Conference Abstract | Volume 9 (ConfPro8): Abstract 16 | Published: 05 Oct 2026
Lidetu Demoze1,&, Tadesse Guadu2, Zemichael Gizaw1, Mekuriaw Nibret Aweke3, Astewil Moges Bazezew4, Gebeyehu Lakew5, Samuel Teferi Chanie6, Gelila Yitageasu1
1Department of Environmental and Occupational Health and Safety, Institute of Public Health, College of Medicine and Health Sciences, University of Gondar, Gondar, Ethiopia; 2Institute of Public Health, College of Medicine and Health Sciences, University of Gondar, Gondar, Ethiopia; 3Department of Human Nutrition, Institute of Public Health, College of Medicine and Health Sciences, University of Gondar, Gondar, Ethiopia; 4Department of Surgical Nursing, School of Nursing, College of Medicine and Health Sciences, University of Gondar, Gondar, Ethiopia; 5Department of Health Promotion and Health Behavior, Institute of Public Health, College of Medicine and Health Sciences, University of Gondar, Gondar, Ethiopia; 6Department of Physiotherapy, School of Medicine, College of Medicine and Health Sciences, University of Gondar, Gondar, Ethiopia
&Corresponding author: Lidetu Demoze, Department of Environmental and Occupational Health and Safety, Institute of Public Health, College of Medicine and Health Sciences, University of Gondar, Gondar, Ethiopia, Email: lidetudemoze12@gmail.com, ORCID: https://orcid.org/0009-0008-8906-0689
Received: 11 Mars 2026, Accepted: 29 Aug 2026, Published: 05 Oct 2026
Domain: Environmental Health
Keywords: Solid fuel, machine learning, spatial analysis, Nigeria, household air pollution
©Lidetu Demoze et al. Journal of Interventional Epidemiology and Public Health (ISSN: 2664-2824). This is an Open Access article distributed under the terms of the Creative Commons Attribution International 4.0 License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Cite this article: Lidetu Demoze et al., Explainable machine learning and spatial analysis of household solid fuel utilization in Nigeria: Insights from the 2024 DHS. Journal of Interventional Epidemiology and Public Health. 2026;9(ConfPro8):16. https://doi.org/10.37432/JIEPH-CONFPRO8-0016
Solid fuels remain widely used for cooking in Nigeria, generating household air pollution and associated health risks. Evidence on complex predictors and geographic patterns of solid fuel use remains limited. This study applied explainable machine learning and spatial analysis to identify key predictors and geographic hotspots of household solid fuel utilization in Nigeria.
We analyzed the 2024 Nigeria Demographic and Health Survey Household Recode dataset, comprising 40,047 weighted households. Machine learning models were developed using tenfold cross-validation, with SMOTE used to address class imbalance. Model performance was assessed using accuracy, precision, recall, F1-score, and AUC-ROC, while SHAP quantified predictor contributions. Spatial patterns were assessed using Global Moran’s I, Getis-Ord Gi* hotspot analysis, Anselin Local Moran’s I, and SaTScan Bernoulli spatial scan statistics.
Solid fuel use was 69.32% (95% CI: 68.86–69.76%), with wood accounting for 79.8% of solid fuel use. XGBoost showed the strongest overall predictive performance (accuracy: 0.9004; F1-score: 0.9261; AUC: 0.9648). SHAP analysis identified wealth index as the dominant predictor, accounting for over 80% of predictive importance, followed by zone, place of residence, family size, and household head age. Significant spatial clustering was observed (Moran’s I = 0.383, p < 0.001), with hotspots concentrated mainly in northern Nigeria.
Solid fuel use remains prevalent among Nigerian households, with substantial socioeconomic and geographic disparities. Wealth, geographic location, residence, household size, and age of the household head were important predictors. The identified northern hotspots highlight areas where geographically and socioeconomically targeted clean cooking interventions may be particularly relevant.
Menu