Средства мониторинга, моделирования и прогнозирования концентрации загрязнений городской воздушной среды микрочастицами
Работая с нашим сайтом, вы даете свое согласие на использование файлов cookie. Это необходимо для нормального функционирования сайта, показа целевой рекламы и анализа трафика. Статистика использования сайта отправляется в «Яндекс» и «Google»
Научный журнал Моделирование, оптимизация и информационные технологииThe scientific journal Modeling, Optimization and Information Technology
Online media
issn 2310-6018

Means for monitoring, modeling and predicting the concentration of urban air pollution by microparticles

Vyalova E.P.,  Kvashnina G.A.,  Fedyanin V.I. 

UDC 614.715: 614.78
DOI: 10.26102/2310-6018/2023.41.2.008

  • Abstract
  • List of references
  • About authors

Air pollution is one of the biggest threats to the environment and humans. Due to meteorological and transport factors, industrial activity and emissions of power plants are the main agents of air pollution. Therefore, environmental authorities are focused on the effects of air pollution and the development of guidelines to minimize it. The main objective of this study is to design a system that uses a machine learning approach for predicting urban air pollution by analyzing a set of data on air pollutants, PM2.5 particulate matter in particular. A linear controlled machine learning algorithm, which has a RMSE error value of 31.29 and a Decision Forest Regression algorithm with an RMSE value of 29.26, is used for predictions. The system is developed on a web-based platform and is accessible for mobile phones; it is user-friendly and represents the values of air pollutant concentration with PM2.5 particles and the values of the air quality index. Values of PM2.5 particle concentration are dependent on other sources and background levels, which indicates the importance of localized factors for understanding spatio-temporal model of air pollution at intersections and supporting individuals making decisions in the field of regulating and controlling pollution in cities.

1. Effects of particulate matter on human health. Note by the World Health Organization/Joint Task Force on Aspects of the Effects of Air Pollution on Human Health. Geneva. Available from: https://unece.org/fileadmin/DAM/env/documents/2012/EB/ECE_EB_AIR_2012_18_ R.pdf (аccessed on 03.04.2023). (In Russ.).

2. Golokhvast KS, Chernyshev VV, Ugay SM Motor vehicle emissions and human ecology (literature review). Human ecology. 2016;1:9–14. (In Russ.).

3. Pshenin V.N. Air pollution by fine particles near highways. Modernization and scientific research in the road industry: a collection of scientific works. 2013;96–104. (In Russ.).

4. Decree of the Chief State Sanitary Doctor of the Russian Federation dated 28.01.2021 No. 2 "On Approval of Sanitary Rules and Norms of SanPiN 1.2.3685-21"Hygienic Standards and Requirements for Ensuring Safety and (or) Harmlessness for Humans of Habitat Factors". Available from: http://pravo.gov.ru (аccessed on 03.04.2023). (In Russ.).

5. RD 52.04.840-2015. Application of atmospheric air quality monitoring results obtained using continuous measurement methods. Available from: http://docs.cntd.ru/document/1200133380 (accessed on 03.04.2023). (In Russ.).

6. On the approval of methodological recommendations for ensuring the quality of measurements of concentrations of suspended particles (RM2.5 and RM10) in the atmospheric air of St. Petersburg: Order of the Committee for Environmental Management, Environmental Protection and Environmental Safety of St. Petersburg dated 20.05.2010 No. 75-R. Available from: http://docs.cntd.ru/document/891832021 (accessed on 03.04.2023). (In Russ.).

7. Mishra A. Air Pollution Monitoring System based on IoT: Forecasting and Predictive Modeling using Machine Learning. International Conference on Applied Electromagnetics, Signal Processing and Communication (AESPC), KIIT. 2018; 10. Available from: https://www.researchgate.net/publication/342338791_Air_Pollution_Monitoring_System_based_on_IoT_Forecasting_and_Predictive_Modeling_using_Machine_Learning (accessed on 03.04.2023).

8. Zhang J., Ding W. Prediction of air pollutants concentration based on an extreme learning machine: the case of Hong Kong. Int. J. Environ. Res. Public. Health. 2017;14(2):114. Available from: https://www.mdpi.com/1660-4601/14/2/114 (accessed on 03.04.2023).

9. Castelli M., Clemente F.M., Popoviс A., Silva S., Vanneschi L. A Machine Learning Approach to Predict Air Quality in California. New Models, New Technologies, New Data and Applications of Urban Complexity from Spatio-temporal Perspectives. Available from: https://www.hindawi.com/journals/complexity/2020/8049504/ (accessed on: 03.04.2023).

10. Jebamalar J.A., Kumar A.S. PM2.5 Prediction using Machine Learning Hybrid Model for Smart Health. International Journal of Engineering and Advanced Technology (IJEAT). 2019;9(1):6500–6503.

Vyalova Ekaterina Pavlovna
Candidate of Technical Sciences

Voronezh State Technical University

Voronezh, The Russian Federation

Kvashnina Galina Anatolyevna
Candidate of Technical Sciences, Associate Professor

Voronezh State Technical University

Voronezh, The Russian Federation

Fedyanin Vitaly Ivanovich
Doctor of Technical Sciences, Professor

Voronezh State Technical University

Voronezh, The Russian Federation

Keywords: air quality, PM2.5 microparticles, machine learning, regression models, SDS011 sensor, forecasting

For citation: Vyalova E.P., Kvashnina G.A., Fedyanin V.I. Means for monitoring, modeling and predicting the concentration of urban air pollution by microparticles. Modeling, Optimization and Information Technology. 2023;11(2). URL: https://moitvivt.ru/ru/journal/pdf?id=1345 DOI: 10.26102/2310-6018/2023.41.2.008 (In Russ).

302

Full text in PDF

Received 31.03.2023

Revised 17.04.2023

Accepted 05.05.2023

Published 30.06.2023