Machine learning for air quality forecasting: Insights from five provinces of Rwanda

Aug 3, 2026

Upload by Aurelia

Accurately predicting air quality remains a critical challenge for public health and environmental management. This study compares machine learning approaches to establish benchmark best practices for Rwanda and to test the added value of advanced statistical methods under data-scarce conditions. Fine particulate matter (PM2.5) concentrations are forecast across five Rwandan provinces using multi-year meteorological and air-quality data, identifying context-specific patterns. The work supports context-optimized early warning systems and policy interventions, showing reduced exposure risk and seasonal variability.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages18

Reading Time45 min

AccessFree to download

Introduction

Air pollution as a global health risk

Policy and mitigation efforts

Methods and Modeling

Forecasting PM2.5 using multi-year data

Benchmarking machine learning approaches

Results and Implications

Capturing non-linear relationships and seasonal variability

Limitations and future needs

Edinburgh Research Explorer Machine learning for air quality forecasting: Insights from five provinces of Rwanda Citation for published version: Faye, D, Lguensat, R, Kaly, F, Sudmant, A, Gaye, AT & Kalisa, E 2025, 'Machine learning for air quality forecasting: Insights from five provinces of Rwanda', Scientific African. [https://doi.org/10.1016/j.sciaf.2025.e02959](https://doi.org/10.1016/j.sciaf.2025.e02959) Digital Object Identifier (DOI): 10.1016/j.sciaf.2025.e02959 Link: Link to publication record in Edinburgh Research Explorer Document Version: Publisher's PDF, also known as Version of record Published In: Scientific African Publisher Rights Statement: © 2025 The Author(s) . General rights Copyright for the publications made accessible via the Edinburgh Research Explorer is retained by the author(s) and / or other copyright owners and it is a condition of accessing these publications that users recognise and abide by the legal requirements associated with these rights. Take down policy The University of Edinburgh has made every reasonable effort to ensure that Edinburgh Research Explorer content complies with UK legislation. If you believe that the public display of this file breaches copyright please [contact openaccess@ed.ac.uk](contact openaccess@ed.ac.uk) providing details, and we will remove access to the work immediately and investigate your claim. Download date: 24. Nov. 2025 Scientiϧc African 30 (2025) e02959 Contents lists available at ScienceDirect Scientific African journal [homepage: www.elsevier.com/locate/sciaf](homepage: www.elsevier.com/locate/sciaf) | Machine learning for air quality forecasting: Insights from five provinces of Rwanda | | | | | --- | --- | --- | --- | | Dioumacor Fayea,b , Redouane Lguensatc, François Kalyb, Andrew Sudmantd, Amadou T. Gayeb, Egide Kalisaa,*
a Department of Epidemiology and Biostatistics, Schulich School of Medicine and Dentistry, University of Western Ontario, London, N6G 2M1, ON, Canada
b Laboratoire Physique de l’Atmosph`ere et de l’Oc´ean-Sim´eon Fongang (LPAO-SF) Ecole Sup´erieure Polytechnique (ESP), Universit´e Cheikh Anta Diop de Dakar, Dakar, 5085, Fann, Senegal
c Institut Pierre-Simon Laplace, IRD, Paris, 4 place de Jussieu, France
d Edinburgh Climate Change Institute, Edinburgh University, High School Yards, Edinburgh, UK | | | | | A R T I C L E I N F O | | A B S T R A C T | | | Editor: Mohamed Fathy El-Amin Mousa | | Accurately predicting air quality is a crucial challenge for public health and environmental management. This study compares and contrasts machine learning approaches to benchmark best practices for the Rwandan context and to evaluate the added value of advanced statistical methods for air quality monitoring in data-scarce settings. We forecast fine particulate matter (PM2.5) concentrations across five provinces in Rwanda, using multi-year meteorological and air quality data to identify context-specific patterns. This work establishes a methodological foundation for context-optimized early warning systems and informs policy interventions to improve air quality management in Rwanda. By rigorously testing machine learning capabilities against regional constraints, we demonstrate how machine learning can reduce population exposure to pollution, quantify attribution gaps in under-monitored regions, and improve sustainable environmental governance in resource-limited settings. The results indicate significant seasonal variability, with higher PM2.5 levels during dry seasons than wet seasons. Our evaluation demonstrates that machine learning models can capture complex, non-linear relationships between environmental variables and pollution trends, although performance varies between algorithms. Limitations remain, including the integration of real-time data streams and localized variables such as industrial emissions, road traffic, and agricultural practices. | | | Keywords:
Air qua

FAQs

What problem does the study address?

The study addresses the challenge of accurately forecasting air quality to support public health and environmental management.

How is PM2.5 forecasting performed in the study?

It forecasts fine particulate matter (PM2.5) concentrations across five provinces using multi-year meteorological and air-quality data.

What are the main findings about model performance?

Machine learning models can capture complex, non-linear environmental relationships and reveal significant seasonal variability, though performance differs by algorithm; limitations remain for real-time and localized emissions data.

Aug 3, 2026

Upload by Aurelia