Data Mining Model Based on Machine Learning to Predict Air Pollution in The Metropolises of Iran

Subject Areas : Environmental pollution

Abbas Maleki ¹ , Sadegh Abedi ² , alireza irajpour ³

1 - Department of Industrial Management, Faculty of Management and Accounting, Qazvin Islamic Azad University, Qazvin, Iran
2 - Assistant Professor, Department of Industrial Management, Faculty of Management and Accounting, Islamic Azad University, Qazvin Branch, Qazvin, Iran
3 - Assistant Professor, Department of Industrial Management, Faculty of Management and Accounting, Islamic Azad University, Qazvin Branch, Qazvin, Iran

Received: 2024-04-28 Accepted : 2024-06-08 Published : 2024-06-19

Keywords: Covid-19, Iranian metropolises, Machine learning, Neural network, Prediction of air pollution,

Abstract :

Introduction: In response to the Covid-19 pandemic, governments around the world have imposed severe restrictions and presented different scenarios of reducing emissions from traffic sources. With the application of traffic restrictions due to the covid-19 epidemic and quarantine, it seemed that there was a reduction in the traffic of vehicles and the concentration of pollutants and the air quality index approached the quality standards. Therefore, it was expected to see changes in the concentration of CO, O3, NO, NO2, NOx, SO2, PM2.5 and PM10 pollutants, which are pathogenic factors and sometimes premature death. Materials and Methods: Using the data mining method, in the first stage, the change in the concentration of pollutants in the period of the Covid-19 epidemic compared to the period before it is investigated in order to determine what effect the application of traffic restrictions has on the change in the concentration of pollutants in each from the metropolises of Tehran and Shiraz. In the second stage, predictive models are presented using feedforward and deep neural networks to predict the level of health importance based on the application of each of the traffic restrictions in each metropolis.
Results and Discussion: This study shows that the change in the concentration of pollutants during the covid-19 era is different compared to before, in the cities of Tehran and Shiraz; In such a way that the concentration of most pollutants increased in Tehran metropolis and decreased in Shiraz metropolis. According to the result obtained and the difference in the process of changing the concentration of pollutants, in order to control the air quality index, predictive models were presented for each metropolis. Conclusion: For pollutants, the same increasing or decreasing pattern is not seen in the studied metropolises, so it can be said that the effect of the same restrictions on changing the concentration of pollutants is different in different cities; Therefore, applying the same restrictions in all cities does not necessarily lead to a reduction in pollution, and for each urban and environmental situation, a model of traffic restrictions specific to that situation should be prepared.

References:

Ahmadi Arkami A, Kamkar A, Aghajani Z. Investigating the spatial and temporal changes of CO and NOX emissions caused by motor vehicles using MOVES software: a case study of Beheshti Boulevard and Modares in Rasht. Iranian Journal of Health and Environment. 1398. 12th volume, 2nd issue. pages 203-216. . https://ijhe.tums.ac.ir/article-1-6212-fa.html [In Persian]
Bengio Y. Learning Deep Architectures for AI (PDF). Foundations and Trends in Machine Learning. 2009. 2 (1): 1–127. CiteSeerX 10.1.1.701.9550. S2CID 207178999. Archived from the original (PDF) on 4 March 2016. Retrieved 3 September 2015. doi: 10.1561/2200000006
Berry M, Linoff G. Mastering Data Mining, John Wiley, Hoboken, NJ. 2000. doi.org/10.1108/imds.2000.100.5.245.2
Berson A, Smith S, Thearling K. Building Data Mining Applications for CRM, McGraw Hill. 2000. https://search.worldcat.org/title/building-data-mining-applications-for-crm/oclc/47008776
Bhatti U.A, Zeeshan Z, Nizamani M.M, Bazai S, Yu Z, Yuan.L. Assessing the change of ambient air quality patterns in Jiangsu Province of China pre-to post-COVID-19. 2022. Chemosphere, Vol.288, 132569. doi: 10.1016/j.chemosphere.2021.132569
Bherwani H, Gautam S, Gupta A. Qualitative and quantitative analyses of impact of COVID-19 on sustainable development goals (SDGs) in Indian subcontinent with a focus on air quality. 2021. Int. J. Environ. Sci. Technol. 18 (4) (2021) 1019–1028. doi.org/10.1007/s13762-020-03122-z
Bherwani H, Kumar S, Musugu K, Nair M, Gautam S, Gupta A, Ho C-H, Anshul A, Kumar R. Assessment and valuation of health impacts of fine particulate matter during COVID-19 lockdown: a comprehensive study of tropical and sub tropical countries, Environ. Sci. 2021. Pollut. Res. 28 (32) (2021) 44522–44537. doi.org/10.1007/s11356-021-13813-w
Chang H, Chad D, Feng A. COVID-19 prevention, air pollution and transportation patterns in the absence of a lockdown. 2021. Journal of Environmental Management 298 (2021) 113522. doi.org/10.1016/j.jenvman.2021.113522
Chelani A, Gautam S. Lockdown during COVID-19 pandemic: a case study from Indian cities shows insignificant effects on persistent property of urban air quality, Geosci. Front. 2022. 13 (6) (2022), 101284. doi.org/10.1016/j.gsf.2021.101284
Fazel-Rastegar F, Sivakmar V. A case study of weather impact on air pollution during the COVID-19 pandemic in South Africa. Scientific African. 2023. Volume 22, November 2023, e01914. doi.org/10.1016/j.sciaf.2023.e01914
Gautam S, Samuel C, Gautam A, Kumar S. Strong link between coronavirus count and bad air: a case study of India. 2021. Environ. Dev. 2021. Sustain. 23 (11) (2021) 16632–16645. doi.org/10.1007/s10668-021-01366-4
Gautam S. The influence of COVID-19 on air quality in India: a boon or inutile, Bull. Environ. 2020. Contam. Toxicol. 104 (6) (2020) 724–726. doi.org/10.1007/s00128-020-02877-y
Gavrilova Y. A Guide to Deep Learning and Neural Networks. archived from the original on 2020-11-02, retrieved 2020-11-16. 2020. https://serokell.io/blog/deep-learning-and-neural-network-guide
Gonzalez-pardo J, Ceballos-Santos S, Manzanas R, Santibanez M, Fernandez-Olmo I. Estimating change in air pollutant levels due to COVID-19 lockdown measures based on a business-as-usual prediction scenario using data mining models: A case-study for urban traffic sites in Spain. 2022. Sci. Total Environ. 823, 153786. doi.org/10.1016/j.scitotenv.2022.153786
Gualtieri G, Brilli L, Carotenuto F, Vagnoli C, Zaldei A, Gioli B. Quantifying road traffic impact on air quality in urban areas: A COVID-19 –inducted lockdown analysis in Italy. 2020. Environmental pollution 267(2020) 115682. doi.org/10.1016/j.envpol.2020.115682
Hardesty L. "Explained: Neural networks". MIT News Office. 2017. Retrieved 2 June 2022. https://news.mit.edu/2017/explained-neural-networks-deep-learning-0414
Hidalgo García D, Diaz J.A, Impacts of the COVID-19 confinement on air quality, the Land Surface Temperature and the urban heat island in eight cities of Andalusia (Spain). 2021. Remote Sensing Applications: Society and Environment. 25. doi.org/10.1016/j.rsase.2021.100667
Kantardzic M. Data Mining: Concepts, Models, Methods, and Algorithms. 2003. John Wiley. https://ieeexplore.ieee.org/book/5265979
Kolluru S.S.R, Nagendra S.M, Patra A.K, Gautam S, Alshetty V.D, Kumar P. Did unprecedented air pollution levels cause spike in Delhi’s COVID cases during second wave? 2022. in: Stochastic Environmental Research and Risk Assessment. pp. 1–16. doi.org/10.1007/s00477-022-02308-w
Larose D, Larose C. Discovering Knowledge in Data. 2014. John Wiley. doi:10.1002/9781118874059
Lin G. Y, Chen W. Y, Chieh S. H, & Yang Y. T. Chang impact analysis of level 3 COVID-19 alert on air pollution indicators using artificial neural network. 2022. Ecological informatics. 69, 101674. doi.org/10.1016/j.ecoinf.2022.101674
Malekzadeh Sh. Investigation and assessment of air pollution in cities and the need to implement laws to reduce pollution, the fourth national conference on urban planning, architecture, construction and environment. 1397. Shirvan. https://civilica.com/doc/774175 [In Persian]
McDuffie E, Martin R, Yin H, Brauer M. Global Burden of Disease from Major Air Pollution Sources (GBD MAPS): A Global Approach. Research Report 210. 2021. Boston, MA:Health Effects Institute. PMCID: PMC9501767. PMID: 36148817 https://pubmed.ncbi.nlm.nih.gov/36148817
Munnoli P M, Nabapure S, Yeshavanth G. Post-COVID-19 precautions based on lessons learned from past pandemics: a review. 2020. J. Public Health 1–9. doi.org/10.1007/s10389-020-01371-3
Sanchez-Lorenzo A, Vaquero-Martínez J, Calbó J, Wild M, Santurtún A, Lopez-Bustins J, Vaquero J, Folini D, Antón M. Did anomalous atmospheric circulation favor the spread of COVID-19 in Europe? 2020. Environ. Res. 194, 110626. doi.org/10.1016/j.envres.2020.110626
Schmidhuber J. Deep Learning in Neural Networks: An Overview". Neural Networks. 2015. 61: 85–117. arXiv:1404.7828. PMID 25462637. S2CID 11715509. doi:10.1016/j.neunet.2014.09.003
Shaygan M, Mokarram M. Investigating Air Pollution during the Corona Era and before that in the Metropolises of Tehran, Isfahan and Qom. 1402. doi.org/ 10.48308/GISJ.2023.103607 [In Persian]
Singh Saharan U, Kumar R, Tripathy P, Sateesh M, Grag J, Kumar Sharma S, Kumar Mandal T. Drivers of air pollution variability during second wave of COVID-19 in Delhi, India. 2022. Urban climate 41 (2022) 101059. doi.org/10.1016/j.uclim.2021.101059
Szegedy C, Toshev A, Erhan D. Deep neural networks for object detection. 2013. Advances in Neural Information Processing Systems: 2553–2561. Archived from the original on 2017-06-29. Retrieved 2017-06-13. https://proceedings.neurips.cc/paper_files/paper/2013/file/f7cade80b7cc92b991cf4d2806d6bd78-Paper.pdf
Uday U, Bethineedi L. D, Hasanain M, Ghazi B. K, Nadeem A, Patel P, Khalid Z. Effect of COVID-19 on air pollution related illnesses in India. 2022. Annals of medicine and surgery 78, 103871. doi.org/10.1016/j.amsu.2022.103871
Wijnands J. S, Nice K.A, Seneviratne S, Thompson J, Stevenson M. The impact of the COVID-19 pandemic on air pollution: A global assessment using machine learning techniques. Atmospheric pollution research. 2022. doi.org/10.1016/j.apr.2022.101438
Yang M, Chen L, Msigwa G, Tang K.H.D, Yap p-s. Implications of COVID-19 on global environmental pollution and carbon emissions with strategies for sustainability in the COVID-19 era. 2022. Sci. Total Environ, Vol.809, 151657. doi.org/10.1016/j.scitotenv.2021.151657
Yiqun M, Federica N, Anne M, Robert D, Patrick L, Annette P, Massimo S, Susanne B, Kai C. Air pollution changes due to COVID-19 lockdowns and attributable mortality changes in four countries. 2024. doi.org/10.1016/j.envint.2024.108668
Zell A. Simulation Neuronaler Netze [Simulation of Neural Networks] (in German) (1st ed.). 1994. Addison-Wesley. p. 73. ISBN 3-89319-554-8. https://www.amazon.com/Simulation-Neuronaler-Netze-German-Andreas/dp/3486243500
Zihao F, Xuhong W, Jiaxin Y, Ying Z, Mengqianxi Y. Changes in air pollution, land surface temperature, and urban heat islands during the COVID-19 lockdown in three Chinese urban agglomerations. 2023. Science of the Total Environment 892 (2023) 164496. doi.org/10.1016/j.scitotenv.2023.164496