Despite its significant impacts on climate, environment, and public health, air pollution monitoring in Africa is still sparse. This study developed a machine learning framework of four models—namely SARIMAX, Random Forest, XGBoost, and LightGBM—that were trained on a daily basis using 25 meteorological variables from ERA5 reanalysis to reproduce daily PM10 surface concentrations in Lamto, C？te d’Ivoire. A total of 2225 daily recorded concentrations from 2017 to 2023 were used, with 80% (1780 days) allocated to training the models and 20% (445 days) for prediction. An assessment of ERA5 reanalysis data against in-situ measurements highlighted its ability to reproduce the pattern of meteorological variables such as temperature and relative humidity, despite some biases. Results show that all models were able to reproduce the observed PM10 variations, although they slightly overestimated concentrations during the main wet season (March-April-May-June-July) and underestimated high pollution events in the main dry season (November-December-January-February). Finally, performance analysis revealed that the Random Forest model outperformed, with an R2 of 0.78 and RMSE of 23 μg/m3, outperforming the other models. This framework successfully demonstrates the utility of machine learning for air quality prediction in West Africa, with potential for future improvements through bias correction and model combination.
References
[1]
IPCC (2001) Climate Change 2001: The Scientific Basis. Contribution of Working Group I to the Third Assessment Report of the Intergovernmental Panel on Climate Change. Cambridge University Press, 881.
[2]
IPCC (2014) Climate Change 2014: Mitigation of Climate Change. Contribution of Working Group III to the Fifth Assessment Report of the Intergovernmental Panel on Climate Change. Cambridge University Press.
[3]
Lohmann, U. and Feichter, J. (2001) Can the Direct and Semi-Direct Aerosol Effect Compete with the Indirect Effect on a Global Scale? GeophysicalResearchLetters, 28, 159-161. https://doi.org/10.1029/2000gl012051
[4]
Nabat, P., Somot, S., Mallet, M., Michou, M., Sevault, F., Driouech, F., et al. (2015) Dust Aerosol Radiative Effects during Summer 2012 Simulated with a Coupled Regional Aerosol-Atmosphere-Ocean Model over the Mediterranean. Atmospheric Che-mistryandPhysics, 15, 3303-3326. https://doi.org/10.5194/acp-15-3303-2015
[5]
Seinfeld, J.H. and Pandis, S.N. (1998) From Air Pollution to Climate Change. Atmospheric Chemistry and Physics, 1326.
[6]
Knippertz, P., Coe, H., Chiu, J.C., Evans, M.J., Fink, A.H., Kalthoff, N., et al. (2015) The DACCIWA Project: Dynamics-Aerosol-Chemistry-Cloud Interactions in West Africa. BulletinoftheAmericanMeteorologicalSociety, 96, 1451-1460. https://doi.org/10.1175/bams-d-14-00108.1
[7]
Fiore, A.M., Naik, V. and Leibensperger, E.M. (2015) Air Quality and Climate Connections. JournaloftheAir&WasteManagementAssociation, 65, 645-685. https://doi.org/10.1080/10962247.2015.1040526
[8]
Nairobi, 2022 United Nations Environment Programme. https://www.ccacoalition.org/sites/default/files/resources/files/Summary%20for%20Decision%20Makers_Integrated%20Assessment%20of%20Air%20Pollution%20and%20Climate%20Change%20for%20Sustainable%20Development%20in%20Africa.pdf
[9]
De Longueville, F., Hountondji, Y., Henry, S. and Ozer, P. (2010) What Do We Know about Effects of Desert Dust on Air Quality and Human Health in West Africa Compared to Other Regions? ScienceoftheTotalEnvironment, 409, 1-8. https://doi.org/10.1016/j.scitotenv.2010.09.025
[10]
Mir Alvarez, C., Hourcade, R., Lefebvre, B. and Pilot, E. (2020) A Scoping Review on Air Quality Monitoring, Policy and Health in West African Cities. InternationalJournalofEnvironmentalResearchandPublicHealth, 17, Article 9151. https://doi.org/10.3390/ijerph17239151
[11]
Bahino, J., Giordano, M., Beekmann, M., Yoboué, V., Ochou, A., Galy-Lacaux, C., et al. (2024) Temporal Variability and Regional Influences of PM2.5 in the West African Cities of Abidjan (Côte d’Ivoire) and Accra (Ghana). EnvironmentalScience: Atmospheres, 4, 468-487. https://doi.org/10.1039/d4ea00012a
[12]
Djossou, J., Léon, J., Akpo, A.B., Liousse, C., Yoboué, V., Bedou, M., et al. (2018) Mass Concentration, Optical Depth and Carbon Composition of Particulate Matter in the Major Southern West African Cities of Cotonou (Benin) and Abidjan (Côte d’Ivoire). AtmosphericChemistryandPhysics, 18, 6275-6291. https://doi.org/10.5194/acp-18-6275-2018
[13]
Anand, A., Touré, N.E., Bahino, J., Gnamien, S., Hughes, A.F., Arku, R.E., et al. (2024) Low-Cost Hourly Ambient Black Carbon Measurements at Multiple Cities in Africa. EnvironmentalScience&Technology, 58, 12575-12584. https://doi.org/10.1021/acs.est.4c02297
[14]
Gnamien, S., Liousse, C., Keita, S., Silué, S., Bahino, J., Gardrat, E., et al. (2023) Chemical Characterization of Urban Aerosols in Abidjan and Korhogo (Côte d’Ivoire) from 2018 to 2020 and the Identification of Their Potential Emission Sources. EnvironmentalScience: Atmospheres, 3, 1741-1757. https://doi.org/10.1039/d3ea00131h
[15]
Silué, S., Kouassi, A.A., N’datchôh, E.T. and Yoboué, V. (2021) Meteorological Factors Contribution over Two Urban Sites in Côte d’Ivoire. RAMReS Science des Structure de la Matiere, 3, 12-39.
[16]
Léon, J., Akpo, A.B., Bedou, M., Djossou, J., Bodjrenou, M., Yoboué, V., et al. (2021) Pm2.5 Surface Concentrations in Southern West African Urban Areas Based on Sun Photometer and Satellite Observations. AtmosphericChemistryandPhysics, 21, 1815-1834. https://doi.org/10.5194/acp-21-1815-2021
[17]
Gnamien, S., Liousse, C., Keita, S., Kumar, R. and Yoboué, V. (2024) High-resolution Modeling of Air Quality in Abidjan (Côte d’Ivoire) Using a New Urban-Scale Inventory. Atmosphere, 15, Article 758. https://doi.org/10.3390/atmos15070758
[18]
de Coëtlogon, G., Deroubaix, A., Flamant, C., Menut, L. and Gaetani, M. (2023) Impact of the Guinea Coast Upwelling on Atmospheric Dynamics, Precipitation and Pollutant Transport over Southern West Africa. AtmosphericChemistryandPhysics, 23, 15507-15521. https://doi.org/10.5194/acp-23-15507-2023
[19]
Flamant, C., Knippertz, P., Fink, A.H., Akpo, A., Brooks, B., Chiu, C.J., et al. (2018) The Dynamics-Aerosol-Chemistry-Cloud Interactions in West Africa Field Campaign: Overview and Research Highlights. BulletinoftheAmericanMeteorologicalSociety, 99, 83-104. https://doi.org/10.1175/bams-d-16-0256.1
[20]
Deroubaix, A., Menut, L., Flamant, C., Brito, J., Denjean, C., Dreiling, V., et al. (2019) Diurnal Cycle of Coastal Anthropogenic Pollutant Transport over Southern West Africa during the DACCIWA Campaign. AtmosphericChemistryandPhysics, 19, 473-497. https://doi.org/10.5194/acp-19-473-2019
[21]
Niamien, A.F., Léon, J., Adon, M., Rajot, J., Feron, A. and Yoboué, V. (2024) Variability of Aerosol Optical Depth and Altitude for Key Aerosol Types over Southern West Africa via CALIPSO/CALIOP Observations. Atmosphere, 15, Article 396. https://doi.org/10.3390/atmos15040396
[22]
Ossohou, M., Galy-Lacaux, C., Yoboué, V., Hickman, J.E., Gardrat, E., Adon, M., et al. (2019) Trends and Seasonal Variability of Atmospheric NO2 and HNO3 Concentrations across Three Major African Biomes Inferred from Long-Term Series of Ground-Based and Satellite Measurements. AtmosphericEnvironment, 207, 148-166. https://doi.org/10.1016/j.atmosenv.2019.03.027
[23]
Adon, M., Galy-Lacaux, C., Yoboué, V., Delon, C., Lacaux, J.P., Castera, P., et al. (2010) Long Term Measurements of Sulfur Dioxide, Nitrogen Dioxide, Ammonia, Nitric Acid and Ozone in Africa Using Passive Samplers. AtmosphericChemistryandPhysics, 10, 7467-7487. https://doi.org/10.5194/acp-10-7467-2010
[24]
Galy-Lacaux, C., Laouali, D., Descroix, L., Gobron, N. and Liousse, C. (2009) Long Term Precipitation Chemistry and Wet Deposition in a Remote Dry Savanna Site in Africa (Niger). AtmosphericChemistryandPhysics, 9, 1579-1595. https://doi.org/10.5194/acp-9-1579-2009
[25]
Galy-Lacaux, C. and Delon, C. (2014) Nitrogen Emission and Deposition Budget in West and Central Africa. EnvironmentalResearchLetters, 9, Article ID: 125002. https://doi.org/10.1088/1748-9326/9/12/125002
[26]
Yoboué, V., Galy-Lacaux, C., Lacaux, J.P. and Silué, S. (2005) Rainwater Chemistry and Wet Deposition over the Wet Savanna Ecosystem of Lamto (Côte d’Ivoire). JournalofAtmosphericChemistry, 52, 117-141. https://doi.org/10.1007/s10874-005-0281-z
[27]
World Health Organization (2021) WHO Global Air Quality Guidelines: Particulate Matter (PM2.5 and PM10), Ozone, Nitrogen Dioxide, Sulfur Dioxide and Carbon Monoxide. World Health Organization.
[28]
United Nations Environment Programme (2023) Integrated Assessment of Air Pollution and Climate Change for Sustainable Development in Africa.
[29]
Lelieveld, J., Evans, J.S., Fnais, M., Giannadaki, D. and Pozzer, A. (2015) The Contribution of Outdoor Air Pollution Sources to Premature Mortality on a Global Scale. Nature, 525, 367-371. https://doi.org/10.1038/nature15371
[30]
Burnett, R., Chen, H., Szyszkowicz, M., Fann, N., Hubbell, B., Pope, C.A., et al. (2018) Global Estimates of Mortality Associated with Long-Term Exposure to Outdoor Fine Particulate Matter. Proceedings of the National Academy of Sciences of the United States of America, 115, 9592-9597. https://doi.org/10.1073/pnas.1803222115
[31]
Garbagna, L., Babu Saheer, L. and Maktab Dar Oghaz, M. (2025) AI-Driven Approaches for Air Pollution Modelling: A Comprehensive Systematic Review. EnvironmentalPollution, 373, Article ID: 125937. https://doi.org/10.1016/j.envpol.2025.125937
[32]
Olawade, D.B., Wada, O.Z., Ige, A.O., Egbewole, B.I., Olojo, A. and Oladapo, B.I. (2024) Artificial Intelligence in Environmental Monitoring: Advancements, Challenges, and Future Directions. HygieneandEnvironmentalHealthAdvances, 12, Article ID: 100114. https://doi.org/10.1016/j.heha.2024.100114
[33]
Zheng, T., Bergin, M., Wang, G. and Carlson, D. (2021) Local PM2.5 Hotspot Detector at 300 M Resolution: A Random Forest-Convolutional Neural Network Joint Model Jointly Trained on Satellite Images and Meteorology. Remote Sensing, 13, Article 1356. https://doi.org/10.3390/rs13071356
[34]
Dobrea, M., Badicu, A., Barbu, M., Subea, O., Balanescu, M., Suciu, G., et al. (2020) Machine Learning Algorithms for Air Pollutants Forecasting. 2020 IEEE 26th International Symposium for Design and Technology in Electronic Packaging (SIITME), Pitesti, 21-24 October 2020, 109-113. https://doi.org/10.1109/siitme50350.2020.9292238
[35]
Subramaniam, S., Raju, N., Ganesan, A., Rajavel, N., Chenniappan, M., Prakash, C., et al. (2022) Artificial Intelligence Technologies for Forecasting Air Pollution and Human Health: A Narrative Review. Sustainability, 14, Article 9951. https://doi.org/10.3390/su14169951
[36]
Fu, L., Li, J. and Chen, Y. (2023) An Innovative Decision Making Method for Air Quality Monitoring Based on Big Data-Assisted Artificial Intelligence Technique. JournalofInnovation&Knowledge, 8, Article ID: 100294. https://doi.org/10.1016/j.jik.2022.100294
[37]
Le Roux, X., Abbadie, L., Lensi, R. and Serça, D. (1995) Emission of Nitrogen Monoxide from African Tropical Ecosystems: Control of Emission by Soil Characteristics in Humid and Dry Savannas of West Africa. JournalofGeophysicalResearch: Atmospheres, 100, 23133-23142. https://doi.org/10.1029/95jd01923
[38]
Le Roux, X., Gauthier, H., Bégué, A. and Sinoquet, H. (1997) Radiation Absorption and Use by Humid Savanna Grassland: Assessment Using Remote Sensing and Modelling. AgriculturalandForestMeteorology, 85, 117-132. https://doi.org/10.1016/s0168-1923(97)00002-6
[39]
Abbadie, L., Gignoux, J., Roux, X. and Lepage, M. (2006) Lamto: Structure, Functioning, and Dynamics of a Savanna Ecosystem (Vol. 179). Springer Science and Business Media.
[40]
Ossohou, M., Galy-Lacaux, C., Yoboué, V., Adon, M., Delon, C., Gardrat, E., et al. (2020) Long-term Atmospheric Inorganic Nitrogen Deposition in West African Savanna over 16 Year Period (Lamto, Côte d’Ivoire). EnvironmentalResearchLetters, 16, Article ID: 015004. https://doi.org/10.1088/1748-9326/abd065
[41]
N’Dri, A.B., Gignoux, J., Dembele, A. and Konate, S. (2012) Short Term Effects of Fire Intensity and Fire Regime on Vegetation Dynamic in a Tropical Humid Savanna (Lamto, Central Côte d’Ivoire). NaturalScience, 4, 1056-1064. https://doi.org/10.4236/ns.2012.412134
[42]
N Dri, A.B. and Konan, L.N. (2018) Does the Date of Burning Affect Carbon and Nutrient Losses in a Humid Savanna of West Africa? Environment and Natural ResourcesResearch, 8, 102-116. https://doi.org/10.5539/enrr.v8n3p102
[43]
Tiemoko, D.T., Yoroba, F., Diawara, A., Kouadio, K., Kouassi, B.K. and Yapo, A.L.M. (2020) Understanding the Local Carbon Fluxes Variations and Their Relationship to Climate Conditions in a Sub-Humid Savannah-Ecosystem during 2008-2015: Case of Lamto in Cote d’Ivoire. AtmosphericandClimateSciences, 10, 186-205. https://doi.org/10.4236/acs.2020.102010
[44]
Tiemoko, D.T., Yoroba, F., Paris, J., Diawara, A., Berchet, A., Pison, I., et al. (2020) Source-Receptor Relationships and Cluster Analysis of CO2, CH4, and CO Concentrations in West Africa: The Case of Lamto in Côte d’Ivoire. Atmosphere, 11, Article 903. https://doi.org/10.3390/atmos11090903
[45]
Bouet, C., Yoboué, V., Marticorena, B., Rajot, J.L., Allègre, M., Féron, A., Gaimoz, C., Maisonneuve, F., Siour, G., Valorso, R., Ki, A.F., Konaté, I. and Ouattara, A. (2021) PM10 Concentration, Lamto, Côte d’Ivoire. https://doi.org/10.25326/279
[46]
Muñoz-Sabater, J., Dutra, E., Agustí-Panareda, A., Albergel, C., Arduini, G., Balsamo, G., et al. (2021) ERA5-Land: A State-of-the-Art Global Reanalysis Dataset for Land Applications. EarthSystemScienceData, 13, 4349-4383. https://doi.org/10.5194/essd-13-4349-2021
[47]
Seibert, P. (2000) Review and Intercomparison of Operational Methods for the Determination of the Mixing Height. AtmosphericEnvironment, 34, 1001-1027. https://doi.org/10.1016/s1352-2310(99)00349-0
[48]
Petäjä, T., Järvi, L., Kerminen, V., Ding, A.J., Sun, J.N., Nie, W., et al. (2016) Enhanced Air Pollution via Aerosol-Boundary Layer Feedback in China. ScientificReports, 6, Article No. 18998. https://doi.org/10.1038/srep18998
[49]
Stull, R.B. (2015) Practical Meteorology: An Algebra-Based Survey of Atmospheric Science. University of British Columbia Press.
[50]
Volná, V. and Hladký, D. (2020) Detailed Assessment of the Effects of Meteorological Conditions on PM10 Concentrations in the Northeastern Part of the Czech Republic. Atmosphere, 11, Article 497. https://doi.org/10.3390/atmos11050497
[51]
Breiman, L. (2001) Random Forests. MachineLearning, 45, 5-32. https://doi.org/10.1023/a:1010933404324
[52]
Géron, A. (2022) Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow. O’Reilly Media, Inc.
[53]
Bergmeir, C., Hyndman, R.J. and Koo, B. (2018) A Note on the Validity of Cross-Validation for Evaluating Autoregressive Time Series Prediction. Computational Statistics&DataAnalysis, 120, 70-83. https://doi.org/10.1016/j.csda.2017.11.003
[54]
Schafer, J.L. and Graham, J.W. (2002) Missing Data: Our View of the State of the Art. PsychologicalMethods, 7, 147-177. https://doi.org/10.1037/1082-989x.7.2.147
[55]
Bodjrènou, R., Sintondji, L.O., N’Tcha, Y.M.P., Germain, D., Azonwade, F.E., Sohindji, F., et al. (2024) Assessment of Hydrologic Data Estimates from ERA5 Reanalyses in Benin, West Africa. GeoscienceDataJournal, 12, e288. https://doi.org/10.1002/gdj3.288
[56]
Humphreys, W.J. (1929) Physics of the Air. McGraw-Hill Book Company.
[57]
Soro, T.D., Koné, M., N’Dri, A.B. and N’Datchoh, E.T. (2021) Identified Main Fire Hotspots and Seasons in Côte d’Ivoire (West Africa) Using MODIS Fire Data. SouthAfricanJournalofScience, 117, Article No. 7659. https://doi.org/10.17159/sajs.2021/7659
[58]
N’Datchoh, E.T., Konaré, A., Diedhiou, A., Diawara, A., Quansah, E. and Assamoi, P. (2015) Effects of Climate Variability on Savannah Fire Regimes in West Africa. EarthSystemDynamics, 6, 161-174. https://doi.org/10.5194/esd-6-161-2015
[59]
Sultan, B. and Janicot, S. (2003) The West African Monsoon Dynamics. Part II: The “Preonset” and “Onset” of the Summer Monsoon. JournalofClimate, 16, 3407-3427. https://doi.org/10.1175/1520-0442(2003)016<3407:twamdp>2.0.co;2
[60]
Hyndman, R.J. and Athanasopoulos, G. (2018) Forecasting: Principles and Practice. OTexts.
[61]
Shumway, R.H. and Stoffer, D.S. (2017) ARIMA Models. In: Shumway, R.H. and Stoffer, D.S., Eds., Time Series Analysis and Its Applications, Springer, 75-163. https://doi.org/10.1007/978-3-319-52452-8_3
[62]
Chen, T. and Guestrin, C. (2016) XGBoost: A Scalable Tree Boosting System. Proceedingsofthe 22ndACMSIGKDDInternationalConferenceonKnowledgeDiscoveryandDataMining, San Francisco, 13-17 August 2016, 785-794. https://doi.org/10.1145/2939672.2939785
[63]
Dickey, D.A. and Fuller, W.A. (1979) Distribution of the Estimators for Autoregressive Time Series with a Unit Root. JournaloftheAmericanStatisticalAssociation, 74, 427-431. https://doi.org/10.1080/01621459.1979.10482531
[64]
Taşpınar, F. (2015) Improving Artificial Neural Network Model Predictions of Daily Average PM10 Concentrations by Applying Principle Component Analysis and Implementing Seasonal Models. JournaloftheAir&WasteManagementAssociation, 65, 800-809. https://doi.org/10.1080/10962247.2015.1019652
[65]
Weed, L., Lok, R., Chawra, D. and Zeitzer, J. (2022) The Impact of Missing Data and Imputation Methods on the Analysis of 24-Hour Activity Patterns. Clocks & Sleep, 4, 497-507.
[66]
Touré, N.E., Konaré, A. and Silué, S. (2012) Intercontinental Transport and Climatic Impact of Saharan and Sahelian Dust. AdvancesinMeteorology, 2012, Article ID: 157020. https://doi.org/10.1155/2012/157020
[67]
Arowosegbe, O.O., Röösli, M., Künzli, N., Saucy, A., Adebayo-Ojo, T.C., Jeebhay, M.F., et al. (2021) Comparing Methods to Impute Missing Daily Ground-Level PM10 Concentrations between 2010-2017 in South Africa. International Journal of EnvironmentalResearchandPublicHealth, 18, Article 3374. https://doi.org/10.3390/ijerph18073374
[68]
Adnane, A., Leghrib, R., Chaoufi, J. and Chirmata, A. (2022) Prediction of PM10 Concentrations in the City of Agadir (Morocco) Using Non-Linear Autoregressive Artificial Neural Networks with Exogenous Inputs (NARX). Materials Today: Proceedings, 52, 146-151. https://doi.org/10.1016/j.matpr.2021.11.340
[69]
Bainomugisha, E., Adrine Warigo, P., Busigu Daka, F., Nshimye, A., Birungi, M. and Okure, D. (2024) AI-Driven Environmental Sensor Networks and Digital Platforms for Urban Air Pollution Monitoring and Modelling. SocietalImpacts, 3, Article ID: 100044. https://doi.org/10.1016/j.socimp.2024.100044
[70]
Sowunmi, A.O., Eze, O.I., Osadolor, U., Iseolorunkanmi, A. and Adeloye, D. (2024) Leveraging AI and Data Science to Mitigate the Respiratory Health Impacts of Climate Change in Africa: Organisation, Costs, and Challenges. JournalofGlobalHealth, 14, Article ID: 03051. https://doi.org/10.7189/jogh.14.03051
