DOI: 10.17587/prin.15.509-521

About Air Quality Assessment using Time Series Analysis Techniques on Air Particles Data

D. O. Brykin, Postgraduate Student, brykin.do@phystech.edu, Moscow Institute of Physics and Technology, Moscow, 117303, Russian Federation, E. A. Kaliberda, Associate Professor, eakaliberda@omgtu.ru, U. A. Bahmutsky, Head of Department, yuabahmutskiy@omgtu.ru, Omsk State Technical University, Omsk, 644050, Russian Federation

Corresponding author: Dmitry O. Brykin, Postgraduate Student, Moscow Institute of Physics and Technology, Moscow, 117303, Russian Federation, E-mail: brykin.do@phystech.edu

This study investigates the dynamics of air pollution caused by particulate matter (PM10 and PM2.5) in Omsk, Russia. Data collected from the Sensor.Community network between 2021 and 2023 were analyzed using time series analysis methods. The findings reveal a subtle weekly seasonality in the data, potentially attributed to fluctuations in industrial activity and traffic patterns throughout the week. Additionally, a concerning trend of deteriorating air quality was identified, characterized by increasing annual average concentrations of PM10 and PM2.5. The study employed various time series analysis techniques, including Empirical Cumulative Distribution Function (ECDF), Seasonal and Trend decomposition using Loess (STL), and autocorrelation function (ACF) analysis. These methods allowed for the visualization and examination of data distribution, trend identification, and seasonality detection. Furthermore, the Mann-Kendall test confirmed a statistically significant trend of increasing pollution levels over the three-year period. To enhance the accuracy of spatial analysis, data interpolation was performed using kriging with a Gaussian model. This method, compared to simple interpolation, provides a more precise assessment of the spatial distribution of pollutants. The study also implemented Long Short-Term Memory (LSTM) for forecasting hourly pollution values. LSTM exhibited promising results, demonstrating its potential for developing early warning systems, particularly when combined with meteorological data such as wind forecasts. The results highlight the need for effective measures to mitigate air pollution in Omsk and emphasize the importance of utilizing data from diverse sources, including official air quality monitoring stations, to ensure accuracy and reliability in air quality assessments.

Keywords: statistical analysis, atmospheric air, monitoring, time series, ECDF, STL, ARIMA, LSTM, PM10, PM2.5

pp. 509—521

For citation:
Brykin D. O., Kaliberda E. A., Bahmutsky U. A. About Air Quality Assessment using Time Series Analysis Techniques on Air Particles Data, Programmnaya Ingeneria, 2024, vol. 15, no. 10, pp. 509—521. DOI: 10.17587/prin.15.509-521 (in Russian).

References:

1. Popova A. Yu., Zaitseva N. V., Mai I. V. Population health as a target function and criterion of effectiveness of measures of the federal project "Clean Air", Analis riska zdoroviu, 2019, no. 4, pp. 4—13. DOI: 10.21668/health.risk/2019.4.01 (in Russian).
2. Mai I. V., Vekovshinina S. A., Klein S. V. Federal project "Clean Air": practical experience of chemical substances selection for the information system of atmospheric air quality analysis in Norilsk, Gigeyana i sanitaria, 2020, no. 8, vol. 99, pp. 766—772 (in Russian).
3. Zaitseva N. V., Mai I. V. Atmospheric air quality and health risk indicators as objective criteria of air protection activity efficiency in the territories of the cities-participants of the federal project "Clean Air", Analis riska zdoroviu, 2023, no. 1, pp. 4—12 (in Russian).
4. Piskunov V. N. Aerosol dynamics, Moscow, Fizmatlit, 2010, 296 p. (in Russian).
5. Lokoshchenko M. A., Elansky N. F., Trifanova A. V. On the limit levels of air pollution in Moscow, Vestnik Moskovskogo universiteta. Seriya 5. Geografiya, 2016, no. 4, pp. 29—39 (in Russian).
6. Tran H. M., Tsai F., Lee Y. et al. The impact of air pollu­tion on respiratory diseases in an era of climate change: A review of the current evidence, Science of The Total Environment, 2023, vol. 898, pp. 166340. DOI: 10.1016/j.scitotenv.2023.166340.
7. Morbidity of the Omsk Oblast population by main classes of diseases, Rosstat, available at: https://55.rosstat.gov.ru/storage/mediabank/zabol-2022.htm (in Russian) (date of access 10.04.2024).
8. Sensor.Community, official site, available at: https://sensor.community (date of access 10.04.2024).
9. Mahajan S., Kumar P., Pinto J. et al. A citizen science approach for enhancing public understanding of air pollution, Sustain Cities Soc., 2020, vol. 52, pp. 101800. DOI: 10.1016/j.scs.2019.101800.
10. Taboga M. Empirical distribution, Lectures on probability theory and mathematical statistics, 2021, avaliable at: https://www.statlect.com/asymptotic-theory/empirical-distribution (date of access 14.07.2024).
11. Decomposition by Seasonal Trends with LOESS, available at: https://doc.arcgis.com/ru/insights/latest/analyze/stl.htm (in Russian) (date of access 20.07.2024).
12. Hyndman, R.J, Athanasopoulos G. Forecasting: principles and practice, 2nd edition, OTexts. Australia, 2018.
13. Augmented Dickey Fuller Test (ADF Test), available at: https://www.machinelearningplus.com/time-series/augmented-dickey-fuller-test/ (date of access 15.07.2024).
14. Koshel S. М., Music O. P. Digital Modeling Methods: Krig-ing and Radial Interpolation, Informacionniy bulliten GIS associacii, 2001, vol. 29, pp. 23—24 (in Russian).
15. Li J., Heap A. D. Spatial interpolation methods applied in the environmental sciences: A review, Environmental Modelling & Soft­ware, 2014, vol. 53, pp. 173—189. DOI: 10.1016/j.envsoft.2013.12.008.
16. Kratkovich P. V. Neural Networks and Arima Mod­els for Price Forecasting, Programmnie producti i systemi, 2011, vol. 1, pp. 95—98. avaliable at: https://swsys.ru/index.php?page=article&id=2724 (in Russian).
17. Bhatti U. A., Yan Y., Zhou M. et al. Time Series Analysis and Forecasting of Air Pollution Particulate Matter (PM 2.5): An SARIMA and Factor Analysis Approach, IEEE Access, 2021, vol. 9, pp. 41019—41031. DOI: 10.1109/ACCESS.2021.3060744.
18. Long Short-Term memory, available at: https://neerc.ifmo.ru/wiki/index.php?title=Долгая_кракосрочная_память (in Russian) (date of access 11.07.2024).
19. EN API Documentation, available at: https://github.com/opendata-stuttgart/meta/wiki/EN-APIs (date of access 11.07.2024).