Rethinking Emission Modelling Approaches for Sub-Saharan Africa's Complex Realities using Machine Learning Methods as a Decision Support System

Authors

Elias Muhatia, iLab Africa, Strathmore University, Kenya

Kennedy Senagi, iLab Africa, Strathmore University, Kenya

Evans Omondi, Strathmore Institute of Mathematical Sciences, Kenya

Betsy Muriithi, iLab Africa, Strathmore University, Kenya

John Olukuru, iLab Africa, Strathmore University, Kenya

Joseph Sevilla, iLab Africa, Strathmore University, Kenya

Published in

IST-Africa 2026 Conference Proceedings

ISSN: 2576-8581

ISBN: 978-1-905824-76-2

DOI: https://doi.org/10.67725/IST-Africa.2026.UYEU2061

Publisher

IST-Africa Institute and IIMC International Information Management Corporation Ltd

Published in Ireland

Abstract

Sub-Saharan Africa contributes minimally to global greenhouse gas emissions yet faces rapidly growing energy demand, population expansion, and increasing development pressures. This study analysed emission trends across 49 sub-Saharan African countries (2000-2023) and evaluated the effectiveness of classical statistical models and modern machine learning techniques in predicting carbon emissions. Using World Bank development indicators, the analysis examined key drivers including fossil fuel dependence, governance quality, and agricultural activity. Total greenhouse gas emissions including land use, land-use change, and forestry exhibited strong positive correlations (r = 0.94-0.97) with sectoral carbon dioxide, Methane, Nitrous Oxide, and Fluorinated gas emissions, particularly from transport, waste, industrial combustion, and energy-related activities, while showing a strong negative association with forest land carbon fluxes (r = -0.83), and weak negative relationships (r < - 0.20) with governance, renewable energy shares, and efficiency indicators. When land-use change was included, linear models demonstrated superior performance (R² = 0.951), while ensemble methods, particularly Random Forest (R² = 0.951) outperformed linear approaches when land-use change was excluded. Principal component analysis identified five dominant emission drivers in Sub-Saharan Africa with strong loadings (=0.85), capturing industrialisation and economic growth (including gross domestic product per unit of energy use = 0.999; manufacturing growth = 0.998), energy mix and efficiency (renewables = 0.977; fossil fuel consumption = 0.949), resource depletion and environmental damage (mineral depletion = 0.965; carbon dioxide damage = 0.914), governance quality (transparency and corruption control = 0.976), and agricultural pressures (agricultural exports = 0.981; Nitrous oxide emissions = 0.990). These components indicate that regional emissions are shaped by interconnected structural, institutional, and environmental dynamics. The findings provide an evidence base to improve emission prediction and forecasting, and support data-driven decisions on clean energy transitions, governance strengthening, and climate mitigation planning. Future research should integrate richer sectoral data and hybrid modelling approaches to strengthen generalisability and long-term forecasting robustness.

Keywords

Development indicators, environmental governance, fossil fuel dependence, greenhouse gas modelling

Cite this paper

E. Muhatia, K. Senagi, E. Omondi, B. Muriithi, J. Olukuru and J. Sevilla (2026) "Rethinking Emission Modelling Approaches for Sub-Saharan Africa's Complex Realities using Machine Learning Methods as a Decision Support System", IST-Africa 2026 Conference Proceedings, Miriam Cunningham and Paul Cunningham (Eds), IST-Africa Institute and IIMC, 2026, ISSN: 2576-8581, ISBN: 978-1-905824-76-2, https://doi.org/10.67725/IST-Africa.2026.UYEU2061

Access Paper

Click here to access this paper

IST-Africa Community Members can download papers by logging into their existing account.

If you wish to become a member of IST-Africa Community, please register your profile and you will then receive login details which you can use to access the papers.

Access to papers in the IST-Africa 2026 Conference Proceedings is for INDIVIDUAL USE only. Neither the Conference Proceedings (or individual double blind peer reviewed papers) are to be included in any public or institutional repository or processed in the context of any AI tool or large language model without prior written permission from the Publishers.

While the IST-Africa Institute and IIMC retain copyright of the Conference Proceedings, each author retains copyright to their individual paper. No paper or part thereof may be reproduced without the written permission of both the Conference Proceedings Publishers and appropriate author(s).