. 1p. |
Abstrakt: |
There is a paucity of air quality data in sub-Saharan African countries to inform science driven air quality management and epidemiological studies. We investigated the use of available remote-sensing aerosol optical depth (AOD) data to develop spatially and temporally resolved models to predict daily particulate matter (PM 10) concentrations across four provinces of South Africa (Gauteng, Mpumalanga, KwaZulu-Natal and Western Cape) for the year 2016 in a two-staged approach. In stage 1, a Random Forest (RF) model was used to impute Multiangle Implementation of Atmospheric Correction AOD data for days where it was missing. In stage 2, the machine learner algorithms RF, Gradient Boosting and Support Vector Regression were used to model the relationship between ground-monitored PM 10 data, AOD and other spatial and temporal predictors. These were subsequently combined in an ensemble model to predict daily PM 10 concentrations at 1 km × 1 km spatial resolution across the four provinces. An out-of-bag R2 of 0.96 was achieved for the first stage model. The stage 2 cross-validated (CV) ensemble model captured 0.84 variability in ground-monitored PM 10 with a spatial CV R2 of 0.48 and temporal CV R2 of 0.80. The stage 2 model indicated an optimal performance of the daily predictions when aggregated to monthly and annual means. Our results suggest that a combination of remote sensing data, chemical transport model estimates and other spatiotemporal predictors has the potential to improve air quality exposure data in South Africa's major industrial provinces. In particular, the use of a combined ensemble approach was found to be useful for this area with limited availability of air pollution ground monitoring data. [Display omitted] • Ensemble averaging outperformed the individual machine learner's performances. • Ensemble averaging explained 81% of overall variation in PM 10 concentrations. • Modelled PM 10 as a predictor was more influential than satellite-derived PM 10. [ABSTRACT FROM AUTHOR] |
Databáze: |
GreenFILE |
Externí odkaz: |
|