2022/08/21 by Paterne Gahungu, Jean Remy Kubwimana, Gahungu, Paterne +5
Engineering · Environmental Science · #Air Quality Monitoring and Forecasting #Air Quality and Health Impacts #Atmospheric and Oceanic Physics (physics.ao-ph) #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #Vehicle emissions and performance
paper · pdf · doi:10.48550/arxiv.2208.12719
openalex publication_date 2022/08/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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/m3 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/m3 and 38.65 μg/m3 for Kigali. In countries located in the central region of Africa, the highest daily average concentration of PM2.5 of 90.075 μg/m3 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.