PREDICTING QUANTITATIVE CHARACTERISTICS OF AIR POLLUTION

Volodymyr Hura, Igor Olenych, Oleh Sinkevych, Oksana Ostrovska, Roman Shuvar

Abstract


Background. Rapid industrialization and urbanization have escalated air pollution, posing significant health and environmental threats. Accurate prediction of quantitative air pollution characteristics (like pollutant concentrations or Air Quality Index) is critical for effective monitoring and mitigation strategies. Fuzzy Logic (FL) provides a robust computational intelligence framework adept at handling the inherent uncertainty, imprecision, and non-linear dynamics present in atmospheric systems.

Materials and Methods. The study explores the application of Fuzzy Logic (FL) for improving the prediction of hourly PM2.5 concentrations by adding new input features to data obtained using localized monitoring data from Variazh, for 2024. A key aspect involves feature engineering, where a secondary Fuzzy Inference System (FIS) was developed to derive Pasquill atmospheric stability class based on measured meteorological inputs (wind speed, solar radiation, cloud cover). This derived stability class was then incorporated as an additional input feature into the primary Mamdani-type FIS designed for PM2.5 prediction correction.

Results and Discussion. The inclusion of the fuzzy-derived atmospheric stability class as an input feature improved the performance of the PM2.5 prediction models tested (XGBoost, LightGBM). Models incorporating this engineered feature achieved high accuracy (R² > 0.98), particularly showing enhanced capability during stable atmospheric conditions. This highlights the value of incorporating physically relevant, engineered features derived via interpretable methods like FIS into data-driven air quality models.

Conclusion. Fuzzy Logic proves to be a valuable tool for effective feature engineering in air pollution modeling. Deriving parameters such as atmospheric stability class via an interpretable, rule-based FIS can enrich datasets and enhance the accuracy of subsequent predictive models, offering a practical approach to improving air quality forecasting, especially when direct measurements of complex parameters are unavailable.

Keywords: air pollution, fuzzy logic, forecasting, pollutant concentration, fuzzy inference system, quantitative prediction, machine learning.


Full Text:

PDF

References


  1. World Health Organization. (2006). WHO air quality guidelines for particulate matter, ozone, nitrogen dioxide and sulfur dioxide: Global assessment 2005: Summary of risk assessment. World Health Organization.
  2. Cohen, A. J., Brauer, M., Burnett, R., Anderson, H. R., Frostad, J., Estep, K., Balakrishnan, K., Brunekreef, B., Dandona, L., Dandona, R., Feigin, V., Freedman, G., Hubbell, B., Jobling, A., Kan, H., Knibbs, L., Liu, Y., Martin, R., Morawska, L., … Forouzanfar, M. H. (2017). 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, 389(10082), 1907–1918. https://doi.org/10.1016/S0140-6736(17)30505-6
  3. Manisalidis, I., Stavropoulou, E., Stavropoulos, A., & Bezirtzoglou, E. (2020). Environmental and Health Impacts of Air Pollution: A Review. Frontiers in Public Health, 8, 14. https://doi.org/10.3389/fpubh.2020.00014
  4. Organization for Economic Co-operation and Development (OECD). (2016). The Economic Consequences of Outdoor Air Pollution. OECD Publishing. https://doi.org/10.1787/9789264257474-en
  5. Zhang, Q., Singh, V. P., Li, P., & Chen, X. (2021). Automatic procedure for selecting flood events and identifying flood characteristics from daily streamflow data. Environmental Modelling & Software, 145, 105180. https://doi.org/10.1016/j.envsoft.2021.105180
  6. Seinfeld, J. H., & Pandis, S. N. (2016). Atmospheric Chemistry and Physics: From Air Pollution to Climate Change (3rd ed.). John Wiley & Sons.
  7. Mullen, N. A., Li, Z., Russell, A. G., & Weber, R. J. (2011). Ultrafine particle concentrations and exposures in four high-rise Beijing apartments. Atmospheric Environment, 45(40), 7574–7582. https://doi.org/10.1016/j.atmosenv.2010.07.060
  8. Zlatev, Z., & Dimov, I. (2006). Computational and Numerical Challenges in Environmental Model-ling. Elsevier Science & Technology Books.
  9. Nurmahaludin, N., & Cahyono, G. R. (2024). Fuzzy Logic Based Nutrient Concentration Control System Using the Internet of Things. In Proceedings of the International Conference on Applied Science and Technology on Engineering Science 2023 (iCAST-ES 2023) (pp. 729–742). Atlantis Press. https://doi.org/10.2991/978-94-6463-364-1_67
  10. Zadeh, L. A. (1965). Fuzzy sets. Information and Control, 8(3), 338–353. https://doi.org/10.1016/S0019-9958(65)90241-X
  11. Mysiuk, R. (2024). ANALYSIS OF EFFECTIVE IMAGE PROCESSING METRICS ON RASPBERRY PI AND NVIDIA JETSON NANO. Electronics and Information Technologies, 28. https://doi.org/10.30970/eli.28.2.
  12. Hura, V., & Monastyrskyi, L. (2023). IOT-based solution for detection of air quality using ESP32. Artificial Intelligence, 28(3), 86–93. https://doi.org/10.15407/jai2023.03.086
  13. Pavlyshenko, B. (2016). Machine learning, linear and Bayesian models for logistic regression in failure detection problems. 2016 IEEE International Conference on Big Data (Big Data), 2046–2050. https://doi.org/10.1109/BigData.2016.7840828
  14. Pavlyshenko, B. M. (2019). Machine-Learning Models for Sales Time Series Forecasting. Data, 4(1), 15. https://doi.org/10.3390/data4010015
  15. Ross, T. J. (2010). Fuzzy Logic with Engineering Applications (3rd ed.). John Wiley & Sons.
  16. Zhang, D., & Chen, T. (2024). Scikit-ANFIS: A Scikit-Learn Compatible Python Implementation for Adaptive Neuro-Fuzzy Inference System. International Journal of Fuzzy Systems. https://doi.org/10.1007/s40815-024-01697-0
  17. Pasquill, F. (1962). Atmospheric diffusion: The dispersion of windborne material from industrial and other sources. D. Van Nostrand Company.




DOI: http://dx.doi.org/10.30970/eli.31.8

Refbacks

  • There are currently no refbacks.