Interpretable forecasting of fine particulate air pollution based on monitoring data and machine learning methods

Atmospheric air pollution by fine particles with an aerodynamic diameter of less than 2.5 micrometers is a serious environmental and social problem in urban areas. In this context, short-term forecasting of fine particulate matter concentrations based on air quality monitoring data is of particular importance. This study investigates the applicability of interpretable machine learning methods for hourly forecasting of fine particulate air pollution. The publicly available Beijing PM2.5 data set, containing hourly measurements of particulate matter concentration and meteorological parameters for the period from 2010 to 2014, was used as the data source. Data preprocessing was performed, and a feature space was constructed with consideration of temporal structure and autocorrelation properties of the time series. Linear regression, random forest, and gradient boosting models were developed and evaluated. Forecasting performance was assessed using mean absolute error, root mean squared error, and the coefficient of determination. The results demonstrate that all considered models provide high accuracy for short-term forecasting, while differences in performance between models of varying complexity remain insignificant. It was found that the dominant contribution to the forecast is provided by the autocorrelation of the particulate matter concentration time series, whereas meteorological parameters play a corrective role. The obtained results confirm the feasibility of using interpretable machine learning models in air quality monitoring and forecasting systems.

1. Cohen A.J., Brauer M., Burnett R., et al. Estimates and 25-year trends of the global burden of disease attributable to ambient air pollution: an analysis of data from the Global Burden of Diseases Study 2015. The Lancet. 2017;389(10082):1907–1918. https://doi.org/10.1016/S0140-6736(17)30505-6

2. Deters J.K., Zalakeviciute R., González M., Rybarczyk Y. Modeling PM2.5 Urban Pollution Using Machine Learning and Selected Meteorological Parameters. Journal of Electrical and Computer Engineering. 2017;2017. https://doi.org/10.1155/2017/5106045

3. Fang Z., Yang H., Li C., Cheng L., Zhao M., Xie C. Prediction of PM2.5 hourly concentrations in Beijing based on machine learning algorithm and ground-based LiDAR. Archives of Environmental Protection. 2021;47(3):98–107. https://doi.org/10.24425/aep.2021.138468

4. Ma J., Yu Zh., Qu Y., Xu J., Cao Y. Application of the XGBoost Machine Learning Method in PM2.5 Prediction: A Case Study of Shanghai. Aerosol and Air Quality Research. 2020;20(1):128–138. https://doi.org/10.4209/aaqr.2019.08.0408

5. Ejohwomu O.A., Oshodi O.Sh., Oladokun M., et al. Modelling and Forecasting Temporal PM2.5 Concentration Using Ensemble Machine Learning Methods. Buildings. 2022;12(1). https://doi.org/10.3390/buildings12010046

6. Zhang Y., Sun Q., Liu J., Petrosian O. Long-Term Forecasting of Air Pollution Particulate Matter (PM2.5) and Analysis of Influencing Factors. Sustainability. 2024;16(1). https://doi.org/10.3390/su16010019

7. Antamoshkin O., Kukarcev V., Pupkov A., Tsarev R. Intellectual Support System of Administrative Decisions in the Big Distributed Geoinformation Systems. In: 14th International Multidisciplinary Scientific GeoConference SGEM 2014, 17–26 June 2014, Albena, Bulgaria. Sofia: STEF92 Technology Ltd; 2014. P. 227–232.

8. Yin P.-Y., Chang R.-I., Day R.-F., Lin Y.-Ch., Hu Ch.-Y. Improving PM2.5 Concentration Forecast with the Identification of Temperature Inversion. Applied Sciences. 2022;12(1). https://doi.org/10.3390/app12010071

9. Xiao Q., Zheng Y., Geng G., et al. Separating emission and meteorological contributions to long-term PM2.5 trends over eastern China during 2000–2018. Atmospheric Chemistry and Physics. 2021;21(12):9475–9496. https://doi.org/10.5194/acp-2021-28

10. Karimian H., Li Q., Wu Ch., et al. Evaluation of Different Machine Learning Approaches to Forecasting PM2.5 Mass Concentrations. Aerosol and Air Quality Research. 2019;19(6):1400–1410. https://doi.org/10.4209/aaqr.2018.12.0450

11. Masood A., Hameed M.M., Srivastava A., et al. Improving PM2.5 prediction in New Delhi using a hybrid extreme learning machine coupled with snake optimization algorithm. Scientific Reports. 2023;13. https://doi.org/10.1038/s41598-023-47492-z

12. Kukartsev V.V., Boyko A.A., Mikhalev A.S., Tynchenko V.S., Rukosueva A.A., Korpacheva L.N. Simulation-Dynamic Model of Working Time Costs Calculation for Performance of Operations on CNC Machines. In: Journal of Physics: Conference Series: Volume 1582: High-Tech and Innovations in Research and Manufacturing (HIRM-2020), 28 February 2020, Siberia, Russia. Bristol: IOP Publishing Ltd; 2020. https://doi.org/10.1088/1742-6596/1582/1/012052

13. Shen J., Valagolam D., McCalla S. Prophet forecasting model: a machine learning approach to predict the concentration of air pollutants (PM2.5, PM10, O3, NO2, SO2, CO) in Seoul, South Korea. PeerJ. 2020;8. https://doi.org/10.7717/peerj.9961

14. Fedorova N.V., Dzhioeva N.N., Kukartsev V.V., Dalisova N.A., Ogol A.R., Tynchenko V.S. Methods of Assessing the Efficiency of the Foundry Industrial Marketing. In: IOP Conference Series: Materials Science and Engineering: Volume 734: II International Scientific Conference "Advanced Technologies in Aerospace, Mechanical and Automation Engineering" – MIST: Aerospace – 2019, 18–21 November 2019, Krasnoyarsk, Russia. Bristol: IOP Publishing Ltd; 2020. https://doi.org/10.1088/1757-899X/734/1/012083

15. Kukartsev V.V., Tynchenko V.S., Chzhan E.A., et al. Solving the Problem of Trucking Optimization by Automating the Management Process. In: Journal of Physics: Conference Series: Volume 1333: The International Conference "Information Technologies in Business and Industry", 18–20 February 2019, Novosibirsk, Russia. Bristol: IOP Publishing Ltd; 2019. https://doi.org/10.1088/1742-6596/1333/7/072027

16. Agibayeva A., Khalikhan R., Guney M., Karaca F., Torezhan A., Avcu E. An Air Quality Modeling and Disability-Adjusted Life Years (DALY) Risk Assessment Case Study: Comparing Statistical and Machine Learning Approaches for PM2.5 Forecasting. Sustainability. 2022;14(24). https://doi.org/10.3390/su142416641

17. Lee M., Lin L., Chen Ch.Y., et al. Forecasting Air Quality in Taiwan by Using Machine Learning. Scientific Reports. 2020;10. https://doi.org/10.1038/s41598-020-61151-7

18. Morapedi T.D., Obagbuwa I.Ch. Air pollution particulate matter (PM2.5) prediction in South African cities using machine learning techniques. Frontiers in Artificial Intelligence. 2023;6. https://doi.org/10.3389/frai.2023.1230087

19. Palanichamy N., Haw S.-Ch., S S., Govindasamy K., Murugan R. Prediction of PM2.5 concentrations in Malaysia using machine learning techniques: a review. F1000Research. 2021;10. https://doi.org/10.12688/f1000research.73163.1