Modelling spatio-temporal trends of air pollution in Africa
This addresses air pollution monitoring in Africa, an incremental study applying existing methods to new regional data.
The paper analyzed spatio-temporal variations of PM2.5 air pollution across Africa, finding high daily averages such as 90.075 μg/m³ in N'Djamena, and compared models, with neural networks outperforming Gaussian processes and ARIMA in predicting future trends.
Atmospheric pollution remains one of the major public health threat worldwide with an estimated 7 millions deaths annually. In Africa, rapid urbanization and poor transport infrastructure are worsening the problem. In this paper, we have analysed spatio-temporal variations of PM2.5 across different geographical regions in Africa. The West African region remains the most affected by the high levels of pollution with a daily average of 40.856 $μg/m^3$ in some cities like Lagos, Abuja and Bamako. In East Africa, Uganda is reporting the highest pollution level with a daily average concentration of 56.14 $μg/m^3$ and 38.65 $μg/m^3$ for Kigali. In countries located in the central region of Africa, the highest daily average concentration of PM2.5 of 90.075 $μg/m^3$ was recorded in N'Djamena. We compare three data driven models in predicting future trends of pollution levels. Neural network is outperforming Gaussian processes and ARIMA models.